Created
January 12, 2021 13:05
-
-
Save gen2brain/f5ead089cbf29110bb7c59bddad8bee7 to your computer and use it in GitHub Desktop.
This file has been truncated, but you can view the full file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| diff -ur x264-go/encode.go x264-go.new/encode.go | |
| --- x264-go/encode.go 2020-04-20 16:40:00.859331841 +0200 | |
| +++ x264-go.new/encode.go 2020-06-06 15:48:52.593083554 +0200 | |
| @@ -82,8 +82,9 @@ | |
| param.IWidth = int32(e.opts.Width) | |
| param.IHeight = int32(e.opts.Height) | |
| - | |
| param.ICsp = e.csp | |
| + | |
| + param.IBitdepth = 8 | |
| param.BVfrInput = 0 | |
| param.BRepeatHeaders = 1 | |
| param.BAnnexb = 1 | |
| @@ -95,7 +96,7 @@ | |
| param.IFpsDen = 1 | |
| param.IKeyintMax = int32(e.opts.FrameRate) | |
| - param.BIntraRefresh = 1 | |
| + //param.BIntraRefresh = 1 | |
| } | |
| if e.opts.Profile != "" { | |
| @@ -108,18 +109,20 @@ | |
| // Allocate on create instead while encoding | |
| var picIn x264c.Picture | |
| - ret := x264c.PictureAlloc(&picIn, e.csp, int32(e.opts.Width), int32(e.opts.Height)) | |
| - if ret < 0 { | |
| - err = fmt.Errorf("x264: cannot allocate picture") | |
| - return | |
| - } | |
| + x264c.PictureInit(&picIn) | |
| + //ret := x264c.PictureAlloc(&picIn, e.csp, int32(e.opts.Width), int32(e.opts.Height)) | |
| + //if ret < 0 { | |
| + //err = fmt.Errorf("x264: cannot allocate picture") | |
| + //return | |
| + //} | |
| + | |
| e.picIn = picIn | |
| - defer func() { | |
| - // Cleanup if intialization fail | |
| - if err != nil { | |
| - x264c.PictureClean(&picIn) | |
| - } | |
| - }() | |
| + //defer func() { | |
| + //// Cleanup if intialization fail | |
| + //if err != nil { | |
| + //x264c.PictureClean(&picIn) | |
| + //} | |
| + //}() | |
| e.e = x264c.EncoderOpen(¶m) | |
| if e.e == nil { | |
| @@ -127,7 +130,7 @@ | |
| return | |
| } | |
| - ret = x264c.EncoderHeaders(e.e, e.nals, &e.nnals) | |
| + ret := x264c.EncoderHeaders(e.e, e.nals, &e.nnals) | |
| if ret < 0 { | |
| err = fmt.Errorf("x264: cannot encode headers") | |
| return | |
| @@ -156,7 +159,20 @@ | |
| e.img.ToYCbCr(im) | |
| picIn := e.picIn | |
| - e.img.CopyToCPointer(picIn.Img.Plane[0], picIn.Img.Plane[1], picIn.Img.Plane[2]) | |
| + | |
| + picIn.Img.ICsp = e.csp | |
| + | |
| + picIn.Img.IPlane = 3 | |
| + picIn.Img.IStride[0] = int32(e.opts.Width) | |
| + picIn.Img.IStride[1] = int32(e.opts.Width) / 2 | |
| + picIn.Img.IStride[2] = int32(e.opts.Width) / 2 | |
| + | |
| + picIn.Img.Plane[0] = C.CBytes(e.img.Y) | |
| + picIn.Img.Plane[1] = C.CBytes(e.img.Cb) | |
| + picIn.Img.Plane[2] = C.CBytes(e.img.Cr) | |
| + | |
| + //e.img.CopyToCPointer(picIn.Img.Plane[0], picIn.Img.Plane[1], picIn.Img.Plane[2]) | |
| + | |
| picIn.IPts = e.pts | |
| e.pts++ | |
| @@ -218,4 +234,4 @@ | |
| x264c.PictureClean(&picIn) | |
| x264c.EncoderClose(e.e) | |
| return nil | |
| -} | |
| \ No newline at end of file | |
| +} | |
| diff -ur x264-go/encode_test.go x264-go.new/encode_test.go | |
| --- x264-go/encode_test.go 2018-03-05 18:23:21.000000000 +0100 | |
| +++ x264-go.new/encode_test.go 2020-06-05 21:13:34.464319909 +0200 | |
| @@ -20,7 +20,7 @@ | |
| FrameRate: 25, | |
| Tune: "zerolatency", | |
| Preset: "veryfast", | |
| - Profile: "baseline", | |
| + Profile: "high", | |
| LogLevel: LogDebug, | |
| } | |
| diff -ur x264-go/examples/basic/basic.go x264-go.new/examples/basic/basic.go | |
| --- x264-go/examples/basic/basic.go 2018-02-14 03:39:14.000000000 +0100 | |
| +++ x264-go.new/examples/basic/basic.go 2020-06-05 21:52:23.943381303 +0200 | |
| @@ -14,9 +14,9 @@ | |
| Width: 640, | |
| Height: 480, | |
| FrameRate: 25, | |
| - Preset: "veryfast", | |
| - Tune: "zerolatency", | |
| - Profile: "baseline", | |
| + Preset: "fast", | |
| + Tune: "stillimage", | |
| + Profile: "high", | |
| LogLevel: x264.LogDebug, | |
| } | |
| @@ -52,5 +52,11 @@ | |
| if err != nil { | |
| fmt.Println(err) | |
| os.Exit(1) | |
| + } | |
| + | |
| + err = enc.Flush() | |
| + if err != nil { | |
| + fmt.Println(err) | |
| + os.Exit(1) | |
| } | |
| } | |
| diff -ur x264-go/examples/screengrab/screengrab.go x264-go.new/examples/screengrab/screengrab.go | |
| --- x264-go/examples/screengrab/screengrab.go 2020-08-24 17:31:59.372106174 +0200 | |
| +++ x264-go.new/examples/screengrab/screengrab.go 2020-06-05 21:20:50.117331390 +0200 | |
| @@ -1,9 +1,7 @@ | |
| package main | |
| import ( | |
| - "bytes" | |
| "fmt" | |
| - "io/ioutil" | |
| "os" | |
| "os/signal" | |
| "syscall" | |
| @@ -13,21 +11,25 @@ | |
| ) | |
| func main() { | |
| - buf := bytes.NewBuffer(make([]byte, 0)) | |
| + file, err := os.Create("screen.264") | |
| + if err != nil { | |
| + fmt.Fprintf(os.Stderr, "%s\n", err.Error()) | |
| + os.Exit(1) | |
| + } | |
| bounds := screenshot.GetDisplayBounds(0) | |
| opts := &x264.Options{ | |
| Width: bounds.Dx(), | |
| Height: bounds.Dy(), | |
| - FrameRate: 15, | |
| + FrameRate: 10, | |
| Tune: "zerolatency", | |
| Preset: "veryfast", | |
| - Profile: "baseline", | |
| + Profile: "high", | |
| LogLevel: x264.LogDebug, | |
| } | |
| - enc, err := x264.NewEncoder(buf, opts) | |
| + enc, err := x264.NewEncoder(file, opts) | |
| if err != nil { | |
| fmt.Fprintf(os.Stderr, "%s\n", err.Error()) | |
| os.Exit(1) | |
| @@ -43,7 +45,7 @@ | |
| case <-s: | |
| enc.Flush() | |
| - err = ioutil.WriteFile("screen.264", buf.Bytes(), 0644) | |
| + err = file.Close() | |
| if err != nil { | |
| fmt.Fprintf(os.Stderr, "%s\n", err.Error()) | |
| os.Exit(1) | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/asm-offsets.c x264-go.new/x264c/external/x264/common/aarch64/asm-offsets.c | |
| --- x264-go/x264c/external/x264/common/aarch64/asm-offsets.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/asm-offsets.c 2020-06-06 15:20:58.684039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * asm-offsets.c: check asm offsets for aarch64 | |
| ***************************************************************************** | |
| - * Copyright (C) 2014-2017 x264 project | |
| + * Copyright (C) 2014-2020 x264 project | |
| * | |
| * Authors: Janne Grunau <janne-x264@jannau.net> | |
| * | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/asm-offsets.h x264-go.new/x264c/external/x264/common/aarch64/asm-offsets.h | |
| --- x264-go/x264c/external/x264/common/aarch64/asm-offsets.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/asm-offsets.h 2020-06-06 15:20:58.684039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * asm-offsets.h: asm offsets for aarch64 | |
| ***************************************************************************** | |
| - * Copyright (C) 2014-2017 x264 project | |
| + * Copyright (C) 2014-2020 x264 project | |
| * | |
| * Authors: Janne Grunau <janne-x264@jannau.net> | |
| * | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: asm.S | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: bitstream-a.S | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: bitstream.h | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: cabac-a.S | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: dct-a.S | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/dct.h x264-go.new/x264c/external/x264/common/aarch64/dct.h | |
| --- x264-go/x264c/external/x264/common/aarch64/dct.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/dct.h 2020-06-06 15:20:58.684039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * dct.h: aarch64 transform and zigzag | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,41 +27,68 @@ | |
| #ifndef X264_AARCH64_DCT_H | |
| #define X264_AARCH64_DCT_H | |
| +#define x264_dct4x4dc_neon x264_template(dct4x4dc_neon) | |
| void x264_dct4x4dc_neon( int16_t d[16] ); | |
| +#define x264_idct4x4dc_neon x264_template(idct4x4dc_neon) | |
| void x264_idct4x4dc_neon( int16_t d[16] ); | |
| +#define x264_sub4x4_dct_neon x264_template(sub4x4_dct_neon) | |
| void x264_sub4x4_dct_neon( int16_t dct[16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_neon x264_template(sub8x8_dct_neon) | |
| void x264_sub8x8_dct_neon( int16_t dct[4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_neon x264_template(sub16x16_dct_neon) | |
| void x264_sub16x16_dct_neon( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_add4x4_idct_neon x264_template(add4x4_idct_neon) | |
| void x264_add4x4_idct_neon( uint8_t *p_dst, int16_t dct[16] ); | |
| +#define x264_add8x8_idct_neon x264_template(add8x8_idct_neon) | |
| void x264_add8x8_idct_neon( uint8_t *p_dst, int16_t dct[4][16] ); | |
| +#define x264_add16x16_idct_neon x264_template(add16x16_idct_neon) | |
| void x264_add16x16_idct_neon( uint8_t *p_dst, int16_t dct[16][16] ); | |
| +#define x264_add8x8_idct_dc_neon x264_template(add8x8_idct_dc_neon) | |
| void x264_add8x8_idct_dc_neon( uint8_t *p_dst, int16_t dct[4] ); | |
| +#define x264_add16x16_idct_dc_neon x264_template(add16x16_idct_dc_neon) | |
| void x264_add16x16_idct_dc_neon( uint8_t *p_dst, int16_t dct[16] ); | |
| +#define x264_sub8x8_dct_dc_neon x264_template(sub8x8_dct_dc_neon) | |
| void x264_sub8x8_dct_dc_neon( int16_t dct[4], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x16_dct_dc_neon x264_template(sub8x16_dct_dc_neon) | |
| void x264_sub8x16_dct_dc_neon( int16_t dct[8], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct8_neon x264_template(sub8x8_dct8_neon) | |
| void x264_sub8x8_dct8_neon( int16_t dct[64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct8_neon x264_template(sub16x16_dct8_neon) | |
| void x264_sub16x16_dct8_neon( int16_t dct[4][64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_add8x8_idct8_neon x264_template(add8x8_idct8_neon) | |
| void x264_add8x8_idct8_neon( uint8_t *p_dst, int16_t dct[64] ); | |
| +#define x264_add16x16_idct8_neon x264_template(add16x16_idct8_neon) | |
| void x264_add16x16_idct8_neon( uint8_t *p_dst, int16_t dct[4][64] ); | |
| +#define x264_zigzag_scan_4x4_frame_neon x264_template(zigzag_scan_4x4_frame_neon) | |
| void x264_zigzag_scan_4x4_frame_neon( int16_t level[16], int16_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_field_neon x264_template(zigzag_scan_4x4_field_neon) | |
| void x264_zigzag_scan_4x4_field_neon( int16_t level[16], int16_t dct[16] ); | |
| +#define x264_zigzag_scan_8x8_frame_neon x264_template(zigzag_scan_8x8_frame_neon) | |
| void x264_zigzag_scan_8x8_frame_neon( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_field_neon x264_template(zigzag_scan_8x8_field_neon) | |
| void x264_zigzag_scan_8x8_field_neon( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_sub_4x4_field_neon x264_template(zigzag_sub_4x4_field_neon) | |
| int x264_zigzag_sub_4x4_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst ); | |
| +#define x264_zigzag_sub_4x4ac_field_neon x264_template(zigzag_sub_4x4ac_field_neon) | |
| int x264_zigzag_sub_4x4ac_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst, dctcoef *dc ); | |
| +#define x264_zigzag_sub_4x4_frame_neon x264_template(zigzag_sub_4x4_frame_neon) | |
| int x264_zigzag_sub_4x4_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst ); | |
| +#define x264_zigzag_sub_4x4ac_frame_neon x264_template(zigzag_sub_4x4ac_frame_neon) | |
| int x264_zigzag_sub_4x4ac_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst, dctcoef *dc ); | |
| +#define x264_zigzag_sub_8x8_field_neon x264_template(zigzag_sub_8x8_field_neon) | |
| int x264_zigzag_sub_8x8_field_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst ); | |
| +#define x264_zigzag_sub_8x8_frame_neon x264_template(zigzag_sub_8x8_frame_neon) | |
| int x264_zigzag_sub_8x8_frame_neon( dctcoef level[16], const pixel *p_src, pixel *p_dst ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_neon x264_template(zigzag_interleave_8x8_cavlc_neon) | |
| void x264_zigzag_interleave_8x8_cavlc_neon( dctcoef *dst, dctcoef *src, uint8_t *nnz ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: deblock-a.S | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: deblock.h | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: mc-a.S | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/mc-c.c x264-go.new/x264c/external/x264/common/aarch64/mc-c.c | |
| --- x264-go/x264c/external/x264/common/aarch64/mc-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/mc-c.c 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc-c.c: aarch64 motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,54 +27,96 @@ | |
| #include "common/common.h" | |
| #include "mc.h" | |
| +#define x264_prefetch_ref_aarch64 x264_template(prefetch_ref_aarch64) | |
| void x264_prefetch_ref_aarch64( uint8_t *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_420_aarch64 x264_template(prefetch_fenc_420_aarch64) | |
| void x264_prefetch_fenc_420_aarch64( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_422_aarch64 x264_template(prefetch_fenc_422_aarch64) | |
| void x264_prefetch_fenc_422_aarch64( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_memcpy_aligned_neon x264_template(memcpy_aligned_neon) | |
| void *x264_memcpy_aligned_neon( void *dst, const void *src, size_t n ); | |
| +#define x264_memzero_aligned_neon x264_template(memzero_aligned_neon) | |
| void x264_memzero_aligned_neon( void *dst, size_t n ); | |
| +#define x264_pixel_avg_16x16_neon x264_template(pixel_avg_16x16_neon) | |
| void x264_pixel_avg_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_16x8_neon x264_template(pixel_avg_16x8_neon) | |
| void x264_pixel_avg_16x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x16_neon x264_template(pixel_avg_8x16_neon) | |
| void x264_pixel_avg_8x16_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x8_neon x264_template(pixel_avg_8x8_neon) | |
| void x264_pixel_avg_8x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x4_neon x264_template(pixel_avg_8x4_neon) | |
| void x264_pixel_avg_8x4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x16_neon x264_template(pixel_avg_4x16_neon) | |
| void x264_pixel_avg_4x16_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x8_neon x264_template(pixel_avg_4x8_neon) | |
| void x264_pixel_avg_4x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x4_neon x264_template(pixel_avg_4x4_neon) | |
| void x264_pixel_avg_4x4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x2_neon x264_template(pixel_avg_4x2_neon) | |
| void x264_pixel_avg_4x2_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg2_w4_neon x264_template(pixel_avg2_w4_neon) | |
| void x264_pixel_avg2_w4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w8_neon x264_template(pixel_avg2_w8_neon) | |
| void x264_pixel_avg2_w8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w16_neon x264_template(pixel_avg2_w16_neon) | |
| void x264_pixel_avg2_w16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w20_neon x264_template(pixel_avg2_w20_neon) | |
| void x264_pixel_avg2_w20_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_plane_copy_core_neon x264_template(plane_copy_core_neon) | |
| void x264_plane_copy_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_swap_core_neon x264_template(plane_copy_swap_core_neon) | |
| void x264_plane_copy_swap_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_neon x264_template(plane_copy_deinterleave_neon) | |
| void x264_plane_copy_deinterleave_neon( pixel *dstu, intptr_t i_dstu, | |
| pixel *dstv, intptr_t i_dstv, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_rgb_neon x264_template(plane_copy_deinterleave_rgb_neon) | |
| void x264_plane_copy_deinterleave_rgb_neon( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *dstc, intptr_t i_dstc, | |
| pixel *src, intptr_t i_src, int pw, int w, int h ); | |
| +#define x264_plane_copy_interleave_core_neon x264_template(plane_copy_interleave_core_neon) | |
| void x264_plane_copy_interleave_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| +#define x264_store_interleave_chroma_neon x264_template(store_interleave_chroma_neon) | |
| void x264_store_interleave_chroma_neon( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_neon x264_template(load_deinterleave_chroma_fdec_neon) | |
| void x264_load_deinterleave_chroma_fdec_neon( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_neon x264_template(load_deinterleave_chroma_fenc_neon) | |
| void x264_load_deinterleave_chroma_fenc_neon( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_mc_weight_w16_neon x264_template(mc_weight_w16_neon) | |
| +#define x264_mc_weight_w16_nodenom_neon x264_template(mc_weight_w16_nodenom_neon) | |
| +#define x264_mc_weight_w16_offsetadd_neon x264_template(mc_weight_w16_offsetadd_neon) | |
| +#define x264_mc_weight_w16_offsetsub_neon x264_template(mc_weight_w16_offsetsub_neon) | |
| +#define x264_mc_weight_w20_neon x264_template(mc_weight_w20_neon) | |
| +#define x264_mc_weight_w20_nodenom_neon x264_template(mc_weight_w20_nodenom_neon) | |
| +#define x264_mc_weight_w20_offsetadd_neon x264_template(mc_weight_w20_offsetadd_neon) | |
| +#define x264_mc_weight_w20_offsetsub_neon x264_template(mc_weight_w20_offsetsub_neon) | |
| +#define x264_mc_weight_w4_neon x264_template(mc_weight_w4_neon) | |
| +#define x264_mc_weight_w4_nodenom_neon x264_template(mc_weight_w4_nodenom_neon) | |
| +#define x264_mc_weight_w4_offsetadd_neon x264_template(mc_weight_w4_offsetadd_neon) | |
| +#define x264_mc_weight_w4_offsetsub_neon x264_template(mc_weight_w4_offsetsub_neon) | |
| +#define x264_mc_weight_w8_neon x264_template(mc_weight_w8_neon) | |
| +#define x264_mc_weight_w8_nodenom_neon x264_template(mc_weight_w8_nodenom_neon) | |
| +#define x264_mc_weight_w8_offsetadd_neon x264_template(mc_weight_w8_offsetadd_neon) | |
| +#define x264_mc_weight_w8_offsetsub_neon x264_template(mc_weight_w8_offsetsub_neon) | |
| #define MC_WEIGHT(func)\ | |
| void x264_mc_weight_w20##func##_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| void x264_mc_weight_w16##func##_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| void x264_mc_weight_w8##func##_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| void x264_mc_weight_w4##func##_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| \ | |
| -static void (* x264_mc##func##_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int ) =\ | |
| +static void (* mc##func##_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int ) =\ | |
| {\ | |
| x264_mc_weight_w4##func##_neon,\ | |
| x264_mc_weight_w4##func##_neon,\ | |
| @@ -84,50 +126,64 @@ | |
| x264_mc_weight_w20##func##_neon,\ | |
| }; | |
| +#if !HIGH_BIT_DEPTH | |
| MC_WEIGHT() | |
| MC_WEIGHT(_nodenom) | |
| MC_WEIGHT(_offsetadd) | |
| MC_WEIGHT(_offsetsub) | |
| +#endif | |
| +#define x264_mc_copy_w4_neon x264_template(mc_copy_w4_neon) | |
| void x264_mc_copy_w4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w8_neon x264_template(mc_copy_w8_neon) | |
| void x264_mc_copy_w8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_neon x264_template(mc_copy_w16_neon) | |
| void x264_mc_copy_w16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_chroma_neon x264_template(mc_chroma_neon) | |
| void x264_mc_chroma_neon( uint8_t *, uint8_t *, intptr_t, uint8_t *, intptr_t, int, int, int, int ); | |
| +#define x264_integral_init4h_neon x264_template(integral_init4h_neon) | |
| void x264_integral_init4h_neon( uint16_t *, uint8_t *, intptr_t ); | |
| +#define x264_integral_init4v_neon x264_template(integral_init4v_neon) | |
| void x264_integral_init4v_neon( uint16_t *, uint16_t *, intptr_t ); | |
| +#define x264_integral_init8h_neon x264_template(integral_init8h_neon) | |
| void x264_integral_init8h_neon( uint16_t *, uint8_t *, intptr_t ); | |
| +#define x264_integral_init8v_neon x264_template(integral_init8v_neon) | |
| void x264_integral_init8v_neon( uint16_t *, intptr_t ); | |
| +#define x264_frame_init_lowres_core_neon x264_template(frame_init_lowres_core_neon) | |
| void x264_frame_init_lowres_core_neon( uint8_t *, uint8_t *, uint8_t *, uint8_t *, uint8_t *, intptr_t, intptr_t, int, int ); | |
| +#define x264_mbtree_propagate_cost_neon x264_template(mbtree_propagate_cost_neon) | |
| void x264_mbtree_propagate_cost_neon( int16_t *, uint16_t *, uint16_t *, uint16_t *, uint16_t *, float *, int ); | |
| +#define x264_mbtree_fix8_pack_neon x264_template(mbtree_fix8_pack_neon) | |
| void x264_mbtree_fix8_pack_neon( uint16_t *dst, float *src, int count ); | |
| +#define x264_mbtree_fix8_unpack_neon x264_template(mbtree_fix8_unpack_neon) | |
| void x264_mbtree_fix8_unpack_neon( float *dst, uint16_t *src, int count ); | |
| #if !HIGH_BIT_DEPTH | |
| -static void x264_weight_cache_neon( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache_neon( x264_t *h, x264_weight_t *w ) | |
| { | |
| if( w->i_scale == 1<<w->i_denom ) | |
| { | |
| if( w->i_offset < 0 ) | |
| { | |
| - w->weightfn = x264_mc_offsetsub_wtab_neon; | |
| + w->weightfn = mc_offsetsub_wtab_neon; | |
| w->cachea[0] = -w->i_offset; | |
| } | |
| else | |
| { | |
| - w->weightfn = x264_mc_offsetadd_wtab_neon; | |
| + w->weightfn = mc_offsetadd_wtab_neon; | |
| w->cachea[0] = w->i_offset; | |
| } | |
| } | |
| else if( !w->i_denom ) | |
| - w->weightfn = x264_mc_nodenom_wtab_neon; | |
| + w->weightfn = mc_nodenom_wtab_neon; | |
| else | |
| - w->weightfn = x264_mc_wtab_neon; | |
| + w->weightfn = mc_wtab_neon; | |
| } | |
| -static void (* const x264_pixel_avg_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ) = | |
| +static void (* const pixel_avg_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ) = | |
| { | |
| NULL, | |
| x264_pixel_avg2_w4_neon, | |
| @@ -137,7 +193,7 @@ | |
| x264_pixel_avg2_w20_neon, | |
| }; | |
| -static void (* const x264_mc_copy_wtab_neon[5])( uint8_t *, intptr_t, uint8_t *, intptr_t, int ) = | |
| +static void (* const mc_copy_wtab_neon[5])( uint8_t *, intptr_t, uint8_t *, intptr_t, int ) = | |
| { | |
| NULL, | |
| x264_mc_copy_w4_neon, | |
| @@ -160,7 +216,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */ | |
| { | |
| uint8_t *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3); | |
| - x264_pixel_avg_wtab_neon[i_width>>2]( | |
| + pixel_avg_wtab_neon[i_width>>2]( | |
| dst, i_dst_stride, src1, i_src_stride, | |
| src2, i_height ); | |
| if( weight->weightfn ) | |
| @@ -169,7 +225,7 @@ | |
| else if( weight->weightfn ) | |
| weight->weightfn[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, weight, i_height ); | |
| else | |
| - x264_mc_copy_wtab_neon[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, i_height ); | |
| + mc_copy_wtab_neon[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, i_height ); | |
| } | |
| static uint8_t *get_ref_neon( uint8_t *dst, intptr_t *i_dst_stride, | |
| @@ -186,7 +242,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */ | |
| { | |
| uint8_t *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3); | |
| - x264_pixel_avg_wtab_neon[i_width>>2]( | |
| + pixel_avg_wtab_neon[i_width>>2]( | |
| dst, *i_dst_stride, src1, i_src_stride, | |
| src2, i_height ); | |
| if( weight->weightfn ) | |
| @@ -205,6 +261,7 @@ | |
| } | |
| } | |
| +#define x264_hpel_filter_neon x264_template(hpel_filter_neon) | |
| void x264_hpel_filter_neon( uint8_t *dsth, uint8_t *dstv, uint8_t *dstc, | |
| uint8_t *src, intptr_t stride, int width, | |
| int height, int16_t *buf ); | |
| @@ -212,11 +269,10 @@ | |
| PLANE_COPY(16, neon) | |
| PLANE_COPY_SWAP(16, neon) | |
| PLANE_INTERLEAVE(neon) | |
| -#endif // !HIGH_BIT_DEPTH | |
| - | |
| PROPAGATE_LIST(neon) | |
| +#endif // !HIGH_BIT_DEPTH | |
| -void x264_mc_init_aarch64( int cpu, x264_mc_functions_t *pf ) | |
| +void x264_mc_init_aarch64( uint32_t cpu, x264_mc_functions_t *pf ) | |
| { | |
| #if !HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_ARMV8 ) | |
| @@ -234,11 +290,11 @@ | |
| pf->copy[PIXEL_8x8] = x264_mc_copy_w8_neon; | |
| pf->copy[PIXEL_4x4] = x264_mc_copy_w4_neon; | |
| - pf->plane_copy = x264_plane_copy_neon; | |
| - pf->plane_copy_swap = x264_plane_copy_swap_neon; | |
| + pf->plane_copy = plane_copy_neon; | |
| + pf->plane_copy_swap = plane_copy_swap_neon; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_neon; | |
| pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_neon; | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_neon; | |
| + pf->plane_copy_interleave = plane_copy_interleave_neon; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_neon; | |
| pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_neon; | |
| @@ -254,10 +310,10 @@ | |
| pf->avg[PIXEL_4x4] = x264_pixel_avg_4x4_neon; | |
| pf->avg[PIXEL_4x2] = x264_pixel_avg_4x2_neon; | |
| - pf->weight = x264_mc_wtab_neon; | |
| - pf->offsetadd = x264_mc_offsetadd_wtab_neon; | |
| - pf->offsetsub = x264_mc_offsetsub_wtab_neon; | |
| - pf->weight_cache = x264_weight_cache_neon; | |
| + pf->weight = mc_wtab_neon; | |
| + pf->offsetadd = mc_offsetadd_wtab_neon; | |
| + pf->offsetsub = mc_offsetsub_wtab_neon; | |
| + pf->weight_cache = weight_cache_neon; | |
| pf->mc_chroma = x264_mc_chroma_neon; | |
| pf->mc_luma = mc_luma_neon; | |
| @@ -271,7 +327,7 @@ | |
| pf->integral_init8v = x264_integral_init8v_neon; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_neon; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_neon; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_neon; | |
| pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_neon; | |
| pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_neon; | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/mc.h x264-go.new/x264c/external/x264/common/aarch64/mc.h | |
| --- x264-go/x264c/external/x264/common/aarch64/mc.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/mc.h 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc.h: aarch64 motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2014-2017 x264 project | |
| + * Copyright (C) 2014-2020 x264 project | |
| * | |
| * Authors: Janne Grunau <janne-x264@jannau.net> | |
| * | |
| @@ -26,6 +26,7 @@ | |
| #ifndef X264_AARCH64_MC_H | |
| #define X264_AARCH64_MC_H | |
| -void x264_mc_init_aarch64( int cpu, x264_mc_functions_t *pf ); | |
| +#define x264_mc_init_aarch64 x264_template(mc_init_aarch64) | |
| +void x264_mc_init_aarch64( uint32_t cpu, x264_mc_functions_t *pf ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: pixel-a.S | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/pixel.h x264-go.new/x264c/external/x264/common/aarch64/pixel.h | |
| --- x264-go/x264c/external/x264/common/aarch64/pixel.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/pixel.h 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * pixel.h: aarch64 pixel metrics | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,6 +27,44 @@ | |
| #ifndef X264_AARCH64_PIXEL_H | |
| #define X264_AARCH64_PIXEL_H | |
| +#define x264_pixel_sad_16x16_neon x264_template(pixel_sad_16x16_neon) | |
| +#define x264_pixel_sad_16x8_neon x264_template(pixel_sad_16x8_neon) | |
| +#define x264_pixel_sad_4x16_neon x264_template(pixel_sad_4x16_neon) | |
| +#define x264_pixel_sad_4x4_neon x264_template(pixel_sad_4x4_neon) | |
| +#define x264_pixel_sad_4x8_neon x264_template(pixel_sad_4x8_neon) | |
| +#define x264_pixel_sad_8x16_neon x264_template(pixel_sad_8x16_neon) | |
| +#define x264_pixel_sad_8x4_neon x264_template(pixel_sad_8x4_neon) | |
| +#define x264_pixel_sad_8x8_neon x264_template(pixel_sad_8x8_neon) | |
| +#define x264_pixel_sad_x3_16x16_neon x264_template(pixel_sad_x3_16x16_neon) | |
| +#define x264_pixel_sad_x3_16x8_neon x264_template(pixel_sad_x3_16x8_neon) | |
| +#define x264_pixel_sad_x3_4x4_neon x264_template(pixel_sad_x3_4x4_neon) | |
| +#define x264_pixel_sad_x3_4x8_neon x264_template(pixel_sad_x3_4x8_neon) | |
| +#define x264_pixel_sad_x3_8x16_neon x264_template(pixel_sad_x3_8x16_neon) | |
| +#define x264_pixel_sad_x3_8x4_neon x264_template(pixel_sad_x3_8x4_neon) | |
| +#define x264_pixel_sad_x3_8x8_neon x264_template(pixel_sad_x3_8x8_neon) | |
| +#define x264_pixel_sad_x4_16x16_neon x264_template(pixel_sad_x4_16x16_neon) | |
| +#define x264_pixel_sad_x4_16x8_neon x264_template(pixel_sad_x4_16x8_neon) | |
| +#define x264_pixel_sad_x4_4x4_neon x264_template(pixel_sad_x4_4x4_neon) | |
| +#define x264_pixel_sad_x4_4x8_neon x264_template(pixel_sad_x4_4x8_neon) | |
| +#define x264_pixel_sad_x4_8x16_neon x264_template(pixel_sad_x4_8x16_neon) | |
| +#define x264_pixel_sad_x4_8x4_neon x264_template(pixel_sad_x4_8x4_neon) | |
| +#define x264_pixel_sad_x4_8x8_neon x264_template(pixel_sad_x4_8x8_neon) | |
| +#define x264_pixel_satd_16x16_neon x264_template(pixel_satd_16x16_neon) | |
| +#define x264_pixel_satd_16x8_neon x264_template(pixel_satd_16x8_neon) | |
| +#define x264_pixel_satd_4x16_neon x264_template(pixel_satd_4x16_neon) | |
| +#define x264_pixel_satd_4x4_neon x264_template(pixel_satd_4x4_neon) | |
| +#define x264_pixel_satd_4x8_neon x264_template(pixel_satd_4x8_neon) | |
| +#define x264_pixel_satd_8x16_neon x264_template(pixel_satd_8x16_neon) | |
| +#define x264_pixel_satd_8x4_neon x264_template(pixel_satd_8x4_neon) | |
| +#define x264_pixel_satd_8x8_neon x264_template(pixel_satd_8x8_neon) | |
| +#define x264_pixel_ssd_16x16_neon x264_template(pixel_ssd_16x16_neon) | |
| +#define x264_pixel_ssd_16x8_neon x264_template(pixel_ssd_16x8_neon) | |
| +#define x264_pixel_ssd_4x16_neon x264_template(pixel_ssd_4x16_neon) | |
| +#define x264_pixel_ssd_4x4_neon x264_template(pixel_ssd_4x4_neon) | |
| +#define x264_pixel_ssd_4x8_neon x264_template(pixel_ssd_4x8_neon) | |
| +#define x264_pixel_ssd_8x16_neon x264_template(pixel_ssd_8x16_neon) | |
| +#define x264_pixel_ssd_8x4_neon x264_template(pixel_ssd_8x4_neon) | |
| +#define x264_pixel_ssd_8x8_neon x264_template(pixel_ssd_8x8_neon) | |
| #define DECL_PIXELS( ret, name, suffix, args ) \ | |
| ret x264_pixel_##name##_16x16_##suffix args;\ | |
| ret x264_pixel_##name##_16x8_##suffix args;\ | |
| @@ -50,30 +88,47 @@ | |
| DECL_X1( ssd, neon ) | |
| +#define x264_pixel_ssd_nv12_core_neon x264_template(pixel_ssd_nv12_core_neon) | |
| void x264_pixel_ssd_nv12_core_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int, int, uint64_t *, uint64_t * ); | |
| +#define x264_pixel_vsad_neon x264_template(pixel_vsad_neon) | |
| int x264_pixel_vsad_neon( uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_sa8d_8x8_neon x264_template(pixel_sa8d_8x8_neon) | |
| int x264_pixel_sa8d_8x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_sa8d_16x16_neon x264_template(pixel_sa8d_16x16_neon) | |
| int x264_pixel_sa8d_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_sa8d_satd_16x16_neon x264_template(pixel_sa8d_satd_16x16_neon) | |
| uint64_t x264_pixel_sa8d_satd_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_8x8_neon x264_template(pixel_var_8x8_neon) | |
| uint64_t x264_pixel_var_8x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_8x16_neon x264_template(pixel_var_8x16_neon) | |
| uint64_t x264_pixel_var_8x16_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_16x16_neon x264_template(pixel_var_16x16_neon) | |
| uint64_t x264_pixel_var_16x16_neon( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var2_8x8_neon x264_template(pixel_var2_8x8_neon) | |
| int x264_pixel_var2_8x8_neon ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_pixel_var2_8x16_neon x264_template(pixel_var2_8x16_neon) | |
| int x264_pixel_var2_8x16_neon( uint8_t *, uint8_t *, int * ); | |
| +#define x264_pixel_hadamard_ac_8x8_neon x264_template(pixel_hadamard_ac_8x8_neon) | |
| uint64_t x264_pixel_hadamard_ac_8x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_8x16_neon x264_template(pixel_hadamard_ac_8x16_neon) | |
| uint64_t x264_pixel_hadamard_ac_8x16_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_16x8_neon x264_template(pixel_hadamard_ac_16x8_neon) | |
| uint64_t x264_pixel_hadamard_ac_16x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_16x16_neon x264_template(pixel_hadamard_ac_16x16_neon) | |
| uint64_t x264_pixel_hadamard_ac_16x16_neon( uint8_t *, intptr_t ); | |
| +#define x264_pixel_ssim_4x4x2_core_neon x264_template(pixel_ssim_4x4x2_core_neon) | |
| void x264_pixel_ssim_4x4x2_core_neon( const uint8_t *, intptr_t, | |
| const uint8_t *, intptr_t, | |
| int sums[2][4] ); | |
| +#define x264_pixel_ssim_end4_neon x264_template(pixel_ssim_end4_neon) | |
| float x264_pixel_ssim_end4_neon( int sum0[5][4], int sum1[5][4], int width ); | |
| +#define x264_pixel_asd8_neon x264_template(pixel_asd8_neon) | |
| int x264_pixel_asd8_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: predict-a.S | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/predict-c.c x264-go.new/x264c/external/x264/common/aarch64/predict-c.c | |
| --- x264-go/x264c/external/x264/common/aarch64/predict-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/predict-c.c 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.c: aarch64 intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -28,30 +28,7 @@ | |
| #include "predict.h" | |
| #include "pixel.h" | |
| -void x264_predict_4x4_dc_top_neon( uint8_t *src ); | |
| -void x264_predict_4x4_ddr_neon( uint8_t *src ); | |
| -void x264_predict_4x4_ddl_neon( uint8_t *src ); | |
| - | |
| -void x264_predict_8x8c_dc_top_neon( uint8_t *src ); | |
| -void x264_predict_8x8c_dc_left_neon( uint8_t *src ); | |
| -void x264_predict_8x8c_p_neon( uint8_t *src ); | |
| - | |
| -void x264_predict_8x16c_dc_left_neon( uint8_t *src ); | |
| -void x264_predict_8x16c_dc_top_neon( uint8_t *src ); | |
| -void x264_predict_8x16c_p_neon( uint8_t *src ); | |
| - | |
| -void x264_predict_8x8_ddl_neon( uint8_t *src, uint8_t edge[36] ); | |
| -void x264_predict_8x8_ddr_neon( uint8_t *src, uint8_t edge[36] ); | |
| -void x264_predict_8x8_vl_neon( uint8_t *src, uint8_t edge[36] ); | |
| -void x264_predict_8x8_vr_neon( uint8_t *src, uint8_t edge[36] ); | |
| -void x264_predict_8x8_hd_neon( uint8_t *src, uint8_t edge[36] ); | |
| -void x264_predict_8x8_hu_neon( uint8_t *src, uint8_t edge[36] ); | |
| - | |
| -void x264_predict_16x16_dc_top_neon( uint8_t *src ); | |
| -void x264_predict_16x16_dc_left_neon( uint8_t *src ); | |
| -void x264_predict_16x16_p_neon( uint8_t *src ); | |
| - | |
| -void x264_predict_4x4_init_aarch64( int cpu, x264_predict_t pf[12] ) | |
| +void x264_predict_4x4_init_aarch64( uint32_t cpu, x264_predict_t pf[12] ) | |
| { | |
| #if !HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_ARMV8 ) | |
| @@ -70,7 +47,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_8x8c_init_aarch64( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x8c_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| #if !HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_ARMV8 ) | |
| @@ -90,7 +67,7 @@ | |
| } | |
| -void x264_predict_8x16c_init_aarch64( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x16c_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| @@ -105,7 +82,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_8x8_init_aarch64( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| +void x264_predict_8x8_init_aarch64( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| @@ -123,7 +100,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_16x16_init_aarch64( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_16x16_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/predict.h x264-go.new/x264c/external/x264/common/aarch64/predict.h | |
| --- x264-go/x264c/external/x264/common/aarch64/predict.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/predict.h 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.h: aarch64 intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,8 +27,11 @@ | |
| #ifndef X264_AARCH64_PREDICT_H | |
| #define X264_AARCH64_PREDICT_H | |
| +#define x264_predict_4x4_h_aarch64 x264_template(predict_4x4_h_aarch64) | |
| void x264_predict_4x4_h_aarch64( uint8_t *src ); | |
| +#define x264_predict_4x4_v_aarch64 x264_template(predict_4x4_v_aarch64) | |
| void x264_predict_4x4_v_aarch64( uint8_t *src ); | |
| +#define x264_predict_8x8c_v_aarch64 x264_template(predict_8x8c_v_aarch64) | |
| void x264_predict_8x8c_v_aarch64( uint8_t *src ); | |
| // for the merged 4x4 intra sad/satd which expects unified suffix | |
| @@ -36,23 +39,81 @@ | |
| #define x264_predict_4x4_v_neon x264_predict_4x4_v_aarch64 | |
| #define x264_predict_8x8c_v_neon x264_predict_8x8c_v_aarch64 | |
| +#define x264_predict_4x4_dc_top_neon x264_template(predict_4x4_dc_top_neon) | |
| +void x264_predict_4x4_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_4x4_ddr_neon x264_template(predict_4x4_ddr_neon) | |
| +void x264_predict_4x4_ddr_neon( uint8_t *src ); | |
| +#define x264_predict_4x4_ddl_neon x264_template(predict_4x4_ddl_neon) | |
| +void x264_predict_4x4_ddl_neon( uint8_t *src ); | |
| + | |
| +#define x264_predict_8x8c_dc_top_neon x264_template(predict_8x8c_dc_top_neon) | |
| +void x264_predict_8x8c_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_dc_left_neon x264_template(predict_8x8c_dc_left_neon) | |
| +void x264_predict_8x8c_dc_left_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_p_neon x264_template(predict_8x8c_p_neon) | |
| +void x264_predict_8x8c_p_neon( uint8_t *src ); | |
| + | |
| +#define x264_predict_8x16c_dc_left_neon x264_template(predict_8x16c_dc_left_neon) | |
| +void x264_predict_8x16c_dc_left_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_dc_top_neon x264_template(predict_8x16c_dc_top_neon) | |
| +void x264_predict_8x16c_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_p_neon x264_template(predict_8x16c_p_neon) | |
| +void x264_predict_8x16c_p_neon( uint8_t *src ); | |
| + | |
| +#define x264_predict_8x8_ddl_neon x264_template(predict_8x8_ddl_neon) | |
| +void x264_predict_8x8_ddl_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_ddr_neon x264_template(predict_8x8_ddr_neon) | |
| +void x264_predict_8x8_ddr_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vl_neon x264_template(predict_8x8_vl_neon) | |
| +void x264_predict_8x8_vl_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vr_neon x264_template(predict_8x8_vr_neon) | |
| +void x264_predict_8x8_vr_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_hd_neon x264_template(predict_8x8_hd_neon) | |
| +void x264_predict_8x8_hd_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_hu_neon x264_template(predict_8x8_hu_neon) | |
| +void x264_predict_8x8_hu_neon( uint8_t *src, uint8_t edge[36] ); | |
| + | |
| +#define x264_predict_16x16_dc_top_neon x264_template(predict_16x16_dc_top_neon) | |
| +void x264_predict_16x16_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_dc_left_neon x264_template(predict_16x16_dc_left_neon) | |
| +void x264_predict_16x16_dc_left_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_p_neon x264_template(predict_16x16_p_neon) | |
| +void x264_predict_16x16_p_neon( uint8_t *src ); | |
| + | |
| +#define x264_predict_4x4_dc_neon x264_template(predict_4x4_dc_neon) | |
| void x264_predict_4x4_dc_neon( uint8_t *src ); | |
| +#define x264_predict_8x8_v_neon x264_template(predict_8x8_v_neon) | |
| void x264_predict_8x8_v_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_h_neon x264_template(predict_8x8_h_neon) | |
| void x264_predict_8x8_h_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_dc_neon x264_template(predict_8x8_dc_neon) | |
| void x264_predict_8x8_dc_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8c_dc_neon x264_template(predict_8x8c_dc_neon) | |
| void x264_predict_8x8c_dc_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_h_neon x264_template(predict_8x8c_h_neon) | |
| void x264_predict_8x8c_h_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_v_neon x264_template(predict_8x16c_v_neon) | |
| void x264_predict_8x16c_v_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_h_neon x264_template(predict_8x16c_h_neon) | |
| void x264_predict_8x16c_h_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_dc_neon x264_template(predict_8x16c_dc_neon) | |
| void x264_predict_8x16c_dc_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_v_neon x264_template(predict_16x16_v_neon) | |
| void x264_predict_16x16_v_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_h_neon x264_template(predict_16x16_h_neon) | |
| void x264_predict_16x16_h_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_dc_neon x264_template(predict_16x16_dc_neon) | |
| void x264_predict_16x16_dc_neon( uint8_t *src ); | |
| -void x264_predict_4x4_init_aarch64( int cpu, x264_predict_t pf[12] ); | |
| -void x264_predict_8x8_init_aarch64( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| -void x264_predict_8x8c_init_aarch64( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x16c_init_aarch64( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_16x16_init_aarch64( int cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_4x4_init_aarch64 x264_template(predict_4x4_init_aarch64) | |
| +void x264_predict_4x4_init_aarch64( uint32_t cpu, x264_predict_t pf[12] ); | |
| +#define x264_predict_8x8_init_aarch64 x264_template(predict_8x8_init_aarch64) | |
| +void x264_predict_8x8_init_aarch64( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| +#define x264_predict_8x8c_init_aarch64 x264_template(predict_8x8c_init_aarch64) | |
| +void x264_predict_8x8c_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x16c_init_aarch64 x264_template(predict_8x16c_init_aarch64) | |
| +void x264_predict_8x16c_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_16x16_init_aarch64 x264_template(predict_16x16_init_aarch64) | |
| +void x264_predict_16x16_init_aarch64( uint32_t cpu, x264_predict_t pf[7] ); | |
| #endif /* X264_AARCH64_PREDICT_H */ | |
| Only in x264-go.new/x264c/external/x264/common/aarch64: quant-a.S | |
| diff -ur x264-go/x264c/external/x264/common/aarch64/quant.h x264-go.new/x264c/external/x264/common/aarch64/quant.h | |
| --- x264-go/x264c/external/x264/common/aarch64/quant.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/aarch64/quant.h 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * quant.h: arm quantization and level-run | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,33 +27,55 @@ | |
| #ifndef X264_AARCH64_QUANT_H | |
| #define X264_AARCH64_QUANT_H | |
| +#define x264_quant_2x2_dc_aarch64 x264_template(quant_2x2_dc_aarch64) | |
| int x264_quant_2x2_dc_aarch64( int16_t dct[4], int mf, int bias ); | |
| +#define x264_quant_2x2_dc_neon x264_template(quant_2x2_dc_neon) | |
| int x264_quant_2x2_dc_neon( int16_t dct[4], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_neon x264_template(quant_4x4_dc_neon) | |
| int x264_quant_4x4_dc_neon( int16_t dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_neon x264_template(quant_4x4_neon) | |
| int x264_quant_4x4_neon( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] ); | |
| +#define x264_quant_4x4x4_neon x264_template(quant_4x4x4_neon) | |
| int x264_quant_4x4x4_neon( int16_t dct[4][16], uint16_t mf[16], uint16_t bias[16] ); | |
| +#define x264_quant_8x8_neon x264_template(quant_8x8_neon) | |
| int x264_quant_8x8_neon( int16_t dct[64], uint16_t mf[64], uint16_t bias[64] ); | |
| +#define x264_dequant_4x4_dc_neon x264_template(dequant_4x4_dc_neon) | |
| void x264_dequant_4x4_dc_neon( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4_neon x264_template(dequant_4x4_neon) | |
| void x264_dequant_4x4_neon( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_neon x264_template(dequant_8x8_neon) | |
| void x264_dequant_8x8_neon( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_decimate_score15_neon x264_template(decimate_score15_neon) | |
| int x264_decimate_score15_neon( int16_t * ); | |
| +#define x264_decimate_score16_neon x264_template(decimate_score16_neon) | |
| int x264_decimate_score16_neon( int16_t * ); | |
| +#define x264_decimate_score64_neon x264_template(decimate_score64_neon) | |
| int x264_decimate_score64_neon( int16_t * ); | |
| +#define x264_coeff_last4_aarch64 x264_template(coeff_last4_aarch64) | |
| int x264_coeff_last4_aarch64( int16_t * ); | |
| +#define x264_coeff_last8_aarch64 x264_template(coeff_last8_aarch64) | |
| int x264_coeff_last8_aarch64( int16_t * ); | |
| +#define x264_coeff_last15_neon x264_template(coeff_last15_neon) | |
| int x264_coeff_last15_neon( int16_t * ); | |
| +#define x264_coeff_last16_neon x264_template(coeff_last16_neon) | |
| int x264_coeff_last16_neon( int16_t * ); | |
| +#define x264_coeff_last64_neon x264_template(coeff_last64_neon) | |
| int x264_coeff_last64_neon( int16_t * ); | |
| +#define x264_coeff_level_run4_aarch64 x264_template(coeff_level_run4_aarch64) | |
| int x264_coeff_level_run4_aarch64( int16_t *, x264_run_level_t * ); | |
| +#define x264_coeff_level_run8_neon x264_template(coeff_level_run8_neon) | |
| int x264_coeff_level_run8_neon( int16_t *, x264_run_level_t * ); | |
| +#define x264_coeff_level_run15_neon x264_template(coeff_level_run15_neon) | |
| int x264_coeff_level_run15_neon( int16_t *, x264_run_level_t * ); | |
| +#define x264_coeff_level_run16_neon x264_template(coeff_level_run16_neon) | |
| int x264_coeff_level_run16_neon( int16_t *, x264_run_level_t * ); | |
| +#define x264_denoise_dct_neon x264_template(denoise_dct_neon) | |
| void x264_denoise_dct_neon( dctcoef *, uint32_t *, udctcoef *, int ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/arm: asm.S | |
| Only in x264-go.new/x264c/external/x264/common/arm: bitstream-a.S | |
| Only in x264-go.new/x264c/external/x264/common/arm: bitstream.h | |
| Only in x264-go.new/x264c/external/x264/common/arm: cpu-a.S | |
| Only in x264-go.new/x264c/external/x264/common/arm: dct-a.S | |
| diff -ur x264-go/x264c/external/x264/common/arm/dct.h x264-go.new/x264c/external/x264/common/arm/dct.h | |
| --- x264-go/x264c/external/x264/common/arm/dct.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/dct.h 2020-06-06 15:20:58.685039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * dct.h: arm transform and zigzag | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -26,28 +26,45 @@ | |
| #ifndef X264_ARM_DCT_H | |
| #define X264_ARM_DCT_H | |
| +#define x264_dct4x4dc_neon x264_template(dct4x4dc_neon) | |
| void x264_dct4x4dc_neon( int16_t d[16] ); | |
| +#define x264_idct4x4dc_neon x264_template(idct4x4dc_neon) | |
| void x264_idct4x4dc_neon( int16_t d[16] ); | |
| +#define x264_sub4x4_dct_neon x264_template(sub4x4_dct_neon) | |
| void x264_sub4x4_dct_neon( int16_t dct[16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_neon x264_template(sub8x8_dct_neon) | |
| void x264_sub8x8_dct_neon( int16_t dct[4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_neon x264_template(sub16x16_dct_neon) | |
| void x264_sub16x16_dct_neon( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_add4x4_idct_neon x264_template(add4x4_idct_neon) | |
| void x264_add4x4_idct_neon( uint8_t *p_dst, int16_t dct[16] ); | |
| +#define x264_add8x8_idct_neon x264_template(add8x8_idct_neon) | |
| void x264_add8x8_idct_neon( uint8_t *p_dst, int16_t dct[4][16] ); | |
| +#define x264_add16x16_idct_neon x264_template(add16x16_idct_neon) | |
| void x264_add16x16_idct_neon( uint8_t *p_dst, int16_t dct[16][16] ); | |
| +#define x264_add8x8_idct_dc_neon x264_template(add8x8_idct_dc_neon) | |
| void x264_add8x8_idct_dc_neon( uint8_t *p_dst, int16_t dct[4] ); | |
| +#define x264_add16x16_idct_dc_neon x264_template(add16x16_idct_dc_neon) | |
| void x264_add16x16_idct_dc_neon( uint8_t *p_dst, int16_t dct[16] ); | |
| +#define x264_sub8x8_dct_dc_neon x264_template(sub8x8_dct_dc_neon) | |
| void x264_sub8x8_dct_dc_neon( int16_t dct[4], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x16_dct_dc_neon x264_template(sub8x16_dct_dc_neon) | |
| void x264_sub8x16_dct_dc_neon( int16_t dct[8], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct8_neon x264_template(sub8x8_dct8_neon) | |
| void x264_sub8x8_dct8_neon( int16_t dct[64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct8_neon x264_template(sub16x16_dct8_neon) | |
| void x264_sub16x16_dct8_neon( int16_t dct[4][64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_add8x8_idct8_neon x264_template(add8x8_idct8_neon) | |
| void x264_add8x8_idct8_neon( uint8_t *p_dst, int16_t dct[64] ); | |
| +#define x264_add16x16_idct8_neon x264_template(add16x16_idct8_neon) | |
| void x264_add16x16_idct8_neon( uint8_t *p_dst, int16_t dct[4][64] ); | |
| +#define x264_zigzag_scan_4x4_frame_neon x264_template(zigzag_scan_4x4_frame_neon) | |
| void x264_zigzag_scan_4x4_frame_neon( int16_t level[16], int16_t dct[16] ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/arm: deblock-a.S | |
| Only in x264-go.new/x264c/external/x264/common/arm: deblock.h | |
| Only in x264-go.new/x264c/external/x264/common/arm: mc-a.S | |
| diff -ur x264-go/x264c/external/x264/common/arm/mc-c.c x264-go.new/x264c/external/x264/common/arm/mc-c.c | |
| --- x264-go/x264c/external/x264/common/arm/mc-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/mc-c.c 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc-c.c: arm motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * Janne Grunau <janne-x264@jannau.net> | |
| @@ -27,46 +27,87 @@ | |
| #include "common/common.h" | |
| #include "mc.h" | |
| +#define x264_prefetch_ref_arm x264_template(prefetch_ref_arm) | |
| void x264_prefetch_ref_arm( uint8_t *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_arm x264_template(prefetch_fenc_arm) | |
| void x264_prefetch_fenc_arm( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_memcpy_aligned_neon x264_template(memcpy_aligned_neon) | |
| void *x264_memcpy_aligned_neon( void *dst, const void *src, size_t n ); | |
| +#define x264_memzero_aligned_neon x264_template(memzero_aligned_neon) | |
| void x264_memzero_aligned_neon( void *dst, size_t n ); | |
| +#define x264_pixel_avg_16x16_neon x264_template(pixel_avg_16x16_neon) | |
| void x264_pixel_avg_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_16x8_neon x264_template(pixel_avg_16x8_neon) | |
| void x264_pixel_avg_16x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x16_neon x264_template(pixel_avg_8x16_neon) | |
| void x264_pixel_avg_8x16_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x8_neon x264_template(pixel_avg_8x8_neon) | |
| void x264_pixel_avg_8x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_8x4_neon x264_template(pixel_avg_8x4_neon) | |
| void x264_pixel_avg_8x4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x16_neon x264_template(pixel_avg_4x16_neon) | |
| void x264_pixel_avg_4x16_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x8_neon x264_template(pixel_avg_4x8_neon) | |
| void x264_pixel_avg_4x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x4_neon x264_template(pixel_avg_4x4_neon) | |
| void x264_pixel_avg_4x4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg_4x2_neon x264_template(pixel_avg_4x2_neon) | |
| void x264_pixel_avg_4x2_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_avg2_w4_neon x264_template(pixel_avg2_w4_neon) | |
| void x264_pixel_avg2_w4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w8_neon x264_template(pixel_avg2_w8_neon) | |
| void x264_pixel_avg2_w8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w16_neon x264_template(pixel_avg2_w16_neon) | |
| void x264_pixel_avg2_w16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_pixel_avg2_w20_neon x264_template(pixel_avg2_w20_neon) | |
| void x264_pixel_avg2_w20_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ); | |
| +#define x264_plane_copy_core_neon x264_template(plane_copy_core_neon) | |
| void x264_plane_copy_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_neon x264_template(plane_copy_deinterleave_neon) | |
| void x264_plane_copy_deinterleave_neon( pixel *dstu, intptr_t i_dstu, | |
| pixel *dstv, intptr_t i_dstv, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_rgb_neon x264_template(plane_copy_deinterleave_rgb_neon) | |
| void x264_plane_copy_deinterleave_rgb_neon( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *dstc, intptr_t i_dstc, | |
| pixel *src, intptr_t i_src, int pw, int w, int h ); | |
| +#define x264_plane_copy_interleave_core_neon x264_template(plane_copy_interleave_core_neon) | |
| void x264_plane_copy_interleave_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| +#define x264_plane_copy_swap_core_neon x264_template(plane_copy_swap_core_neon) | |
| void x264_plane_copy_swap_core_neon( pixel *dst, intptr_t i_dst, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_store_interleave_chroma_neon x264_template(store_interleave_chroma_neon) | |
| void x264_store_interleave_chroma_neon( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_neon x264_template(load_deinterleave_chroma_fdec_neon) | |
| void x264_load_deinterleave_chroma_fdec_neon( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_neon x264_template(load_deinterleave_chroma_fenc_neon) | |
| void x264_load_deinterleave_chroma_fenc_neon( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_mc_weight_w16_neon x264_template(mc_weight_w16_neon) | |
| +#define x264_mc_weight_w16_nodenom_neon x264_template(mc_weight_w16_nodenom_neon) | |
| +#define x264_mc_weight_w16_offsetadd_neon x264_template(mc_weight_w16_offsetadd_neon) | |
| +#define x264_mc_weight_w16_offsetsub_neon x264_template(mc_weight_w16_offsetsub_neon) | |
| +#define x264_mc_weight_w20_neon x264_template(mc_weight_w20_neon) | |
| +#define x264_mc_weight_w20_nodenom_neon x264_template(mc_weight_w20_nodenom_neon) | |
| +#define x264_mc_weight_w20_offsetadd_neon x264_template(mc_weight_w20_offsetadd_neon) | |
| +#define x264_mc_weight_w20_offsetsub_neon x264_template(mc_weight_w20_offsetsub_neon) | |
| +#define x264_mc_weight_w4_neon x264_template(mc_weight_w4_neon) | |
| +#define x264_mc_weight_w4_nodenom_neon x264_template(mc_weight_w4_nodenom_neon) | |
| +#define x264_mc_weight_w4_offsetadd_neon x264_template(mc_weight_w4_offsetadd_neon) | |
| +#define x264_mc_weight_w4_offsetsub_neon x264_template(mc_weight_w4_offsetsub_neon) | |
| +#define x264_mc_weight_w8_neon x264_template(mc_weight_w8_neon) | |
| +#define x264_mc_weight_w8_nodenom_neon x264_template(mc_weight_w8_nodenom_neon) | |
| +#define x264_mc_weight_w8_offsetadd_neon x264_template(mc_weight_w8_offsetadd_neon) | |
| +#define x264_mc_weight_w8_offsetsub_neon x264_template(mc_weight_w8_offsetsub_neon) | |
| #if !HIGH_BIT_DEPTH | |
| #define MC_WEIGHT(func)\ | |
| void x264_mc_weight_w20##func##_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| @@ -74,7 +115,7 @@ | |
| void x264_mc_weight_w8##func##_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| void x264_mc_weight_w4##func##_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\ | |
| \ | |
| -static weight_fn_t x264_mc##func##_wtab_neon[6] =\ | |
| +static weight_fn_t mc##func##_wtab_neon[6] =\ | |
| {\ | |
| x264_mc_weight_w4##func##_neon,\ | |
| x264_mc_weight_w4##func##_neon,\ | |
| @@ -90,51 +131,67 @@ | |
| MC_WEIGHT(_offsetsub) | |
| #endif | |
| +#define x264_mc_copy_w4_neon x264_template(mc_copy_w4_neon) | |
| void x264_mc_copy_w4_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w8_neon x264_template(mc_copy_w8_neon) | |
| void x264_mc_copy_w8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_neon x264_template(mc_copy_w16_neon) | |
| void x264_mc_copy_w16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_aligned_neon x264_template(mc_copy_w16_aligned_neon) | |
| void x264_mc_copy_w16_aligned_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| +#define x264_mc_chroma_neon x264_template(mc_chroma_neon) | |
| void x264_mc_chroma_neon( uint8_t *, uint8_t *, intptr_t, uint8_t *, intptr_t, int, int, int, int ); | |
| +#define x264_frame_init_lowres_core_neon x264_template(frame_init_lowres_core_neon) | |
| void x264_frame_init_lowres_core_neon( uint8_t *, uint8_t *, uint8_t *, uint8_t *, uint8_t *, intptr_t, intptr_t, int, int ); | |
| +#define x264_hpel_filter_v_neon x264_template(hpel_filter_v_neon) | |
| void x264_hpel_filter_v_neon( uint8_t *, uint8_t *, int16_t *, intptr_t, int ); | |
| +#define x264_hpel_filter_c_neon x264_template(hpel_filter_c_neon) | |
| void x264_hpel_filter_c_neon( uint8_t *, int16_t *, int ); | |
| +#define x264_hpel_filter_h_neon x264_template(hpel_filter_h_neon) | |
| void x264_hpel_filter_h_neon( uint8_t *, uint8_t *, int ); | |
| +#define x264_integral_init4h_neon x264_template(integral_init4h_neon) | |
| void x264_integral_init4h_neon( uint16_t *, uint8_t *, intptr_t ); | |
| +#define x264_integral_init4v_neon x264_template(integral_init4v_neon) | |
| void x264_integral_init4v_neon( uint16_t *, uint16_t *, intptr_t ); | |
| +#define x264_integral_init8h_neon x264_template(integral_init8h_neon) | |
| void x264_integral_init8h_neon( uint16_t *, uint8_t *, intptr_t ); | |
| +#define x264_integral_init8v_neon x264_template(integral_init8v_neon) | |
| void x264_integral_init8v_neon( uint16_t *, intptr_t ); | |
| +#define x264_mbtree_propagate_cost_neon x264_template(mbtree_propagate_cost_neon) | |
| void x264_mbtree_propagate_cost_neon( int16_t *, uint16_t *, uint16_t *, uint16_t *, uint16_t *, float *, int ); | |
| +#define x264_mbtree_fix8_pack_neon x264_template(mbtree_fix8_pack_neon) | |
| void x264_mbtree_fix8_pack_neon( uint16_t *dst, float *src, int count ); | |
| +#define x264_mbtree_fix8_unpack_neon x264_template(mbtree_fix8_unpack_neon) | |
| void x264_mbtree_fix8_unpack_neon( float *dst, uint16_t *src, int count ); | |
| #if !HIGH_BIT_DEPTH | |
| -static void x264_weight_cache_neon( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache_neon( x264_t *h, x264_weight_t *w ) | |
| { | |
| if( w->i_scale == 1<<w->i_denom ) | |
| { | |
| if( w->i_offset < 0 ) | |
| { | |
| - w->weightfn = x264_mc_offsetsub_wtab_neon; | |
| + w->weightfn = mc_offsetsub_wtab_neon; | |
| w->cachea[0] = -w->i_offset; | |
| } | |
| else | |
| { | |
| - w->weightfn = x264_mc_offsetadd_wtab_neon; | |
| + w->weightfn = mc_offsetadd_wtab_neon; | |
| w->cachea[0] = w->i_offset; | |
| } | |
| } | |
| else if( !w->i_denom ) | |
| - w->weightfn = x264_mc_nodenom_wtab_neon; | |
| + w->weightfn = mc_nodenom_wtab_neon; | |
| else | |
| - w->weightfn = x264_mc_wtab_neon; | |
| + w->weightfn = mc_wtab_neon; | |
| } | |
| -static void (* const x264_pixel_avg_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ) = | |
| +static void (* const pixel_avg_wtab_neon[6])( uint8_t *, intptr_t, uint8_t *, intptr_t, uint8_t *, int ) = | |
| { | |
| NULL, | |
| x264_pixel_avg2_w4_neon, | |
| @@ -144,7 +201,7 @@ | |
| x264_pixel_avg2_w20_neon, | |
| }; | |
| -static void (* const x264_mc_copy_wtab_neon[5])( uint8_t *, intptr_t, uint8_t *, intptr_t, int ) = | |
| +static void (* const mc_copy_wtab_neon[5])( uint8_t *, intptr_t, uint8_t *, intptr_t, int ) = | |
| { | |
| NULL, | |
| x264_mc_copy_w4_neon, | |
| @@ -167,7 +224,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */ | |
| { | |
| uint8_t *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3); | |
| - x264_pixel_avg_wtab_neon[i_width>>2]( | |
| + pixel_avg_wtab_neon[i_width>>2]( | |
| dst, i_dst_stride, src1, i_src_stride, | |
| src2, i_height ); | |
| if( weight->weightfn ) | |
| @@ -176,7 +233,7 @@ | |
| else if( weight->weightfn ) | |
| weight->weightfn[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, weight, i_height ); | |
| else | |
| - x264_mc_copy_wtab_neon[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, i_height ); | |
| + mc_copy_wtab_neon[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, i_height ); | |
| } | |
| static uint8_t *get_ref_neon( uint8_t *dst, intptr_t *i_dst_stride, | |
| @@ -193,7 +250,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */ | |
| { | |
| uint8_t *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3); | |
| - x264_pixel_avg_wtab_neon[i_width>>2]( | |
| + pixel_avg_wtab_neon[i_width>>2]( | |
| dst, *i_dst_stride, src1, i_src_stride, | |
| src2, i_height ); | |
| if( weight->weightfn ) | |
| @@ -236,11 +293,10 @@ | |
| PLANE_COPY(16, neon) | |
| PLANE_COPY_SWAP(16, neon) | |
| PLANE_INTERLEAVE(neon) | |
| -#endif // !HIGH_BIT_DEPTH | |
| - | |
| PROPAGATE_LIST(neon) | |
| +#endif // !HIGH_BIT_DEPTH | |
| -void x264_mc_init_arm( int cpu, x264_mc_functions_t *pf ) | |
| +void x264_mc_init_arm( uint32_t cpu, x264_mc_functions_t *pf ) | |
| { | |
| if( !(cpu&X264_CPU_ARMV6) ) | |
| return; | |
| @@ -260,11 +316,11 @@ | |
| pf->copy[PIXEL_8x8] = x264_mc_copy_w8_neon; | |
| pf->copy[PIXEL_4x4] = x264_mc_copy_w4_neon; | |
| - pf->plane_copy = x264_plane_copy_neon; | |
| + pf->plane_copy = plane_copy_neon; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_neon; | |
| pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_neon; | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_neon; | |
| - pf->plane_copy_swap = x264_plane_copy_swap_neon; | |
| + pf->plane_copy_interleave = plane_copy_interleave_neon; | |
| + pf->plane_copy_swap = plane_copy_swap_neon; | |
| pf->store_interleave_chroma = x264_store_interleave_chroma_neon; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_neon; | |
| @@ -280,10 +336,10 @@ | |
| pf->avg[PIXEL_4x4] = x264_pixel_avg_4x4_neon; | |
| pf->avg[PIXEL_4x2] = x264_pixel_avg_4x2_neon; | |
| - pf->weight = x264_mc_wtab_neon; | |
| - pf->offsetadd = x264_mc_offsetadd_wtab_neon; | |
| - pf->offsetsub = x264_mc_offsetsub_wtab_neon; | |
| - pf->weight_cache = x264_weight_cache_neon; | |
| + pf->weight = mc_wtab_neon; | |
| + pf->offsetadd = mc_offsetadd_wtab_neon; | |
| + pf->offsetsub = mc_offsetsub_wtab_neon; | |
| + pf->weight_cache = weight_cache_neon; | |
| pf->mc_chroma = x264_mc_chroma_neon; | |
| pf->mc_luma = mc_luma_neon; | |
| @@ -297,7 +353,7 @@ | |
| pf->integral_init8v = x264_integral_init8v_neon; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_neon; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_neon; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_neon; | |
| pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_neon; | |
| pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_neon; | |
| #endif // !HIGH_BIT_DEPTH | |
| diff -ur x264-go/x264c/external/x264/common/arm/mc.h x264-go.new/x264c/external/x264/common/arm/mc.h | |
| --- x264-go/x264c/external/x264/common/arm/mc.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/mc.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc.h: arm motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -26,6 +26,7 @@ | |
| #ifndef X264_ARM_MC_H | |
| #define X264_ARM_MC_H | |
| -void x264_mc_init_arm( int cpu, x264_mc_functions_t *pf ); | |
| +#define x264_mc_init_arm x264_template(mc_init_arm) | |
| +void x264_mc_init_arm( uint32_t cpu, x264_mc_functions_t *pf ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/arm: pixel-a.S | |
| diff -ur x264-go/x264c/external/x264/common/arm/pixel.h x264-go.new/x264c/external/x264/common/arm/pixel.h | |
| --- x264-go/x264c/external/x264/common/arm/pixel.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/pixel.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * pixel.h: arm pixel metrics | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -26,6 +26,68 @@ | |
| #ifndef X264_ARM_PIXEL_H | |
| #define X264_ARM_PIXEL_H | |
| +#define x264_pixel_avg2_w16_neon x264_template(pixel_avg2_w16_neon) | |
| +#define x264_pixel_avg2_w20_neon x264_template(pixel_avg2_w20_neon) | |
| +#define x264_pixel_avg2_w4_neon x264_template(pixel_avg2_w4_neon) | |
| +#define x264_pixel_avg2_w8_neon x264_template(pixel_avg2_w8_neon) | |
| +#define x264_pixel_avg_16x16_neon x264_template(pixel_avg_16x16_neon) | |
| +#define x264_pixel_avg_16x8_neon x264_template(pixel_avg_16x8_neon) | |
| +#define x264_pixel_avg_4x16_neon x264_template(pixel_avg_4x16_neon) | |
| +#define x264_pixel_avg_4x2_neon x264_template(pixel_avg_4x2_neon) | |
| +#define x264_pixel_avg_4x4_neon x264_template(pixel_avg_4x4_neon) | |
| +#define x264_pixel_avg_4x8_neon x264_template(pixel_avg_4x8_neon) | |
| +#define x264_pixel_avg_8x16_neon x264_template(pixel_avg_8x16_neon) | |
| +#define x264_pixel_avg_8x4_neon x264_template(pixel_avg_8x4_neon) | |
| +#define x264_pixel_avg_8x8_neon x264_template(pixel_avg_8x8_neon) | |
| +#define x264_pixel_sad_16x16_neon x264_template(pixel_sad_16x16_neon) | |
| +#define x264_pixel_sad_16x8_neon x264_template(pixel_sad_16x8_neon) | |
| +#define x264_pixel_sad_4x4_armv6 x264_template(pixel_sad_4x4_armv6) | |
| +#define x264_pixel_sad_4x4_neon x264_template(pixel_sad_4x4_neon) | |
| +#define x264_pixel_sad_4x8_armv6 x264_template(pixel_sad_4x8_armv6) | |
| +#define x264_pixel_sad_4x8_neon x264_template(pixel_sad_4x8_neon) | |
| +#define x264_pixel_sad_8x16_neon x264_template(pixel_sad_8x16_neon) | |
| +#define x264_pixel_sad_8x4_neon x264_template(pixel_sad_8x4_neon) | |
| +#define x264_pixel_sad_8x8_neon x264_template(pixel_sad_8x8_neon) | |
| +#define x264_pixel_sad_aligned_16x16_neon x264_template(pixel_sad_aligned_16x16_neon) | |
| +#define x264_pixel_sad_aligned_16x16_neon_dual x264_template(pixel_sad_aligned_16x16_neon_dual) | |
| +#define x264_pixel_sad_aligned_16x8_neon x264_template(pixel_sad_aligned_16x8_neon) | |
| +#define x264_pixel_sad_aligned_16x8_neon_dual x264_template(pixel_sad_aligned_16x8_neon_dual) | |
| +#define x264_pixel_sad_aligned_4x4_neon x264_template(pixel_sad_aligned_4x4_neon) | |
| +#define x264_pixel_sad_aligned_4x8_neon x264_template(pixel_sad_aligned_4x8_neon) | |
| +#define x264_pixel_sad_aligned_8x16_neon x264_template(pixel_sad_aligned_8x16_neon) | |
| +#define x264_pixel_sad_aligned_8x16_neon_dual x264_template(pixel_sad_aligned_8x16_neon_dual) | |
| +#define x264_pixel_sad_aligned_8x4_neon x264_template(pixel_sad_aligned_8x4_neon) | |
| +#define x264_pixel_sad_aligned_8x4_neon_dual x264_template(pixel_sad_aligned_8x4_neon_dual) | |
| +#define x264_pixel_sad_aligned_8x8_neon x264_template(pixel_sad_aligned_8x8_neon) | |
| +#define x264_pixel_sad_aligned_8x8_neon_dual x264_template(pixel_sad_aligned_8x8_neon_dual) | |
| +#define x264_pixel_sad_x3_16x16_neon x264_template(pixel_sad_x3_16x16_neon) | |
| +#define x264_pixel_sad_x3_16x8_neon x264_template(pixel_sad_x3_16x8_neon) | |
| +#define x264_pixel_sad_x3_4x4_neon x264_template(pixel_sad_x3_4x4_neon) | |
| +#define x264_pixel_sad_x3_4x8_neon x264_template(pixel_sad_x3_4x8_neon) | |
| +#define x264_pixel_sad_x3_8x16_neon x264_template(pixel_sad_x3_8x16_neon) | |
| +#define x264_pixel_sad_x3_8x4_neon x264_template(pixel_sad_x3_8x4_neon) | |
| +#define x264_pixel_sad_x3_8x8_neon x264_template(pixel_sad_x3_8x8_neon) | |
| +#define x264_pixel_sad_x4_16x16_neon x264_template(pixel_sad_x4_16x16_neon) | |
| +#define x264_pixel_sad_x4_16x8_neon x264_template(pixel_sad_x4_16x8_neon) | |
| +#define x264_pixel_sad_x4_4x4_neon x264_template(pixel_sad_x4_4x4_neon) | |
| +#define x264_pixel_sad_x4_4x8_neon x264_template(pixel_sad_x4_4x8_neon) | |
| +#define x264_pixel_sad_x4_8x16_neon x264_template(pixel_sad_x4_8x16_neon) | |
| +#define x264_pixel_sad_x4_8x4_neon x264_template(pixel_sad_x4_8x4_neon) | |
| +#define x264_pixel_sad_x4_8x8_neon x264_template(pixel_sad_x4_8x8_neon) | |
| +#define x264_pixel_satd_16x16_neon x264_template(pixel_satd_16x16_neon) | |
| +#define x264_pixel_satd_16x8_neon x264_template(pixel_satd_16x8_neon) | |
| +#define x264_pixel_satd_4x4_neon x264_template(pixel_satd_4x4_neon) | |
| +#define x264_pixel_satd_4x8_neon x264_template(pixel_satd_4x8_neon) | |
| +#define x264_pixel_satd_8x16_neon x264_template(pixel_satd_8x16_neon) | |
| +#define x264_pixel_satd_8x4_neon x264_template(pixel_satd_8x4_neon) | |
| +#define x264_pixel_satd_8x8_neon x264_template(pixel_satd_8x8_neon) | |
| +#define x264_pixel_ssd_16x16_neon x264_template(pixel_ssd_16x16_neon) | |
| +#define x264_pixel_ssd_16x8_neon x264_template(pixel_ssd_16x8_neon) | |
| +#define x264_pixel_ssd_4x4_neon x264_template(pixel_ssd_4x4_neon) | |
| +#define x264_pixel_ssd_4x8_neon x264_template(pixel_ssd_4x8_neon) | |
| +#define x264_pixel_ssd_8x16_neon x264_template(pixel_ssd_8x16_neon) | |
| +#define x264_pixel_ssd_8x4_neon x264_template(pixel_ssd_8x4_neon) | |
| +#define x264_pixel_ssd_8x8_neon x264_template(pixel_ssd_8x8_neon) | |
| #define DECL_PIXELS( ret, name, suffix, args ) \ | |
| ret x264_pixel_##name##_16x16_##suffix args;\ | |
| ret x264_pixel_##name##_16x8_##suffix args;\ | |
| @@ -52,30 +114,47 @@ | |
| DECL_X1( satd, neon ) | |
| DECL_X1( ssd, neon ) | |
| +#define x264_pixel_ssd_nv12_core_neon x264_template(pixel_ssd_nv12_core_neon) | |
| void x264_pixel_ssd_nv12_core_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int, int, uint64_t *, uint64_t * ); | |
| +#define x264_pixel_vsad_neon x264_template(pixel_vsad_neon) | |
| int x264_pixel_vsad_neon( uint8_t *, intptr_t, int ); | |
| +#define x264_pixel_sa8d_8x8_neon x264_template(pixel_sa8d_8x8_neon) | |
| int x264_pixel_sa8d_8x8_neon ( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_sa8d_16x16_neon x264_template(pixel_sa8d_16x16_neon) | |
| int x264_pixel_sa8d_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_sa8d_satd_16x16_neon x264_template(pixel_sa8d_satd_16x16_neon) | |
| uint64_t x264_pixel_sa8d_satd_16x16_neon( uint8_t *, intptr_t, uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_8x8_neon x264_template(pixel_var_8x8_neon) | |
| uint64_t x264_pixel_var_8x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_8x16_neon x264_template(pixel_var_8x16_neon) | |
| uint64_t x264_pixel_var_8x16_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var_16x16_neon x264_template(pixel_var_16x16_neon) | |
| uint64_t x264_pixel_var_16x16_neon( uint8_t *, intptr_t ); | |
| +#define x264_pixel_var2_8x8_neon x264_template(pixel_var2_8x8_neon) | |
| int x264_pixel_var2_8x8_neon ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_pixel_var2_8x16_neon x264_template(pixel_var2_8x16_neon) | |
| int x264_pixel_var2_8x16_neon( uint8_t *, uint8_t *, int * ); | |
| +#define x264_pixel_hadamard_ac_8x8_neon x264_template(pixel_hadamard_ac_8x8_neon) | |
| uint64_t x264_pixel_hadamard_ac_8x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_8x16_neon x264_template(pixel_hadamard_ac_8x16_neon) | |
| uint64_t x264_pixel_hadamard_ac_8x16_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_16x8_neon x264_template(pixel_hadamard_ac_16x8_neon) | |
| uint64_t x264_pixel_hadamard_ac_16x8_neon ( uint8_t *, intptr_t ); | |
| +#define x264_pixel_hadamard_ac_16x16_neon x264_template(pixel_hadamard_ac_16x16_neon) | |
| uint64_t x264_pixel_hadamard_ac_16x16_neon( uint8_t *, intptr_t ); | |
| +#define x264_pixel_ssim_4x4x2_core_neon x264_template(pixel_ssim_4x4x2_core_neon) | |
| void x264_pixel_ssim_4x4x2_core_neon( const uint8_t *, intptr_t, | |
| const uint8_t *, intptr_t, | |
| int sums[2][4] ); | |
| +#define x264_pixel_ssim_end4_neon x264_template(pixel_ssim_end4_neon) | |
| float x264_pixel_ssim_end4_neon( int sum0[5][4], int sum1[5][4], int width ); | |
| +#define x264_pixel_asd8_neon x264_template(pixel_asd8_neon) | |
| int x264_pixel_asd8_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, int ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/arm: predict-a.S | |
| diff -ur x264-go/x264c/external/x264/common/arm/predict-c.c x264-go.new/x264c/external/x264/common/arm/predict-c.c | |
| --- x264-go/x264c/external/x264/common/arm/predict-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/predict-c.c 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.c: arm intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -27,7 +27,7 @@ | |
| #include "predict.h" | |
| #include "pixel.h" | |
| -void x264_predict_4x4_init_arm( int cpu, x264_predict_t pf[12] ) | |
| +void x264_predict_4x4_init_arm( uint32_t cpu, x264_predict_t pf[12] ) | |
| { | |
| if( !(cpu&X264_CPU_ARMV6) ) | |
| return; | |
| @@ -46,7 +46,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_8x8c_init_arm( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x8c_init_arm( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| @@ -61,7 +61,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_8x16c_init_arm( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x16c_init_arm( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| @@ -74,7 +74,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_8x8_init_arm( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| +void x264_predict_8x8_init_arm( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| @@ -92,7 +92,7 @@ | |
| #endif // !HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_16x16_init_arm( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_16x16_init_arm( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_NEON) ) | |
| return; | |
| diff -ur x264-go/x264c/external/x264/common/arm/predict.h x264-go.new/x264c/external/x264/common/arm/predict.h | |
| --- x264-go/x264c/external/x264/common/arm/predict.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/predict.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.h: arm intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2009-2017 x264 project | |
| + * Copyright (C) 2009-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -26,45 +26,80 @@ | |
| #ifndef X264_ARM_PREDICT_H | |
| #define X264_ARM_PREDICT_H | |
| +#define x264_predict_4x4_dc_armv6 x264_template(predict_4x4_dc_armv6) | |
| void x264_predict_4x4_dc_armv6( uint8_t *src ); | |
| +#define x264_predict_4x4_dc_top_neon x264_template(predict_4x4_dc_top_neon) | |
| void x264_predict_4x4_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_4x4_v_armv6 x264_template(predict_4x4_v_armv6) | |
| void x264_predict_4x4_v_armv6( uint8_t *src ); | |
| +#define x264_predict_4x4_h_armv6 x264_template(predict_4x4_h_armv6) | |
| void x264_predict_4x4_h_armv6( uint8_t *src ); | |
| +#define x264_predict_4x4_ddr_armv6 x264_template(predict_4x4_ddr_armv6) | |
| void x264_predict_4x4_ddr_armv6( uint8_t *src ); | |
| +#define x264_predict_4x4_ddl_neon x264_template(predict_4x4_ddl_neon) | |
| void x264_predict_4x4_ddl_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_dc_neon x264_template(predict_8x8c_dc_neon) | |
| void x264_predict_8x8c_dc_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_dc_top_neon x264_template(predict_8x8c_dc_top_neon) | |
| void x264_predict_8x8c_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_dc_left_neon x264_template(predict_8x8c_dc_left_neon) | |
| void x264_predict_8x8c_dc_left_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_h_neon x264_template(predict_8x8c_h_neon) | |
| void x264_predict_8x8c_h_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_v_neon x264_template(predict_8x8c_v_neon) | |
| void x264_predict_8x8c_v_neon( uint8_t *src ); | |
| +#define x264_predict_8x8c_p_neon x264_template(predict_8x8c_p_neon) | |
| void x264_predict_8x8c_p_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_h_neon x264_template(predict_8x16c_h_neon) | |
| void x264_predict_8x16c_h_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_dc_top_neon x264_template(predict_8x16c_dc_top_neon) | |
| void x264_predict_8x16c_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_8x16c_p_neon x264_template(predict_8x16c_p_neon) | |
| void x264_predict_8x16c_p_neon( uint8_t *src ); | |
| +#define x264_predict_8x8_dc_neon x264_template(predict_8x8_dc_neon) | |
| void x264_predict_8x8_dc_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_ddl_neon x264_template(predict_8x8_ddl_neon) | |
| void x264_predict_8x8_ddl_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_ddr_neon x264_template(predict_8x8_ddr_neon) | |
| void x264_predict_8x8_ddr_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vl_neon x264_template(predict_8x8_vl_neon) | |
| void x264_predict_8x8_vl_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vr_neon x264_template(predict_8x8_vr_neon) | |
| void x264_predict_8x8_vr_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_v_neon x264_template(predict_8x8_v_neon) | |
| void x264_predict_8x8_v_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_h_neon x264_template(predict_8x8_h_neon) | |
| void x264_predict_8x8_h_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_hd_neon x264_template(predict_8x8_hd_neon) | |
| void x264_predict_8x8_hd_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_hu_neon x264_template(predict_8x8_hu_neon) | |
| void x264_predict_8x8_hu_neon( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_16x16_dc_neon x264_template(predict_16x16_dc_neon) | |
| void x264_predict_16x16_dc_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_dc_top_neon x264_template(predict_16x16_dc_top_neon) | |
| void x264_predict_16x16_dc_top_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_dc_left_neon x264_template(predict_16x16_dc_left_neon) | |
| void x264_predict_16x16_dc_left_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_h_neon x264_template(predict_16x16_h_neon) | |
| void x264_predict_16x16_h_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_v_neon x264_template(predict_16x16_v_neon) | |
| void x264_predict_16x16_v_neon( uint8_t *src ); | |
| +#define x264_predict_16x16_p_neon x264_template(predict_16x16_p_neon) | |
| void x264_predict_16x16_p_neon( uint8_t *src ); | |
| -void x264_predict_4x4_init_arm( int cpu, x264_predict_t pf[12] ); | |
| -void x264_predict_8x8_init_arm( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| -void x264_predict_8x8c_init_arm( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x16c_init_arm( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_16x16_init_arm( int cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_4x4_init_arm x264_template(predict_4x4_init_arm) | |
| +void x264_predict_4x4_init_arm( uint32_t cpu, x264_predict_t pf[12] ); | |
| +#define x264_predict_8x8_init_arm x264_template(predict_8x8_init_arm) | |
| +void x264_predict_8x8_init_arm( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| +#define x264_predict_8x8c_init_arm x264_template(predict_8x8c_init_arm) | |
| +void x264_predict_8x8c_init_arm( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x16c_init_arm x264_template(predict_8x16c_init_arm) | |
| +void x264_predict_8x16c_init_arm( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_16x16_init_arm x264_template(predict_16x16_init_arm) | |
| +void x264_predict_16x16_init_arm( uint32_t cpu, x264_predict_t pf[7] ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/arm: quant-a.S | |
| diff -ur x264-go/x264c/external/x264/common/arm/quant.h x264-go.new/x264c/external/x264/common/arm/quant.h | |
| --- x264-go/x264c/external/x264/common/arm/quant.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/arm/quant.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * quant.h: arm quantization and level-run | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: David Conrad <lessen42@gmail.com> | |
| * | |
| @@ -26,28 +26,46 @@ | |
| #ifndef X264_ARM_QUANT_H | |
| #define X264_ARM_QUANT_H | |
| +#define x264_quant_2x2_dc_armv6 x264_template(quant_2x2_dc_armv6) | |
| int x264_quant_2x2_dc_armv6( int16_t dct[4], int mf, int bias ); | |
| +#define x264_quant_2x2_dc_neon x264_template(quant_2x2_dc_neon) | |
| int x264_quant_2x2_dc_neon( int16_t dct[4], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_neon x264_template(quant_4x4_dc_neon) | |
| int x264_quant_4x4_dc_neon( int16_t dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_neon x264_template(quant_4x4_neon) | |
| int x264_quant_4x4_neon( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] ); | |
| +#define x264_quant_4x4x4_neon x264_template(quant_4x4x4_neon) | |
| int x264_quant_4x4x4_neon( int16_t dct[4][16], uint16_t mf[16], uint16_t bias[16] ); | |
| +#define x264_quant_8x8_neon x264_template(quant_8x8_neon) | |
| int x264_quant_8x8_neon( int16_t dct[64], uint16_t mf[64], uint16_t bias[64] ); | |
| +#define x264_dequant_4x4_dc_neon x264_template(dequant_4x4_dc_neon) | |
| void x264_dequant_4x4_dc_neon( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4_neon x264_template(dequant_4x4_neon) | |
| void x264_dequant_4x4_neon( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_neon x264_template(dequant_8x8_neon) | |
| void x264_dequant_8x8_neon( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_decimate_score15_neon x264_template(decimate_score15_neon) | |
| int x264_decimate_score15_neon( int16_t * ); | |
| +#define x264_decimate_score16_neon x264_template(decimate_score16_neon) | |
| int x264_decimate_score16_neon( int16_t * ); | |
| +#define x264_decimate_score64_neon x264_template(decimate_score64_neon) | |
| int x264_decimate_score64_neon( int16_t * ); | |
| +#define x264_coeff_last4_arm x264_template(coeff_last4_arm) | |
| int x264_coeff_last4_arm( int16_t * ); | |
| +#define x264_coeff_last8_arm x264_template(coeff_last8_arm) | |
| int x264_coeff_last8_arm( int16_t * ); | |
| +#define x264_coeff_last15_neon x264_template(coeff_last15_neon) | |
| int x264_coeff_last15_neon( int16_t * ); | |
| +#define x264_coeff_last16_neon x264_template(coeff_last16_neon) | |
| int x264_coeff_last16_neon( int16_t * ); | |
| +#define x264_coeff_last64_neon x264_template(coeff_last64_neon) | |
| int x264_coeff_last64_neon( int16_t * ); | |
| +#define x264_denoise_dct_neon x264_template(denoise_dct_neon) | |
| void x264_denoise_dct_neon( dctcoef *, uint32_t *, udctcoef *, int ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common: base.c | |
| Only in x264-go.new/x264c/external/x264/common: base.h | |
| diff -ur x264-go/x264c/external/x264/common/bitstream.c x264-go.new/x264c/external/x264/common/bitstream.c | |
| --- x264-go/x264c/external/x264/common/bitstream.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/bitstream.c 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * bitstream.c: bitstream writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -26,7 +26,7 @@ | |
| #include "common.h" | |
| -static uint8_t *x264_nal_escape_c( uint8_t *dst, uint8_t *src, uint8_t *end ) | |
| +static uint8_t *nal_escape_c( uint8_t *dst, uint8_t *src, uint8_t *end ) | |
| { | |
| if( src < end ) *dst++ = *src++; | |
| if( src < end ) *dst++ = *src++; | |
| @@ -39,25 +39,15 @@ | |
| return dst; | |
| } | |
| -uint8_t *x264_nal_escape_mmx2( uint8_t *dst, uint8_t *src, uint8_t *end ); | |
| -uint8_t *x264_nal_escape_sse2( uint8_t *dst, uint8_t *src, uint8_t *end ); | |
| -uint8_t *x264_nal_escape_avx2( uint8_t *dst, uint8_t *src, uint8_t *end ); | |
| -void x264_cabac_block_residual_rd_internal_sse2 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_rd_internal_lzcnt ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_rd_internal_ssse3 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_rd_internal_ssse3_lzcnt( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_rd_internal_avx512 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_8x8_rd_internal_sse2 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_8x8_rd_internal_lzcnt ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_8x8_rd_internal_ssse3 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_8x8_rd_internal_ssse3_lzcnt( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_8x8_rd_internal_avx512 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_internal_sse2 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_internal_lzcnt ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_internal_avx2 ( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| -void x264_cabac_block_residual_internal_avx512( dctcoef *l, int b_interlaced, intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| - | |
| -uint8_t *x264_nal_escape_neon( uint8_t *dst, uint8_t *src, uint8_t *end ); | |
| +#if HAVE_MMX | |
| +#include "x86/bitstream.h" | |
| +#endif | |
| +#if HAVE_ARMV6 | |
| +#include "arm/bitstream.h" | |
| +#endif | |
| +#if HAVE_AARCH64 | |
| +#include "aarch64/bitstream.h" | |
| +#endif | |
| /**************************************************************************** | |
| * x264_nal_encode: | |
| @@ -113,11 +103,11 @@ | |
| x264_emms(); | |
| } | |
| -void x264_bitstream_init( int cpu, x264_bitstream_function_t *pf ) | |
| +void x264_bitstream_init( uint32_t cpu, x264_bitstream_function_t *pf ) | |
| { | |
| memset( pf, 0, sizeof(*pf) ); | |
| - pf->nal_escape = x264_nal_escape_c; | |
| + pf->nal_escape = nal_escape_c; | |
| #if HAVE_MMX | |
| #if ARCH_X86_64 && !defined( __MACH__ ) | |
| pf->cabac_block_residual_internal = x264_cabac_block_residual_internal_sse2; | |
| @@ -169,7 +159,7 @@ | |
| if( cpu&X264_CPU_NEON ) | |
| pf->nal_escape = x264_nal_escape_neon; | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| pf->nal_escape = x264_nal_escape_neon; | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/bitstream.h x264-go.new/x264c/external/x264/common/bitstream.h | |
| --- x264-go/x264c/external/x264/common/bitstream.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/bitstream.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * bitstream.h: bitstream writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -30,12 +30,6 @@ | |
| typedef struct | |
| { | |
| - uint8_t i_bits; | |
| - uint8_t i_size; | |
| -} vlc_t; | |
| - | |
| -typedef struct | |
| -{ | |
| uint16_t i_bits; | |
| uint8_t i_size; | |
| /* Next level table to use */ | |
| @@ -60,12 +54,6 @@ | |
| ALIGNED_16( dctcoef level[18] ); | |
| } x264_run_level_t; | |
| -extern const vlc_t x264_coeff0_token[6]; | |
| -extern const vlc_t x264_coeff_token[6][16][4]; | |
| -extern const vlc_t x264_total_zeros[15][16]; | |
| -extern const vlc_t x264_total_zeros_2x2_dc[3][4]; | |
| -extern const vlc_t x264_total_zeros_2x4_dc[7][8]; | |
| - | |
| typedef struct | |
| { | |
| uint8_t *(*nal_escape)( uint8_t *dst, uint8_t *src, uint8_t *end ); | |
| @@ -77,7 +65,8 @@ | |
| intptr_t ctx_block_cat, x264_cabac_t *cb ); | |
| } x264_bitstream_function_t; | |
| -void x264_bitstream_init( int cpu, x264_bitstream_function_t *pf ); | |
| +#define x264_bitstream_init x264_template(bitstream_init) | |
| +void x264_bitstream_init( uint32_t cpu, x264_bitstream_function_t *pf ); | |
| /* A larger level table size theoretically could help a bit at extremely | |
| * high bitrates, but the cost in cache is usually too high for it to be | |
| @@ -85,11 +74,13 @@ | |
| * This size appears to be optimal for QP18 encoding on a Nehalem CPU. | |
| * FIXME: Do further testing? */ | |
| #define LEVEL_TABLE_SIZE 128 | |
| +#define x264_level_token x264_template(level_token) | |
| extern vlc_large_t x264_level_token[7][LEVEL_TABLE_SIZE]; | |
| /* The longest possible set of zero run codes sums to 25 bits. This leaves | |
| * plenty of room for both the code (25 bits) and size (5 bits) in a uint32_t. */ | |
| +#define x264_run_before x264_template(run_before) | |
| extern uint32_t x264_run_before[1<<16]; | |
| static inline void bs_init( bs_t *s, void *p_data, int i_data ) | |
| @@ -98,8 +89,13 @@ | |
| s->p = s->p_start = (uint8_t*)p_data - offset; | |
| s->p_end = (uint8_t*)p_data + i_data; | |
| s->i_left = (WORD_SIZE - offset)*8; | |
| - s->cur_bits = endian_fix32( M32(s->p) ); | |
| - s->cur_bits >>= (4-offset)*8; | |
| + if( offset ) | |
| + { | |
| + s->cur_bits = endian_fix32( M32(s->p) ); | |
| + s->cur_bits >>= (4-offset)*8; | |
| + } | |
| + else | |
| + s->cur_bits = 0; | |
| } | |
| static inline int bs_pos( bs_t *s ) | |
| { | |
| @@ -197,6 +193,7 @@ | |
| { | |
| if( s->i_left&7 ) | |
| bs_write( s, s->i_left&7, 1 << ( (s->i_left&7) - 1 ) ); | |
| + bs_flush( s ); | |
| } | |
| /* golomb functions */ | |
| diff -ur x264-go/x264c/external/x264/common/cabac.c x264-go.new/x264c/external/x264/common/cabac.c | |
| --- x264-go/x264c/external/x264/common/cabac.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/cabac.c 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cabac.c: arithmetic coder | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -27,1305 +27,7 @@ | |
| #include "common.h" | |
| - | |
| -static const int8_t x264_cabac_context_init_I[1024][2] = | |
| -{ | |
| - /* 0 - 10 */ | |
| - { 20, -15 }, { 2, 54 }, { 3, 74 }, { 20, -15 }, | |
| - { 2, 54 }, { 3, 74 }, { -28,127 }, { -23, 104 }, | |
| - { -6, 53 }, { -1, 54 }, { 7, 51 }, | |
| - | |
| - /* 11 - 23 unused for I */ | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, | |
| - | |
| - /* 24- 39 */ | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - | |
| - /* 40 - 53 */ | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, | |
| - | |
| - /* 54 - 59 */ | |
| - { 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 }, | |
| - { 0, 0 }, { 0, 0 }, | |
| - | |
| - /* 60 - 69 */ | |
| - { 0, 41 }, { 0, 63 }, { 0, 63 }, { 0, 63 }, | |
| - { -9, 83 }, { 4, 86 }, { 0, 97 }, { -7, 72 }, | |
| - { 13, 41 }, { 3, 62 }, | |
| - | |
| - /* 70 -> 87 */ | |
| - { 0, 11 }, { 1, 55 }, { 0, 69 }, { -17, 127 }, | |
| - { -13, 102 },{ 0, 82 }, { -7, 74 }, { -21, 107 }, | |
| - { -27, 127 },{ -31, 127 },{ -24, 127 }, { -18, 95 }, | |
| - { -27, 127 },{ -21, 114 },{ -30, 127 }, { -17, 123 }, | |
| - { -12, 115 },{ -16, 122 }, | |
| - | |
| - /* 88 -> 104 */ | |
| - { -11, 115 },{ -12, 63 }, { -2, 68 }, { -15, 84 }, | |
| - { -13, 104 },{ -3, 70 }, { -8, 93 }, { -10, 90 }, | |
| - { -30, 127 },{ -1, 74 }, { -6, 97 }, { -7, 91 }, | |
| - { -20, 127 },{ -4, 56 }, { -5, 82 }, { -7, 76 }, | |
| - { -22, 125 }, | |
| - | |
| - /* 105 -> 135 */ | |
| - { -7, 93 }, { -11, 87 }, { -3, 77 }, { -5, 71 }, | |
| - { -4, 63 }, { -4, 68 }, { -12, 84 }, { -7, 62 }, | |
| - { -7, 65 }, { 8, 61 }, { 5, 56 }, { -2, 66 }, | |
| - { 1, 64 }, { 0, 61 }, { -2, 78 }, { 1, 50 }, | |
| - { 7, 52 }, { 10, 35 }, { 0, 44 }, { 11, 38 }, | |
| - { 1, 45 }, { 0, 46 }, { 5, 44 }, { 31, 17 }, | |
| - { 1, 51 }, { 7, 50 }, { 28, 19 }, { 16, 33 }, | |
| - { 14, 62 }, { -13, 108 },{ -15, 100 }, | |
| - | |
| - /* 136 -> 165 */ | |
| - { -13, 101 },{ -13, 91 }, { -12, 94 }, { -10, 88 }, | |
| - { -16, 84 }, { -10, 86 }, { -7, 83 }, { -13, 87 }, | |
| - { -19, 94 }, { 1, 70 }, { 0, 72 }, { -5, 74 }, | |
| - { 18, 59 }, { -8, 102 }, { -15, 100 }, { 0, 95 }, | |
| - { -4, 75 }, { 2, 72 }, { -11, 75 }, { -3, 71 }, | |
| - { 15, 46 }, { -13, 69 }, { 0, 62 }, { 0, 65 }, | |
| - { 21, 37 }, { -15, 72 }, { 9, 57 }, { 16, 54 }, | |
| - { 0, 62 }, { 12, 72 }, | |
| - | |
| - /* 166 -> 196 */ | |
| - { 24, 0 }, { 15, 9 }, { 8, 25 }, { 13, 18 }, | |
| - { 15, 9 }, { 13, 19 }, { 10, 37 }, { 12, 18 }, | |
| - { 6, 29 }, { 20, 33 }, { 15, 30 }, { 4, 45 }, | |
| - { 1, 58 }, { 0, 62 }, { 7, 61 }, { 12, 38 }, | |
| - { 11, 45 }, { 15, 39 }, { 11, 42 }, { 13, 44 }, | |
| - { 16, 45 }, { 12, 41 }, { 10, 49 }, { 30, 34 }, | |
| - { 18, 42 }, { 10, 55 }, { 17, 51 }, { 17, 46 }, | |
| - { 0, 89 }, { 26, -19 }, { 22, -17 }, | |
| - | |
| - /* 197 -> 226 */ | |
| - { 26, -17 }, { 30, -25 }, { 28, -20 }, { 33, -23 }, | |
| - { 37, -27 }, { 33, -23 }, { 40, -28 }, { 38, -17 }, | |
| - { 33, -11 }, { 40, -15 }, { 41, -6 }, { 38, 1 }, | |
| - { 41, 17 }, { 30, -6 }, { 27, 3 }, { 26, 22 }, | |
| - { 37, -16 }, { 35, -4 }, { 38, -8 }, { 38, -3 }, | |
| - { 37, 3 }, { 38, 5 }, { 42, 0 }, { 35, 16 }, | |
| - { 39, 22 }, { 14, 48 }, { 27, 37 }, { 21, 60 }, | |
| - { 12, 68 }, { 2, 97 }, | |
| - | |
| - /* 227 -> 251 */ | |
| - { -3, 71 }, { -6, 42 }, { -5, 50 }, { -3, 54 }, | |
| - { -2, 62 }, { 0, 58 }, { 1, 63 }, { -2, 72 }, | |
| - { -1, 74 }, { -9, 91 }, { -5, 67 }, { -5, 27 }, | |
| - { -3, 39 }, { -2, 44 }, { 0, 46 }, { -16, 64 }, | |
| - { -8, 68 }, { -10, 78 }, { -6, 77 }, { -10, 86 }, | |
| - { -12, 92 }, { -15, 55 }, { -10, 60 }, { -6, 62 }, | |
| - { -4, 65 }, | |
| - | |
| - /* 252 -> 275 */ | |
| - { -12, 73 }, { -8, 76 }, { -7, 80 }, { -9, 88 }, | |
| - { -17, 110 },{ -11, 97 }, { -20, 84 }, { -11, 79 }, | |
| - { -6, 73 }, { -4, 74 }, { -13, 86 }, { -13, 96 }, | |
| - { -11, 97 }, { -19, 117 },{ -8, 78 }, { -5, 33 }, | |
| - { -4, 48 }, { -2, 53 }, { -3, 62 }, { -13, 71 }, | |
| - { -10, 79 }, { -12, 86 }, { -13, 90 }, { -14, 97 }, | |
| - | |
| - /* 276 a bit special (not used, x264_cabac_encode_bypass is used instead) */ | |
| - { 0, 0 }, | |
| - | |
| - /* 277 -> 307 */ | |
| - { -6, 93 }, { -6, 84 }, { -8, 79 }, { 0, 66 }, | |
| - { -1, 71 }, { 0, 62 }, { -2, 60 }, { -2, 59 }, | |
| - { -5, 75 }, { -3, 62 }, { -4, 58 }, { -9, 66 }, | |
| - { -1, 79 }, { 0, 71 }, { 3, 68 }, { 10, 44 }, | |
| - { -7, 62 }, { 15, 36 }, { 14, 40 }, { 16, 27 }, | |
| - { 12, 29 }, { 1, 44 }, { 20, 36 }, { 18, 32 }, | |
| - { 5, 42 }, { 1, 48 }, { 10, 62 }, { 17, 46 }, | |
| - { 9, 64 }, { -12, 104 },{ -11, 97 }, | |
| - | |
| - /* 308 -> 337 */ | |
| - { -16, 96 }, { -7, 88 }, { -8, 85 }, { -7, 85 }, | |
| - { -9, 85 }, { -13, 88 }, { 4, 66 }, { -3, 77 }, | |
| - { -3, 76 }, { -6, 76 }, { 10, 58 }, { -1, 76 }, | |
| - { -1, 83 }, { -7, 99 }, { -14, 95 }, { 2, 95 }, | |
| - { 0, 76 }, { -5, 74 }, { 0, 70 }, { -11, 75 }, | |
| - { 1, 68 }, { 0, 65 }, { -14, 73 }, { 3, 62 }, | |
| - { 4, 62 }, { -1, 68 }, { -13, 75 }, { 11, 55 }, | |
| - { 5, 64 }, { 12, 70 }, | |
| - | |
| - /* 338 -> 368 */ | |
| - { 15, 6 }, { 6, 19 }, { 7, 16 }, { 12, 14 }, | |
| - { 18, 13 }, { 13, 11 }, { 13, 15 }, { 15, 16 }, | |
| - { 12, 23 }, { 13, 23 }, { 15, 20 }, { 14, 26 }, | |
| - { 14, 44 }, { 17, 40 }, { 17, 47 }, { 24, 17 }, | |
| - { 21, 21 }, { 25, 22 }, { 31, 27 }, { 22, 29 }, | |
| - { 19, 35 }, { 14, 50 }, { 10, 57 }, { 7, 63 }, | |
| - { -2, 77 }, { -4, 82 }, { -3, 94 }, { 9, 69 }, | |
| - { -12, 109 },{ 36, -35 }, { 36, -34 }, | |
| - | |
| - /* 369 -> 398 */ | |
| - { 32, -26 }, { 37, -30 }, { 44, -32 }, { 34, -18 }, | |
| - { 34, -15 }, { 40, -15 }, { 33, -7 }, { 35, -5 }, | |
| - { 33, 0 }, { 38, 2 }, { 33, 13 }, { 23, 35 }, | |
| - { 13, 58 }, { 29, -3 }, { 26, 0 }, { 22, 30 }, | |
| - { 31, -7 }, { 35, -15 }, { 34, -3 }, { 34, 3 }, | |
| - { 36, -1 }, { 34, 5 }, { 32, 11 }, { 35, 5 }, | |
| - { 34, 12 }, { 39, 11 }, { 30, 29 }, { 34, 26 }, | |
| - { 29, 39 }, { 19, 66 }, | |
| - | |
| - /* 399 -> 435 */ | |
| - { 31, 21 }, { 31, 31 }, { 25, 50 }, | |
| - { -17, 120 }, { -20, 112 }, { -18, 114 }, { -11, 85 }, | |
| - { -15, 92 }, { -14, 89 }, { -26, 71 }, { -15, 81 }, | |
| - { -14, 80 }, { 0, 68 }, { -14, 70 }, { -24, 56 }, | |
| - { -23, 68 }, { -24, 50 }, { -11, 74 }, { 23, -13 }, | |
| - { 26, -13 }, { 40, -15 }, { 49, -14 }, { 44, 3 }, | |
| - { 45, 6 }, { 44, 34 }, { 33, 54 }, { 19, 82 }, | |
| - { -3, 75 }, { -1, 23 }, { 1, 34 }, { 1, 43 }, | |
| - { 0, 54 }, { -2, 55 }, { 0, 61 }, { 1, 64 }, | |
| - { 0, 68 }, { -9, 92 }, | |
| - | |
| - /* 436 -> 459 */ | |
| - { -14, 106 }, { -13, 97 }, { -15, 90 }, { -12, 90 }, | |
| - { -18, 88 }, { -10, 73 }, { -9, 79 }, { -14, 86 }, | |
| - { -10, 73 }, { -10, 70 }, { -10, 69 }, { -5, 66 }, | |
| - { -9, 64 }, { -5, 58 }, { 2, 59 }, { 21, -10 }, | |
| - { 24, -11 }, { 28, -8 }, { 28, -1 }, { 29, 3 }, | |
| - { 29, 9 }, { 35, 20 }, { 29, 36 }, { 14, 67 }, | |
| - | |
| - /* 460 -> 1024 */ | |
| - { -17, 123 }, { -12, 115 }, { -16, 122 }, { -11, 115 }, | |
| - { -12, 63 }, { -2, 68 }, { -15, 84 }, { -13, 104 }, | |
| - { -3, 70 }, { -8, 93 }, { -10, 90 }, { -30, 127 }, | |
| - { -17, 123 }, { -12, 115 }, { -16, 122 }, { -11, 115 }, | |
| - { -12, 63 }, { -2, 68 }, { -15, 84 }, { -13, 104 }, | |
| - { -3, 70 }, { -8, 93 }, { -10, 90 }, { -30, 127 }, | |
| - { -7, 93 }, { -11, 87 }, { -3, 77 }, { -5, 71 }, | |
| - { -4, 63 }, { -4, 68 }, { -12, 84 }, { -7, 62 }, | |
| - { -7, 65 }, { 8, 61 }, { 5, 56 }, { -2, 66 }, | |
| - { 1, 64 }, { 0, 61 }, { -2, 78 }, { 1, 50 }, | |
| - { 7, 52 }, { 10, 35 }, { 0, 44 }, { 11, 38 }, | |
| - { 1, 45 }, { 0, 46 }, { 5, 44 }, { 31, 17 }, | |
| - { 1, 51 }, { 7, 50 }, { 28, 19 }, { 16, 33 }, | |
| - { 14, 62 }, { -13, 108 }, { -15, 100 }, { -13, 101 }, | |
| - { -13, 91 }, { -12, 94 }, { -10, 88 }, { -16, 84 }, | |
| - { -10, 86 }, { -7, 83 }, { -13, 87 }, { -19, 94 }, | |
| - { 1, 70 }, { 0, 72 }, { -5, 74 }, { 18, 59 }, | |
| - { -7, 93 }, { -11, 87 }, { -3, 77 }, { -5, 71 }, | |
| - { -4, 63 }, { -4, 68 }, { -12, 84 }, { -7, 62 }, | |
| - { -7, 65 }, { 8, 61 }, { 5, 56 }, { -2, 66 }, | |
| - { 1, 64 }, { 0, 61 }, { -2, 78 }, { 1, 50 }, | |
| - { 7, 52 }, { 10, 35 }, { 0, 44 }, { 11, 38 }, | |
| - { 1, 45 }, { 0, 46 }, { 5, 44 }, { 31, 17 }, | |
| - { 1, 51 }, { 7, 50 }, { 28, 19 }, { 16, 33 }, | |
| - { 14, 62 }, { -13, 108 }, { -15, 100 }, { -13, 101 }, | |
| - { -13, 91 }, { -12, 94 }, { -10, 88 }, { -16, 84 }, | |
| - { -10, 86 }, { -7, 83 }, { -13, 87 }, { -19, 94 }, | |
| - { 1, 70 }, { 0, 72 }, { -5, 74 }, { 18, 59 }, | |
| - { 24, 0 }, { 15, 9 }, { 8, 25 }, { 13, 18 }, | |
| - { 15, 9 }, { 13, 19 }, { 10, 37 }, { 12, 18 }, | |
| - { 6, 29 }, { 20, 33 }, { 15, 30 }, { 4, 45 }, | |
| - { 1, 58 }, { 0, 62 }, { 7, 61 }, { 12, 38 }, | |
| - { 11, 45 }, { 15, 39 }, { 11, 42 }, { 13, 44 }, | |
| - { 16, 45 }, { 12, 41 }, { 10, 49 }, { 30, 34 }, | |
| - { 18, 42 }, { 10, 55 }, { 17, 51 }, { 17, 46 }, | |
| - { 0, 89 }, { 26, -19 }, { 22, -17 }, { 26, -17 }, | |
| - { 30, -25 }, { 28, -20 }, { 33, -23 }, { 37, -27 }, | |
| - { 33, -23 }, { 40, -28 }, { 38, -17 }, { 33, -11 }, | |
| - { 40, -15 }, { 41, -6 }, { 38, 1 }, { 41, 17 }, | |
| - { 24, 0 }, { 15, 9 }, { 8, 25 }, { 13, 18 }, | |
| - { 15, 9 }, { 13, 19 }, { 10, 37 }, { 12, 18 }, | |
| - { 6, 29 }, { 20, 33 }, { 15, 30 }, { 4, 45 }, | |
| - { 1, 58 }, { 0, 62 }, { 7, 61 }, { 12, 38 }, | |
| - { 11, 45 }, { 15, 39 }, { 11, 42 }, { 13, 44 }, | |
| - { 16, 45 }, { 12, 41 }, { 10, 49 }, { 30, 34 }, | |
| - { 18, 42 }, { 10, 55 }, { 17, 51 }, { 17, 46 }, | |
| - { 0, 89 }, { 26, -19 }, { 22, -17 }, { 26, -17 }, | |
| - { 30, -25 }, { 28, -20 }, { 33, -23 }, { 37, -27 }, | |
| - { 33, -23 }, { 40, -28 }, { 38, -17 }, { 33, -11 }, | |
| - { 40, -15 }, { 41, -6 }, { 38, 1 }, { 41, 17 }, | |
| - { -17, 120 }, { -20, 112 }, { -18, 114 }, { -11, 85 }, | |
| - { -15, 92 }, { -14, 89 }, { -26, 71 }, { -15, 81 }, | |
| - { -14, 80 }, { 0, 68 }, { -14, 70 }, { -24, 56 }, | |
| - { -23, 68 }, { -24, 50 }, { -11, 74 }, { -14, 106 }, | |
| - { -13, 97 }, { -15, 90 }, { -12, 90 }, { -18, 88 }, | |
| - { -10, 73 }, { -9, 79 }, { -14, 86 }, { -10, 73 }, | |
| - { -10, 70 }, { -10, 69 }, { -5, 66 }, { -9, 64 }, | |
| - { -5, 58 }, { 2, 59 }, { 23, -13 }, { 26, -13 }, | |
| - { 40, -15 }, { 49, -14 }, { 44, 3 }, { 45, 6 }, | |
| - { 44, 34 }, { 33, 54 }, { 19, 82 }, { 21, -10 }, | |
| - { 24, -11 }, { 28, -8 }, { 28, -1 }, { 29, 3 }, | |
| - { 29, 9 }, { 35, 20 }, { 29, 36 }, { 14, 67 }, | |
| - { -3, 75 }, { -1, 23 }, { 1, 34 }, { 1, 43 }, | |
| - { 0, 54 }, { -2, 55 }, { 0, 61 }, { 1, 64 }, | |
| - { 0, 68 }, { -9, 92 }, { -17, 120 }, { -20, 112 }, | |
| - { -18, 114 }, { -11, 85 }, { -15, 92 }, { -14, 89 }, | |
| - { -26, 71 }, { -15, 81 }, { -14, 80 }, { 0, 68 }, | |
| - { -14, 70 }, { -24, 56 }, { -23, 68 }, { -24, 50 }, | |
| - { -11, 74 }, { -14, 106 }, { -13, 97 }, { -15, 90 }, | |
| - { -12, 90 }, { -18, 88 }, { -10, 73 }, { -9, 79 }, | |
| - { -14, 86 }, { -10, 73 }, { -10, 70 }, { -10, 69 }, | |
| - { -5, 66 }, { -9, 64 }, { -5, 58 }, { 2, 59 }, | |
| - { 23, -13 }, { 26, -13 }, { 40, -15 }, { 49, -14 }, | |
| - { 44, 3 }, { 45, 6 }, { 44, 34 }, { 33, 54 }, | |
| - { 19, 82 }, { 21, -10 }, { 24, -11 }, { 28, -8 }, | |
| - { 28, -1 }, { 29, 3 }, { 29, 9 }, { 35, 20 }, | |
| - { 29, 36 }, { 14, 67 }, { -3, 75 }, { -1, 23 }, | |
| - { 1, 34 }, { 1, 43 }, { 0, 54 }, { -2, 55 }, | |
| - { 0, 61 }, { 1, 64 }, { 0, 68 }, { -9, 92 }, | |
| - { -6, 93 }, { -6, 84 }, { -8, 79 }, { 0, 66 }, | |
| - { -1, 71 }, { 0, 62 }, { -2, 60 }, { -2, 59 }, | |
| - { -5, 75 }, { -3, 62 }, { -4, 58 }, { -9, 66 }, | |
| - { -1, 79 }, { 0, 71 }, { 3, 68 }, { 10, 44 }, | |
| - { -7, 62 }, { 15, 36 }, { 14, 40 }, { 16, 27 }, | |
| - { 12, 29 }, { 1, 44 }, { 20, 36 }, { 18, 32 }, | |
| - { 5, 42 }, { 1, 48 }, { 10, 62 }, { 17, 46 }, | |
| - { 9, 64 }, { -12, 104 }, { -11, 97 }, { -16, 96 }, | |
| - { -7, 88 }, { -8, 85 }, { -7, 85 }, { -9, 85 }, | |
| - { -13, 88 }, { 4, 66 }, { -3, 77 }, { -3, 76 }, | |
| - { -6, 76 }, { 10, 58 }, { -1, 76 }, { -1, 83 }, | |
| - { -6, 93 }, { -6, 84 }, { -8, 79 }, { 0, 66 }, | |
| - { -1, 71 }, { 0, 62 }, { -2, 60 }, { -2, 59 }, | |
| - { -5, 75 }, { -3, 62 }, { -4, 58 }, { -9, 66 }, | |
| - { -1, 79 }, { 0, 71 }, { 3, 68 }, { 10, 44 }, | |
| - { -7, 62 }, { 15, 36 }, { 14, 40 }, { 16, 27 }, | |
| - { 12, 29 }, { 1, 44 }, { 20, 36 }, { 18, 32 }, | |
| - { 5, 42 }, { 1, 48 }, { 10, 62 }, { 17, 46 }, | |
| - { 9, 64 }, { -12, 104 }, { -11, 97 }, { -16, 96 }, | |
| - { -7, 88 }, { -8, 85 }, { -7, 85 }, { -9, 85 }, | |
| - { -13, 88 }, { 4, 66 }, { -3, 77 }, { -3, 76 }, | |
| - { -6, 76 }, { 10, 58 }, { -1, 76 }, { -1, 83 }, | |
| - { 15, 6 }, { 6, 19 }, { 7, 16 }, { 12, 14 }, | |
| - { 18, 13 }, { 13, 11 }, { 13, 15 }, { 15, 16 }, | |
| - { 12, 23 }, { 13, 23 }, { 15, 20 }, { 14, 26 }, | |
| - { 14, 44 }, { 17, 40 }, { 17, 47 }, { 24, 17 }, | |
| - { 21, 21 }, { 25, 22 }, { 31, 27 }, { 22, 29 }, | |
| - { 19, 35 }, { 14, 50 }, { 10, 57 }, { 7, 63 }, | |
| - { -2, 77 }, { -4, 82 }, { -3, 94 }, { 9, 69 }, | |
| - { -12, 109 }, { 36, -35 }, { 36, -34 }, { 32, -26 }, | |
| - { 37, -30 }, { 44, -32 }, { 34, -18 }, { 34, -15 }, | |
| - { 40, -15 }, { 33, -7 }, { 35, -5 }, { 33, 0 }, | |
| - { 38, 2 }, { 33, 13 }, { 23, 35 }, { 13, 58 }, | |
| - { 15, 6 }, { 6, 19 }, { 7, 16 }, { 12, 14 }, | |
| - { 18, 13 }, { 13, 11 }, { 13, 15 }, { 15, 16 }, | |
| - { 12, 23 }, { 13, 23 }, { 15, 20 }, { 14, 26 }, | |
| - { 14, 44 }, { 17, 40 }, { 17, 47 }, { 24, 17 }, | |
| - { 21, 21 }, { 25, 22 }, { 31, 27 }, { 22, 29 }, | |
| - { 19, 35 }, { 14, 50 }, { 10, 57 }, { 7, 63 }, | |
| - { -2, 77 }, { -4, 82 }, { -3, 94 }, { 9, 69 }, | |
| - { -12, 109 }, { 36, -35 }, { 36, -34 }, { 32, -26 }, | |
| - { 37, -30 }, { 44, -32 }, { 34, -18 }, { 34, -15 }, | |
| - { 40, -15 }, { 33, -7 }, { 35, -5 }, { 33, 0 }, | |
| - { 38, 2 }, { 33, 13 }, { 23, 35 }, { 13, 58 }, | |
| - { -3, 71 }, { -6, 42 }, { -5, 50 }, { -3, 54 }, | |
| - { -2, 62 }, { 0, 58 }, { 1, 63 }, { -2, 72 }, | |
| - { -1, 74 }, { -9, 91 }, { -5, 67 }, { -5, 27 }, | |
| - { -3, 39 }, { -2, 44 }, { 0, 46 }, { -16, 64 }, | |
| - { -8, 68 }, { -10, 78 }, { -6, 77 }, { -10, 86 }, | |
| - { -12, 92 }, { -15, 55 }, { -10, 60 }, { -6, 62 }, | |
| - { -4, 65 }, { -12, 73 }, { -8, 76 }, { -7, 80 }, | |
| - { -9, 88 }, { -17, 110 }, { -3, 71 }, { -6, 42 }, | |
| - { -5, 50 }, { -3, 54 }, { -2, 62 }, { 0, 58 }, | |
| - { 1, 63 }, { -2, 72 }, { -1, 74 }, { -9, 91 }, | |
| - { -5, 67 }, { -5, 27 }, { -3, 39 }, { -2, 44 }, | |
| - { 0, 46 }, { -16, 64 }, { -8, 68 }, { -10, 78 }, | |
| - { -6, 77 }, { -10, 86 }, { -12, 92 }, { -15, 55 }, | |
| - { -10, 60 }, { -6, 62 }, { -4, 65 }, { -12, 73 }, | |
| - { -8, 76 }, { -7, 80 }, { -9, 88 }, { -17, 110 }, | |
| - { -3, 70 }, { -8, 93 }, { -10, 90 }, { -30, 127 }, | |
| - { -3, 70 }, { -8, 93 }, { -10, 90 }, { -30, 127 }, | |
| - { -3, 70 }, { -8, 93 }, { -10, 90 }, { -30, 127 } | |
| -}; | |
| - | |
| -static const int8_t x264_cabac_context_init_PB[3][1024][2] = | |
| -{ | |
| - /* i_cabac_init_idc == 0 */ | |
| - { | |
| - /* 0 - 10 */ | |
| - { 20, -15 }, { 2, 54 }, { 3, 74 }, { 20, -15 }, | |
| - { 2, 54 }, { 3, 74 }, { -28, 127 }, { -23, 104 }, | |
| - { -6, 53 }, { -1, 54 }, { 7, 51 }, | |
| - | |
| - /* 11 - 23 */ | |
| - { 23, 33 }, { 23, 2 }, { 21, 0 }, { 1, 9 }, | |
| - { 0, 49 }, { -37, 118 }, { 5, 57 }, { -13, 78 }, | |
| - { -11, 65 }, { 1, 62 }, { 12, 49 }, { -4, 73 }, | |
| - { 17, 50 }, | |
| - | |
| - /* 24 - 39 */ | |
| - { 18, 64 }, { 9, 43 }, { 29, 0 }, { 26, 67 }, | |
| - { 16, 90 }, { 9, 104 }, { -46, 127 }, { -20, 104 }, | |
| - { 1, 67 }, { -13, 78 }, { -11, 65 }, { 1, 62 }, | |
| - { -6, 86 }, { -17, 95 }, { -6, 61 }, { 9, 45 }, | |
| - | |
| - /* 40 - 53 */ | |
| - { -3, 69 }, { -6, 81 }, { -11, 96 }, { 6, 55 }, | |
| - { 7, 67 }, { -5, 86 }, { 2, 88 }, { 0, 58 }, | |
| - { -3, 76 }, { -10, 94 }, { 5, 54 }, { 4, 69 }, | |
| - { -3, 81 }, { 0, 88 }, | |
| - | |
| - /* 54 - 59 */ | |
| - { -7, 67 }, { -5, 74 }, { -4, 74 }, { -5, 80 }, | |
| - { -7, 72 }, { 1, 58 }, | |
| - | |
| - /* 60 - 69 */ | |
| - { 0, 41 }, { 0, 63 }, { 0, 63 }, { 0, 63 }, | |
| - { -9, 83 }, { 4, 86 }, { 0, 97 }, { -7, 72 }, | |
| - { 13, 41 }, { 3, 62 }, | |
| - | |
| - /* 70 - 87 */ | |
| - { 0, 45 }, { -4, 78 }, { -3, 96 }, { -27, 126 }, | |
| - { -28, 98 }, { -25, 101 }, { -23, 67 }, { -28, 82 }, | |
| - { -20, 94 }, { -16, 83 }, { -22, 110 }, { -21, 91 }, | |
| - { -18, 102 }, { -13, 93 }, { -29, 127 }, { -7, 92 }, | |
| - { -5, 89 }, { -7, 96 }, { -13, 108 }, { -3, 46 }, | |
| - { -1, 65 }, { -1, 57 }, { -9, 93 }, { -3, 74 }, | |
| - { -9, 92 }, { -8, 87 }, { -23, 126 }, { 5, 54 }, | |
| - { 6, 60 }, { 6, 59 }, { 6, 69 }, { -1, 48 }, | |
| - { 0, 68 }, { -4, 69 }, { -8, 88 }, | |
| - | |
| - /* 105 -> 165 */ | |
| - { -2, 85 }, { -6, 78 }, { -1, 75 }, { -7, 77 }, | |
| - { 2, 54 }, { 5, 50 }, { -3, 68 }, { 1, 50 }, | |
| - { 6, 42 }, { -4, 81 }, { 1, 63 }, { -4, 70 }, | |
| - { 0, 67 }, { 2, 57 }, { -2, 76 }, { 11, 35 }, | |
| - { 4, 64 }, { 1, 61 }, { 11, 35 }, { 18, 25 }, | |
| - { 12, 24 }, { 13, 29 }, { 13, 36 }, { -10, 93 }, | |
| - { -7, 73 }, { -2, 73 }, { 13, 46 }, { 9, 49 }, | |
| - { -7, 100 }, { 9, 53 }, { 2, 53 }, { 5, 53 }, | |
| - { -2, 61 }, { 0, 56 }, { 0, 56 }, { -13, 63 }, | |
| - { -5, 60 }, { -1, 62 }, { 4, 57 }, { -6, 69 }, | |
| - { 4, 57 }, { 14, 39 }, { 4, 51 }, { 13, 68 }, | |
| - { 3, 64 }, { 1, 61 }, { 9, 63 }, { 7, 50 }, | |
| - { 16, 39 }, { 5, 44 }, { 4, 52 }, { 11, 48 }, | |
| - { -5, 60 }, { -1, 59 }, { 0, 59 }, { 22, 33 }, | |
| - { 5, 44 }, { 14, 43 }, { -1, 78 }, { 0, 60 }, | |
| - { 9, 69 }, | |
| - | |
| - /* 166 - 226 */ | |
| - { 11, 28 }, { 2, 40 }, { 3, 44 }, { 0, 49 }, | |
| - { 0, 46 }, { 2, 44 }, { 2, 51 }, { 0, 47 }, | |
| - { 4, 39 }, { 2, 62 }, { 6, 46 }, { 0, 54 }, | |
| - { 3, 54 }, { 2, 58 }, { 4, 63 }, { 6, 51 }, | |
| - { 6, 57 }, { 7, 53 }, { 6, 52 }, { 6, 55 }, | |
| - { 11, 45 }, { 14, 36 }, { 8, 53 }, { -1, 82 }, | |
| - { 7, 55 }, { -3, 78 }, { 15, 46 }, { 22, 31 }, | |
| - { -1, 84 }, { 25, 7 }, { 30, -7 }, { 28, 3 }, | |
| - { 28, 4 }, { 32, 0 }, { 34, -1 }, { 30, 6 }, | |
| - { 30, 6 }, { 32, 9 }, { 31, 19 }, { 26, 27 }, | |
| - { 26, 30 }, { 37, 20 }, { 28, 34 }, { 17, 70 }, | |
| - { 1, 67 }, { 5, 59 }, { 9, 67 }, { 16, 30 }, | |
| - { 18, 32 }, { 18, 35 }, { 22, 29 }, { 24, 31 }, | |
| - { 23, 38 }, { 18, 43 }, { 20, 41 }, { 11, 63 }, | |
| - { 9, 59 }, { 9, 64 }, { -1, 94 }, { -2, 89 }, | |
| - { -9, 108 }, | |
| - | |
| - /* 227 - 275 */ | |
| - { -6, 76 }, { -2, 44 }, { 0, 45 }, { 0, 52 }, | |
| - { -3, 64 }, { -2, 59 }, { -4, 70 }, { -4, 75 }, | |
| - { -8, 82 }, { -17, 102 }, { -9, 77 }, { 3, 24 }, | |
| - { 0, 42 }, { 0, 48 }, { 0, 55 }, { -6, 59 }, | |
| - { -7, 71 }, { -12, 83 }, { -11, 87 }, { -30, 119 }, | |
| - { 1, 58 }, { -3, 29 }, { -1, 36 }, { 1, 38 }, | |
| - { 2, 43 }, { -6, 55 }, { 0, 58 }, { 0, 64 }, | |
| - { -3, 74 }, { -10, 90 }, { 0, 70 }, { -4, 29 }, | |
| - { 5, 31 }, { 7, 42 }, { 1, 59 }, { -2, 58 }, | |
| - { -3, 72 }, { -3, 81 }, { -11, 97 }, { 0, 58 }, | |
| - { 8, 5 }, { 10, 14 }, { 14, 18 }, { 13, 27 }, | |
| - { 2, 40 }, { 0, 58 }, { -3, 70 }, { -6, 79 }, | |
| - { -8, 85 }, | |
| - | |
| - /* 276 a bit special (not used, x264_cabac_encode_bypass is used instead) */ | |
| - { 0, 0 }, | |
| - | |
| - /* 277 - 337 */ | |
| - { -13, 106 }, { -16, 106 }, { -10, 87 }, { -21, 114 }, | |
| - { -18, 110 }, { -14, 98 }, { -22, 110 }, { -21, 106 }, | |
| - { -18, 103 }, { -21, 107 }, { -23, 108 }, { -26, 112 }, | |
| - { -10, 96 }, { -12, 95 }, { -5, 91 }, { -9, 93 }, | |
| - { -22, 94 }, { -5, 86 }, { 9, 67 }, { -4, 80 }, | |
| - { -10, 85 }, { -1, 70 }, { 7, 60 }, { 9, 58 }, | |
| - { 5, 61 }, { 12, 50 }, { 15, 50 }, { 18, 49 }, | |
| - { 17, 54 }, { 10, 41 }, { 7, 46 }, { -1, 51 }, | |
| - { 7, 49 }, { 8, 52 }, { 9, 41 }, { 6, 47 }, | |
| - { 2, 55 }, { 13, 41 }, { 10, 44 }, { 6, 50 }, | |
| - { 5, 53 }, { 13, 49 }, { 4, 63 }, { 6, 64 }, | |
| - { -2, 69 }, { -2, 59 }, { 6, 70 }, { 10, 44 }, | |
| - { 9, 31 }, { 12, 43 }, { 3, 53 }, { 14, 34 }, | |
| - { 10, 38 }, { -3, 52 }, { 13, 40 }, { 17, 32 }, | |
| - { 7, 44 }, { 7, 38 }, { 13, 50 }, { 10, 57 }, | |
| - { 26, 43 }, | |
| - | |
| - /* 338 - 398 */ | |
| - { 14, 11 }, { 11, 14 }, { 9, 11 }, { 18, 11 }, | |
| - { 21, 9 }, { 23, -2 }, { 32, -15 }, { 32, -15 }, | |
| - { 34, -21 }, { 39, -23 }, { 42, -33 }, { 41, -31 }, | |
| - { 46, -28 }, { 38, -12 }, { 21, 29 }, { 45, -24 }, | |
| - { 53, -45 }, { 48, -26 }, { 65, -43 }, { 43, -19 }, | |
| - { 39, -10 }, { 30, 9 }, { 18, 26 }, { 20, 27 }, | |
| - { 0, 57 }, { -14, 82 }, { -5, 75 }, { -19, 97 }, | |
| - { -35, 125 }, { 27, 0 }, { 28, 0 }, { 31, -4 }, | |
| - { 27, 6 }, { 34, 8 }, { 30, 10 }, { 24, 22 }, | |
| - { 33, 19 }, { 22, 32 }, { 26, 31 }, { 21, 41 }, | |
| - { 26, 44 }, { 23, 47 }, { 16, 65 }, { 14, 71 }, | |
| - { 8, 60 }, { 6, 63 }, { 17, 65 }, { 21, 24 }, | |
| - { 23, 20 }, { 26, 23 }, { 27, 32 }, { 28, 23 }, | |
| - { 28, 24 }, { 23, 40 }, { 24, 32 }, { 28, 29 }, | |
| - { 23, 42 }, { 19, 57 }, { 22, 53 }, { 22, 61 }, | |
| - { 11, 86 }, | |
| - | |
| - /* 399 -> 435 */ | |
| - { 12, 40 }, { 11, 51 }, { 14, 59 }, | |
| - { -4, 79 }, { -7, 71 }, { -5, 69 }, { -9, 70 }, | |
| - { -8, 66 }, { -10, 68 }, { -19, 73 }, { -12, 69 }, | |
| - { -16, 70 }, { -15, 67 }, { -20, 62 }, { -19, 70 }, | |
| - { -16, 66 }, { -22, 65 }, { -20, 63 }, { 9, -2 }, | |
| - { 26, -9 }, { 33, -9 }, { 39, -7 }, { 41, -2 }, | |
| - { 45, 3 }, { 49, 9 }, { 45, 27 }, { 36, 59 }, | |
| - { -6, 66 }, { -7, 35 }, { -7, 42 }, { -8, 45 }, | |
| - { -5, 48 }, { -12, 56 }, { -6, 60 }, { -5, 62 }, | |
| - { -8, 66 }, { -8, 76 }, | |
| - | |
| - /* 436 -> 459 */ | |
| - { -5, 85 }, { -6, 81 }, { -10, 77 }, { -7, 81 }, | |
| - { -17, 80 }, { -18, 73 }, { -4, 74 }, { -10, 83 }, | |
| - { -9, 71 }, { -9, 67 }, { -1, 61 }, { -8, 66 }, | |
| - { -14, 66 }, { 0, 59 }, { 2, 59 }, { 21, -13 }, | |
| - { 33, -14 }, { 39, -7 }, { 46, -2 }, { 51, 2 }, | |
| - { 60, 6 }, { 61, 17 }, { 55, 34 }, { 42, 62 }, | |
| - | |
| - /* 460 - 1024 */ | |
| - { -7, 92 }, { -5, 89 }, { -7, 96 }, { -13, 108 }, | |
| - { -3, 46 }, { -1, 65 }, { -1, 57 }, { -9, 93 }, | |
| - { -3, 74 }, { -9, 92 }, { -8, 87 }, { -23, 126 }, | |
| - { -7, 92 }, { -5, 89 }, { -7, 96 }, { -13, 108 }, | |
| - { -3, 46 }, { -1, 65 }, { -1, 57 }, { -9, 93 }, | |
| - { -3, 74 }, { -9, 92 }, { -8, 87 }, { -23, 126 }, | |
| - { -2, 85 }, { -6, 78 }, { -1, 75 }, { -7, 77 }, | |
| - { 2, 54 }, { 5, 50 }, { -3, 68 }, { 1, 50 }, | |
| - { 6, 42 }, { -4, 81 }, { 1, 63 }, { -4, 70 }, | |
| - { 0, 67 }, { 2, 57 }, { -2, 76 }, { 11, 35 }, | |
| - { 4, 64 }, { 1, 61 }, { 11, 35 }, { 18, 25 }, | |
| - { 12, 24 }, { 13, 29 }, { 13, 36 }, { -10, 93 }, | |
| - { -7, 73 }, { -2, 73 }, { 13, 46 }, { 9, 49 }, | |
| - { -7, 100 }, { 9, 53 }, { 2, 53 }, { 5, 53 }, | |
| - { -2, 61 }, { 0, 56 }, { 0, 56 }, { -13, 63 }, | |
| - { -5, 60 }, { -1, 62 }, { 4, 57 }, { -6, 69 }, | |
| - { 4, 57 }, { 14, 39 }, { 4, 51 }, { 13, 68 }, | |
| - { -2, 85 }, { -6, 78 }, { -1, 75 }, { -7, 77 }, | |
| - { 2, 54 }, { 5, 50 }, { -3, 68 }, { 1, 50 }, | |
| - { 6, 42 }, { -4, 81 }, { 1, 63 }, { -4, 70 }, | |
| - { 0, 67 }, { 2, 57 }, { -2, 76 }, { 11, 35 }, | |
| - { 4, 64 }, { 1, 61 }, { 11, 35 }, { 18, 25 }, | |
| - { 12, 24 }, { 13, 29 }, { 13, 36 }, { -10, 93 }, | |
| - { -7, 73 }, { -2, 73 }, { 13, 46 }, { 9, 49 }, | |
| - { -7, 100 }, { 9, 53 }, { 2, 53 }, { 5, 53 }, | |
| - { -2, 61 }, { 0, 56 }, { 0, 56 }, { -13, 63 }, | |
| - { -5, 60 }, { -1, 62 }, { 4, 57 }, { -6, 69 }, | |
| - { 4, 57 }, { 14, 39 }, { 4, 51 }, { 13, 68 }, | |
| - { 11, 28 }, { 2, 40 }, { 3, 44 }, { 0, 49 }, | |
| - { 0, 46 }, { 2, 44 }, { 2, 51 }, { 0, 47 }, | |
| - { 4, 39 }, { 2, 62 }, { 6, 46 }, { 0, 54 }, | |
| - { 3, 54 }, { 2, 58 }, { 4, 63 }, { 6, 51 }, | |
| - { 6, 57 }, { 7, 53 }, { 6, 52 }, { 6, 55 }, | |
| - { 11, 45 }, { 14, 36 }, { 8, 53 }, { -1, 82 }, | |
| - { 7, 55 }, { -3, 78 }, { 15, 46 }, { 22, 31 }, | |
| - { -1, 84 }, { 25, 7 }, { 30, -7 }, { 28, 3 }, | |
| - { 28, 4 }, { 32, 0 }, { 34, -1 }, { 30, 6 }, | |
| - { 30, 6 }, { 32, 9 }, { 31, 19 }, { 26, 27 }, | |
| - { 26, 30 }, { 37, 20 }, { 28, 34 }, { 17, 70 }, | |
| - { 11, 28 }, { 2, 40 }, { 3, 44 }, { 0, 49 }, | |
| - { 0, 46 }, { 2, 44 }, { 2, 51 }, { 0, 47 }, | |
| - { 4, 39 }, { 2, 62 }, { 6, 46 }, { 0, 54 }, | |
| - { 3, 54 }, { 2, 58 }, { 4, 63 }, { 6, 51 }, | |
| - { 6, 57 }, { 7, 53 }, { 6, 52 }, { 6, 55 }, | |
| - { 11, 45 }, { 14, 36 }, { 8, 53 }, { -1, 82 }, | |
| - { 7, 55 }, { -3, 78 }, { 15, 46 }, { 22, 31 }, | |
| - { -1, 84 }, { 25, 7 }, { 30, -7 }, { 28, 3 }, | |
| - { 28, 4 }, { 32, 0 }, { 34, -1 }, { 30, 6 }, | |
| - { 30, 6 }, { 32, 9 }, { 31, 19 }, { 26, 27 }, | |
| - { 26, 30 }, { 37, 20 }, { 28, 34 }, { 17, 70 }, | |
| - { -4, 79 }, { -7, 71 }, { -5, 69 }, { -9, 70 }, | |
| - { -8, 66 }, { -10, 68 }, { -19, 73 }, { -12, 69 }, | |
| - { -16, 70 }, { -15, 67 }, { -20, 62 }, { -19, 70 }, | |
| - { -16, 66 }, { -22, 65 }, { -20, 63 }, { -5, 85 }, | |
| - { -6, 81 }, { -10, 77 }, { -7, 81 }, { -17, 80 }, | |
| - { -18, 73 }, { -4, 74 }, { -10, 83 }, { -9, 71 }, | |
| - { -9, 67 }, { -1, 61 }, { -8, 66 }, { -14, 66 }, | |
| - { 0, 59 }, { 2, 59 }, { 9, -2 }, { 26, -9 }, | |
| - { 33, -9 }, { 39, -7 }, { 41, -2 }, { 45, 3 }, | |
| - { 49, 9 }, { 45, 27 }, { 36, 59 }, { 21, -13 }, | |
| - { 33, -14 }, { 39, -7 }, { 46, -2 }, { 51, 2 }, | |
| - { 60, 6 }, { 61, 17 }, { 55, 34 }, { 42, 62 }, | |
| - { -6, 66 }, { -7, 35 }, { -7, 42 }, { -8, 45 }, | |
| - { -5, 48 }, { -12, 56 }, { -6, 60 }, { -5, 62 }, | |
| - { -8, 66 }, { -8, 76 }, { -4, 79 }, { -7, 71 }, | |
| - { -5, 69 }, { -9, 70 }, { -8, 66 }, { -10, 68 }, | |
| - { -19, 73 }, { -12, 69 }, { -16, 70 }, { -15, 67 }, | |
| - { -20, 62 }, { -19, 70 }, { -16, 66 }, { -22, 65 }, | |
| - { -20, 63 }, { -5, 85 }, { -6, 81 }, { -10, 77 }, | |
| - { -7, 81 }, { -17, 80 }, { -18, 73 }, { -4, 74 }, | |
| - { -10, 83 }, { -9, 71 }, { -9, 67 }, { -1, 61 }, | |
| - { -8, 66 }, { -14, 66 }, { 0, 59 }, { 2, 59 }, | |
| - { 9, -2 }, { 26, -9 }, { 33, -9 }, { 39, -7 }, | |
| - { 41, -2 }, { 45, 3 }, { 49, 9 }, { 45, 27 }, | |
| - { 36, 59 }, { 21, -13 }, { 33, -14 }, { 39, -7 }, | |
| - { 46, -2 }, { 51, 2 }, { 60, 6 }, { 61, 17 }, | |
| - { 55, 34 }, { 42, 62 }, { -6, 66 }, { -7, 35 }, | |
| - { -7, 42 }, { -8, 45 }, { -5, 48 }, { -12, 56 }, | |
| - { -6, 60 }, { -5, 62 }, { -8, 66 }, { -8, 76 }, | |
| - { -13, 106 }, { -16, 106 }, { -10, 87 }, { -21, 114 }, | |
| - { -18, 110 }, { -14, 98 }, { -22, 110 }, { -21, 106 }, | |
| - { -18, 103 }, { -21, 107 }, { -23, 108 }, { -26, 112 }, | |
| - { -10, 96 }, { -12, 95 }, { -5, 91 }, { -9, 93 }, | |
| - { -22, 94 }, { -5, 86 }, { 9, 67 }, { -4, 80 }, | |
| - { -10, 85 }, { -1, 70 }, { 7, 60 }, { 9, 58 }, | |
| - { 5, 61 }, { 12, 50 }, { 15, 50 }, { 18, 49 }, | |
| - { 17, 54 }, { 10, 41 }, { 7, 46 }, { -1, 51 }, | |
| - { 7, 49 }, { 8, 52 }, { 9, 41 }, { 6, 47 }, | |
| - { 2, 55 }, { 13, 41 }, { 10, 44 }, { 6, 50 }, | |
| - { 5, 53 }, { 13, 49 }, { 4, 63 }, { 6, 64 }, | |
| - { -13, 106 }, { -16, 106 }, { -10, 87 }, { -21, 114 }, | |
| - { -18, 110 }, { -14, 98 }, { -22, 110 }, { -21, 106 }, | |
| - { -18, 103 }, { -21, 107 }, { -23, 108 }, { -26, 112 }, | |
| - { -10, 96 }, { -12, 95 }, { -5, 91 }, { -9, 93 }, | |
| - { -22, 94 }, { -5, 86 }, { 9, 67 }, { -4, 80 }, | |
| - { -10, 85 }, { -1, 70 }, { 7, 60 }, { 9, 58 }, | |
| - { 5, 61 }, { 12, 50 }, { 15, 50 }, { 18, 49 }, | |
| - { 17, 54 }, { 10, 41 }, { 7, 46 }, { -1, 51 }, | |
| - { 7, 49 }, { 8, 52 }, { 9, 41 }, { 6, 47 }, | |
| - { 2, 55 }, { 13, 41 }, { 10, 44 }, { 6, 50 }, | |
| - { 5, 53 }, { 13, 49 }, { 4, 63 }, { 6, 64 }, | |
| - { 14, 11 }, { 11, 14 }, { 9, 11 }, { 18, 11 }, | |
| - { 21, 9 }, { 23, -2 }, { 32, -15 }, { 32, -15 }, | |
| - { 34, -21 }, { 39, -23 }, { 42, -33 }, { 41, -31 }, | |
| - { 46, -28 }, { 38, -12 }, { 21, 29 }, { 45, -24 }, | |
| - { 53, -45 }, { 48, -26 }, { 65, -43 }, { 43, -19 }, | |
| - { 39, -10 }, { 30, 9 }, { 18, 26 }, { 20, 27 }, | |
| - { 0, 57 }, { -14, 82 }, { -5, 75 }, { -19, 97 }, | |
| - { -35, 125 }, { 27, 0 }, { 28, 0 }, { 31, -4 }, | |
| - { 27, 6 }, { 34, 8 }, { 30, 10 }, { 24, 22 }, | |
| - { 33, 19 }, { 22, 32 }, { 26, 31 }, { 21, 41 }, | |
| - { 26, 44 }, { 23, 47 }, { 16, 65 }, { 14, 71 }, | |
| - { 14, 11 }, { 11, 14 }, { 9, 11 }, { 18, 11 }, | |
| - { 21, 9 }, { 23, -2 }, { 32, -15 }, { 32, -15 }, | |
| - { 34, -21 }, { 39, -23 }, { 42, -33 }, { 41, -31 }, | |
| - { 46, -28 }, { 38, -12 }, { 21, 29 }, { 45, -24 }, | |
| - { 53, -45 }, { 48, -26 }, { 65, -43 }, { 43, -19 }, | |
| - { 39, -10 }, { 30, 9 }, { 18, 26 }, { 20, 27 }, | |
| - { 0, 57 }, { -14, 82 }, { -5, 75 }, { -19, 97 }, | |
| - { -35, 125 }, { 27, 0 }, { 28, 0 }, { 31, -4 }, | |
| - { 27, 6 }, { 34, 8 }, { 30, 10 }, { 24, 22 }, | |
| - { 33, 19 }, { 22, 32 }, { 26, 31 }, { 21, 41 }, | |
| - { 26, 44 }, { 23, 47 }, { 16, 65 }, { 14, 71 }, | |
| - { -6, 76 }, { -2, 44 }, { 0, 45 }, { 0, 52 }, | |
| - { -3, 64 }, { -2, 59 }, { -4, 70 }, { -4, 75 }, | |
| - { -8, 82 }, { -17, 102 }, { -9, 77 }, { 3, 24 }, | |
| - { 0, 42 }, { 0, 48 }, { 0, 55 }, { -6, 59 }, | |
| - { -7, 71 }, { -12, 83 }, { -11, 87 }, { -30, 119 }, | |
| - { 1, 58 }, { -3, 29 }, { -1, 36 }, { 1, 38 }, | |
| - { 2, 43 }, { -6, 55 }, { 0, 58 }, { 0, 64 }, | |
| - { -3, 74 }, { -10, 90 }, { -6, 76 }, { -2, 44 }, | |
| - { 0, 45 }, { 0, 52 }, { -3, 64 }, { -2, 59 }, | |
| - { -4, 70 }, { -4, 75 }, { -8, 82 }, { -17, 102 }, | |
| - { -9, 77 }, { 3, 24 }, { 0, 42 }, { 0, 48 }, | |
| - { 0, 55 }, { -6, 59 }, { -7, 71 }, { -12, 83 }, | |
| - { -11, 87 }, { -30, 119 }, { 1, 58 }, { -3, 29 }, | |
| - { -1, 36 }, { 1, 38 }, { 2, 43 }, { -6, 55 }, | |
| - { 0, 58 }, { 0, 64 }, { -3, 74 }, { -10, 90 }, | |
| - { -3, 74 }, { -9, 92 }, { -8, 87 }, { -23, 126 }, | |
| - { -3, 74 }, { -9, 92 }, { -8, 87 }, { -23, 126 }, | |
| - { -3, 74 }, { -9, 92 }, { -8, 87 }, { -23, 126 } | |
| - }, | |
| - | |
| - /* i_cabac_init_idc == 1 */ | |
| - { | |
| - /* 0 - 10 */ | |
| - { 20, -15 }, { 2, 54 }, { 3, 74 }, { 20, -15 }, | |
| - { 2, 54 }, { 3, 74 }, { -28, 127 }, { -23, 104 }, | |
| - { -6, 53 }, { -1, 54 }, { 7, 51 }, | |
| - | |
| - /* 11 - 23 */ | |
| - { 22, 25 }, { 34, 0 }, { 16, 0 }, { -2, 9 }, | |
| - { 4, 41 }, { -29, 118 }, { 2, 65 }, { -6, 71 }, | |
| - { -13, 79 }, { 5, 52 }, { 9, 50 }, { -3, 70 }, | |
| - { 10, 54 }, | |
| - | |
| - /* 24 - 39 */ | |
| - { 26, 34 }, { 19, 22 }, { 40, 0 }, { 57, 2 }, | |
| - { 41, 36 }, { 26, 69 }, { -45, 127 }, { -15, 101 }, | |
| - { -4, 76 }, { -6, 71 }, { -13, 79 }, { 5, 52 }, | |
| - { 6, 69 }, { -13, 90 }, { 0, 52 }, { 8, 43 }, | |
| - | |
| - /* 40 - 53 */ | |
| - { -2, 69 },{ -5, 82 },{ -10, 96 },{ 2, 59 }, | |
| - { 2, 75 },{ -3, 87 },{ -3, 100 },{ 1, 56 }, | |
| - { -3, 74 },{ -6, 85 },{ 0, 59 },{ -3, 81 }, | |
| - { -7, 86 },{ -5, 95 }, | |
| - | |
| - /* 54 - 59 */ | |
| - { -1, 66 },{ -1, 77 },{ 1, 70 },{ -2, 86 }, | |
| - { -5, 72 },{ 0, 61 }, | |
| - | |
| - /* 60 - 69 */ | |
| - { 0, 41 }, { 0, 63 }, { 0, 63 }, { 0, 63 }, | |
| - { -9, 83 }, { 4, 86 }, { 0, 97 }, { -7, 72 }, | |
| - { 13, 41 }, { 3, 62 }, | |
| - | |
| - /* 70 - 104 */ | |
| - { 13, 15 }, { 7, 51 }, { 2, 80 }, { -39, 127 }, | |
| - { -18, 91 }, { -17, 96 }, { -26, 81 }, { -35, 98 }, | |
| - { -24, 102 }, { -23, 97 }, { -27, 119 }, { -24, 99 }, | |
| - { -21, 110 }, { -18, 102 }, { -36, 127 }, { 0, 80 }, | |
| - { -5, 89 }, { -7, 94 }, { -4, 92 }, { 0, 39 }, | |
| - { 0, 65 }, { -15, 84 }, { -35, 127 }, { -2, 73 }, | |
| - { -12, 104 }, { -9, 91 }, { -31, 127 }, { 3, 55 }, | |
| - { 7, 56 }, { 7, 55 }, { 8, 61 }, { -3, 53 }, | |
| - { 0, 68 }, { -7, 74 }, { -9, 88 }, | |
| - | |
| - /* 105 -> 165 */ | |
| - { -13, 103 }, { -13, 91 }, { -9, 89 }, { -14, 92 }, | |
| - { -8, 76 }, { -12, 87 }, { -23, 110 }, { -24, 105 }, | |
| - { -10, 78 }, { -20, 112 }, { -17, 99 }, { -78, 127 }, | |
| - { -70, 127 }, { -50, 127 }, { -46, 127 }, { -4, 66 }, | |
| - { -5, 78 }, { -4, 71 }, { -8, 72 }, { 2, 59 }, | |
| - { -1, 55 }, { -7, 70 }, { -6, 75 }, { -8, 89 }, | |
| - { -34, 119 }, { -3, 75 }, { 32, 20 }, { 30, 22 }, | |
| - { -44, 127 }, { 0, 54 }, { -5, 61 }, { 0, 58 }, | |
| - { -1, 60 }, { -3, 61 }, { -8, 67 }, { -25, 84 }, | |
| - { -14, 74 }, { -5, 65 }, { 5, 52 }, { 2, 57 }, | |
| - { 0, 61 }, { -9, 69 }, { -11, 70 }, { 18, 55 }, | |
| - { -4, 71 }, { 0, 58 }, { 7, 61 }, { 9, 41 }, | |
| - { 18, 25 }, { 9, 32 }, { 5, 43 }, { 9, 47 }, | |
| - { 0, 44 }, { 0, 51 }, { 2, 46 }, { 19, 38 }, | |
| - { -4, 66 }, { 15, 38 }, { 12, 42 }, { 9, 34 }, | |
| - { 0, 89 }, | |
| - | |
| - /* 166 - 226 */ | |
| - { 4, 45 }, { 10, 28 }, { 10, 31 }, { 33, -11 }, | |
| - { 52, -43 }, { 18, 15 }, { 28, 0 }, { 35, -22 }, | |
| - { 38, -25 }, { 34, 0 }, { 39, -18 }, { 32, -12 }, | |
| - { 102, -94 }, { 0, 0 }, { 56, -15 }, { 33, -4 }, | |
| - { 29, 10 }, { 37, -5 }, { 51, -29 }, { 39, -9 }, | |
| - { 52, -34 }, { 69, -58 }, { 67, -63 }, { 44, -5 }, | |
| - { 32, 7 }, { 55, -29 }, { 32, 1 }, { 0, 0 }, | |
| - { 27, 36 }, { 33, -25 }, { 34, -30 }, { 36, -28 }, | |
| - { 38, -28 }, { 38, -27 }, { 34, -18 }, { 35, -16 }, | |
| - { 34, -14 }, { 32, -8 }, { 37, -6 }, { 35, 0 }, | |
| - { 30, 10 }, { 28, 18 }, { 26, 25 }, { 29, 41 }, | |
| - { 0, 75 }, { 2, 72 }, { 8, 77 }, { 14, 35 }, | |
| - { 18, 31 }, { 17, 35 }, { 21, 30 }, { 17, 45 }, | |
| - { 20, 42 }, { 18, 45 }, { 27, 26 }, { 16, 54 }, | |
| - { 7, 66 }, { 16, 56 }, { 11, 73 }, { 10, 67 }, | |
| - { -10, 116 }, | |
| - | |
| - /* 227 - 275 */ | |
| - { -23, 112 }, { -15, 71 }, { -7, 61 }, { 0, 53 }, | |
| - { -5, 66 }, { -11, 77 }, { -9, 80 }, { -9, 84 }, | |
| - { -10, 87 }, { -34, 127 }, { -21, 101 }, { -3, 39 }, | |
| - { -5, 53 }, { -7, 61 }, { -11, 75 }, { -15, 77 }, | |
| - { -17, 91 }, { -25, 107 }, { -25, 111 }, { -28, 122 }, | |
| - { -11, 76 }, { -10, 44 }, { -10, 52 }, { -10, 57 }, | |
| - { -9, 58 }, { -16, 72 }, { -7, 69 }, { -4, 69 }, | |
| - { -5, 74 }, { -9, 86 }, { 2, 66 }, { -9, 34 }, | |
| - { 1, 32 }, { 11, 31 }, { 5, 52 }, { -2, 55 }, | |
| - { -2, 67 }, { 0, 73 }, { -8, 89 }, { 3, 52 }, | |
| - { 7, 4 }, { 10, 8 }, { 17, 8 }, { 16, 19 }, | |
| - { 3, 37 }, { -1, 61 }, { -5, 73 }, { -1, 70 }, | |
| - { -4, 78 }, | |
| - | |
| - /* 276 a bit special (not used, x264_cabac_encode_bypass is used instead) */ | |
| - { 0, 0 }, | |
| - | |
| - /* 277 - 337 */ | |
| - { -21, 126 }, { -23, 124 }, { -20, 110 }, { -26, 126 }, | |
| - { -25, 124 }, { -17, 105 }, { -27, 121 }, { -27, 117 }, | |
| - { -17, 102 }, { -26, 117 }, { -27, 116 }, { -33, 122 }, | |
| - { -10, 95 }, { -14, 100 }, { -8, 95 }, { -17, 111 }, | |
| - { -28, 114 }, { -6, 89 }, { -2, 80 }, { -4, 82 }, | |
| - { -9, 85 }, { -8, 81 }, { -1, 72 }, { 5, 64 }, | |
| - { 1, 67 }, { 9, 56 }, { 0, 69 }, { 1, 69 }, | |
| - { 7, 69 }, { -7, 69 }, { -6, 67 }, { -16, 77 }, | |
| - { -2, 64 }, { 2, 61 }, { -6, 67 }, { -3, 64 }, | |
| - { 2, 57 }, { -3, 65 }, { -3, 66 }, { 0, 62 }, | |
| - { 9, 51 }, { -1, 66 }, { -2, 71 }, { -2, 75 }, | |
| - { -1, 70 }, { -9, 72 }, { 14, 60 }, { 16, 37 }, | |
| - { 0, 47 }, { 18, 35 }, { 11, 37 }, { 12, 41 }, | |
| - { 10, 41 }, { 2, 48 }, { 12, 41 }, { 13, 41 }, | |
| - { 0, 59 }, { 3, 50 }, { 19, 40 }, { 3, 66 }, | |
| - { 18, 50 }, | |
| - | |
| - /* 338 - 398 */ | |
| - { 19, -6 }, { 18, -6 }, { 14, 0 }, { 26, -12 }, | |
| - { 31, -16 }, { 33, -25 }, { 33, -22 }, { 37, -28 }, | |
| - { 39, -30 }, { 42, -30 }, { 47, -42 }, { 45, -36 }, | |
| - { 49, -34 }, { 41, -17 }, { 32, 9 }, { 69, -71 }, | |
| - { 63, -63 }, { 66, -64 }, { 77, -74 }, { 54, -39 }, | |
| - { 52, -35 }, { 41, -10 }, { 36, 0 }, { 40, -1 }, | |
| - { 30, 14 }, { 28, 26 }, { 23, 37 }, { 12, 55 }, | |
| - { 11, 65 }, { 37, -33 }, { 39, -36 }, { 40, -37 }, | |
| - { 38, -30 }, { 46, -33 }, { 42, -30 }, { 40, -24 }, | |
| - { 49, -29 }, { 38, -12 }, { 40, -10 }, { 38, -3 }, | |
| - { 46, -5 }, { 31, 20 }, { 29, 30 }, { 25, 44 }, | |
| - { 12, 48 }, { 11, 49 }, { 26, 45 }, { 22, 22 }, | |
| - { 23, 22 }, { 27, 21 }, { 33, 20 }, { 26, 28 }, | |
| - { 30, 24 }, { 27, 34 }, { 18, 42 }, { 25, 39 }, | |
| - { 18, 50 }, { 12, 70 }, { 21, 54 }, { 14, 71 }, | |
| - { 11, 83 }, | |
| - | |
| - /* 399 -> 435 */ | |
| - { 25, 32 }, { 21, 49 }, { 21, 54 }, | |
| - { -5, 85 }, { -6, 81 }, { -10, 77 }, { -7, 81 }, | |
| - { -17, 80 }, { -18, 73 }, { -4, 74 }, { -10, 83 }, | |
| - { -9, 71 }, { -9, 67 }, { -1, 61 }, { -8, 66 }, | |
| - { -14, 66 }, { 0, 59 }, { 2, 59 }, { 17, -10 }, | |
| - { 32, -13 }, { 42, -9 }, { 49, -5 }, { 53, 0 }, | |
| - { 64, 3 }, { 68, 10 }, { 66, 27 }, { 47, 57 }, | |
| - { -5, 71 }, { 0, 24 }, { -1, 36 }, { -2, 42 }, | |
| - { -2, 52 }, { -9, 57 }, { -6, 63 }, { -4, 65 }, | |
| - { -4, 67 }, { -7, 82 }, | |
| - | |
| - /* 436 -> 459 */ | |
| - { -3, 81 }, { -3, 76 }, { -7, 72 }, { -6, 78 }, | |
| - { -12, 72 }, { -14, 68 }, { -3, 70 }, { -6, 76 }, | |
| - { -5, 66 }, { -5, 62 }, { 0, 57 }, { -4, 61 }, | |
| - { -9, 60 }, { 1, 54 }, { 2, 58 }, { 17, -10 }, | |
| - { 32, -13 }, { 42, -9 }, { 49, -5 }, { 53, 0 }, | |
| - { 64, 3 }, { 68, 10 }, { 66, 27 }, { 47, 57 }, | |
| - | |
| - /* 460 - 1024 */ | |
| - { 0, 80 }, { -5, 89 }, { -7, 94 }, { -4, 92 }, | |
| - { 0, 39 }, { 0, 65 }, { -15, 84 }, { -35, 127 }, | |
| - { -2, 73 }, { -12, 104 }, { -9, 91 }, { -31, 127 }, | |
| - { 0, 80 }, { -5, 89 }, { -7, 94 }, { -4, 92 }, | |
| - { 0, 39 }, { 0, 65 }, { -15, 84 }, { -35, 127 }, | |
| - { -2, 73 }, { -12, 104 }, { -9, 91 }, { -31, 127 }, | |
| - { -13, 103 }, { -13, 91 }, { -9, 89 }, { -14, 92 }, | |
| - { -8, 76 }, { -12, 87 }, { -23, 110 }, { -24, 105 }, | |
| - { -10, 78 }, { -20, 112 }, { -17, 99 }, { -78, 127 }, | |
| - { -70, 127 }, { -50, 127 }, { -46, 127 }, { -4, 66 }, | |
| - { -5, 78 }, { -4, 71 }, { -8, 72 }, { 2, 59 }, | |
| - { -1, 55 }, { -7, 70 }, { -6, 75 }, { -8, 89 }, | |
| - { -34, 119 }, { -3, 75 }, { 32, 20 }, { 30, 22 }, | |
| - { -44, 127 }, { 0, 54 }, { -5, 61 }, { 0, 58 }, | |
| - { -1, 60 }, { -3, 61 }, { -8, 67 }, { -25, 84 }, | |
| - { -14, 74 }, { -5, 65 }, { 5, 52 }, { 2, 57 }, | |
| - { 0, 61 }, { -9, 69 }, { -11, 70 }, { 18, 55 }, | |
| - { -13, 103 }, { -13, 91 }, { -9, 89 }, { -14, 92 }, | |
| - { -8, 76 }, { -12, 87 }, { -23, 110 }, { -24, 105 }, | |
| - { -10, 78 }, { -20, 112 }, { -17, 99 }, { -78, 127 }, | |
| - { -70, 127 }, { -50, 127 }, { -46, 127 }, { -4, 66 }, | |
| - { -5, 78 }, { -4, 71 }, { -8, 72 }, { 2, 59 }, | |
| - { -1, 55 }, { -7, 70 }, { -6, 75 }, { -8, 89 }, | |
| - { -34, 119 }, { -3, 75 }, { 32, 20 }, { 30, 22 }, | |
| - { -44, 127 }, { 0, 54 }, { -5, 61 }, { 0, 58 }, | |
| - { -1, 60 }, { -3, 61 }, { -8, 67 }, { -25, 84 }, | |
| - { -14, 74 }, { -5, 65 }, { 5, 52 }, { 2, 57 }, | |
| - { 0, 61 }, { -9, 69 }, { -11, 70 }, { 18, 55 }, | |
| - { 4, 45 }, { 10, 28 }, { 10, 31 }, { 33, -11 }, | |
| - { 52, -43 }, { 18, 15 }, { 28, 0 }, { 35, -22 }, | |
| - { 38, -25 }, { 34, 0 }, { 39, -18 }, { 32, -12 }, | |
| - { 102, -94 }, { 0, 0 }, { 56, -15 }, { 33, -4 }, | |
| - { 29, 10 }, { 37, -5 }, { 51, -29 }, { 39, -9 }, | |
| - { 52, -34 }, { 69, -58 }, { 67, -63 }, { 44, -5 }, | |
| - { 32, 7 }, { 55, -29 }, { 32, 1 }, { 0, 0 }, | |
| - { 27, 36 }, { 33, -25 }, { 34, -30 }, { 36, -28 }, | |
| - { 38, -28 }, { 38, -27 }, { 34, -18 }, { 35, -16 }, | |
| - { 34, -14 }, { 32, -8 }, { 37, -6 }, { 35, 0 }, | |
| - { 30, 10 }, { 28, 18 }, { 26, 25 }, { 29, 41 }, | |
| - { 4, 45 }, { 10, 28 }, { 10, 31 }, { 33, -11 }, | |
| - { 52, -43 }, { 18, 15 }, { 28, 0 }, { 35, -22 }, | |
| - { 38, -25 }, { 34, 0 }, { 39, -18 }, { 32, -12 }, | |
| - { 102, -94 }, { 0, 0 }, { 56, -15 }, { 33, -4 }, | |
| - { 29, 10 }, { 37, -5 }, { 51, -29 }, { 39, -9 }, | |
| - { 52, -34 }, { 69, -58 }, { 67, -63 }, { 44, -5 }, | |
| - { 32, 7 }, { 55, -29 }, { 32, 1 }, { 0, 0 }, | |
| - { 27, 36 }, { 33, -25 }, { 34, -30 }, { 36, -28 }, | |
| - { 38, -28 }, { 38, -27 }, { 34, -18 }, { 35, -16 }, | |
| - { 34, -14 }, { 32, -8 }, { 37, -6 }, { 35, 0 }, | |
| - { 30, 10 }, { 28, 18 }, { 26, 25 }, { 29, 41 }, | |
| - { -5, 85 }, { -6, 81 }, { -10, 77 }, { -7, 81 }, | |
| - { -17, 80 }, { -18, 73 }, { -4, 74 }, { -10, 83 }, | |
| - { -9, 71 }, { -9, 67 }, { -1, 61 }, { -8, 66 }, | |
| - { -14, 66 }, { 0, 59 }, { 2, 59 }, { -3, 81 }, | |
| - { -3, 76 }, { -7, 72 }, { -6, 78 }, { -12, 72 }, | |
| - { -14, 68 }, { -3, 70 }, { -6, 76 }, { -5, 66 }, | |
| - { -5, 62 }, { 0, 57 }, { -4, 61 }, { -9, 60 }, | |
| - { 1, 54 }, { 2, 58 }, { 17, -10 }, { 32, -13 }, | |
| - { 42, -9 }, { 49, -5 }, { 53, 0 }, { 64, 3 }, | |
| - { 68, 10 }, { 66, 27 }, { 47, 57 }, { 17, -10 }, | |
| - { 32, -13 }, { 42, -9 }, { 49, -5 }, { 53, 0 }, | |
| - { 64, 3 }, { 68, 10 }, { 66, 27 }, { 47, 57 }, | |
| - { -5, 71 }, { 0, 24 }, { -1, 36 }, { -2, 42 }, | |
| - { -2, 52 }, { -9, 57 }, { -6, 63 }, { -4, 65 }, | |
| - { -4, 67 }, { -7, 82 }, { -5, 85 }, { -6, 81 }, | |
| - { -10, 77 }, { -7, 81 }, { -17, 80 }, { -18, 73 }, | |
| - { -4, 74 }, { -10, 83 }, { -9, 71 }, { -9, 67 }, | |
| - { -1, 61 }, { -8, 66 }, { -14, 66 }, { 0, 59 }, | |
| - { 2, 59 }, { -3, 81 }, { -3, 76 }, { -7, 72 }, | |
| - { -6, 78 }, { -12, 72 }, { -14, 68 }, { -3, 70 }, | |
| - { -6, 76 }, { -5, 66 }, { -5, 62 }, { 0, 57 }, | |
| - { -4, 61 }, { -9, 60 }, { 1, 54 }, { 2, 58 }, | |
| - { 17, -10 }, { 32, -13 }, { 42, -9 }, { 49, -5 }, | |
| - { 53, 0 }, { 64, 3 }, { 68, 10 }, { 66, 27 }, | |
| - { 47, 57 }, { 17, -10 }, { 32, -13 }, { 42, -9 }, | |
| - { 49, -5 }, { 53, 0 }, { 64, 3 }, { 68, 10 }, | |
| - { 66, 27 }, { 47, 57 }, { -5, 71 }, { 0, 24 }, | |
| - { -1, 36 }, { -2, 42 }, { -2, 52 }, { -9, 57 }, | |
| - { -6, 63 }, { -4, 65 }, { -4, 67 }, { -7, 82 }, | |
| - { -21, 126 }, { -23, 124 }, { -20, 110 }, { -26, 126 }, | |
| - { -25, 124 }, { -17, 105 }, { -27, 121 }, { -27, 117 }, | |
| - { -17, 102 }, { -26, 117 }, { -27, 116 }, { -33, 122 }, | |
| - { -10, 95 }, { -14, 100 }, { -8, 95 }, { -17, 111 }, | |
| - { -28, 114 }, { -6, 89 }, { -2, 80 }, { -4, 82 }, | |
| - { -9, 85 }, { -8, 81 }, { -1, 72 }, { 5, 64 }, | |
| - { 1, 67 }, { 9, 56 }, { 0, 69 }, { 1, 69 }, | |
| - { 7, 69 }, { -7, 69 }, { -6, 67 }, { -16, 77 }, | |
| - { -2, 64 }, { 2, 61 }, { -6, 67 }, { -3, 64 }, | |
| - { 2, 57 }, { -3, 65 }, { -3, 66 }, { 0, 62 }, | |
| - { 9, 51 }, { -1, 66 }, { -2, 71 }, { -2, 75 }, | |
| - { -21, 126 }, { -23, 124 }, { -20, 110 }, { -26, 126 }, | |
| - { -25, 124 }, { -17, 105 }, { -27, 121 }, { -27, 117 }, | |
| - { -17, 102 }, { -26, 117 }, { -27, 116 }, { -33, 122 }, | |
| - { -10, 95 }, { -14, 100 }, { -8, 95 }, { -17, 111 }, | |
| - { -28, 114 }, { -6, 89 }, { -2, 80 }, { -4, 82 }, | |
| - { -9, 85 }, { -8, 81 }, { -1, 72 }, { 5, 64 }, | |
| - { 1, 67 }, { 9, 56 }, { 0, 69 }, { 1, 69 }, | |
| - { 7, 69 }, { -7, 69 }, { -6, 67 }, { -16, 77 }, | |
| - { -2, 64 }, { 2, 61 }, { -6, 67 }, { -3, 64 }, | |
| - { 2, 57 }, { -3, 65 }, { -3, 66 }, { 0, 62 }, | |
| - { 9, 51 }, { -1, 66 }, { -2, 71 }, { -2, 75 }, | |
| - { 19, -6 }, { 18, -6 }, { 14, 0 }, { 26, -12 }, | |
| - { 31, -16 }, { 33, -25 }, { 33, -22 }, { 37, -28 }, | |
| - { 39, -30 }, { 42, -30 }, { 47, -42 }, { 45, -36 }, | |
| - { 49, -34 }, { 41, -17 }, { 32, 9 }, { 69, -71 }, | |
| - { 63, -63 }, { 66, -64 }, { 77, -74 }, { 54, -39 }, | |
| - { 52, -35 }, { 41, -10 }, { 36, 0 }, { 40, -1 }, | |
| - { 30, 14 }, { 28, 26 }, { 23, 37 }, { 12, 55 }, | |
| - { 11, 65 }, { 37, -33 }, { 39, -36 }, { 40, -37 }, | |
| - { 38, -30 }, { 46, -33 }, { 42, -30 }, { 40, -24 }, | |
| - { 49, -29 }, { 38, -12 }, { 40, -10 }, { 38, -3 }, | |
| - { 46, -5 }, { 31, 20 }, { 29, 30 }, { 25, 44 }, | |
| - { 19, -6 }, { 18, -6 }, { 14, 0 }, { 26, -12 }, | |
| - { 31, -16 }, { 33, -25 }, { 33, -22 }, { 37, -28 }, | |
| - { 39, -30 }, { 42, -30 }, { 47, -42 }, { 45, -36 }, | |
| - { 49, -34 }, { 41, -17 }, { 32, 9 }, { 69, -71 }, | |
| - { 63, -63 }, { 66, -64 }, { 77, -74 }, { 54, -39 }, | |
| - { 52, -35 }, { 41, -10 }, { 36, 0 }, { 40, -1 }, | |
| - { 30, 14 }, { 28, 26 }, { 23, 37 }, { 12, 55 }, | |
| - { 11, 65 }, { 37, -33 }, { 39, -36 }, { 40, -37 }, | |
| - { 38, -30 }, { 46, -33 }, { 42, -30 }, { 40, -24 }, | |
| - { 49, -29 }, { 38, -12 }, { 40, -10 }, { 38, -3 }, | |
| - { 46, -5 }, { 31, 20 }, { 29, 30 }, { 25, 44 }, | |
| - { -23, 112 }, { -15, 71 }, { -7, 61 }, { 0, 53 }, | |
| - { -5, 66 }, { -11, 77 }, { -9, 80 }, { -9, 84 }, | |
| - { -10, 87 }, { -34, 127 }, { -21, 101 }, { -3, 39 }, | |
| - { -5, 53 }, { -7, 61 }, { -11, 75 }, { -15, 77 }, | |
| - { -17, 91 }, { -25, 107 }, { -25, 111 }, { -28, 122 }, | |
| - { -11, 76 }, { -10, 44 }, { -10, 52 }, { -10, 57 }, | |
| - { -9, 58 }, { -16, 72 }, { -7, 69 }, { -4, 69 }, | |
| - { -5, 74 }, { -9, 86 }, { -23, 112 }, { -15, 71 }, | |
| - { -7, 61 }, { 0, 53 }, { -5, 66 }, { -11, 77 }, | |
| - { -9, 80 }, { -9, 84 }, { -10, 87 }, { -34, 127 }, | |
| - { -21, 101 }, { -3, 39 }, { -5, 53 }, { -7, 61 }, | |
| - { -11, 75 }, { -15, 77 }, { -17, 91 }, { -25, 107 }, | |
| - { -25, 111 }, { -28, 122 }, { -11, 76 }, { -10, 44 }, | |
| - { -10, 52 }, { -10, 57 }, { -9, 58 }, { -16, 72 }, | |
| - { -7, 69 }, { -4, 69 }, { -5, 74 }, { -9, 86 }, | |
| - { -2, 73 }, { -12, 104 }, { -9, 91 }, { -31, 127 }, | |
| - { -2, 73 }, { -12, 104 }, { -9, 91 }, { -31, 127 }, | |
| - { -2, 73 }, { -12, 104 }, { -9, 91 }, { -31, 127 } | |
| - }, | |
| - | |
| - /* i_cabac_init_idc == 2 */ | |
| - { | |
| - /* 0 - 10 */ | |
| - { 20, -15 }, { 2, 54 }, { 3, 74 }, { 20, -15 }, | |
| - { 2, 54 }, { 3, 74 }, { -28, 127 }, { -23, 104 }, | |
| - { -6, 53 }, { -1, 54 }, { 7, 51 }, | |
| - | |
| - /* 11 - 23 */ | |
| - { 29, 16 }, { 25, 0 }, { 14, 0 }, { -10, 51 }, | |
| - { -3, 62 }, { -27, 99 }, { 26, 16 }, { -4, 85 }, | |
| - { -24, 102 }, { 5, 57 }, { 6, 57 }, { -17, 73 }, | |
| - { 14, 57 }, | |
| - | |
| - /* 24 - 39 */ | |
| - { 20, 40 }, { 20, 10 }, { 29, 0 }, { 54, 0 }, | |
| - { 37, 42 }, { 12, 97 }, { -32, 127 }, { -22, 117 }, | |
| - { -2, 74 }, { -4, 85 }, { -24, 102 }, { 5, 57 }, | |
| - { -6, 93 }, { -14, 88 }, { -6, 44 }, { 4, 55 }, | |
| - | |
| - /* 40 - 53 */ | |
| - { -11, 89 },{ -15, 103 },{ -21, 116 },{ 19, 57 }, | |
| - { 20, 58 },{ 4, 84 },{ 6, 96 },{ 1, 63 }, | |
| - { -5, 85 },{ -13, 106 },{ 5, 63 },{ 6, 75 }, | |
| - { -3, 90 },{ -1, 101 }, | |
| - | |
| - /* 54 - 59 */ | |
| - { 3, 55 },{ -4, 79 },{ -2, 75 },{ -12, 97 }, | |
| - { -7, 50 },{ 1, 60 }, | |
| - | |
| - /* 60 - 69 */ | |
| - { 0, 41 }, { 0, 63 }, { 0, 63 }, { 0, 63 }, | |
| - { -9, 83 }, { 4, 86 }, { 0, 97 }, { -7, 72 }, | |
| - { 13, 41 }, { 3, 62 }, | |
| - | |
| - /* 70 - 104 */ | |
| - { 7, 34 }, { -9, 88 }, { -20, 127 }, { -36, 127 }, | |
| - { -17, 91 }, { -14, 95 }, { -25, 84 }, { -25, 86 }, | |
| - { -12, 89 }, { -17, 91 }, { -31, 127 }, { -14, 76 }, | |
| - { -18, 103 }, { -13, 90 }, { -37, 127 }, { 11, 80 }, | |
| - { 5, 76 }, { 2, 84 }, { 5, 78 }, { -6, 55 }, | |
| - { 4, 61 }, { -14, 83 }, { -37, 127 }, { -5, 79 }, | |
| - { -11, 104 }, { -11, 91 }, { -30, 127 }, { 0, 65 }, | |
| - { -2, 79 }, { 0, 72 }, { -4, 92 }, { -6, 56 }, | |
| - { 3, 68 }, { -8, 71 }, { -13, 98 }, | |
| - | |
| - /* 105 -> 165 */ | |
| - { -4, 86 }, { -12, 88 }, { -5, 82 }, { -3, 72 }, | |
| - { -4, 67 }, { -8, 72 }, { -16, 89 }, { -9, 69 }, | |
| - { -1, 59 }, { 5, 66 }, { 4, 57 }, { -4, 71 }, | |
| - { -2, 71 }, { 2, 58 }, { -1, 74 }, { -4, 44 }, | |
| - { -1, 69 }, { 0, 62 }, { -7, 51 }, { -4, 47 }, | |
| - { -6, 42 }, { -3, 41 }, { -6, 53 }, { 8, 76 }, | |
| - { -9, 78 }, { -11, 83 }, { 9, 52 }, { 0, 67 }, | |
| - { -5, 90 }, { 1, 67 }, { -15, 72 }, { -5, 75 }, | |
| - { -8, 80 }, { -21, 83 }, { -21, 64 }, { -13, 31 }, | |
| - { -25, 64 }, { -29, 94 }, { 9, 75 }, { 17, 63 }, | |
| - { -8, 74 }, { -5, 35 }, { -2, 27 }, { 13, 91 }, | |
| - { 3, 65 }, { -7, 69 }, { 8, 77 }, { -10, 66 }, | |
| - { 3, 62 }, { -3, 68 }, { -20, 81 }, { 0, 30 }, | |
| - { 1, 7 }, { -3, 23 }, { -21, 74 }, { 16, 66 }, | |
| - { -23, 124 }, { 17, 37 }, { 44, -18 }, { 50, -34 }, | |
| - { -22, 127 }, | |
| - | |
| - /* 166 - 226 */ | |
| - { 4, 39 }, { 0, 42 }, { 7, 34 }, { 11, 29 }, | |
| - { 8, 31 }, { 6, 37 }, { 7, 42 }, { 3, 40 }, | |
| - { 8, 33 }, { 13, 43 }, { 13, 36 }, { 4, 47 }, | |
| - { 3, 55 }, { 2, 58 }, { 6, 60 }, { 8, 44 }, | |
| - { 11, 44 }, { 14, 42 }, { 7, 48 }, { 4, 56 }, | |
| - { 4, 52 }, { 13, 37 }, { 9, 49 }, { 19, 58 }, | |
| - { 10, 48 }, { 12, 45 }, { 0, 69 }, { 20, 33 }, | |
| - { 8, 63 }, { 35, -18 }, { 33, -25 }, { 28, -3 }, | |
| - { 24, 10 }, { 27, 0 }, { 34, -14 }, { 52, -44 }, | |
| - { 39, -24 }, { 19, 17 }, { 31, 25 }, { 36, 29 }, | |
| - { 24, 33 }, { 34, 15 }, { 30, 20 }, { 22, 73 }, | |
| - { 20, 34 }, { 19, 31 }, { 27, 44 }, { 19, 16 }, | |
| - { 15, 36 }, { 15, 36 }, { 21, 28 }, { 25, 21 }, | |
| - { 30, 20 }, { 31, 12 }, { 27, 16 }, { 24, 42 }, | |
| - { 0, 93 }, { 14, 56 }, { 15, 57 }, { 26, 38 }, | |
| - { -24, 127 }, | |
| - | |
| - /* 227 - 275 */ | |
| - { -24, 115 }, { -22, 82 }, { -9, 62 }, { 0, 53 }, | |
| - { 0, 59 }, { -14, 85 }, { -13, 89 }, { -13, 94 }, | |
| - { -11, 92 }, { -29, 127 }, { -21, 100 }, { -14, 57 }, | |
| - { -12, 67 }, { -11, 71 }, { -10, 77 }, { -21, 85 }, | |
| - { -16, 88 }, { -23, 104 }, { -15, 98 }, { -37, 127 }, | |
| - { -10, 82 }, { -8, 48 }, { -8, 61 }, { -8, 66 }, | |
| - { -7, 70 }, { -14, 75 }, { -10, 79 }, { -9, 83 }, | |
| - { -12, 92 }, { -18, 108 }, { -4, 79 }, { -22, 69 }, | |
| - { -16, 75 }, { -2, 58 }, { 1, 58 }, { -13, 78 }, | |
| - { -9, 83 }, { -4, 81 }, { -13, 99 }, { -13, 81 }, | |
| - { -6, 38 }, { -13, 62 }, { -6, 58 }, { -2, 59 }, | |
| - { -16, 73 }, { -10, 76 }, { -13, 86 }, { -9, 83 }, | |
| - { -10, 87 }, | |
| - | |
| - /* 276 a bit special (not used, x264_cabac_encode_bypass is used instead) */ | |
| - { 0, 0 }, | |
| - | |
| - /* 277 - 337 */ | |
| - { -22, 127 }, { -25, 127 }, { -25, 120 }, { -27, 127 }, | |
| - { -19, 114 }, { -23, 117 }, { -25, 118 }, { -26, 117 }, | |
| - { -24, 113 }, { -28, 118 }, { -31, 120 }, { -37, 124 }, | |
| - { -10, 94 }, { -15, 102 }, { -10, 99 }, { -13, 106 }, | |
| - { -50, 127 }, { -5, 92 }, { 17, 57 }, { -5, 86 }, | |
| - { -13, 94 }, { -12, 91 }, { -2, 77 }, { 0, 71 }, | |
| - { -1, 73 }, { 4, 64 }, { -7, 81 }, { 5, 64 }, | |
| - { 15, 57 }, { 1, 67 }, { 0, 68 }, { -10, 67 }, | |
| - { 1, 68 }, { 0, 77 }, { 2, 64 }, { 0, 68 }, | |
| - { -5, 78 }, { 7, 55 }, { 5, 59 }, { 2, 65 }, | |
| - { 14, 54 }, { 15, 44 }, { 5, 60 }, { 2, 70 }, | |
| - { -2, 76 }, { -18, 86 }, { 12, 70 }, { 5, 64 }, | |
| - { -12, 70 }, { 11, 55 }, { 5, 56 }, { 0, 69 }, | |
| - { 2, 65 }, { -6, 74 }, { 5, 54 }, { 7, 54 }, | |
| - { -6, 76 }, { -11, 82 }, { -2, 77 }, { -2, 77 }, | |
| - { 25, 42 }, | |
| - | |
| - /* 338 - 398 */ | |
| - { 17, -13 }, { 16, -9 }, { 17, -12 }, { 27, -21 }, | |
| - { 37, -30 }, { 41, -40 }, { 42, -41 }, { 48, -47 }, | |
| - { 39, -32 }, { 46, -40 }, { 52, -51 }, { 46, -41 }, | |
| - { 52, -39 }, { 43, -19 }, { 32, 11 }, { 61, -55 }, | |
| - { 56, -46 }, { 62, -50 }, { 81, -67 }, { 45, -20 }, | |
| - { 35, -2 }, { 28, 15 }, { 34, 1 }, { 39, 1 }, | |
| - { 30, 17 }, { 20, 38 }, { 18, 45 }, { 15, 54 }, | |
| - { 0, 79 }, { 36, -16 }, { 37, -14 }, { 37, -17 }, | |
| - { 32, 1 }, { 34, 15 }, { 29, 15 }, { 24, 25 }, | |
| - { 34, 22 }, { 31, 16 }, { 35, 18 }, { 31, 28 }, | |
| - { 33, 41 }, { 36, 28 }, { 27, 47 }, { 21, 62 }, | |
| - { 18, 31 }, { 19, 26 }, { 36, 24 }, { 24, 23 }, | |
| - { 27, 16 }, { 24, 30 }, { 31, 29 }, { 22, 41 }, | |
| - { 22, 42 }, { 16, 60 }, { 15, 52 }, { 14, 60 }, | |
| - { 3, 78 }, { -16, 123 }, { 21, 53 }, { 22, 56 }, | |
| - { 25, 61 }, | |
| - | |
| - /* 399 -> 435 */ | |
| - { 21, 33 }, { 19, 50 }, { 17, 61 }, | |
| - { -3, 78 }, { -8, 74 }, { -9, 72 }, { -10, 72 }, | |
| - { -18, 75 }, { -12, 71 }, { -11, 63 }, { -5, 70 }, | |
| - { -17, 75 }, { -14, 72 }, { -16, 67 }, { -8, 53 }, | |
| - { -14, 59 }, { -9, 52 }, { -11, 68 }, { 9, -2 }, | |
| - { 30, -10 }, { 31, -4 }, { 33, -1 }, { 33, 7 }, | |
| - { 31, 12 }, { 37, 23 }, { 31, 38 }, { 20, 64 }, | |
| - { -9, 71 }, { -7, 37 }, { -8, 44 }, { -11, 49 }, | |
| - { -10, 56 }, { -12, 59 }, { -8, 63 }, { -9, 67 }, | |
| - { -6, 68 }, { -10, 79 }, | |
| - | |
| - /* 436 -> 459 */ | |
| - { -3, 78 }, { -8, 74 }, { -9, 72 }, { -10, 72 }, | |
| - { -18, 75 }, { -12, 71 }, { -11, 63 }, { -5, 70 }, | |
| - { -17, 75 }, { -14, 72 }, { -16, 67 }, { -8, 53 }, | |
| - { -14, 59 }, { -9, 52 }, { -11, 68 }, { 9, -2 }, | |
| - { 30, -10 }, { 31, -4 }, { 33, -1 }, { 33, 7 }, | |
| - { 31, 12 }, { 37, 23 }, { 31, 38 }, { 20, 64 }, | |
| - | |
| - /* 460 - 1024 */ | |
| - { 11, 80 }, { 5, 76 }, { 2, 84 }, { 5, 78 }, | |
| - { -6, 55 }, { 4, 61 }, { -14, 83 }, { -37, 127 }, | |
| - { -5, 79 }, { -11, 104 }, { -11, 91 }, { -30, 127 }, | |
| - { 11, 80 }, { 5, 76 }, { 2, 84 }, { 5, 78 }, | |
| - { -6, 55 }, { 4, 61 }, { -14, 83 }, { -37, 127 }, | |
| - { -5, 79 }, { -11, 104 }, { -11, 91 }, { -30, 127 }, | |
| - { -4, 86 }, { -12, 88 }, { -5, 82 }, { -3, 72 }, | |
| - { -4, 67 }, { -8, 72 }, { -16, 89 }, { -9, 69 }, | |
| - { -1, 59 }, { 5, 66 }, { 4, 57 }, { -4, 71 }, | |
| - { -2, 71 }, { 2, 58 }, { -1, 74 }, { -4, 44 }, | |
| - { -1, 69 }, { 0, 62 }, { -7, 51 }, { -4, 47 }, | |
| - { -6, 42 }, { -3, 41 }, { -6, 53 }, { 8, 76 }, | |
| - { -9, 78 }, { -11, 83 }, { 9, 52 }, { 0, 67 }, | |
| - { -5, 90 }, { 1, 67 }, { -15, 72 }, { -5, 75 }, | |
| - { -8, 80 }, { -21, 83 }, { -21, 64 }, { -13, 31 }, | |
| - { -25, 64 }, { -29, 94 }, { 9, 75 }, { 17, 63 }, | |
| - { -8, 74 }, { -5, 35 }, { -2, 27 }, { 13, 91 }, | |
| - { -4, 86 }, { -12, 88 }, { -5, 82 }, { -3, 72 }, | |
| - { -4, 67 }, { -8, 72 }, { -16, 89 }, { -9, 69 }, | |
| - { -1, 59 }, { 5, 66 }, { 4, 57 }, { -4, 71 }, | |
| - { -2, 71 }, { 2, 58 }, { -1, 74 }, { -4, 44 }, | |
| - { -1, 69 }, { 0, 62 }, { -7, 51 }, { -4, 47 }, | |
| - { -6, 42 }, { -3, 41 }, { -6, 53 }, { 8, 76 }, | |
| - { -9, 78 }, { -11, 83 }, { 9, 52 }, { 0, 67 }, | |
| - { -5, 90 }, { 1, 67 }, { -15, 72 }, { -5, 75 }, | |
| - { -8, 80 }, { -21, 83 }, { -21, 64 }, { -13, 31 }, | |
| - { -25, 64 }, { -29, 94 }, { 9, 75 }, { 17, 63 }, | |
| - { -8, 74 }, { -5, 35 }, { -2, 27 }, { 13, 91 }, | |
| - { 4, 39 }, { 0, 42 }, { 7, 34 }, { 11, 29 }, | |
| - { 8, 31 }, { 6, 37 }, { 7, 42 }, { 3, 40 }, | |
| - { 8, 33 }, { 13, 43 }, { 13, 36 }, { 4, 47 }, | |
| - { 3, 55 }, { 2, 58 }, { 6, 60 }, { 8, 44 }, | |
| - { 11, 44 }, { 14, 42 }, { 7, 48 }, { 4, 56 }, | |
| - { 4, 52 }, { 13, 37 }, { 9, 49 }, { 19, 58 }, | |
| - { 10, 48 }, { 12, 45 }, { 0, 69 }, { 20, 33 }, | |
| - { 8, 63 }, { 35, -18 }, { 33, -25 }, { 28, -3 }, | |
| - { 24, 10 }, { 27, 0 }, { 34, -14 }, { 52, -44 }, | |
| - { 39, -24 }, { 19, 17 }, { 31, 25 }, { 36, 29 }, | |
| - { 24, 33 }, { 34, 15 }, { 30, 20 }, { 22, 73 }, | |
| - { 4, 39 }, { 0, 42 }, { 7, 34 }, { 11, 29 }, | |
| - { 8, 31 }, { 6, 37 }, { 7, 42 }, { 3, 40 }, | |
| - { 8, 33 }, { 13, 43 }, { 13, 36 }, { 4, 47 }, | |
| - { 3, 55 }, { 2, 58 }, { 6, 60 }, { 8, 44 }, | |
| - { 11, 44 }, { 14, 42 }, { 7, 48 }, { 4, 56 }, | |
| - { 4, 52 }, { 13, 37 }, { 9, 49 }, { 19, 58 }, | |
| - { 10, 48 }, { 12, 45 }, { 0, 69 }, { 20, 33 }, | |
| - { 8, 63 }, { 35, -18 }, { 33, -25 }, { 28, -3 }, | |
| - { 24, 10 }, { 27, 0 }, { 34, -14 }, { 52, -44 }, | |
| - { 39, -24 }, { 19, 17 }, { 31, 25 }, { 36, 29 }, | |
| - { 24, 33 }, { 34, 15 }, { 30, 20 }, { 22, 73 }, | |
| - { -3, 78 }, { -8, 74 }, { -9, 72 }, { -10, 72 }, | |
| - { -18, 75 }, { -12, 71 }, { -11, 63 }, { -5, 70 }, | |
| - { -17, 75 }, { -14, 72 }, { -16, 67 }, { -8, 53 }, | |
| - { -14, 59 }, { -9, 52 }, { -11, 68 }, { -3, 78 }, | |
| - { -8, 74 }, { -9, 72 }, { -10, 72 }, { -18, 75 }, | |
| - { -12, 71 }, { -11, 63 }, { -5, 70 }, { -17, 75 }, | |
| - { -14, 72 }, { -16, 67 }, { -8, 53 }, { -14, 59 }, | |
| - { -9, 52 }, { -11, 68 }, { 9, -2 }, { 30, -10 }, | |
| - { 31, -4 }, { 33, -1 }, { 33, 7 }, { 31, 12 }, | |
| - { 37, 23 }, { 31, 38 }, { 20, 64 }, { 9, -2 }, | |
| - { 30, -10 }, { 31, -4 }, { 33, -1 }, { 33, 7 }, | |
| - { 31, 12 }, { 37, 23 }, { 31, 38 }, { 20, 64 }, | |
| - { -9, 71 }, { -7, 37 }, { -8, 44 }, { -11, 49 }, | |
| - { -10, 56 }, { -12, 59 }, { -8, 63 }, { -9, 67 }, | |
| - { -6, 68 }, { -10, 79 }, { -3, 78 }, { -8, 74 }, | |
| - { -9, 72 }, { -10, 72 }, { -18, 75 }, { -12, 71 }, | |
| - { -11, 63 }, { -5, 70 }, { -17, 75 }, { -14, 72 }, | |
| - { -16, 67 }, { -8, 53 }, { -14, 59 }, { -9, 52 }, | |
| - { -11, 68 }, { -3, 78 }, { -8, 74 }, { -9, 72 }, | |
| - { -10, 72 }, { -18, 75 }, { -12, 71 }, { -11, 63 }, | |
| - { -5, 70 }, { -17, 75 }, { -14, 72 }, { -16, 67 }, | |
| - { -8, 53 }, { -14, 59 }, { -9, 52 }, { -11, 68 }, | |
| - { 9, -2 }, { 30, -10 }, { 31, -4 }, { 33, -1 }, | |
| - { 33, 7 }, { 31, 12 }, { 37, 23 }, { 31, 38 }, | |
| - { 20, 64 }, { 9, -2 }, { 30, -10 }, { 31, -4 }, | |
| - { 33, -1 }, { 33, 7 }, { 31, 12 }, { 37, 23 }, | |
| - { 31, 38 }, { 20, 64 }, { -9, 71 }, { -7, 37 }, | |
| - { -8, 44 }, { -11, 49 }, { -10, 56 }, { -12, 59 }, | |
| - { -8, 63 }, { -9, 67 }, { -6, 68 }, { -10, 79 }, | |
| - { -22, 127 }, { -25, 127 }, { -25, 120 }, { -27, 127 }, | |
| - { -19, 114 }, { -23, 117 }, { -25, 118 }, { -26, 117 }, | |
| - { -24, 113 }, { -28, 118 }, { -31, 120 }, { -37, 124 }, | |
| - { -10, 94 }, { -15, 102 }, { -10, 99 }, { -13, 106 }, | |
| - { -50, 127 }, { -5, 92 }, { 17, 57 }, { -5, 86 }, | |
| - { -13, 94 }, { -12, 91 }, { -2, 77 }, { 0, 71 }, | |
| - { -1, 73 }, { 4, 64 }, { -7, 81 }, { 5, 64 }, | |
| - { 15, 57 }, { 1, 67 }, { 0, 68 }, { -10, 67 }, | |
| - { 1, 68 }, { 0, 77 }, { 2, 64 }, { 0, 68 }, | |
| - { -5, 78 }, { 7, 55 }, { 5, 59 }, { 2, 65 }, | |
| - { 14, 54 }, { 15, 44 }, { 5, 60 }, { 2, 70 }, | |
| - { -22, 127 }, { -25, 127 }, { -25, 120 }, { -27, 127 }, | |
| - { -19, 114 }, { -23, 117 }, { -25, 118 }, { -26, 117 }, | |
| - { -24, 113 }, { -28, 118 }, { -31, 120 }, { -37, 124 }, | |
| - { -10, 94 }, { -15, 102 }, { -10, 99 }, { -13, 106 }, | |
| - { -50, 127 }, { -5, 92 }, { 17, 57 }, { -5, 86 }, | |
| - { -13, 94 }, { -12, 91 }, { -2, 77 }, { 0, 71 }, | |
| - { -1, 73 }, { 4, 64 }, { -7, 81 }, { 5, 64 }, | |
| - { 15, 57 }, { 1, 67 }, { 0, 68 }, { -10, 67 }, | |
| - { 1, 68 }, { 0, 77 }, { 2, 64 }, { 0, 68 }, | |
| - { -5, 78 }, { 7, 55 }, { 5, 59 }, { 2, 65 }, | |
| - { 14, 54 }, { 15, 44 }, { 5, 60 }, { 2, 70 }, | |
| - { 17, -13 }, { 16, -9 }, { 17, -12 }, { 27, -21 }, | |
| - { 37, -30 }, { 41, -40 }, { 42, -41 }, { 48, -47 }, | |
| - { 39, -32 }, { 46, -40 }, { 52, -51 }, { 46, -41 }, | |
| - { 52, -39 }, { 43, -19 }, { 32, 11 }, { 61, -55 }, | |
| - { 56, -46 }, { 62, -50 }, { 81, -67 }, { 45, -20 }, | |
| - { 35, -2 }, { 28, 15 }, { 34, 1 }, { 39, 1 }, | |
| - { 30, 17 }, { 20, 38 }, { 18, 45 }, { 15, 54 }, | |
| - { 0, 79 }, { 36, -16 }, { 37, -14 }, { 37, -17 }, | |
| - { 32, 1 }, { 34, 15 }, { 29, 15 }, { 24, 25 }, | |
| - { 34, 22 }, { 31, 16 }, { 35, 18 }, { 31, 28 }, | |
| - { 33, 41 }, { 36, 28 }, { 27, 47 }, { 21, 62 }, | |
| - { 17, -13 }, { 16, -9 }, { 17, -12 }, { 27, -21 }, | |
| - { 37, -30 }, { 41, -40 }, { 42, -41 }, { 48, -47 }, | |
| - { 39, -32 }, { 46, -40 }, { 52, -51 }, { 46, -41 }, | |
| - { 52, -39 }, { 43, -19 }, { 32, 11 }, { 61, -55 }, | |
| - { 56, -46 }, { 62, -50 }, { 81, -67 }, { 45, -20 }, | |
| - { 35, -2 }, { 28, 15 }, { 34, 1 }, { 39, 1 }, | |
| - { 30, 17 }, { 20, 38 }, { 18, 45 }, { 15, 54 }, | |
| - { 0, 79 }, { 36, -16 }, { 37, -14 }, { 37, -17 }, | |
| - { 32, 1 }, { 34, 15 }, { 29, 15 }, { 24, 25 }, | |
| - { 34, 22 }, { 31, 16 }, { 35, 18 }, { 31, 28 }, | |
| - { 33, 41 }, { 36, 28 }, { 27, 47 }, { 21, 62 }, | |
| - { -24, 115 }, { -22, 82 }, { -9, 62 }, { 0, 53 }, | |
| - { 0, 59 }, { -14, 85 }, { -13, 89 }, { -13, 94 }, | |
| - { -11, 92 }, { -29, 127 }, { -21, 100 }, { -14, 57 }, | |
| - { -12, 67 }, { -11, 71 }, { -10, 77 }, { -21, 85 }, | |
| - { -16, 88 }, { -23, 104 }, { -15, 98 }, { -37, 127 }, | |
| - { -10, 82 }, { -8, 48 }, { -8, 61 }, { -8, 66 }, | |
| - { -7, 70 }, { -14, 75 }, { -10, 79 }, { -9, 83 }, | |
| - { -12, 92 }, { -18, 108 }, { -24, 115 }, { -22, 82 }, | |
| - { -9, 62 }, { 0, 53 }, { 0, 59 }, { -14, 85 }, | |
| - { -13, 89 }, { -13, 94 }, { -11, 92 }, { -29, 127 }, | |
| - { -21, 100 }, { -14, 57 }, { -12, 67 }, { -11, 71 }, | |
| - { -10, 77 }, { -21, 85 }, { -16, 88 }, { -23, 104 }, | |
| - { -15, 98 }, { -37, 127 }, { -10, 82 }, { -8, 48 }, | |
| - { -8, 61 }, { -8, 66 }, { -7, 70 }, { -14, 75 }, | |
| - { -10, 79 }, { -9, 83 }, { -12, 92 }, { -18, 108 }, | |
| - { -5, 79 }, { -11, 104 }, { -11, 91 }, { -30, 127 }, | |
| - { -5, 79 }, { -11, 104 }, { -11, 91 }, { -30, 127 }, | |
| - { -5, 79 }, { -11, 104 }, { -11, 91 }, { -30, 127 } | |
| - } | |
| -}; | |
| - | |
| -const uint8_t x264_cabac_range_lps[64][4] = | |
| -{ | |
| - { 2, 2, 2, 2}, { 6, 7, 8, 9}, { 6, 7, 9, 10}, { 6, 8, 9, 11}, | |
| - { 7, 8, 10, 11}, { 7, 9, 10, 12}, { 7, 9, 11, 12}, { 8, 9, 11, 13}, | |
| - { 8, 10, 12, 14}, { 9, 11, 12, 14}, { 9, 11, 13, 15}, { 10, 12, 14, 16}, | |
| - { 10, 12, 15, 17}, { 11, 13, 15, 18}, { 11, 14, 16, 19}, { 12, 14, 17, 20}, | |
| - { 12, 15, 18, 21}, { 13, 16, 19, 22}, { 14, 17, 20, 23}, { 14, 18, 21, 24}, | |
| - { 15, 19, 22, 25}, { 16, 20, 23, 27}, { 17, 21, 25, 28}, { 18, 22, 26, 30}, | |
| - { 19, 23, 27, 31}, { 20, 24, 29, 33}, { 21, 26, 30, 35}, { 22, 27, 32, 37}, | |
| - { 23, 28, 33, 39}, { 24, 30, 35, 41}, { 26, 31, 37, 43}, { 27, 33, 39, 45}, | |
| - { 29, 35, 41, 48}, { 30, 37, 43, 50}, { 32, 39, 46, 53}, { 33, 41, 48, 56}, | |
| - { 35, 43, 51, 59}, { 37, 45, 54, 62}, { 39, 48, 56, 65}, { 41, 50, 59, 69}, | |
| - { 43, 53, 63, 72}, { 46, 56, 66, 76}, { 48, 59, 69, 80}, { 51, 62, 73, 85}, | |
| - { 53, 65, 77, 89}, { 56, 69, 81, 94}, { 59, 72, 86, 99}, { 62, 76, 90, 104}, | |
| - { 66, 80, 95, 110}, { 69, 85, 100, 116}, { 73, 89, 105, 122}, { 77, 94, 111, 128}, | |
| - { 81, 99, 117, 135}, { 85, 104, 123, 142}, { 90, 110, 130, 150}, { 95, 116, 137, 158}, | |
| - {100, 122, 144, 166}, {105, 128, 152, 175}, {111, 135, 160, 185}, {116, 142, 169, 195}, | |
| - {123, 150, 178, 205}, {128, 158, 187, 216}, {128, 167, 197, 227}, {128, 176, 208, 240} | |
| -}; | |
| - | |
| -const uint8_t x264_cabac_transition[128][2] = | |
| -{ | |
| - { 0, 0}, { 1, 1}, { 2, 50}, { 51, 3}, { 2, 50}, { 51, 3}, { 4, 52}, { 53, 5}, | |
| - { 6, 52}, { 53, 7}, { 8, 52}, { 53, 9}, { 10, 54}, { 55, 11}, { 12, 54}, { 55, 13}, | |
| - { 14, 54}, { 55, 15}, { 16, 56}, { 57, 17}, { 18, 56}, { 57, 19}, { 20, 56}, { 57, 21}, | |
| - { 22, 58}, { 59, 23}, { 24, 58}, { 59, 25}, { 26, 60}, { 61, 27}, { 28, 60}, { 61, 29}, | |
| - { 30, 60}, { 61, 31}, { 32, 62}, { 63, 33}, { 34, 62}, { 63, 35}, { 36, 64}, { 65, 37}, | |
| - { 38, 66}, { 67, 39}, { 40, 66}, { 67, 41}, { 42, 66}, { 67, 43}, { 44, 68}, { 69, 45}, | |
| - { 46, 68}, { 69, 47}, { 48, 70}, { 71, 49}, { 50, 72}, { 73, 51}, { 52, 72}, { 73, 53}, | |
| - { 54, 74}, { 75, 55}, { 56, 74}, { 75, 57}, { 58, 76}, { 77, 59}, { 60, 78}, { 79, 61}, | |
| - { 62, 78}, { 79, 63}, { 64, 80}, { 81, 65}, { 66, 82}, { 83, 67}, { 68, 82}, { 83, 69}, | |
| - { 70, 84}, { 85, 71}, { 72, 84}, { 85, 73}, { 74, 88}, { 89, 75}, { 76, 88}, { 89, 77}, | |
| - { 78, 90}, { 91, 79}, { 80, 90}, { 91, 81}, { 82, 94}, { 95, 83}, { 84, 94}, { 95, 85}, | |
| - { 86, 96}, { 97, 87}, { 88, 96}, { 97, 89}, { 90, 100}, {101, 91}, { 92, 100}, {101, 93}, | |
| - { 94, 102}, {103, 95}, { 96, 104}, {105, 97}, { 98, 104}, {105, 99}, {100, 108}, {109, 101}, | |
| - {102, 108}, {109, 103}, {104, 110}, {111, 105}, {106, 112}, {113, 107}, {108, 114}, {115, 109}, | |
| - {110, 116}, {117, 111}, {112, 118}, {119, 113}, {114, 118}, {119, 115}, {116, 122}, {123, 117}, | |
| - {118, 122}, {123, 119}, {120, 124}, {125, 121}, {122, 126}, {127, 123}, {124, 127}, {126, 125} | |
| -}; | |
| - | |
| -const uint8_t x264_cabac_renorm_shift[64] = | |
| -{ | |
| - 6,5,4,4,3,3,3,3,2,2,2,2,2,2,2,2, | |
| - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, | |
| - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | |
| - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | |
| -}; | |
| - | |
| -/* -ln2(probability) */ | |
| -const uint16_t x264_cabac_entropy[128] = | |
| -{ | |
| - FIX8(0.0273), FIX8(5.7370), FIX8(0.0288), FIX8(5.6618), | |
| - FIX8(0.0303), FIX8(5.5866), FIX8(0.0320), FIX8(5.5114), | |
| - FIX8(0.0337), FIX8(5.4362), FIX8(0.0355), FIX8(5.3610), | |
| - FIX8(0.0375), FIX8(5.2859), FIX8(0.0395), FIX8(5.2106), | |
| - FIX8(0.0416), FIX8(5.1354), FIX8(0.0439), FIX8(5.0602), | |
| - FIX8(0.0463), FIX8(4.9851), FIX8(0.0488), FIX8(4.9099), | |
| - FIX8(0.0515), FIX8(4.8347), FIX8(0.0543), FIX8(4.7595), | |
| - FIX8(0.0572), FIX8(4.6843), FIX8(0.0604), FIX8(4.6091), | |
| - FIX8(0.0637), FIX8(4.5339), FIX8(0.0671), FIX8(4.4588), | |
| - FIX8(0.0708), FIX8(4.3836), FIX8(0.0747), FIX8(4.3083), | |
| - FIX8(0.0788), FIX8(4.2332), FIX8(0.0832), FIX8(4.1580), | |
| - FIX8(0.0878), FIX8(4.0828), FIX8(0.0926), FIX8(4.0076), | |
| - FIX8(0.0977), FIX8(3.9324), FIX8(0.1032), FIX8(3.8572), | |
| - FIX8(0.1089), FIX8(3.7820), FIX8(0.1149), FIX8(3.7068), | |
| - FIX8(0.1214), FIX8(3.6316), FIX8(0.1282), FIX8(3.5565), | |
| - FIX8(0.1353), FIX8(3.4813), FIX8(0.1429), FIX8(3.4061), | |
| - FIX8(0.1510), FIX8(3.3309), FIX8(0.1596), FIX8(3.2557), | |
| - FIX8(0.1686), FIX8(3.1805), FIX8(0.1782), FIX8(3.1053), | |
| - FIX8(0.1884), FIX8(3.0301), FIX8(0.1992), FIX8(2.9549), | |
| - FIX8(0.2107), FIX8(2.8797), FIX8(0.2229), FIX8(2.8046), | |
| - FIX8(0.2358), FIX8(2.7294), FIX8(0.2496), FIX8(2.6542), | |
| - FIX8(0.2642), FIX8(2.5790), FIX8(0.2798), FIX8(2.5038), | |
| - FIX8(0.2964), FIX8(2.4286), FIX8(0.3142), FIX8(2.3534), | |
| - FIX8(0.3331), FIX8(2.2782), FIX8(0.3532), FIX8(2.2030), | |
| - FIX8(0.3748), FIX8(2.1278), FIX8(0.3979), FIX8(2.0527), | |
| - FIX8(0.4226), FIX8(1.9775), FIX8(0.4491), FIX8(1.9023), | |
| - FIX8(0.4776), FIX8(1.8271), FIX8(0.5082), FIX8(1.7519), | |
| - FIX8(0.5412), FIX8(1.6767), FIX8(0.5768), FIX8(1.6015), | |
| - FIX8(0.6152), FIX8(1.5263), FIX8(0.6568), FIX8(1.4511), | |
| - FIX8(0.7020), FIX8(1.3759), FIX8(0.7513), FIX8(1.3008), | |
| - FIX8(0.8050), FIX8(1.2256), FIX8(0.8638), FIX8(1.1504), | |
| - FIX8(0.9285), FIX8(1.0752), FIX8(1.0000), FIX8(1.0000) | |
| -}; | |
| - | |
| -uint8_t x264_cabac_contexts[4][QP_MAX_SPEC+1][1024]; | |
| +static uint8_t cabac_contexts[4][QP_MAX_SPEC+1][1024]; | |
| void x264_cabac_init( x264_t *h ) | |
| { | |
| @@ -1338,17 +40,14 @@ | |
| for( int j = 0; j < ctx_count; j++ ) | |
| { | |
| int state = x264_clip3( (((*cabac_context_init)[j][0] * qp) >> 4) + (*cabac_context_init)[j][1], 1, 126 ); | |
| - x264_cabac_contexts[i][qp][j] = (X264_MIN( state, 127-state ) << 1) | (state >> 6); | |
| + cabac_contexts[i][qp][j] = (X264_MIN( state, 127-state ) << 1) | (state >> 6); | |
| } | |
| } | |
| } | |
| -/***************************************************************************** | |
| - * | |
| - *****************************************************************************/ | |
| void x264_cabac_context_init( x264_t *h, x264_cabac_t *cb, int i_slice_type, int i_qp, int i_model ) | |
| { | |
| - memcpy( cb->state, x264_cabac_contexts[i_slice_type == SLICE_TYPE_I ? 0 : i_model + 1][i_qp], CHROMA444 ? 1024 : 460 ); | |
| + memcpy( cb->state, cabac_contexts[i_slice_type == SLICE_TYPE_I ? 0 : i_model + 1][i_qp], CHROMA444 ? 1024 : 460 ); | |
| } | |
| void x264_cabac_encode_init_core( x264_cabac_t *cb ) | |
| @@ -1367,7 +66,7 @@ | |
| cb->p_end = p_end; | |
| } | |
| -static inline void x264_cabac_putbyte( x264_cabac_t *cb ) | |
| +static inline void cabac_putbyte( x264_cabac_t *cb ) | |
| { | |
| if( cb->i_queue >= 0 ) | |
| { | |
| @@ -1399,13 +98,13 @@ | |
| } | |
| } | |
| -static inline void x264_cabac_encode_renorm( x264_cabac_t *cb ) | |
| +static inline void cabac_encode_renorm( x264_cabac_t *cb ) | |
| { | |
| int shift = x264_cabac_renorm_shift[cb->i_range>>3]; | |
| cb->i_range <<= shift; | |
| cb->i_low <<= shift; | |
| cb->i_queue += shift; | |
| - x264_cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| } | |
| /* Making custom versions of this function, even in asm, for the cases where | |
| @@ -1422,7 +121,7 @@ | |
| cb->i_range = i_range_lps; | |
| } | |
| cb->state[i_ctx] = x264_cabac_transition[i_state][b]; | |
| - x264_cabac_encode_renorm( cb ); | |
| + cabac_encode_renorm( cb ); | |
| } | |
| /* Note: b is negated for this function */ | |
| @@ -1431,7 +130,7 @@ | |
| cb->i_low <<= 1; | |
| cb->i_low += b & cb->i_range; | |
| cb->i_queue += 1; | |
| - x264_cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| } | |
| static const int bypass_lut[16] = | |
| @@ -1452,7 +151,7 @@ | |
| cb->i_low <<= i; | |
| cb->i_low += ((x>>k)&0xff) * cb->i_range; | |
| cb->i_queue += i; | |
| - x264_cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| i = 8; | |
| } while( k > 0 ); | |
| } | |
| @@ -1460,7 +159,7 @@ | |
| void x264_cabac_encode_terminal_c( x264_cabac_t *cb ) | |
| { | |
| cb->i_range -= 2; | |
| - x264_cabac_encode_renorm( cb ); | |
| + cabac_encode_renorm( cb ); | |
| } | |
| void x264_cabac_encode_flush( x264_t *h, x264_cabac_t *cb ) | |
| @@ -1469,12 +168,12 @@ | |
| cb->i_low |= 1; | |
| cb->i_low <<= 9; | |
| cb->i_queue += 9; | |
| - x264_cabac_putbyte( cb ); | |
| - x264_cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| cb->i_low <<= -cb->i_queue; | |
| cb->i_low |= (0x35a4e4f5 >> (h->i_frame & 31) & 1) << 10; | |
| cb->i_queue = 0; | |
| - x264_cabac_putbyte( cb ); | |
| + cabac_putbyte( cb ); | |
| while( cb->i_bytes_outstanding > 0 ) | |
| { | |
| diff -ur x264-go/x264c/external/x264/common/cabac.h x264-go.new/x264c/external/x264/common/cabac.h | |
| --- x264-go/x264c/external/x264/common/cabac.h 2020-06-05 14:39:42.416697080 +0200 | |
| +++ x264-go.new/x264c/external/x264/common/cabac.h 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cabac.h: arithmetic coder | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -51,36 +51,44 @@ | |
| uint8_t padding[12]; | |
| } x264_cabac_t; | |
| -extern const uint8_t x264_cabac_transition[128][2]; | |
| -extern const uint16_t x264_cabac_entropy[128]; | |
| - | |
| /* init the contexts given i_slice_type, the quantif and the model */ | |
| +#define x264_cabac_context_init x264_template(cabac_context_init) | |
| void x264_cabac_context_init( x264_t *h, x264_cabac_t *cb, int i_slice_type, int i_qp, int i_model ); | |
| +#define x264_cabac_encode_init_core x264_template(cabac_encode_init_core) | |
| void x264_cabac_encode_init_core( x264_cabac_t *cb ); | |
| +#define x264_cabac_encode_init x264_template(cabac_encode_init) | |
| void x264_cabac_encode_init( x264_cabac_t *cb, uint8_t *p_data, uint8_t *p_end ); | |
| +#define x264_cabac_encode_decision_c x264_template(cabac_encode_decision_c) | |
| void x264_cabac_encode_decision_c( x264_cabac_t *cb, int i_ctx, int b ); | |
| +#define x264_cabac_encode_decision_asm x264_template(cabac_encode_decision_asm) | |
| void x264_cabac_encode_decision_asm( x264_cabac_t *cb, int i_ctx, int b ); | |
| +#define x264_cabac_encode_bypass_c x264_template(cabac_encode_bypass_c) | |
| void x264_cabac_encode_bypass_c( x264_cabac_t *cb, int b ); | |
| +#define x264_cabac_encode_bypass_asm x264_template(cabac_encode_bypass_asm) | |
| void x264_cabac_encode_bypass_asm( x264_cabac_t *cb, int b ); | |
| +#define x264_cabac_encode_terminal_c x264_template(cabac_encode_terminal_c) | |
| void x264_cabac_encode_terminal_c( x264_cabac_t *cb ); | |
| +#define x264_cabac_encode_terminal_asm x264_template(cabac_encode_terminal_asm) | |
| void x264_cabac_encode_terminal_asm( x264_cabac_t *cb ); | |
| +#define x264_cabac_encode_ue_bypass x264_template(cabac_encode_ue_bypass) | |
| void x264_cabac_encode_ue_bypass( x264_cabac_t *cb, int exp_bits, int val ); | |
| +#define x264_cabac_encode_flush x264_template(cabac_encode_flush) | |
| void x264_cabac_encode_flush( x264_t *h, x264_cabac_t *cb ); | |
| -//#if HAVE_MMX | |
| -//#define x264_cabac_encode_decision x264_cabac_encode_decision_asm | |
| -//#define x264_cabac_encode_bypass x264_cabac_encode_bypass_asm | |
| -//#define x264_cabac_encode_terminal x264_cabac_encode_terminal_asm | |
| -//#elif defined(ARCH_AARCH64) | |
| -//#define x264_cabac_encode_decision x264_cabac_encode_decision_asm | |
| -//#define x264_cabac_encode_bypass x264_cabac_encode_bypass_asm | |
| -//#define x264_cabac_encode_terminal x264_cabac_encode_terminal_asm | |
| -//#else | |
| +#if HAVE_MMX | |
| +#define x264_cabac_encode_decision x264_cabac_encode_decision_asm | |
| +#define x264_cabac_encode_bypass x264_cabac_encode_bypass_asm | |
| +#define x264_cabac_encode_terminal x264_cabac_encode_terminal_asm | |
| +#elif HAVE_AARCH64 | |
| +#define x264_cabac_encode_decision x264_cabac_encode_decision_asm | |
| +#define x264_cabac_encode_bypass x264_cabac_encode_bypass_asm | |
| +#define x264_cabac_encode_terminal x264_cabac_encode_terminal_asm | |
| +#else | |
| #define x264_cabac_encode_decision x264_cabac_encode_decision_c | |
| #define x264_cabac_encode_bypass x264_cabac_encode_bypass_c | |
| #define x264_cabac_encode_terminal x264_cabac_encode_terminal_c | |
| -//#endif | |
| +#endif | |
| #define x264_cabac_encode_decision_noup x264_cabac_encode_decision | |
| static ALWAYS_INLINE int x264_cabac_pos( x264_cabac_t *cb ) | |
| diff -ur x264-go/x264c/external/x264/common/common.c x264-go.new/x264c/external/x264/common/common.c | |
| --- x264-go/x264c/external/x264/common/common.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/common.c 2020-06-06 15:20:58.686039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * common.c: misc common functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -26,1049 +26,6 @@ | |
| #include "common.h" | |
| -#include <ctype.h> | |
| - | |
| -#if HAVE_MALLOC_H | |
| -#include <malloc.h> | |
| -#endif | |
| -#if HAVE_THP | |
| -#include <sys/mman.h> | |
| -#endif | |
| - | |
| -const int x264_bit_depth = BIT_DEPTH; | |
| - | |
| -const int x264_chroma_format = X264_CHROMA_FORMAT; | |
| - | |
| -static void x264_log_default( void *, int, const char *, va_list ); | |
| - | |
| -/**************************************************************************** | |
| - * x264_param_default: | |
| - ****************************************************************************/ | |
| -void x264_param_default( x264_param_t *param ) | |
| -{ | |
| - /* */ | |
| - memset( param, 0, sizeof( x264_param_t ) ); | |
| - | |
| - /* CPU autodetect */ | |
| - param->cpu = x264_cpu_detect(); | |
| - param->i_threads = X264_THREADS_AUTO; | |
| - param->i_lookahead_threads = X264_THREADS_AUTO; | |
| - param->b_deterministic = 1; | |
| - param->i_sync_lookahead = X264_SYNC_LOOKAHEAD_AUTO; | |
| - | |
| - /* Video properties */ | |
| - param->i_csp = X264_CHROMA_FORMAT ? X264_CHROMA_FORMAT : X264_CSP_I420; | |
| - param->i_width = 0; | |
| - param->i_height = 0; | |
| - param->vui.i_sar_width = 0; | |
| - param->vui.i_sar_height= 0; | |
| - param->vui.i_overscan = 0; /* undef */ | |
| - param->vui.i_vidformat = 5; /* undef */ | |
| - param->vui.b_fullrange = -1; /* default depends on input */ | |
| - param->vui.i_colorprim = 2; /* undef */ | |
| - param->vui.i_transfer = 2; /* undef */ | |
| - param->vui.i_colmatrix = -1; /* default depends on input */ | |
| - param->vui.i_chroma_loc= 0; /* left center */ | |
| - param->i_fps_num = 25; | |
| - param->i_fps_den = 1; | |
| - param->i_level_idc = -1; | |
| - param->i_slice_max_size = 0; | |
| - param->i_slice_max_mbs = 0; | |
| - param->i_slice_count = 0; | |
| - | |
| - /* Encoder parameters */ | |
| - param->i_frame_reference = 3; | |
| - param->i_keyint_max = 250; | |
| - param->i_keyint_min = X264_KEYINT_MIN_AUTO; | |
| - param->i_bframe = 3; | |
| - param->i_scenecut_threshold = 40; | |
| - param->i_bframe_adaptive = X264_B_ADAPT_FAST; | |
| - param->i_bframe_bias = 0; | |
| - param->i_bframe_pyramid = X264_B_PYRAMID_NORMAL; | |
| - param->b_interlaced = 0; | |
| - param->b_constrained_intra = 0; | |
| - | |
| - param->b_deblocking_filter = 1; | |
| - param->i_deblocking_filter_alphac0 = 0; | |
| - param->i_deblocking_filter_beta = 0; | |
| - | |
| - param->b_cabac = 1; | |
| - param->i_cabac_init_idc = 0; | |
| - | |
| - param->rc.i_rc_method = X264_RC_CRF; | |
| - param->rc.i_bitrate = 0; | |
| - param->rc.f_rate_tolerance = 1.0; | |
| - param->rc.i_vbv_max_bitrate = 0; | |
| - param->rc.i_vbv_buffer_size = 0; | |
| - param->rc.f_vbv_buffer_init = 0.9; | |
| - param->rc.i_qp_constant = 23 + QP_BD_OFFSET; | |
| - param->rc.f_rf_constant = 23; | |
| - param->rc.i_qp_min = 0; | |
| - param->rc.i_qp_max = QP_MAX; | |
| - param->rc.i_qp_step = 4; | |
| - param->rc.f_ip_factor = 1.4; | |
| - param->rc.f_pb_factor = 1.3; | |
| - param->rc.i_aq_mode = X264_AQ_VARIANCE; | |
| - param->rc.f_aq_strength = 1.0; | |
| - param->rc.i_lookahead = 40; | |
| - | |
| - param->rc.b_stat_write = 0; | |
| - param->rc.psz_stat_out = "x264_2pass.log"; | |
| - param->rc.b_stat_read = 0; | |
| - param->rc.psz_stat_in = "x264_2pass.log"; | |
| - param->rc.f_qcompress = 0.6; | |
| - param->rc.f_qblur = 0.5; | |
| - param->rc.f_complexity_blur = 20; | |
| - param->rc.i_zones = 0; | |
| - param->rc.b_mb_tree = 1; | |
| - | |
| - /* Log */ | |
| - param->pf_log = x264_log_default; | |
| - param->p_log_private = NULL; | |
| - param->i_log_level = X264_LOG_INFO; | |
| - | |
| - /* */ | |
| - param->analyse.intra = X264_ANALYSE_I4x4 | X264_ANALYSE_I8x8; | |
| - param->analyse.inter = X264_ANALYSE_I4x4 | X264_ANALYSE_I8x8 | |
| - | X264_ANALYSE_PSUB16x16 | X264_ANALYSE_BSUB16x16; | |
| - param->analyse.i_direct_mv_pred = X264_DIRECT_PRED_SPATIAL; | |
| - param->analyse.i_me_method = X264_ME_HEX; | |
| - param->analyse.f_psy_rd = 1.0; | |
| - param->analyse.b_psy = 1; | |
| - param->analyse.f_psy_trellis = 0; | |
| - param->analyse.i_me_range = 16; | |
| - param->analyse.i_subpel_refine = 7; | |
| - param->analyse.b_mixed_references = 1; | |
| - param->analyse.b_chroma_me = 1; | |
| - param->analyse.i_mv_range_thread = -1; | |
| - param->analyse.i_mv_range = -1; // set from level_idc | |
| - param->analyse.i_chroma_qp_offset = 0; | |
| - param->analyse.b_fast_pskip = 1; | |
| - param->analyse.b_weighted_bipred = 1; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_SMART; | |
| - param->analyse.b_dct_decimate = 1; | |
| - param->analyse.b_transform_8x8 = 1; | |
| - param->analyse.i_trellis = 1; | |
| - param->analyse.i_luma_deadzone[0] = 21; | |
| - param->analyse.i_luma_deadzone[1] = 11; | |
| - param->analyse.b_psnr = 0; | |
| - param->analyse.b_ssim = 0; | |
| - | |
| - param->i_cqm_preset = X264_CQM_FLAT; | |
| - memset( param->cqm_4iy, 16, sizeof( param->cqm_4iy ) ); | |
| - memset( param->cqm_4py, 16, sizeof( param->cqm_4py ) ); | |
| - memset( param->cqm_4ic, 16, sizeof( param->cqm_4ic ) ); | |
| - memset( param->cqm_4pc, 16, sizeof( param->cqm_4pc ) ); | |
| - memset( param->cqm_8iy, 16, sizeof( param->cqm_8iy ) ); | |
| - memset( param->cqm_8py, 16, sizeof( param->cqm_8py ) ); | |
| - memset( param->cqm_8ic, 16, sizeof( param->cqm_8ic ) ); | |
| - memset( param->cqm_8pc, 16, sizeof( param->cqm_8pc ) ); | |
| - | |
| - param->b_repeat_headers = 1; | |
| - param->b_annexb = 1; | |
| - param->b_aud = 0; | |
| - param->b_vfr_input = 1; | |
| - param->i_nal_hrd = X264_NAL_HRD_NONE; | |
| - param->b_tff = 1; | |
| - param->b_pic_struct = 0; | |
| - param->b_fake_interlaced = 0; | |
| - param->i_frame_packing = -1; | |
| - param->b_opencl = 0; | |
| - param->i_opencl_device = 0; | |
| - param->opencl_device_id = NULL; | |
| - param->psz_clbin_file = NULL; | |
| -} | |
| - | |
| -static int x264_param_apply_preset( x264_param_t *param, const char *preset ) | |
| -{ | |
| - char *end; | |
| - int i = strtol( preset, &end, 10 ); | |
| - if( *end == 0 && i >= 0 && i < sizeof(x264_preset_names)/sizeof(*x264_preset_names)-1 ) | |
| - preset = x264_preset_names[i]; | |
| - | |
| - if( !strcasecmp( preset, "ultrafast" ) ) | |
| - { | |
| - param->i_frame_reference = 1; | |
| - param->i_scenecut_threshold = 0; | |
| - param->b_deblocking_filter = 0; | |
| - param->b_cabac = 0; | |
| - param->i_bframe = 0; | |
| - param->analyse.intra = 0; | |
| - param->analyse.inter = 0; | |
| - param->analyse.b_transform_8x8 = 0; | |
| - param->analyse.i_me_method = X264_ME_DIA; | |
| - param->analyse.i_subpel_refine = 0; | |
| - param->rc.i_aq_mode = 0; | |
| - param->analyse.b_mixed_references = 0; | |
| - param->analyse.i_trellis = 0; | |
| - param->i_bframe_adaptive = X264_B_ADAPT_NONE; | |
| - param->rc.b_mb_tree = 0; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_NONE; | |
| - param->analyse.b_weighted_bipred = 0; | |
| - param->rc.i_lookahead = 0; | |
| - } | |
| - else if( !strcasecmp( preset, "superfast" ) ) | |
| - { | |
| - param->analyse.inter = X264_ANALYSE_I8x8|X264_ANALYSE_I4x4; | |
| - param->analyse.i_me_method = X264_ME_DIA; | |
| - param->analyse.i_subpel_refine = 1; | |
| - param->i_frame_reference = 1; | |
| - param->analyse.b_mixed_references = 0; | |
| - param->analyse.i_trellis = 0; | |
| - param->rc.b_mb_tree = 0; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_SIMPLE; | |
| - param->rc.i_lookahead = 0; | |
| - } | |
| - else if( !strcasecmp( preset, "veryfast" ) ) | |
| - { | |
| - param->analyse.i_subpel_refine = 2; | |
| - param->i_frame_reference = 1; | |
| - param->analyse.b_mixed_references = 0; | |
| - param->analyse.i_trellis = 0; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_SIMPLE; | |
| - param->rc.i_lookahead = 10; | |
| - } | |
| - else if( !strcasecmp( preset, "faster" ) ) | |
| - { | |
| - param->analyse.b_mixed_references = 0; | |
| - param->i_frame_reference = 2; | |
| - param->analyse.i_subpel_refine = 4; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_SIMPLE; | |
| - param->rc.i_lookahead = 20; | |
| - } | |
| - else if( !strcasecmp( preset, "fast" ) ) | |
| - { | |
| - param->i_frame_reference = 2; | |
| - param->analyse.i_subpel_refine = 6; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_SIMPLE; | |
| - param->rc.i_lookahead = 30; | |
| - } | |
| - else if( !strcasecmp( preset, "medium" ) ) | |
| - { | |
| - /* Default is medium */ | |
| - } | |
| - else if( !strcasecmp( preset, "slow" ) ) | |
| - { | |
| - param->analyse.i_subpel_refine = 8; | |
| - param->i_frame_reference = 5; | |
| - param->analyse.i_direct_mv_pred = X264_DIRECT_PRED_AUTO; | |
| - param->analyse.i_trellis = 2; | |
| - param->rc.i_lookahead = 50; | |
| - } | |
| - else if( !strcasecmp( preset, "slower" ) ) | |
| - { | |
| - param->analyse.i_me_method = X264_ME_UMH; | |
| - param->analyse.i_subpel_refine = 9; | |
| - param->i_frame_reference = 8; | |
| - param->i_bframe_adaptive = X264_B_ADAPT_TRELLIS; | |
| - param->analyse.i_direct_mv_pred = X264_DIRECT_PRED_AUTO; | |
| - param->analyse.inter |= X264_ANALYSE_PSUB8x8; | |
| - param->analyse.i_trellis = 2; | |
| - param->rc.i_lookahead = 60; | |
| - } | |
| - else if( !strcasecmp( preset, "veryslow" ) ) | |
| - { | |
| - param->analyse.i_me_method = X264_ME_UMH; | |
| - param->analyse.i_subpel_refine = 10; | |
| - param->analyse.i_me_range = 24; | |
| - param->i_frame_reference = 16; | |
| - param->i_bframe_adaptive = X264_B_ADAPT_TRELLIS; | |
| - param->analyse.i_direct_mv_pred = X264_DIRECT_PRED_AUTO; | |
| - param->analyse.inter |= X264_ANALYSE_PSUB8x8; | |
| - param->analyse.i_trellis = 2; | |
| - param->i_bframe = 8; | |
| - param->rc.i_lookahead = 60; | |
| - } | |
| - else if( !strcasecmp( preset, "placebo" ) ) | |
| - { | |
| - param->analyse.i_me_method = X264_ME_TESA; | |
| - param->analyse.i_subpel_refine = 11; | |
| - param->analyse.i_me_range = 24; | |
| - param->i_frame_reference = 16; | |
| - param->i_bframe_adaptive = X264_B_ADAPT_TRELLIS; | |
| - param->analyse.i_direct_mv_pred = X264_DIRECT_PRED_AUTO; | |
| - param->analyse.inter |= X264_ANALYSE_PSUB8x8; | |
| - param->analyse.b_fast_pskip = 0; | |
| - param->analyse.i_trellis = 2; | |
| - param->i_bframe = 16; | |
| - param->rc.i_lookahead = 60; | |
| - } | |
| - else | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "invalid preset '%s'\n", preset ); | |
| - return -1; | |
| - } | |
| - return 0; | |
| -} | |
| - | |
| -static int x264_param_apply_tune( x264_param_t *param, const char *tune ) | |
| -{ | |
| - char *tmp = x264_malloc( strlen( tune ) + 1 ); | |
| - if( !tmp ) | |
| - return -1; | |
| - tmp = strcpy( tmp, tune ); | |
| - char *s = strtok( tmp, ",./-+" ); | |
| - int psy_tuning_used = 0; | |
| - while( s ) | |
| - { | |
| - if( !strncasecmp( s, "film", 4 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->i_deblocking_filter_alphac0 = -1; | |
| - param->i_deblocking_filter_beta = -1; | |
| - param->analyse.f_psy_trellis = 0.15; | |
| - } | |
| - else if( !strncasecmp( s, "animation", 9 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->i_frame_reference = param->i_frame_reference > 1 ? param->i_frame_reference*2 : 1; | |
| - param->i_deblocking_filter_alphac0 = 1; | |
| - param->i_deblocking_filter_beta = 1; | |
| - param->analyse.f_psy_rd = 0.4; | |
| - param->rc.f_aq_strength = 0.6; | |
| - param->i_bframe += 2; | |
| - } | |
| - else if( !strncasecmp( s, "grain", 5 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->i_deblocking_filter_alphac0 = -2; | |
| - param->i_deblocking_filter_beta = -2; | |
| - param->analyse.f_psy_trellis = 0.25; | |
| - param->analyse.b_dct_decimate = 0; | |
| - param->rc.f_pb_factor = 1.1; | |
| - param->rc.f_ip_factor = 1.1; | |
| - param->rc.f_aq_strength = 0.5; | |
| - param->analyse.i_luma_deadzone[0] = 6; | |
| - param->analyse.i_luma_deadzone[1] = 6; | |
| - param->rc.f_qcompress = 0.8; | |
| - } | |
| - else if( !strncasecmp( s, "stillimage", 10 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->i_deblocking_filter_alphac0 = -3; | |
| - param->i_deblocking_filter_beta = -3; | |
| - param->analyse.f_psy_rd = 2.0; | |
| - param->analyse.f_psy_trellis = 0.7; | |
| - param->rc.f_aq_strength = 1.2; | |
| - } | |
| - else if( !strncasecmp( s, "psnr", 4 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->rc.i_aq_mode = X264_AQ_NONE; | |
| - param->analyse.b_psy = 0; | |
| - } | |
| - else if( !strncasecmp( s, "ssim", 4 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->rc.i_aq_mode = X264_AQ_AUTOVARIANCE; | |
| - param->analyse.b_psy = 0; | |
| - } | |
| - else if( !strncasecmp( s, "fastdecode", 10 ) ) | |
| - { | |
| - param->b_deblocking_filter = 0; | |
| - param->b_cabac = 0; | |
| - param->analyse.b_weighted_bipred = 0; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_NONE; | |
| - } | |
| - else if( !strncasecmp( s, "zerolatency", 11 ) ) | |
| - { | |
| - param->rc.i_lookahead = 0; | |
| - param->i_sync_lookahead = 0; | |
| - param->i_bframe = 0; | |
| - param->b_sliced_threads = 1; | |
| - param->b_vfr_input = 0; | |
| - param->rc.b_mb_tree = 0; | |
| - } | |
| - else if( !strncasecmp( s, "touhou", 6 ) ) | |
| - { | |
| - if( psy_tuning_used++ ) goto psy_failure; | |
| - param->i_frame_reference = param->i_frame_reference > 1 ? param->i_frame_reference*2 : 1; | |
| - param->i_deblocking_filter_alphac0 = -1; | |
| - param->i_deblocking_filter_beta = -1; | |
| - param->analyse.f_psy_trellis = 0.2; | |
| - param->rc.f_aq_strength = 1.3; | |
| - if( param->analyse.inter & X264_ANALYSE_PSUB16x16 ) | |
| - param->analyse.inter |= X264_ANALYSE_PSUB8x8; | |
| - } | |
| - else | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "invalid tune '%s'\n", s ); | |
| - x264_free( tmp ); | |
| - return -1; | |
| - } | |
| - if( 0 ) | |
| - { | |
| - psy_failure: | |
| - x264_log( NULL, X264_LOG_WARNING, "only 1 psy tuning can be used: ignoring tune %s\n", s ); | |
| - } | |
| - s = strtok( NULL, ",./-+" ); | |
| - } | |
| - x264_free( tmp ); | |
| - return 0; | |
| -} | |
| - | |
| -int x264_param_default_preset( x264_param_t *param, const char *preset, const char *tune ) | |
| -{ | |
| - x264_param_default( param ); | |
| - | |
| - if( preset && x264_param_apply_preset( param, preset ) < 0 ) | |
| - return -1; | |
| - if( tune && x264_param_apply_tune( param, tune ) < 0 ) | |
| - return -1; | |
| - return 0; | |
| -} | |
| - | |
| -void x264_param_apply_fastfirstpass( x264_param_t *param ) | |
| -{ | |
| - /* Set faster options in case of turbo firstpass. */ | |
| - if( param->rc.b_stat_write && !param->rc.b_stat_read ) | |
| - { | |
| - param->i_frame_reference = 1; | |
| - param->analyse.b_transform_8x8 = 0; | |
| - param->analyse.inter = 0; | |
| - param->analyse.i_me_method = X264_ME_DIA; | |
| - param->analyse.i_subpel_refine = X264_MIN( 2, param->analyse.i_subpel_refine ); | |
| - param->analyse.i_trellis = 0; | |
| - param->analyse.b_fast_pskip = 1; | |
| - } | |
| -} | |
| - | |
| -static int profile_string_to_int( const char *str ) | |
| -{ | |
| - if( !strcasecmp( str, "baseline" ) ) | |
| - return PROFILE_BASELINE; | |
| - if( !strcasecmp( str, "main" ) ) | |
| - return PROFILE_MAIN; | |
| - if( !strcasecmp( str, "high" ) ) | |
| - return PROFILE_HIGH; | |
| - if( !strcasecmp( str, "high10" ) ) | |
| - return PROFILE_HIGH10; | |
| - if( !strcasecmp( str, "high422" ) ) | |
| - return PROFILE_HIGH422; | |
| - if( !strcasecmp( str, "high444" ) ) | |
| - return PROFILE_HIGH444_PREDICTIVE; | |
| - return -1; | |
| -} | |
| - | |
| -int x264_param_apply_profile( x264_param_t *param, const char *profile ) | |
| -{ | |
| - if( !profile ) | |
| - return 0; | |
| - | |
| - int p = profile_string_to_int( profile ); | |
| - if( p < 0 ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "invalid profile: %s\n", profile ); | |
| - return -1; | |
| - } | |
| - if( p < PROFILE_HIGH444_PREDICTIVE && ((param->rc.i_rc_method == X264_RC_CQP && param->rc.i_qp_constant <= 0) || | |
| - (param->rc.i_rc_method == X264_RC_CRF && (int)(param->rc.f_rf_constant + QP_BD_OFFSET) <= 0)) ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "%s profile doesn't support lossless\n", profile ); | |
| - return -1; | |
| - } | |
| - if( p < PROFILE_HIGH444_PREDICTIVE && (param->i_csp & X264_CSP_MASK) >= X264_CSP_I444 ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "%s profile doesn't support 4:4:4\n", profile ); | |
| - return -1; | |
| - } | |
| - if( p < PROFILE_HIGH422 && (param->i_csp & X264_CSP_MASK) >= X264_CSP_I422 ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "%s profile doesn't support 4:2:2\n", profile ); | |
| - return -1; | |
| - } | |
| - if( p < PROFILE_HIGH10 && BIT_DEPTH > 8 ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "%s profile doesn't support a bit depth of %d\n", profile, BIT_DEPTH ); | |
| - return -1; | |
| - } | |
| - | |
| - if( p == PROFILE_BASELINE ) | |
| - { | |
| - param->analyse.b_transform_8x8 = 0; | |
| - param->b_cabac = 0; | |
| - param->i_cqm_preset = X264_CQM_FLAT; | |
| - param->psz_cqm_file = NULL; | |
| - param->i_bframe = 0; | |
| - param->analyse.i_weighted_pred = X264_WEIGHTP_NONE; | |
| - if( param->b_interlaced ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "baseline profile doesn't support interlacing\n" ); | |
| - return -1; | |
| - } | |
| - if( param->b_fake_interlaced ) | |
| - { | |
| - x264_log( NULL, X264_LOG_ERROR, "baseline profile doesn't support fake interlacing\n" ); | |
| - return -1; | |
| - } | |
| - } | |
| - else if( p == PROFILE_MAIN ) | |
| - { | |
| - param->analyse.b_transform_8x8 = 0; | |
| - param->i_cqm_preset = X264_CQM_FLAT; | |
| - param->psz_cqm_file = NULL; | |
| - } | |
| - return 0; | |
| -} | |
| - | |
| -static int parse_enum( const char *arg, const char * const *names, int *dst ) | |
| -{ | |
| - for( int i = 0; names[i]; i++ ) | |
| - if( !strcasecmp( arg, names[i] ) ) | |
| - { | |
| - *dst = i; | |
| - return 0; | |
| - } | |
| - return -1; | |
| -} | |
| - | |
| -static int parse_cqm( const char *str, uint8_t *cqm, int length ) | |
| -{ | |
| - int i = 0; | |
| - do { | |
| - int coef; | |
| - if( !sscanf( str, "%d", &coef ) || coef < 1 || coef > 255 ) | |
| - return -1; | |
| - cqm[i++] = coef; | |
| - } while( i < length && (str = strchr( str, ',' )) && str++ ); | |
| - return (i == length) ? 0 : -1; | |
| -} | |
| - | |
| -static int x264_atobool( const char *str, int *b_error ) | |
| -{ | |
| - if( !strcmp(str, "1") || | |
| - !strcasecmp(str, "true") || | |
| - !strcasecmp(str, "yes") ) | |
| - return 1; | |
| - if( !strcmp(str, "0") || | |
| - !strcasecmp(str, "false") || | |
| - !strcasecmp(str, "no") ) | |
| - return 0; | |
| - *b_error = 1; | |
| - return 0; | |
| -} | |
| - | |
| -static int x264_atoi( const char *str, int *b_error ) | |
| -{ | |
| - char *end; | |
| - int v = strtol( str, &end, 0 ); | |
| - if( end == str || *end != '\0' ) | |
| - *b_error = 1; | |
| - return v; | |
| -} | |
| - | |
| -static double x264_atof( const char *str, int *b_error ) | |
| -{ | |
| - char *end; | |
| - double v = strtod( str, &end ); | |
| - if( end == str || *end != '\0' ) | |
| - *b_error = 1; | |
| - return v; | |
| -} | |
| - | |
| -#define atobool(str) ( name_was_bool = 1, x264_atobool( str, &b_error ) ) | |
| -#undef atoi | |
| -#undef atof | |
| -#define atoi(str) x264_atoi( str, &b_error ) | |
| -#define atof(str) x264_atof( str, &b_error ) | |
| - | |
| -int x264_param_parse( x264_param_t *p, const char *name, const char *value ) | |
| -{ | |
| - char *name_buf = NULL; | |
| - int b_error = 0; | |
| - int errortype = X264_PARAM_BAD_VALUE; | |
| - int name_was_bool; | |
| - int value_was_null = !value; | |
| - | |
| - if( !name ) | |
| - return X264_PARAM_BAD_NAME; | |
| - if( !value ) | |
| - value = "true"; | |
| - | |
| - if( value[0] == '=' ) | |
| - value++; | |
| - | |
| - if( strchr( name, '_' ) ) // s/_/-/g | |
| - { | |
| - char *c; | |
| - name_buf = strdup(name); | |
| - if( !name_buf ) | |
| - return X264_PARAM_BAD_NAME; | |
| - while( (c = strchr( name_buf, '_' )) ) | |
| - *c = '-'; | |
| - name = name_buf; | |
| - } | |
| - | |
| - if( !strncmp( name, "no", 2 ) ) | |
| - { | |
| - name += 2; | |
| - if( name[0] == '-' ) | |
| - name++; | |
| - value = atobool(value) ? "false" : "true"; | |
| - } | |
| - name_was_bool = 0; | |
| - | |
| -#define OPT(STR) else if( !strcmp( name, STR ) ) | |
| -#define OPT2(STR0, STR1) else if( !strcmp( name, STR0 ) || !strcmp( name, STR1 ) ) | |
| - if( 0 ); | |
| - OPT("asm") | |
| - { | |
| - p->cpu = isdigit(value[0]) ? atoi(value) : | |
| - !strcasecmp(value, "auto") || atobool(value) ? x264_cpu_detect() : 0; | |
| - if( b_error ) | |
| - { | |
| - char *buf = strdup( value ); | |
| - if( buf ) | |
| - { | |
| - char *tok, UNUSED *saveptr=NULL, *init; | |
| - b_error = 0; | |
| - p->cpu = 0; | |
| - for( init=buf; (tok=strtok_r(init, ",", &saveptr)); init=NULL ) | |
| - { | |
| - int i = 0; | |
| - while( x264_cpu_names[i].flags && strcasecmp(tok, x264_cpu_names[i].name) ) | |
| - i++; | |
| - p->cpu |= x264_cpu_names[i].flags; | |
| - if( !x264_cpu_names[i].flags ) | |
| - b_error = 1; | |
| - } | |
| - free( buf ); | |
| - if( (p->cpu&X264_CPU_SSSE3) && !(p->cpu&X264_CPU_SSE2_IS_SLOW) ) | |
| - p->cpu |= X264_CPU_SSE2_IS_FAST; | |
| - } | |
| - } | |
| - } | |
| - OPT("threads") | |
| - { | |
| - if( !strcasecmp(value, "auto") ) | |
| - p->i_threads = X264_THREADS_AUTO; | |
| - else | |
| - p->i_threads = atoi(value); | |
| - } | |
| - OPT("lookahead-threads") | |
| - { | |
| - if( !strcasecmp(value, "auto") ) | |
| - p->i_lookahead_threads = X264_THREADS_AUTO; | |
| - else | |
| - p->i_lookahead_threads = atoi(value); | |
| - } | |
| - OPT("sliced-threads") | |
| - p->b_sliced_threads = atobool(value); | |
| - OPT("sync-lookahead") | |
| - { | |
| - if( !strcasecmp(value, "auto") ) | |
| - p->i_sync_lookahead = X264_SYNC_LOOKAHEAD_AUTO; | |
| - else | |
| - p->i_sync_lookahead = atoi(value); | |
| - } | |
| - OPT2("deterministic", "n-deterministic") | |
| - p->b_deterministic = atobool(value); | |
| - OPT("cpu-independent") | |
| - p->b_cpu_independent = atobool(value); | |
| - OPT2("level", "level-idc") | |
| - { | |
| - if( !strcmp(value, "1b") ) | |
| - p->i_level_idc = 9; | |
| - else if( atof(value) < 7 ) | |
| - p->i_level_idc = (int)(10*atof(value)+.5); | |
| - else | |
| - p->i_level_idc = atoi(value); | |
| - } | |
| - OPT("bluray-compat") | |
| - p->b_bluray_compat = atobool(value); | |
| - OPT("avcintra-class") | |
| - p->i_avcintra_class = atoi(value); | |
| - OPT("sar") | |
| - { | |
| - b_error = ( 2 != sscanf( value, "%d:%d", &p->vui.i_sar_width, &p->vui.i_sar_height ) && | |
| - 2 != sscanf( value, "%d/%d", &p->vui.i_sar_width, &p->vui.i_sar_height ) ); | |
| - } | |
| - OPT("overscan") | |
| - b_error |= parse_enum( value, x264_overscan_names, &p->vui.i_overscan ); | |
| - OPT("videoformat") | |
| - b_error |= parse_enum( value, x264_vidformat_names, &p->vui.i_vidformat ); | |
| - OPT("fullrange") | |
| - b_error |= parse_enum( value, x264_fullrange_names, &p->vui.b_fullrange ); | |
| - OPT("colorprim") | |
| - b_error |= parse_enum( value, x264_colorprim_names, &p->vui.i_colorprim ); | |
| - OPT("transfer") | |
| - b_error |= parse_enum( value, x264_transfer_names, &p->vui.i_transfer ); | |
| - OPT("colormatrix") | |
| - b_error |= parse_enum( value, x264_colmatrix_names, &p->vui.i_colmatrix ); | |
| - OPT("chromaloc") | |
| - { | |
| - p->vui.i_chroma_loc = atoi(value); | |
| - b_error = ( p->vui.i_chroma_loc < 0 || p->vui.i_chroma_loc > 5 ); | |
| - } | |
| - OPT("fps") | |
| - { | |
| - if( sscanf( value, "%u/%u", &p->i_fps_num, &p->i_fps_den ) != 2 ) | |
| - { | |
| - double fps = atof(value); | |
| - if( fps > 0.0 && fps <= INT_MAX/1000.0 ) | |
| - { | |
| - p->i_fps_num = (int)(fps * 1000.0 + .5); | |
| - p->i_fps_den = 1000; | |
| - } | |
| - else | |
| - { | |
| - p->i_fps_num = atoi(value); | |
| - p->i_fps_den = 1; | |
| - } | |
| - } | |
| - } | |
| - OPT2("ref", "frameref") | |
| - p->i_frame_reference = atoi(value); | |
| - OPT("dpb-size") | |
| - p->i_dpb_size = atoi(value); | |
| - OPT("keyint") | |
| - { | |
| - if( strstr( value, "infinite" ) ) | |
| - p->i_keyint_max = X264_KEYINT_MAX_INFINITE; | |
| - else | |
| - p->i_keyint_max = atoi(value); | |
| - } | |
| - OPT2("min-keyint", "keyint-min") | |
| - { | |
| - p->i_keyint_min = atoi(value); | |
| - if( p->i_keyint_max < p->i_keyint_min ) | |
| - p->i_keyint_max = p->i_keyint_min; | |
| - } | |
| - OPT("scenecut") | |
| - { | |
| - p->i_scenecut_threshold = atobool(value); | |
| - if( b_error || p->i_scenecut_threshold ) | |
| - { | |
| - b_error = 0; | |
| - p->i_scenecut_threshold = atoi(value); | |
| - } | |
| - } | |
| - OPT("intra-refresh") | |
| - p->b_intra_refresh = atobool(value); | |
| - OPT("bframes") | |
| - p->i_bframe = atoi(value); | |
| - OPT("b-adapt") | |
| - { | |
| - p->i_bframe_adaptive = atobool(value); | |
| - if( b_error ) | |
| - { | |
| - b_error = 0; | |
| - p->i_bframe_adaptive = atoi(value); | |
| - } | |
| - } | |
| - OPT("b-bias") | |
| - p->i_bframe_bias = atoi(value); | |
| - OPT("b-pyramid") | |
| - { | |
| - b_error |= parse_enum( value, x264_b_pyramid_names, &p->i_bframe_pyramid ); | |
| - if( b_error ) | |
| - { | |
| - b_error = 0; | |
| - p->i_bframe_pyramid = atoi(value); | |
| - } | |
| - } | |
| - OPT("open-gop") | |
| - p->b_open_gop = atobool(value); | |
| - OPT("nf") | |
| - p->b_deblocking_filter = !atobool(value); | |
| - OPT2("filter", "deblock") | |
| - { | |
| - if( 2 == sscanf( value, "%d:%d", &p->i_deblocking_filter_alphac0, &p->i_deblocking_filter_beta ) || | |
| - 2 == sscanf( value, "%d,%d", &p->i_deblocking_filter_alphac0, &p->i_deblocking_filter_beta ) ) | |
| - { | |
| - p->b_deblocking_filter = 1; | |
| - } | |
| - else if( sscanf( value, "%d", &p->i_deblocking_filter_alphac0 ) ) | |
| - { | |
| - p->b_deblocking_filter = 1; | |
| - p->i_deblocking_filter_beta = p->i_deblocking_filter_alphac0; | |
| - } | |
| - else | |
| - p->b_deblocking_filter = atobool(value); | |
| - } | |
| - OPT("slice-max-size") | |
| - p->i_slice_max_size = atoi(value); | |
| - OPT("slice-max-mbs") | |
| - p->i_slice_max_mbs = atoi(value); | |
| - OPT("slice-min-mbs") | |
| - p->i_slice_min_mbs = atoi(value); | |
| - OPT("slices") | |
| - p->i_slice_count = atoi(value); | |
| - OPT("slices-max") | |
| - p->i_slice_count_max = atoi(value); | |
| - OPT("cabac") | |
| - p->b_cabac = atobool(value); | |
| - OPT("cabac-idc") | |
| - p->i_cabac_init_idc = atoi(value); | |
| - OPT("interlaced") | |
| - p->b_interlaced = atobool(value); | |
| - OPT("tff") | |
| - p->b_interlaced = p->b_tff = atobool(value); | |
| - OPT("bff") | |
| - { | |
| - p->b_interlaced = atobool(value); | |
| - p->b_tff = !p->b_interlaced; | |
| - } | |
| - OPT("constrained-intra") | |
| - p->b_constrained_intra = atobool(value); | |
| - OPT("cqm") | |
| - { | |
| - if( strstr( value, "flat" ) ) | |
| - p->i_cqm_preset = X264_CQM_FLAT; | |
| - else if( strstr( value, "jvt" ) ) | |
| - p->i_cqm_preset = X264_CQM_JVT; | |
| - else | |
| - p->psz_cqm_file = strdup(value); | |
| - } | |
| - OPT("cqmfile") | |
| - p->psz_cqm_file = strdup(value); | |
| - OPT("cqm4") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4iy, 16 ); | |
| - b_error |= parse_cqm( value, p->cqm_4py, 16 ); | |
| - b_error |= parse_cqm( value, p->cqm_4ic, 16 ); | |
| - b_error |= parse_cqm( value, p->cqm_4pc, 16 ); | |
| - } | |
| - OPT("cqm8") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_8iy, 64 ); | |
| - b_error |= parse_cqm( value, p->cqm_8py, 64 ); | |
| - b_error |= parse_cqm( value, p->cqm_8ic, 64 ); | |
| - b_error |= parse_cqm( value, p->cqm_8pc, 64 ); | |
| - } | |
| - OPT("cqm4i") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4iy, 16 ); | |
| - b_error |= parse_cqm( value, p->cqm_4ic, 16 ); | |
| - } | |
| - OPT("cqm4p") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4py, 16 ); | |
| - b_error |= parse_cqm( value, p->cqm_4pc, 16 ); | |
| - } | |
| - OPT("cqm4iy") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4iy, 16 ); | |
| - } | |
| - OPT("cqm4ic") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4ic, 16 ); | |
| - } | |
| - OPT("cqm4py") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4py, 16 ); | |
| - } | |
| - OPT("cqm4pc") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_4pc, 16 ); | |
| - } | |
| - OPT("cqm8i") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_8iy, 64 ); | |
| - b_error |= parse_cqm( value, p->cqm_8ic, 64 ); | |
| - } | |
| - OPT("cqm8p") | |
| - { | |
| - p->i_cqm_preset = X264_CQM_CUSTOM; | |
| - b_error |= parse_cqm( value, p->cqm_8py, 64 ); | |
| - b_error |= parse_cqm( value, p->cqm_8pc, 64 ); | |
| - } | |
| - OPT("log") | |
| - p->i_log_level = atoi(value); | |
| - OPT("dump-yuv") | |
| - p->psz_dump_yuv = strdup(value); | |
| - OPT2("analyse", "partitions") | |
| - { | |
| - p->analyse.inter = 0; | |
| - if( strstr( value, "none" ) ) p->analyse.inter = 0; | |
| - if( strstr( value, "all" ) ) p->analyse.inter = ~0; | |
| - | |
| - if( strstr( value, "i4x4" ) ) p->analyse.inter |= X264_ANALYSE_I4x4; | |
| - if( strstr( value, "i8x8" ) ) p->analyse.inter |= X264_ANALYSE_I8x8; | |
| - if( strstr( value, "p8x8" ) ) p->analyse.inter |= X264_ANALYSE_PSUB16x16; | |
| - if( strstr( value, "p4x4" ) ) p->analyse.inter |= X264_ANALYSE_PSUB8x8; | |
| - if( strstr( value, "b8x8" ) ) p->analyse.inter |= X264_ANALYSE_BSUB16x16; | |
| - } | |
| - OPT("8x8dct") | |
| - p->analyse.b_transform_8x8 = atobool(value); | |
| - OPT2("weightb", "weight-b") | |
| - p->analyse.b_weighted_bipred = atobool(value); | |
| - OPT("weightp") | |
| - p->analyse.i_weighted_pred = atoi(value); | |
| - OPT2("direct", "direct-pred") | |
| - b_error |= parse_enum( value, x264_direct_pred_names, &p->analyse.i_direct_mv_pred ); | |
| - OPT("chroma-qp-offset") | |
| - p->analyse.i_chroma_qp_offset = atoi(value); | |
| - OPT("me") | |
| - b_error |= parse_enum( value, x264_motion_est_names, &p->analyse.i_me_method ); | |
| - OPT2("merange", "me-range") | |
| - p->analyse.i_me_range = atoi(value); | |
| - OPT2("mvrange", "mv-range") | |
| - p->analyse.i_mv_range = atoi(value); | |
| - OPT2("mvrange-thread", "mv-range-thread") | |
| - p->analyse.i_mv_range_thread = atoi(value); | |
| - OPT2("subme", "subq") | |
| - p->analyse.i_subpel_refine = atoi(value); | |
| - OPT("psy-rd") | |
| - { | |
| - if( 2 == sscanf( value, "%f:%f", &p->analyse.f_psy_rd, &p->analyse.f_psy_trellis ) || | |
| - 2 == sscanf( value, "%f,%f", &p->analyse.f_psy_rd, &p->analyse.f_psy_trellis ) || | |
| - 2 == sscanf( value, "%f|%f", &p->analyse.f_psy_rd, &p->analyse.f_psy_trellis )) | |
| - { } | |
| - else if( sscanf( value, "%f", &p->analyse.f_psy_rd ) ) | |
| - { | |
| - p->analyse.f_psy_trellis = 0; | |
| - } | |
| - else | |
| - { | |
| - p->analyse.f_psy_rd = 0; | |
| - p->analyse.f_psy_trellis = 0; | |
| - } | |
| - } | |
| - OPT("psy") | |
| - p->analyse.b_psy = atobool(value); | |
| - OPT("chroma-me") | |
| - p->analyse.b_chroma_me = atobool(value); | |
| - OPT("mixed-refs") | |
| - p->analyse.b_mixed_references = atobool(value); | |
| - OPT("trellis") | |
| - p->analyse.i_trellis = atoi(value); | |
| - OPT("fast-pskip") | |
| - p->analyse.b_fast_pskip = atobool(value); | |
| - OPT("dct-decimate") | |
| - p->analyse.b_dct_decimate = atobool(value); | |
| - OPT("deadzone-inter") | |
| - p->analyse.i_luma_deadzone[0] = atoi(value); | |
| - OPT("deadzone-intra") | |
| - p->analyse.i_luma_deadzone[1] = atoi(value); | |
| - OPT("nr") | |
| - p->analyse.i_noise_reduction = atoi(value); | |
| - OPT("bitrate") | |
| - { | |
| - p->rc.i_bitrate = atoi(value); | |
| - p->rc.i_rc_method = X264_RC_ABR; | |
| - } | |
| - OPT2("qp", "qp_constant") | |
| - { | |
| - p->rc.i_qp_constant = atoi(value); | |
| - p->rc.i_rc_method = X264_RC_CQP; | |
| - } | |
| - OPT("crf") | |
| - { | |
| - p->rc.f_rf_constant = atof(value); | |
| - p->rc.i_rc_method = X264_RC_CRF; | |
| - } | |
| - OPT("crf-max") | |
| - p->rc.f_rf_constant_max = atof(value); | |
| - OPT("rc-lookahead") | |
| - p->rc.i_lookahead = atoi(value); | |
| - OPT2("qpmin", "qp-min") | |
| - p->rc.i_qp_min = atoi(value); | |
| - OPT2("qpmax", "qp-max") | |
| - p->rc.i_qp_max = atoi(value); | |
| - OPT2("qpstep", "qp-step") | |
| - p->rc.i_qp_step = atoi(value); | |
| - OPT("ratetol") | |
| - p->rc.f_rate_tolerance = !strncmp("inf", value, 3) ? 1e9 : atof(value); | |
| - OPT("vbv-maxrate") | |
| - p->rc.i_vbv_max_bitrate = atoi(value); | |
| - OPT("vbv-bufsize") | |
| - p->rc.i_vbv_buffer_size = atoi(value); | |
| - OPT("vbv-init") | |
| - p->rc.f_vbv_buffer_init = atof(value); | |
| - OPT2("ipratio", "ip-factor") | |
| - p->rc.f_ip_factor = atof(value); | |
| - OPT2("pbratio", "pb-factor") | |
| - p->rc.f_pb_factor = atof(value); | |
| - OPT("aq-mode") | |
| - p->rc.i_aq_mode = atoi(value); | |
| - OPT("aq-strength") | |
| - p->rc.f_aq_strength = atof(value); | |
| - OPT("pass") | |
| - { | |
| - int pass = x264_clip3( atoi(value), 0, 3 ); | |
| - p->rc.b_stat_write = pass & 1; | |
| - p->rc.b_stat_read = pass & 2; | |
| - } | |
| - OPT("stats") | |
| - { | |
| - p->rc.psz_stat_in = strdup(value); | |
| - p->rc.psz_stat_out = strdup(value); | |
| - } | |
| - OPT("qcomp") | |
| - p->rc.f_qcompress = atof(value); | |
| - OPT("mbtree") | |
| - p->rc.b_mb_tree = atobool(value); | |
| - OPT("qblur") | |
| - p->rc.f_qblur = atof(value); | |
| - OPT2("cplxblur", "cplx-blur") | |
| - p->rc.f_complexity_blur = atof(value); | |
| - OPT("zones") | |
| - p->rc.psz_zones = strdup(value); | |
| - OPT("crop-rect") | |
| - b_error |= sscanf( value, "%u,%u,%u,%u", &p->crop_rect.i_left, &p->crop_rect.i_top, | |
| - &p->crop_rect.i_right, &p->crop_rect.i_bottom ) != 4; | |
| - OPT("psnr") | |
| - p->analyse.b_psnr = atobool(value); | |
| - OPT("ssim") | |
| - p->analyse.b_ssim = atobool(value); | |
| - OPT("aud") | |
| - p->b_aud = atobool(value); | |
| - OPT("sps-id") | |
| - p->i_sps_id = atoi(value); | |
| - OPT("global-header") | |
| - p->b_repeat_headers = !atobool(value); | |
| - OPT("repeat-headers") | |
| - p->b_repeat_headers = atobool(value); | |
| - OPT("annexb") | |
| - p->b_annexb = atobool(value); | |
| - OPT("force-cfr") | |
| - p->b_vfr_input = !atobool(value); | |
| - OPT("nal-hrd") | |
| - b_error |= parse_enum( value, x264_nal_hrd_names, &p->i_nal_hrd ); | |
| - OPT("filler") | |
| - p->rc.b_filler = atobool(value); | |
| - OPT("pic-struct") | |
| - p->b_pic_struct = atobool(value); | |
| - OPT("fake-interlaced") | |
| - p->b_fake_interlaced = atobool(value); | |
| - OPT("frame-packing") | |
| - p->i_frame_packing = atoi(value); | |
| - OPT("stitchable") | |
| - p->b_stitchable = atobool(value); | |
| - OPT("opencl") | |
| - p->b_opencl = atobool( value ); | |
| - OPT("opencl-clbin") | |
| - p->psz_clbin_file = strdup( value ); | |
| - OPT("opencl-device") | |
| - p->i_opencl_device = atoi( value ); | |
| - else | |
| - { | |
| - b_error = 1; | |
| - errortype = X264_PARAM_BAD_NAME; | |
| - } | |
| -#undef OPT | |
| -#undef OPT2 | |
| -#undef atobool | |
| -#undef atoi | |
| -#undef atof | |
| - | |
| - if( name_buf ) | |
| - free( name_buf ); | |
| - | |
| - b_error |= value_was_null && !name_was_bool; | |
| - return b_error ? errortype : 0; | |
| -} | |
| - | |
| /**************************************************************************** | |
| * x264_log: | |
| ****************************************************************************/ | |
| @@ -1085,362 +42,3 @@ | |
| va_end( arg ); | |
| } | |
| } | |
| - | |
| -static void x264_log_default( void *p_unused, int i_level, const char *psz_fmt, va_list arg ) | |
| -{ | |
| - char *psz_prefix; | |
| - switch( i_level ) | |
| - { | |
| - case X264_LOG_ERROR: | |
| - psz_prefix = "error"; | |
| - break; | |
| - case X264_LOG_WARNING: | |
| - psz_prefix = "warning"; | |
| - break; | |
| - case X264_LOG_INFO: | |
| - psz_prefix = "info"; | |
| - break; | |
| - case X264_LOG_DEBUG: | |
| - psz_prefix = "debug"; | |
| - break; | |
| - default: | |
| - psz_prefix = "unknown"; | |
| - break; | |
| - } | |
| - fprintf( stderr, "x264 [%s]: ", psz_prefix ); | |
| - x264_vfprintf( stderr, psz_fmt, arg ); | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_picture_init: | |
| - ****************************************************************************/ | |
| -void x264_picture_init( x264_picture_t *pic ) | |
| -{ | |
| - memset( pic, 0, sizeof( x264_picture_t ) ); | |
| - pic->i_type = X264_TYPE_AUTO; | |
| - pic->i_qpplus1 = X264_QP_AUTO; | |
| - pic->i_pic_struct = PIC_STRUCT_AUTO; | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_picture_alloc: | |
| - ****************************************************************************/ | |
| -int x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_height ) | |
| -{ | |
| - typedef struct | |
| - { | |
| - int planes; | |
| - int width_fix8[3]; | |
| - int height_fix8[3]; | |
| - } x264_csp_tab_t; | |
| - | |
| - static const x264_csp_tab_t x264_csp_tab[] = | |
| - { | |
| - [X264_CSP_I420] = { 3, { 256*1, 256/2, 256/2 }, { 256*1, 256/2, 256/2 } }, | |
| - [X264_CSP_YV12] = { 3, { 256*1, 256/2, 256/2 }, { 256*1, 256/2, 256/2 } }, | |
| - [X264_CSP_NV12] = { 2, { 256*1, 256*1 }, { 256*1, 256/2 }, }, | |
| - [X264_CSP_NV21] = { 2, { 256*1, 256*1 }, { 256*1, 256/2 }, }, | |
| - [X264_CSP_I422] = { 3, { 256*1, 256/2, 256/2 }, { 256*1, 256*1, 256*1 } }, | |
| - [X264_CSP_YV16] = { 3, { 256*1, 256/2, 256/2 }, { 256*1, 256*1, 256*1 } }, | |
| - [X264_CSP_NV16] = { 2, { 256*1, 256*1 }, { 256*1, 256*1 }, }, | |
| - [X264_CSP_YUYV] = { 1, { 256*2 }, { 256*1 }, }, | |
| - [X264_CSP_UYVY] = { 1, { 256*2 }, { 256*1 }, }, | |
| - [X264_CSP_I444] = { 3, { 256*1, 256*1, 256*1 }, { 256*1, 256*1, 256*1 } }, | |
| - [X264_CSP_YV24] = { 3, { 256*1, 256*1, 256*1 }, { 256*1, 256*1, 256*1 } }, | |
| - [X264_CSP_BGR] = { 1, { 256*3 }, { 256*1 }, }, | |
| - [X264_CSP_BGRA] = { 1, { 256*4 }, { 256*1 }, }, | |
| - [X264_CSP_RGB] = { 1, { 256*3 }, { 256*1 }, }, | |
| - }; | |
| - | |
| - int csp = i_csp & X264_CSP_MASK; | |
| - if( csp <= X264_CSP_NONE || csp >= X264_CSP_MAX || csp == X264_CSP_V210 ) | |
| - return -1; | |
| - x264_picture_init( pic ); | |
| - pic->img.i_csp = i_csp; | |
| - pic->img.i_plane = x264_csp_tab[csp].planes; | |
| - int depth_factor = i_csp & X264_CSP_HIGH_DEPTH ? 2 : 1; | |
| - int plane_offset[3] = {0}; | |
| - int frame_size = 0; | |
| - for( int i = 0; i < pic->img.i_plane; i++ ) | |
| - { | |
| - int stride = (((int64_t)i_width * x264_csp_tab[csp].width_fix8[i]) >> 8) * depth_factor; | |
| - int plane_size = (((int64_t)i_height * x264_csp_tab[csp].height_fix8[i]) >> 8) * stride; | |
| - pic->img.i_stride[i] = stride; | |
| - plane_offset[i] = frame_size; | |
| - frame_size += plane_size; | |
| - } | |
| - pic->img.plane[0] = x264_malloc( frame_size ); | |
| - if( !pic->img.plane[0] ) | |
| - return -1; | |
| - for( int i = 1; i < pic->img.i_plane; i++ ) | |
| - pic->img.plane[i] = pic->img.plane[0] + plane_offset[i]; | |
| - return 0; | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_picture_clean: | |
| - ****************************************************************************/ | |
| -void x264_picture_clean( x264_picture_t *pic ) | |
| -{ | |
| - x264_free( pic->img.plane[0] ); | |
| - | |
| - /* just to be safe */ | |
| - memset( pic, 0, sizeof( x264_picture_t ) ); | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_malloc: | |
| - ****************************************************************************/ | |
| -void *x264_malloc( int i_size ) | |
| -{ | |
| - uint8_t *align_buf = NULL; | |
| -#if HAVE_MALLOC_H | |
| -#if HAVE_THP | |
| -#define HUGE_PAGE_SIZE 2*1024*1024 | |
| -#define HUGE_PAGE_THRESHOLD HUGE_PAGE_SIZE*7/8 /* FIXME: Is this optimal? */ | |
| - /* Attempt to allocate huge pages to reduce TLB misses. */ | |
| - if( i_size >= HUGE_PAGE_THRESHOLD ) | |
| - { | |
| - align_buf = memalign( HUGE_PAGE_SIZE, i_size ); | |
| - if( align_buf ) | |
| - { | |
| - /* Round up to the next huge page boundary if we are close enough. */ | |
| - size_t madv_size = (i_size + HUGE_PAGE_SIZE - HUGE_PAGE_THRESHOLD) & ~(HUGE_PAGE_SIZE-1); | |
| - madvise( align_buf, madv_size, MADV_HUGEPAGE ); | |
| - } | |
| - } | |
| - else | |
| -#undef HUGE_PAGE_SIZE | |
| -#undef HUGE_PAGE_THRESHOLD | |
| -#endif | |
| - align_buf = memalign( NATIVE_ALIGN, i_size ); | |
| -#else | |
| - uint8_t *buf = malloc( i_size + (NATIVE_ALIGN-1) + sizeof(void **) ); | |
| - if( buf ) | |
| - { | |
| - align_buf = buf + (NATIVE_ALIGN-1) + sizeof(void **); | |
| - align_buf -= (intptr_t) align_buf & (NATIVE_ALIGN-1); | |
| - *( (void **) ( align_buf - sizeof(void **) ) ) = buf; | |
| - } | |
| -#endif | |
| - if( !align_buf ) | |
| - x264_log( NULL, X264_LOG_ERROR, "malloc of size %d failed\n", i_size ); | |
| - return align_buf; | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_free: | |
| - ****************************************************************************/ | |
| -void x264_free( void *p ) | |
| -{ | |
| - if( p ) | |
| - { | |
| -#if HAVE_MALLOC_H | |
| - free( p ); | |
| -#else | |
| - free( *( ( ( void **) p ) - 1 ) ); | |
| -#endif | |
| - } | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_reduce_fraction: | |
| - ****************************************************************************/ | |
| -#define REDUCE_FRACTION( name, type )\ | |
| -void name( type *n, type *d )\ | |
| -{ \ | |
| - type a = *n; \ | |
| - type b = *d; \ | |
| - type c; \ | |
| - if( !a || !b ) \ | |
| - return; \ | |
| - c = a % b; \ | |
| - while( c ) \ | |
| - { \ | |
| - a = b; \ | |
| - b = c; \ | |
| - c = a % b; \ | |
| - } \ | |
| - *n /= b; \ | |
| - *d /= b; \ | |
| -} | |
| - | |
| -REDUCE_FRACTION( x264_reduce_fraction , uint32_t ) | |
| -REDUCE_FRACTION( x264_reduce_fraction64, uint64_t ) | |
| - | |
| -/**************************************************************************** | |
| - * x264_slurp_file: | |
| - ****************************************************************************/ | |
| -char *x264_slurp_file( const char *filename ) | |
| -{ | |
| - int b_error = 0; | |
| - int64_t i_size; | |
| - char *buf; | |
| - FILE *fh = x264_fopen( filename, "rb" ); | |
| - if( !fh ) | |
| - return NULL; | |
| - | |
| - b_error |= fseek( fh, 0, SEEK_END ) < 0; | |
| - b_error |= ( i_size = ftell( fh ) ) <= 0; | |
| - if( WORD_SIZE == 4 ) | |
| - b_error |= i_size > INT32_MAX; | |
| - b_error |= fseek( fh, 0, SEEK_SET ) < 0; | |
| - if( b_error ) | |
| - goto error; | |
| - | |
| - buf = x264_malloc( i_size+2 ); | |
| - if( !buf ) | |
| - goto error; | |
| - | |
| - b_error |= fread( buf, 1, i_size, fh ) != i_size; | |
| - fclose( fh ); | |
| - if( b_error ) | |
| - { | |
| - x264_free( buf ); | |
| - return NULL; | |
| - } | |
| - | |
| - if( buf[i_size-1] != '\n' ) | |
| - buf[i_size++] = '\n'; | |
| - buf[i_size] = '\0'; | |
| - | |
| - return buf; | |
| -error: | |
| - fclose( fh ); | |
| - return NULL; | |
| -} | |
| - | |
| -/**************************************************************************** | |
| - * x264_param2string: | |
| - ****************************************************************************/ | |
| -char *x264_param2string( x264_param_t *p, int b_res ) | |
| -{ | |
| - int len = 1000; | |
| - char *buf, *s; | |
| - if( p->rc.psz_zones ) | |
| - len += strlen(p->rc.psz_zones); | |
| - buf = s = x264_malloc( len ); | |
| - if( !buf ) | |
| - return NULL; | |
| - | |
| - if( b_res ) | |
| - { | |
| - s += sprintf( s, "%dx%d ", p->i_width, p->i_height ); | |
| - s += sprintf( s, "fps=%u/%u ", p->i_fps_num, p->i_fps_den ); | |
| - s += sprintf( s, "timebase=%u/%u ", p->i_timebase_num, p->i_timebase_den ); | |
| - s += sprintf( s, "bitdepth=%d ", BIT_DEPTH ); | |
| - } | |
| - | |
| - if( p->b_opencl ) | |
| - s += sprintf( s, "opencl=%d ", p->b_opencl ); | |
| - s += sprintf( s, "cabac=%d", p->b_cabac ); | |
| - s += sprintf( s, " ref=%d", p->i_frame_reference ); | |
| - s += sprintf( s, " deblock=%d:%d:%d", p->b_deblocking_filter, | |
| - p->i_deblocking_filter_alphac0, p->i_deblocking_filter_beta ); | |
| - s += sprintf( s, " analyse=%#x:%#x", p->analyse.intra, p->analyse.inter ); | |
| - s += sprintf( s, " me=%s", x264_motion_est_names[ p->analyse.i_me_method ] ); | |
| - s += sprintf( s, " subme=%d", p->analyse.i_subpel_refine ); | |
| - s += sprintf( s, " psy=%d", p->analyse.b_psy ); | |
| - if( p->analyse.b_psy ) | |
| - s += sprintf( s, " psy_rd=%.2f:%.2f", p->analyse.f_psy_rd, p->analyse.f_psy_trellis ); | |
| - s += sprintf( s, " mixed_ref=%d", p->analyse.b_mixed_references ); | |
| - s += sprintf( s, " me_range=%d", p->analyse.i_me_range ); | |
| - s += sprintf( s, " chroma_me=%d", p->analyse.b_chroma_me ); | |
| - s += sprintf( s, " trellis=%d", p->analyse.i_trellis ); | |
| - s += sprintf( s, " 8x8dct=%d", p->analyse.b_transform_8x8 ); | |
| - s += sprintf( s, " cqm=%d", p->i_cqm_preset ); | |
| - s += sprintf( s, " deadzone=%d,%d", p->analyse.i_luma_deadzone[0], p->analyse.i_luma_deadzone[1] ); | |
| - s += sprintf( s, " fast_pskip=%d", p->analyse.b_fast_pskip ); | |
| - s += sprintf( s, " chroma_qp_offset=%d", p->analyse.i_chroma_qp_offset ); | |
| - s += sprintf( s, " threads=%d", p->i_threads ); | |
| - s += sprintf( s, " lookahead_threads=%d", p->i_lookahead_threads ); | |
| - s += sprintf( s, " sliced_threads=%d", p->b_sliced_threads ); | |
| - if( p->i_slice_count ) | |
| - s += sprintf( s, " slices=%d", p->i_slice_count ); | |
| - if( p->i_slice_count_max ) | |
| - s += sprintf( s, " slices_max=%d", p->i_slice_count_max ); | |
| - if( p->i_slice_max_size ) | |
| - s += sprintf( s, " slice_max_size=%d", p->i_slice_max_size ); | |
| - if( p->i_slice_max_mbs ) | |
| - s += sprintf( s, " slice_max_mbs=%d", p->i_slice_max_mbs ); | |
| - if( p->i_slice_min_mbs ) | |
| - s += sprintf( s, " slice_min_mbs=%d", p->i_slice_min_mbs ); | |
| - s += sprintf( s, " nr=%d", p->analyse.i_noise_reduction ); | |
| - s += sprintf( s, " decimate=%d", p->analyse.b_dct_decimate ); | |
| - s += sprintf( s, " interlaced=%s", p->b_interlaced ? p->b_tff ? "tff" : "bff" : p->b_fake_interlaced ? "fake" : "0" ); | |
| - s += sprintf( s, " bluray_compat=%d", p->b_bluray_compat ); | |
| - if( p->b_stitchable ) | |
| - s += sprintf( s, " stitchable=%d", p->b_stitchable ); | |
| - | |
| - s += sprintf( s, " constrained_intra=%d", p->b_constrained_intra ); | |
| - | |
| - s += sprintf( s, " bframes=%d", p->i_bframe ); | |
| - if( p->i_bframe ) | |
| - { | |
| - s += sprintf( s, " b_pyramid=%d b_adapt=%d b_bias=%d direct=%d weightb=%d open_gop=%d", | |
| - p->i_bframe_pyramid, p->i_bframe_adaptive, p->i_bframe_bias, | |
| - p->analyse.i_direct_mv_pred, p->analyse.b_weighted_bipred, p->b_open_gop ); | |
| - } | |
| - s += sprintf( s, " weightp=%d", p->analyse.i_weighted_pred > 0 ? p->analyse.i_weighted_pred : 0 ); | |
| - | |
| - if( p->i_keyint_max == X264_KEYINT_MAX_INFINITE ) | |
| - s += sprintf( s, " keyint=infinite" ); | |
| - else | |
| - s += sprintf( s, " keyint=%d", p->i_keyint_max ); | |
| - s += sprintf( s, " keyint_min=%d scenecut=%d intra_refresh=%d", | |
| - p->i_keyint_min, p->i_scenecut_threshold, p->b_intra_refresh ); | |
| - | |
| - if( p->rc.b_mb_tree || p->rc.i_vbv_buffer_size ) | |
| - s += sprintf( s, " rc_lookahead=%d", p->rc.i_lookahead ); | |
| - | |
| - s += sprintf( s, " rc=%s mbtree=%d", p->rc.i_rc_method == X264_RC_ABR ? | |
| - ( p->rc.b_stat_read ? "2pass" : p->rc.i_vbv_max_bitrate == p->rc.i_bitrate ? "cbr" : "abr" ) | |
| - : p->rc.i_rc_method == X264_RC_CRF ? "crf" : "cqp", p->rc.b_mb_tree ); | |
| - if( p->rc.i_rc_method == X264_RC_ABR || p->rc.i_rc_method == X264_RC_CRF ) | |
| - { | |
| - if( p->rc.i_rc_method == X264_RC_CRF ) | |
| - s += sprintf( s, " crf=%.1f", p->rc.f_rf_constant ); | |
| - else | |
| - s += sprintf( s, " bitrate=%d ratetol=%.1f", | |
| - p->rc.i_bitrate, p->rc.f_rate_tolerance ); | |
| - s += sprintf( s, " qcomp=%.2f qpmin=%d qpmax=%d qpstep=%d", | |
| - p->rc.f_qcompress, p->rc.i_qp_min, p->rc.i_qp_max, p->rc.i_qp_step ); | |
| - if( p->rc.b_stat_read ) | |
| - s += sprintf( s, " cplxblur=%.1f qblur=%.1f", | |
| - p->rc.f_complexity_blur, p->rc.f_qblur ); | |
| - if( p->rc.i_vbv_buffer_size ) | |
| - { | |
| - s += sprintf( s, " vbv_maxrate=%d vbv_bufsize=%d", | |
| - p->rc.i_vbv_max_bitrate, p->rc.i_vbv_buffer_size ); | |
| - if( p->rc.i_rc_method == X264_RC_CRF ) | |
| - s += sprintf( s, " crf_max=%.1f", p->rc.f_rf_constant_max ); | |
| - } | |
| - } | |
| - else if( p->rc.i_rc_method == X264_RC_CQP ) | |
| - s += sprintf( s, " qp=%d", p->rc.i_qp_constant ); | |
| - | |
| - if( p->rc.i_vbv_buffer_size ) | |
| - s += sprintf( s, " nal_hrd=%s filler=%d", x264_nal_hrd_names[p->i_nal_hrd], p->rc.b_filler ); | |
| - if( p->crop_rect.i_left | p->crop_rect.i_top | p->crop_rect.i_right | p->crop_rect.i_bottom ) | |
| - s += sprintf( s, " crop_rect=%u,%u,%u,%u", p->crop_rect.i_left, p->crop_rect.i_top, | |
| - p->crop_rect.i_right, p->crop_rect.i_bottom ); | |
| - if( p->i_frame_packing >= 0 ) | |
| - s += sprintf( s, " frame-packing=%d", p->i_frame_packing ); | |
| - | |
| - if( !(p->rc.i_rc_method == X264_RC_CQP && p->rc.i_qp_constant == 0) ) | |
| - { | |
| - s += sprintf( s, " ip_ratio=%.2f", p->rc.f_ip_factor ); | |
| - if( p->i_bframe && !p->rc.b_mb_tree ) | |
| - s += sprintf( s, " pb_ratio=%.2f", p->rc.f_pb_factor ); | |
| - s += sprintf( s, " aq=%d", p->rc.i_aq_mode ); | |
| - if( p->rc.i_aq_mode ) | |
| - s += sprintf( s, ":%.2f", p->rc.f_aq_strength ); | |
| - if( p->rc.psz_zones ) | |
| - s += sprintf( s, " zones=%s", p->rc.psz_zones ); | |
| - else if( p->rc.i_zones ) | |
| - s += sprintf( s, " zones" ); | |
| - } | |
| - | |
| - return buf; | |
| -} | |
| - | |
| diff -ur x264-go/x264c/external/x264/common/common.h x264-go.new/x264c/external/x264/common/common.h | |
| --- x264-go/x264c/external/x264/common/common.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/common.h 2020-06-06 15:29:13.027052466 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * common.h: misc common functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -27,101 +27,46 @@ | |
| #ifndef X264_COMMON_H | |
| #define X264_COMMON_H | |
| +#include "base.h" | |
| + | |
| +/* Macros for templating function calls according to bit depth */ | |
| +#define x264_template(w) x264_glue3(x264, BIT_DEPTH, w) | |
| + | |
| +/**************************************************************************** | |
| + * API Templates | |
| + ****************************************************************************/ | |
| +//#define x264_nal_encode x264_template(nal_encode) | |
| +//#define x264_encoder_reconfig x264_template(encoder_reconfig) | |
| +//#define x264_encoder_parameters x264_template(encoder_parameters) | |
| +//#define x264_encoder_headers x264_template(encoder_headers) | |
| +//#define x264_encoder_encode x264_template(encoder_encode) | |
| +//#define x264_encoder_close x264_template(encoder_close) | |
| +//#define x264_encoder_delayed_frames x264_template(encoder_delayed_frames) | |
| +//#define x264_encoder_maximum_delayed_frames x264_template(encoder_maximum_delayed_frames) | |
| +//#define x264_encoder_intra_refresh x264_template(encoder_intra_refresh) | |
| +//#define x264_encoder_invalidate_reference x264_template(encoder_invalidate_reference) | |
| + | |
| +/* This undef allows to rename the external symbol and force link failure in case | |
| + * of incompatible libraries. Then the define enables templating as above. */ | |
| +//#undef x264_encoder_open | |
| +//#define x264_encoder_open x264_template(encoder_open) | |
| + | |
| /**************************************************************************** | |
| * Macros | |
| ****************************************************************************/ | |
| -#define X264_MIN(a,b) ( (a)<(b) ? (a) : (b) ) | |
| -#define X264_MAX(a,b) ( (a)>(b) ? (a) : (b) ) | |
| -#define X264_MIN3(a,b,c) X264_MIN((a),X264_MIN((b),(c))) | |
| -#define X264_MAX3(a,b,c) X264_MAX((a),X264_MAX((b),(c))) | |
| -#define X264_MIN4(a,b,c,d) X264_MIN((a),X264_MIN3((b),(c),(d))) | |
| -#define X264_MAX4(a,b,c,d) X264_MAX((a),X264_MAX3((b),(c),(d))) | |
| -#define XCHG(type,a,b) do { type t = a; a = b; b = t; } while( 0 ) | |
| -#define IS_DISPOSABLE(type) ( type == X264_TYPE_B ) | |
| -#define FIX8(f) ((int)(f*(1<<8)+.5)) | |
| -#define ALIGN(x,a) (((x)+((a)-1))&~((a)-1)) | |
| -#define ARRAY_ELEMS(a) ((sizeof(a))/(sizeof(a[0]))) | |
| - | |
| -#define CHECKED_MALLOC( var, size )\ | |
| -do {\ | |
| - var = x264_malloc( size );\ | |
| - if( !var )\ | |
| - goto fail;\ | |
| -} while( 0 ) | |
| -#define CHECKED_MALLOCZERO( var, size )\ | |
| -do {\ | |
| - CHECKED_MALLOC( var, size );\ | |
| - memset( var, 0, size );\ | |
| -} while( 0 ) | |
| - | |
| -/* Macros for merging multiple allocations into a single large malloc, for improved | |
| - * use with huge pages. */ | |
| - | |
| -/* Needs to be enough to contain any set of buffers that use combined allocations */ | |
| -#define PREALLOC_BUF_SIZE 1024 | |
| - | |
| -#define PREALLOC_INIT\ | |
| - int prealloc_idx = 0;\ | |
| - size_t prealloc_size = 0;\ | |
| - uint8_t **preallocs[PREALLOC_BUF_SIZE]; | |
| - | |
| -#define PREALLOC( var, size )\ | |
| -do {\ | |
| - var = (void*)prealloc_size;\ | |
| - preallocs[prealloc_idx++] = (uint8_t**)&var;\ | |
| - prealloc_size += ALIGN(size, NATIVE_ALIGN);\ | |
| -} while( 0 ) | |
| - | |
| -#define PREALLOC_END( ptr )\ | |
| -do {\ | |
| - CHECKED_MALLOC( ptr, prealloc_size );\ | |
| - while( prealloc_idx-- )\ | |
| - *preallocs[prealloc_idx] += (intptr_t)ptr;\ | |
| -} while( 0 ) | |
| - | |
| -#define ARRAY_SIZE(array) (sizeof(array)/sizeof(array[0])) | |
| - | |
| -#define X264_BFRAME_MAX 16 | |
| -#define X264_REF_MAX 16 | |
| -#define X264_THREAD_MAX 128 | |
| -#define X264_LOOKAHEAD_THREAD_MAX 16 | |
| #define X264_PCM_COST (FRAME_SIZE(256*BIT_DEPTH)+16) | |
| -#define X264_LOOKAHEAD_MAX 250 | |
| #define QP_BD_OFFSET (6*(BIT_DEPTH-8)) | |
| #define QP_MAX_SPEC (51+QP_BD_OFFSET) | |
| #define QP_MAX (QP_MAX_SPEC+18) | |
| -#define QP_MAX_MAX (51+2*6+18) | |
| #define PIXEL_MAX ((1 << BIT_DEPTH)-1) | |
| // arbitrary, but low because SATD scores are 1/4 normal | |
| #define X264_LOOKAHEAD_QP (12+QP_BD_OFFSET) | |
| #define SPEC_QP(x) X264_MIN((x), QP_MAX_SPEC) | |
| -// number of pixels (per thread) in progress at any given time. | |
| -// 16 for the macroblock in progress + 3 for deblocking + 3 for motion compensation filter + 2 for extra safety | |
| -#define X264_THREAD_HEIGHT 24 | |
| - | |
| -/* WEIGHTP_FAKE is set when mb_tree & psy are enabled, but normal weightp is disabled | |
| - * (such as in baseline). It checks for fades in lookahead and adjusts qp accordingly | |
| - * to increase quality. Defined as (-1) so that if(i_weighted_pred > 0) is true only when | |
| - * real weights are being used. */ | |
| - | |
| -#define X264_WEIGHTP_FAKE (-1) | |
| - | |
| #define NALU_OVERHEAD 5 // startcode + NAL type costs 5 bytes per frame | |
| #define FILLER_OVERHEAD (NALU_OVERHEAD+1) | |
| #define SEI_OVERHEAD (NALU_OVERHEAD - (h->param.b_annexb && !h->param.i_avcintra_class && (h->out.i_nal-1))) | |
| -/**************************************************************************** | |
| - * Includes | |
| - ****************************************************************************/ | |
| -#include "osdep.h" | |
| -#include <stdarg.h> | |
| -#include <stddef.h> | |
| -#include <stdlib.h> | |
| -#include <string.h> | |
| -#include <assert.h> | |
| -#include <limits.h> | |
| - | |
| #if HAVE_INTERLACED | |
| # define MB_INTERLACED h->mb.b_interlaced | |
| # define SLICE_MBAFF h->sh.b_mbaff | |
| @@ -141,29 +86,10 @@ | |
| # define CHROMA_V_SHIFT h->mb.chroma_v_shift | |
| #endif | |
| -#define CHROMA_SIZE(s) ((s)>>(CHROMA_H_SHIFT+CHROMA_V_SHIFT)) | |
| +#define CHROMA_SIZE(s) (CHROMA_FORMAT ? (s)>>(CHROMA_H_SHIFT+CHROMA_V_SHIFT) : 0) | |
| #define FRAME_SIZE(s) ((s)+2*CHROMA_SIZE(s)) | |
| #define CHROMA444 (CHROMA_FORMAT == CHROMA_444) | |
| -/* Unions for type-punning. | |
| - * Mn: load or store n bits, aligned, native-endian | |
| - * CPn: copy n bits, aligned, native-endian | |
| - * we don't use memcpy for CPn because memcpy's args aren't assumed to be aligned */ | |
| -typedef union { uint16_t i; uint8_t c[2]; } MAY_ALIAS x264_union16_t; | |
| -typedef union { uint32_t i; uint16_t b[2]; uint8_t c[4]; } MAY_ALIAS x264_union32_t; | |
| -typedef union { uint64_t i; uint32_t a[2]; uint16_t b[4]; uint8_t c[8]; } MAY_ALIAS x264_union64_t; | |
| -typedef struct { uint64_t i[2]; } x264_uint128_t; | |
| -typedef union { x264_uint128_t i; uint64_t a[2]; uint32_t b[4]; uint16_t c[8]; uint8_t d[16]; } MAY_ALIAS x264_union128_t; | |
| -#define M16(src) (((x264_union16_t*)(src))->i) | |
| -#define M32(src) (((x264_union32_t*)(src))->i) | |
| -#define M64(src) (((x264_union64_t*)(src))->i) | |
| -#define M128(src) (((x264_union128_t*)(src))->i) | |
| -#define M128_ZERO ((x264_uint128_t){{0,0}}) | |
| -#define CP16(dst,src) M16(dst) = M16(src) | |
| -#define CP32(dst,src) M32(dst) = M32(src) | |
| -#define CP64(dst,src) M64(dst) = M64(src) | |
| -#define CP128(dst,src) M128(dst) = M128(src) | |
| - | |
| #if HIGH_BIT_DEPTH | |
| typedef uint16_t pixel; | |
| typedef uint64_t pixel4; | |
| @@ -182,55 +108,13 @@ | |
| # define MPIXEL_X4(src) M32(src) | |
| #endif | |
| -#define BIT_DEPTH X264_BIT_DEPTH | |
| +#define SIZEOF_PIXEL ((int)sizeof(pixel)) | |
| #define CPPIXEL_X4(dst,src) MPIXEL_X4(dst) = MPIXEL_X4(src) | |
| -#define X264_SCAN8_LUMA_SIZE (5*8) | |
| -#define X264_SCAN8_SIZE (X264_SCAN8_LUMA_SIZE*3) | |
| -#define X264_SCAN8_0 (4+1*8) | |
| - | |
| -/* Scan8 organization: | |
| - * 0 1 2 3 4 5 6 7 | |
| - * 0 DY y y y y y | |
| - * 1 y Y Y Y Y | |
| - * 2 y Y Y Y Y | |
| - * 3 y Y Y Y Y | |
| - * 4 y Y Y Y Y | |
| - * 5 DU u u u u u | |
| - * 6 u U U U U | |
| - * 7 u U U U U | |
| - * 8 u U U U U | |
| - * 9 u U U U U | |
| - * 10 DV v v v v v | |
| - * 11 v V V V V | |
| - * 12 v V V V V | |
| - * 13 v V V V V | |
| - * 14 v V V V V | |
| - * DY/DU/DV are for luma/chroma DC. | |
| - */ | |
| - | |
| -#define LUMA_DC 48 | |
| -#define CHROMA_DC 49 | |
| - | |
| -static const uint8_t x264_scan8[16*3 + 3] = | |
| -{ | |
| - 4+ 1*8, 5+ 1*8, 4+ 2*8, 5+ 2*8, | |
| - 6+ 1*8, 7+ 1*8, 6+ 2*8, 7+ 2*8, | |
| - 4+ 3*8, 5+ 3*8, 4+ 4*8, 5+ 4*8, | |
| - 6+ 3*8, 7+ 3*8, 6+ 4*8, 7+ 4*8, | |
| - 4+ 6*8, 5+ 6*8, 4+ 7*8, 5+ 7*8, | |
| - 6+ 6*8, 7+ 6*8, 6+ 7*8, 7+ 7*8, | |
| - 4+ 8*8, 5+ 8*8, 4+ 9*8, 5+ 9*8, | |
| - 6+ 8*8, 7+ 8*8, 6+ 9*8, 7+ 9*8, | |
| - 4+11*8, 5+11*8, 4+12*8, 5+12*8, | |
| - 6+11*8, 7+11*8, 6+12*8, 7+12*8, | |
| - 4+13*8, 5+13*8, 4+14*8, 5+14*8, | |
| - 6+13*8, 7+13*8, 6+14*8, 7+14*8, | |
| - 0+ 0*8, 0+ 5*8, 0+10*8 | |
| -}; | |
| - | |
| -#include "x264.h" | |
| +/**************************************************************************** | |
| + * Includes | |
| + ****************************************************************************/ | |
| #if HAVE_OPENCL | |
| #include "opencl.h" | |
| #endif | |
| @@ -243,30 +127,19 @@ | |
| #include "frame.h" | |
| #include "dct.h" | |
| #include "quant.h" | |
| -#include "cpu.h" | |
| #include "threadpool.h" | |
| /**************************************************************************** | |
| * General functions | |
| ****************************************************************************/ | |
| -/* x264_malloc : will do or emulate a memalign | |
| - * you have to use x264_free for buffers allocated with x264_malloc */ | |
| -void *x264_malloc( int ); | |
| -void x264_free( void * ); | |
| - | |
| -/* x264_slurp_file: malloc space for the whole file and read it */ | |
| -char *x264_slurp_file( const char *filename ); | |
| - | |
| -/* x264_param2string: return a (malloced) string containing most of | |
| - * the encoding options */ | |
| -char *x264_param2string( x264_param_t *p, int b_res ); | |
| /* log */ | |
| +#define x264_log x264_template(log) | |
| void x264_log( x264_t *h, int i_level, const char *psz_fmt, ... ); | |
| -void x264_reduce_fraction( uint32_t *n, uint32_t *d ); | |
| -void x264_reduce_fraction64( uint64_t *n, uint64_t *d ); | |
| +#define x264_cavlc_init x264_template(cavlc_init) | |
| void x264_cavlc_init( x264_t *h ); | |
| +#define x264_cabac_init x264_template(cabac_init) | |
| void x264_cabac_init( x264_t *h ); | |
| static ALWAYS_INLINE pixel x264_clip_pixel( int x ) | |
| @@ -274,97 +147,9 @@ | |
| return ( (x & ~PIXEL_MAX) ? (-x)>>31 & PIXEL_MAX : x ); | |
| } | |
| -static ALWAYS_INLINE int x264_clip3( int v, int i_min, int i_max ) | |
| -{ | |
| - return ( (v < i_min) ? i_min : (v > i_max) ? i_max : v ); | |
| -} | |
| - | |
| -static ALWAYS_INLINE double x264_clip3f( double v, double f_min, double f_max ) | |
| -{ | |
| - return ( (v < f_min) ? f_min : (v > f_max) ? f_max : v ); | |
| -} | |
| - | |
| -static ALWAYS_INLINE int x264_median( int a, int b, int c ) | |
| -{ | |
| - int t = (a-b)&((a-b)>>31); | |
| - a -= t; | |
| - b += t; | |
| - b -= (b-c)&((b-c)>>31); | |
| - b += (a-b)&((a-b)>>31); | |
| - return b; | |
| -} | |
| - | |
| -static ALWAYS_INLINE void x264_median_mv( int16_t *dst, int16_t *a, int16_t *b, int16_t *c ) | |
| -{ | |
| - dst[0] = x264_median( a[0], b[0], c[0] ); | |
| - dst[1] = x264_median( a[1], b[1], c[1] ); | |
| -} | |
| - | |
| -static ALWAYS_INLINE int x264_predictor_difference( int16_t (*mvc)[2], intptr_t i_mvc ) | |
| -{ | |
| - int sum = 0; | |
| - for( int i = 0; i < i_mvc-1; i++ ) | |
| - { | |
| - sum += abs( mvc[i][0] - mvc[i+1][0] ) | |
| - + abs( mvc[i][1] - mvc[i+1][1] ); | |
| - } | |
| - return sum; | |
| -} | |
| - | |
| -static ALWAYS_INLINE uint16_t x264_cabac_mvd_sum( uint8_t *mvdleft, uint8_t *mvdtop ) | |
| -{ | |
| - int amvd0 = mvdleft[0] + mvdtop[0]; | |
| - int amvd1 = mvdleft[1] + mvdtop[1]; | |
| - amvd0 = (amvd0 > 2) + (amvd0 > 32); | |
| - amvd1 = (amvd1 > 2) + (amvd1 > 32); | |
| - return amvd0 + (amvd1<<8); | |
| -} | |
| - | |
| -extern const uint8_t x264_exp2_lut[64]; | |
| -extern const float x264_log2_lut[128]; | |
| -extern const float x264_log2_lz_lut[32]; | |
| - | |
| -/* Not a general-purpose function; multiplies input by -1/6 to convert | |
| - * qp to qscale. */ | |
| -static ALWAYS_INLINE int x264_exp2fix8( float x ) | |
| -{ | |
| - int i = x*(-64.f/6.f) + 512.5f; | |
| - if( i < 0 ) return 0; | |
| - if( i > 1023 ) return 0xffff; | |
| - return (x264_exp2_lut[i&63]+256) << (i>>6) >> 8; | |
| -} | |
| - | |
| -static ALWAYS_INLINE float x264_log2( uint32_t x ) | |
| -{ | |
| - int lz = x264_clz( x ); | |
| - return x264_log2_lut[(x<<lz>>24)&0x7f] + x264_log2_lz_lut[lz]; | |
| -} | |
| - | |
| /**************************************************************************** | |
| * | |
| ****************************************************************************/ | |
| -enum slice_type_e | |
| -{ | |
| - SLICE_TYPE_P = 0, | |
| - SLICE_TYPE_B = 1, | |
| - SLICE_TYPE_I = 2, | |
| -}; | |
| - | |
| -static const char slice_type_to_char[] = { 'P', 'B', 'I' }; | |
| - | |
| -enum sei_payload_type_e | |
| -{ | |
| - SEI_BUFFERING_PERIOD = 0, | |
| - SEI_PIC_TIMING = 1, | |
| - SEI_PAN_SCAN_RECT = 2, | |
| - SEI_FILLER = 3, | |
| - SEI_USER_DATA_REGISTERED = 4, | |
| - SEI_USER_DATA_UNREGISTERED = 5, | |
| - SEI_RECOVERY_POINT = 6, | |
| - SEI_DEC_REF_PIC_MARKING = 7, | |
| - SEI_FRAME_PACKING = 45, | |
| -}; | |
| - | |
| typedef struct | |
| { | |
| x264_sps_t *sps; | |
| @@ -560,9 +345,14 @@ | |
| udctcoef (*quant8_bias0[4])[64]; /* [4][QP_MAX_SPEC+1][64] */ | |
| udctcoef (*nr_offset_emergency)[4][64]; | |
| - /* mv/ref cost arrays. */ | |
| + /* mv/ref/mode cost arrays. */ | |
| uint16_t *cost_mv[QP_MAX+1]; | |
| uint16_t *cost_mv_fpel[QP_MAX+1][4]; | |
| + struct | |
| + { | |
| + uint16_t ref[QP_MAX+1][3][33]; | |
| + uint16_t i4x4_mode[QP_MAX+1][17]; | |
| + } *cost_table; | |
| const uint8_t *chroma_qp_table; /* includes both the nonlinear luma->chroma mapping and chroma_qp_offset */ | |
| @@ -740,7 +530,7 @@ | |
| int16_t (*mvr[2][X264_REF_MAX*2])[2];/* 16x16 mv for each possible ref */ | |
| int8_t *skipbp; /* block pattern for SKIP or DIRECT (sub)mbs. B-frames + cabac only */ | |
| int8_t *mb_transform_size; /* transform_size_8x8_flag of each mb */ | |
| - uint32_t *slice_table; /* sh->first_mb of the slice that the indexed mb is part of */ | |
| + int32_t *slice_table; /* sh->first_mb of the slice that the indexed mb is part of */ | |
| uint8_t *field; | |
| /* buffer for weighted versions of the reference frames */ | |
| @@ -781,16 +571,16 @@ | |
| ALIGNED_64( pixel fdec_buf[54*FDEC_STRIDE] ); | |
| /* i4x4 and i8x8 backup data, for skipping the encode stage when possible */ | |
| - ALIGNED_16( pixel i4x4_fdec_buf[16*16] ); | |
| - ALIGNED_16( pixel i8x8_fdec_buf[16*16] ); | |
| + ALIGNED_32( pixel i4x4_fdec_buf[16*16] ); | |
| + ALIGNED_32( pixel i8x8_fdec_buf[16*16] ); | |
| ALIGNED_64( dctcoef i8x8_dct_buf[3][64] ); | |
| ALIGNED_64( dctcoef i4x4_dct_buf[15][16] ); | |
| uint32_t i4x4_nnz_buf[4]; | |
| uint32_t i8x8_nnz_buf[4]; | |
| /* Psy trellis DCT data */ | |
| - ALIGNED_16( dctcoef fenc_dct8[4][64] ); | |
| - ALIGNED_16( dctcoef fenc_dct4[16][16] ); | |
| + ALIGNED_64( dctcoef fenc_dct8[4][64] ); | |
| + ALIGNED_64( dctcoef fenc_dct4[16][16] ); | |
| /* Psy RD SATD/SA8D scores cache */ | |
| ALIGNED_64( uint32_t fenc_satd_cache[32] ); | |
| @@ -979,7 +769,7 @@ | |
| // included at the end because it needs x264_t | |
| #include "macroblock.h" | |
| -static int ALWAYS_INLINE x264_predictor_roundclip( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| +static ALWAYS_INLINE int x264_predictor_roundclip( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| { | |
| int cnt = 0; | |
| for( int i = 0; i < i_mvc; i++ ) | |
| @@ -995,7 +785,7 @@ | |
| return cnt; | |
| } | |
| -static int ALWAYS_INLINE x264_predictor_clip( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| +static ALWAYS_INLINE int x264_predictor_clip( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| { | |
| int cnt = 0; | |
| int qpel_limit[4] = {mv_limit[0][0] << 2, mv_limit[0][1] << 2, mv_limit[1][0] << 2, mv_limit[1][1] << 2}; | |
| @@ -1019,4 +809,3 @@ | |
| #include "rectangle.h" | |
| #endif | |
| - | |
| diff -ur x264-go/x264c/external/x264/common/cpu.c x264-go.new/x264c/external/x264/common/cpu.c | |
| --- x264-go/x264c/external/x264/common/cpu.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/cpu.c 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cpu.c: cpu detection | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -25,7 +25,7 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#include "common.h" | |
| +#include "base.h" | |
| #if HAVE_POSIXTHREAD && SYS_LINUX | |
| #include <sched.h> | |
| @@ -45,7 +45,7 @@ | |
| const x264_cpu_name_t x264_cpu_names[] = | |
| { | |
| -#if HAVE_MMX | |
| +#if ARCH_X86 || ARCH_X86_64 | |
| // {"MMX", X264_CPU_MMX}, // we don't support asm on mmx1 cpus anymore | |
| #define MMX2 X264_CPU_MMX|X264_CPU_MMX2 | |
| {"MMX2", MMX2}, | |
| @@ -97,7 +97,7 @@ | |
| {"", 0}, | |
| }; | |
| -#if (ARCH_PPC && SYS_LINUX) || (ARCH_ARM && !HAVE_NEON) | |
| +#if (HAVE_ALTIVEC && SYS_LINUX) || (HAVE_ARMV6 && !HAVE_NEON) | |
| #include <signal.h> | |
| #include <setjmp.h> | |
| static sigjmp_buf jmpbuf; | |
| @@ -235,16 +235,8 @@ | |
| int model = ((eax>>4)&0xf) + ((eax>>12)&0xf0); | |
| if( family == 6 ) | |
| { | |
| - /* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah") | |
| - * theoretically support sse2, but it's significantly slower than mmx for | |
| - * almost all of x264's functions, so let's just pretend they don't. */ | |
| - if( model == 9 || model == 13 || model == 14 ) | |
| - { | |
| - cpu &= ~(X264_CPU_SSE2|X264_CPU_SSE3); | |
| - assert(!(cpu&(X264_CPU_SSSE3|X264_CPU_SSE4))); | |
| - } | |
| /* Detect Atom CPU */ | |
| - else if( model == 28 ) | |
| + if( model == 28 ) | |
| { | |
| cpu |= X264_CPU_SLOW_ATOM; | |
| cpu |= X264_CPU_SLOW_PSHUFB; | |
| @@ -296,7 +288,7 @@ | |
| else if( cache == 64 ) | |
| cpu |= X264_CPU_CACHELINE_64; | |
| else | |
| - x264_log( NULL, X264_LOG_WARNING, "unable to determine cacheline size\n" ); | |
| + x264_log_internal( X264_LOG_WARNING, "unable to determine cacheline size\n" ); | |
| } | |
| #if STACK_ALIGNMENT < 16 | |
| @@ -306,7 +298,7 @@ | |
| return cpu; | |
| } | |
| -#elif ARCH_PPC && HAVE_ALTIVEC | |
| +#elif HAVE_ALTIVEC | |
| #if SYS_MACOSX || SYS_OPENBSD || SYS_FREEBSD | |
| #include <sys/sysctl.h> | |
| @@ -363,15 +355,14 @@ | |
| } | |
| #endif | |
| -#elif ARCH_ARM | |
| +#elif HAVE_ARMV6 | |
| void x264_cpu_neon_test( void ); | |
| int x264_cpu_fast_neon_mrc_test( void ); | |
| uint32_t x264_cpu_detect( void ) | |
| { | |
| - int flags = 0; | |
| -#if HAVE_ARMV6 | |
| + uint32_t flags = 0; | |
| flags |= X264_CPU_ARMV6; | |
| // don't do this hack if compiled with -mfpu=neon | |
| @@ -404,26 +395,25 @@ | |
| flags |= x264_cpu_fast_neon_mrc_test() ? X264_CPU_FAST_NEON_MRC : 0; | |
| #endif | |
| // TODO: write dual issue test? currently it's A8 (dual issue) vs. A9 (fast mrc) | |
| -#endif | |
| return flags; | |
| } | |
| -#elif ARCH_AARCH64 | |
| +#elif HAVE_AARCH64 | |
| uint32_t x264_cpu_detect( void ) | |
| { | |
| +#if HAVE_NEON | |
| return X264_CPU_ARMV8 | X264_CPU_NEON; | |
| +#else | |
| + return X264_CPU_ARMV8; | |
| +#endif | |
| } | |
| -#elif ARCH_MIPS | |
| +#elif HAVE_MSA | |
| uint32_t x264_cpu_detect( void ) | |
| { | |
| - uint32_t flags = 0; | |
| -#if HAVE_MSA | |
| - flags |= X264_CPU_MSA; | |
| -#endif | |
| - return flags; | |
| + return X264_CPU_MSA; | |
| } | |
| #else | |
| @@ -459,7 +449,7 @@ | |
| return CPU_COUNT(&p_aff); | |
| #else | |
| int np = 0; | |
| - for( unsigned int bit = 0; bit < 8 * sizeof(p_aff); bit++ ) | |
| + for( size_t bit = 0; bit < 8 * sizeof(p_aff); bit++ ) | |
| np += (((uint8_t *)&p_aff)[bit / 8] >> (bit % 8)) & 1; | |
| return np; | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/cpu.h x264-go.new/x264c/external/x264/common/cpu.h | |
| --- x264-go/x264c/external/x264/common/cpu.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/cpu.h 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cpu.h: cpu detection | |
| ***************************************************************************** | |
| - * Copyright (C) 2004-2017 x264 project | |
| + * Copyright (C) 2004-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * | |
| @@ -26,8 +26,8 @@ | |
| #ifndef X264_CPU_H | |
| #define X264_CPU_H | |
| -uint32_t x264_cpu_detect( void ); | |
| -int x264_cpu_num_processors( void ); | |
| +X264_API uint32_t x264_cpu_detect( void ); | |
| +X264_API int x264_cpu_num_processors( void ); | |
| void x264_cpu_emms( void ); | |
| void x264_cpu_sfence( void ); | |
| #if HAVE_MMX | |
| @@ -46,28 +46,11 @@ | |
| #endif | |
| #define x264_sfence x264_cpu_sfence | |
| -/* kludge: | |
| - * gcc can't give variables any greater alignment than the stack frame has. | |
| - * We need 32 byte alignment for AVX2, so here we make sure that the stack is | |
| - * aligned to 32 bytes. | |
| - * gcc 4.2 introduced __attribute__((force_align_arg_pointer)) to fix this | |
| - * problem, but I don't want to require such a new version. | |
| - * aligning to 32 bytes only works if the compiler supports keeping that | |
| - * alignment between functions (osdep.h handles manual alignment of arrays | |
| - * if it doesn't). | |
| - */ | |
| -#if HAVE_MMX && (STACK_ALIGNMENT > 16 || (ARCH_X86 && STACK_ALIGNMENT > 4)) | |
| -intptr_t x264_stack_align( void (*func)(), ... ); | |
| -#define x264_stack_align(func,...) x264_stack_align((void (*)())func, __VA_ARGS__) | |
| -#else | |
| -#define x264_stack_align(func,...) func(__VA_ARGS__) | |
| -#endif | |
| - | |
| typedef struct | |
| { | |
| const char *name; | |
| uint32_t flags; | |
| } x264_cpu_name_t; | |
| -extern const x264_cpu_name_t x264_cpu_names[]; | |
| +X264_API extern const x264_cpu_name_t x264_cpu_names[]; | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/dct.c x264-go.new/x264c/external/x264/common/dct.c | |
| --- x264-go/x264c/external/x264/common/dct.c 2018-02-15 14:44:18.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/dct.c 2020-06-06 15:39:30.345068735 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * dct.c: transform and zigzag | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -29,83 +29,19 @@ | |
| #if HAVE_MMX | |
| # include "x86/dct.h" | |
| #endif | |
| -#if ARCH_PPC | |
| +#if HAVE_ALTIVEC | |
| # include "ppc/dct.h" | |
| #endif | |
| -#if ARCH_ARM | |
| +#if HAVE_ARMV6 | |
| # include "arm/dct.h" | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| # include "aarch64/dct.h" | |
| #endif | |
| -#if ARCH_MIPS | |
| +#if HAVE_MSA | |
| # include "mips/dct.h" | |
| #endif | |
| -/* the inverse of the scaling factors introduced by 8x8 fdct */ | |
| -/* uint32 is for the asm implementation of trellis. the actual values fit in uint16. */ | |
| -#define W(i) (i==0 ? FIX8(1.0000) :\ | |
| - i==1 ? FIX8(0.8859) :\ | |
| - i==2 ? FIX8(1.6000) :\ | |
| - i==3 ? FIX8(0.9415) :\ | |
| - i==4 ? FIX8(1.2651) :\ | |
| - i==5 ? FIX8(1.1910) :0) | |
| -const uint32_t x264_dct8_weight_tab[64] = { | |
| - W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - | |
| - W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1) | |
| -}; | |
| -#undef W | |
| - | |
| -#define W(i) (i==0 ? FIX8(1.76777) :\ | |
| - i==1 ? FIX8(1.11803) :\ | |
| - i==2 ? FIX8(0.70711) :0) | |
| -const uint32_t x264_dct4_weight_tab[16] = { | |
| - W(0), W(1), W(0), W(1), | |
| - W(1), W(2), W(1), W(2), | |
| - W(0), W(1), W(0), W(1), | |
| - W(1), W(2), W(1), W(2) | |
| -}; | |
| -#undef W | |
| - | |
| -/* inverse squared */ | |
| -#define W(i) (i==0 ? FIX8(3.125) :\ | |
| - i==1 ? FIX8(1.25) :\ | |
| - i==2 ? FIX8(0.5) :0) | |
| -const uint32_t x264_dct4_weight2_tab[16] = { | |
| - W(0), W(1), W(0), W(1), | |
| - W(1), W(2), W(1), W(2), | |
| - W(0), W(1), W(0), W(1), | |
| - W(1), W(2), W(1), W(2) | |
| -}; | |
| -#undef W | |
| - | |
| -#define W(i) (i==0 ? FIX8(1.00000) :\ | |
| - i==1 ? FIX8(0.78487) :\ | |
| - i==2 ? FIX8(2.56132) :\ | |
| - i==3 ? FIX8(0.88637) :\ | |
| - i==4 ? FIX8(1.60040) :\ | |
| - i==5 ? FIX8(1.41850) :0) | |
| -const uint32_t x264_dct8_weight2_tab[64] = { | |
| - W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - | |
| - W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1), | |
| - W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5), | |
| - W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1) | |
| -}; | |
| -#undef W | |
| - | |
| - | |
| static void dct4x4dc( dctcoef d[16] ) | |
| { | |
| dctcoef tmp[16]; | |
| @@ -502,7 +438,7 @@ | |
| add8x8_idct8( &dst[8*FDEC_STRIDE+8], dct[3] ); | |
| } | |
| -static void inline add4x4_idct_dc( pixel *p_dst, dctcoef dc ) | |
| +static inline void add4x4_idct_dc( pixel *p_dst, dctcoef dc ) | |
| { | |
| dc = (dc + 32) >> 6; | |
| for( int i = 0; i < 4; i++, p_dst += FDEC_STRIDE ) | |
| @@ -537,7 +473,7 @@ | |
| /**************************************************************************** | |
| * x264_dct_init: | |
| ****************************************************************************/ | |
| -void x264_dct_init( int cpu, x264_dct_function_t *dctf ) | |
| +void x264_dct_init( uint32_t cpu, x264_dct_function_t *dctf ) | |
| { | |
| dctf->sub4x4_dct = sub4x4_dct; | |
| dctf->add4x4_idct = add4x4_idct; | |
| @@ -732,6 +668,7 @@ | |
| dctf->sub16x16_dct = x264_sub16x16_dct_altivec; | |
| dctf->add8x8_idct_dc = x264_add8x8_idct_dc_altivec; | |
| + dctf->add16x16_idct_dc = x264_add16x16_idct_dc_altivec; | |
| dctf->add4x4_idct = x264_add4x4_idct_altivec; | |
| dctf->add8x8_idct = x264_add8x8_idct_altivec; | |
| @@ -746,7 +683,7 @@ | |
| } | |
| #endif | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| +#if HAVE_ARMV6 || HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| dctf->sub4x4_dct = x264_sub4x4_dct_neon; | |
| @@ -965,7 +902,7 @@ | |
| } | |
| } | |
| -void x264_zigzag_init( int cpu, x264_zigzag_function_t *pf_progressive, x264_zigzag_function_t *pf_interlaced ) | |
| +void x264_zigzag_init( uint32_t cpu, x264_zigzag_function_t *pf_progressive, x264_zigzag_function_t *pf_interlaced ) | |
| { | |
| pf_interlaced->scan_8x8 = zigzag_scan_8x8_field; | |
| pf_progressive->scan_8x8 = zigzag_scan_8x8_frame; | |
| @@ -1060,11 +997,11 @@ | |
| pf_progressive->scan_8x8 = x264_zigzag_scan_8x8_frame_altivec; | |
| } | |
| #endif | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| +#if HAVE_ARMV6 || HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| pf_progressive->scan_4x4 = x264_zigzag_scan_4x4_frame_neon; | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| pf_interlaced->scan_4x4 = x264_zigzag_scan_4x4_field_neon; | |
| pf_interlaced->scan_8x8 = x264_zigzag_scan_8x8_field_neon; | |
| pf_interlaced->sub_4x4 = x264_zigzag_sub_4x4_field_neon; | |
| @@ -1074,9 +1011,9 @@ | |
| pf_progressive->sub_4x4 = x264_zigzag_sub_4x4_frame_neon; | |
| pf_progressive->sub_4x4ac = x264_zigzag_sub_4x4ac_frame_neon; | |
| pf_progressive->sub_8x8 = x264_zigzag_sub_8x8_frame_neon; | |
| -#endif // ARCH_AARCH64 | |
| +#endif // HAVE_AARCH64 | |
| } | |
| -#endif // HAVE_ARMV6 || ARCH_AARCH64 | |
| +#endif // HAVE_ARMV6 || HAVE_AARCH64 | |
| #endif // HIGH_BIT_DEPTH | |
| pf_interlaced->interleave_8x8_cavlc = | |
| @@ -1129,13 +1066,13 @@ | |
| #endif // HIGH_BIT_DEPTH | |
| #endif | |
| #if !HIGH_BIT_DEPTH | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| pf_interlaced->interleave_8x8_cavlc = | |
| pf_progressive->interleave_8x8_cavlc = x264_zigzag_interleave_8x8_cavlc_neon; | |
| } | |
| -#endif // ARCH_AARCH64 | |
| +#endif // HAVE_AARCH64 | |
| #if HAVE_ALTIVEC | |
| if( cpu&X264_CPU_ALTIVEC ) | |
| diff -ur x264-go/x264c/external/x264/common/dct.h x264-go.new/x264c/external/x264/common/dct.h | |
| --- x264-go/x264c/external/x264/common/dct.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/dct.h 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * dct.h: transform and zigzag | |
| ***************************************************************************** | |
| - * Copyright (C) 2004-2017 x264 project | |
| + * Copyright (C) 2004-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * | |
| @@ -26,11 +26,6 @@ | |
| #ifndef X264_DCT_H | |
| #define X264_DCT_H | |
| -extern const uint32_t x264_dct4_weight_tab[16]; | |
| -extern const uint32_t x264_dct8_weight_tab[64]; | |
| -extern const uint32_t x264_dct4_weight2_tab[16]; | |
| -extern const uint32_t x264_dct8_weight2_tab[64]; | |
| - | |
| typedef struct | |
| { | |
| // pix1 stride = FENC_STRIDE | |
| @@ -74,7 +69,9 @@ | |
| } x264_zigzag_function_t; | |
| -void x264_dct_init( int cpu, x264_dct_function_t *dctf ); | |
| -void x264_zigzag_init( int cpu, x264_zigzag_function_t *pf_progressive, x264_zigzag_function_t *pf_interlaced ); | |
| +#define x264_dct_init x264_template(dct_init) | |
| +void x264_dct_init( uint32_t cpu, x264_dct_function_t *dctf ); | |
| +#define x264_zigzag_init x264_template(zigzag_init) | |
| +void x264_zigzag_init( uint32_t cpu, x264_zigzag_function_t *pf_progressive, x264_zigzag_function_t *pf_interlaced ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/deblock.c x264-go.new/x264c/external/x264/common/deblock.c | |
| --- x264-go/x264c/external/x264/common/deblock.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/deblock.c 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * deblock.c: deblocking | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -337,7 +337,7 @@ | |
| pf_intra( pix, i_stride, alpha, beta ); | |
| } | |
| -static ALWAYS_INLINE void x264_macroblock_cache_load_neighbours_deblock( x264_t *h, int mb_x, int mb_y ) | |
| +static ALWAYS_INLINE void macroblock_cache_load_neighbours_deblock( x264_t *h, int mb_x, int mb_y ) | |
| { | |
| int deblock_on_slice_edges = h->sh.i_disable_deblocking_filter_idc != 2; | |
| @@ -383,6 +383,7 @@ | |
| int qp_thresh = 15 - X264_MIN( a, b ) - X264_MAX( 0, h->pps->i_chroma_qp_index_offset ); | |
| int stridey = h->fdec->i_stride[0]; | |
| int strideuv = h->fdec->i_stride[1]; | |
| + int chroma_format = CHROMA_FORMAT; | |
| int chroma444 = CHROMA444; | |
| int chroma_height = 16 >> CHROMA_V_SHIFT; | |
| intptr_t uvdiff = chroma444 ? h->fdec->plane[2] - h->fdec->plane[1] : 1; | |
| @@ -390,7 +391,7 @@ | |
| for( int mb_x = 0; mb_x < h->mb.i_mb_width; mb_x += (~b_interlaced | mb_y)&1, mb_y ^= b_interlaced ) | |
| { | |
| x264_prefetch_fenc( h, h->fdec, mb_x, mb_y ); | |
| - x264_macroblock_cache_load_neighbours_deblock( h, mb_x, mb_y ); | |
| + macroblock_cache_load_neighbours_deblock( h, mb_x, mb_y ); | |
| int mb_xy = h->mb.i_mb_xy; | |
| int transform_8x8 = h->mb.mb_transform_size[mb_xy]; | |
| @@ -398,12 +399,13 @@ | |
| uint8_t (*bs)[8][4] = h->deblock_strength[mb_y&1][h->param.b_sliced_threads?mb_xy:mb_x]; | |
| pixel *pixy = h->fdec->plane[0] + 16*mb_y*stridey + 16*mb_x; | |
| - pixel *pixuv = h->fdec->plane[1] + chroma_height*mb_y*strideuv + 16*mb_x; | |
| + pixel *pixuv = CHROMA_FORMAT ? h->fdec->plane[1] + chroma_height*mb_y*strideuv + 16*mb_x : NULL; | |
| if( mb_y & MB_INTERLACED ) | |
| { | |
| pixy -= 15*stridey; | |
| - pixuv -= (chroma_height-1)*strideuv; | |
| + if( CHROMA_FORMAT ) | |
| + pixuv -= (chroma_height-1)*strideuv; | |
| } | |
| int stride2y = stridey << MB_INTERLACED; | |
| @@ -420,7 +422,7 @@ | |
| deblock_edge##intra( h, pixy + 4*edge*(dir?stride2y:1),\ | |
| stride2y, bs[dir][edge], qp, a, b, 0,\ | |
| h->loopf.deblock_luma##intra[dir] );\ | |
| - if( CHROMA_FORMAT == CHROMA_444 )\ | |
| + if( chroma_format == CHROMA_444 )\ | |
| {\ | |
| deblock_edge##intra( h, pixuv + 4*edge*(dir?stride2uv:1),\ | |
| stride2uv, bs[dir][edge], chroma_qp, a, b, 0,\ | |
| @@ -429,14 +431,14 @@ | |
| stride2uv, bs[dir][edge], chroma_qp, a, b, 0,\ | |
| h->loopf.deblock_luma##intra[dir] );\ | |
| }\ | |
| - else if( CHROMA_FORMAT == CHROMA_420 && !(edge & 1) )\ | |
| + else if( chroma_format == CHROMA_420 && !(edge & 1) )\ | |
| {\ | |
| deblock_edge##intra( h, pixuv + edge*(dir?2*stride2uv:4),\ | |
| stride2uv, bs[dir][edge], chroma_qp, a, b, 1,\ | |
| h->loopf.deblock_chroma##intra[dir] );\ | |
| }\ | |
| }\ | |
| - if( CHROMA_FORMAT == CHROMA_422 && (dir || !(edge & 1)) )\ | |
| + if( chroma_format == CHROMA_422 && (dir || !(edge & 1)) )\ | |
| {\ | |
| deblock_edge##intra( h, pixuv + edge*(dir?4*stride2uv:4),\ | |
| stride2uv, bs[dir][edge], chroma_qp, a, b, 1,\ | |
| @@ -463,16 +465,22 @@ | |
| if( intra_cur || IS_INTRA( h->mb.type[h->mb.i_mb_left_xy[0]] ) ) | |
| { | |
| deblock_edge_intra( h, pixy, 2*stridey, bs[0][0], luma_qp[0], a, b, 0, luma_intra_deblock ); | |
| - deblock_edge_intra( h, pixuv, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_intra_deblock ); | |
| - if( chroma444 ) | |
| - deblock_edge_intra( h, pixuv + uvdiff, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_intra_deblock ); | |
| + if( chroma_format ) | |
| + { | |
| + deblock_edge_intra( h, pixuv, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_intra_deblock ); | |
| + if( chroma444 ) | |
| + deblock_edge_intra( h, pixuv + uvdiff, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_intra_deblock ); | |
| + } | |
| } | |
| else | |
| { | |
| deblock_edge( h, pixy, 2*stridey, bs[0][0], luma_qp[0], a, b, 0, luma_deblock ); | |
| - deblock_edge( h, pixuv, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_deblock ); | |
| - if( chroma444 ) | |
| - deblock_edge( h, pixuv + uvdiff, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_deblock ); | |
| + if( chroma_format ) | |
| + { | |
| + deblock_edge( h, pixuv, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_deblock ); | |
| + if( chroma444 ) | |
| + deblock_edge( h, pixuv + uvdiff, 2*strideuv, bs[0][0], chroma_qp[0], a, b, c, chroma_deblock ); | |
| + } | |
| } | |
| int offy = MB_INTERLACED ? 4 : 0; | |
| @@ -483,16 +491,22 @@ | |
| if( intra_cur || IS_INTRA( h->mb.type[h->mb.i_mb_left_xy[1]] ) ) | |
| { | |
| deblock_edge_intra( h, pixy + (stridey<<offy), 2*stridey, bs[0][4], luma_qp[1], a, b, 0, luma_intra_deblock ); | |
| - deblock_edge_intra( h, pixuv + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_intra_deblock ); | |
| - if( chroma444 ) | |
| - deblock_edge_intra( h, pixuv + uvdiff + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_intra_deblock ); | |
| + if( chroma_format ) | |
| + { | |
| + deblock_edge_intra( h, pixuv + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_intra_deblock ); | |
| + if( chroma444 ) | |
| + deblock_edge_intra( h, pixuv + uvdiff + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_intra_deblock ); | |
| + } | |
| } | |
| else | |
| { | |
| deblock_edge( h, pixy + (stridey<<offy), 2*stridey, bs[0][4], luma_qp[1], a, b, 0, luma_deblock ); | |
| - deblock_edge( h, pixuv + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_deblock ); | |
| - if( chroma444 ) | |
| - deblock_edge( h, pixuv + uvdiff + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_deblock ); | |
| + if( chroma_format ) | |
| + { | |
| + deblock_edge( h, pixuv + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_deblock ); | |
| + if( chroma444 ) | |
| + deblock_edge( h, pixuv + uvdiff + (strideuv<<offuv), 2*strideuv, bs[0][4], chroma_qp[1], a, b, c, chroma_deblock ); | |
| + } | |
| } | |
| } | |
| else | |
| @@ -548,7 +562,7 @@ | |
| deblock_edge( h, pixuv + j*strideuv, 2*strideuv, bs[1][4*j], qpc_top, a, b, 0, h->loopf.deblock_luma[1] ); | |
| deblock_edge( h, pixuv + uvdiff + j*strideuv, 2*strideuv, bs[1][4*j], qpc_top, a, b, 0, h->loopf.deblock_luma[1] ); | |
| } | |
| - else | |
| + else if( chroma_format ) | |
| deblock_edge( h, pixuv + j*strideuv, 2*strideuv, bs[1][4*j], qpc_top, a, b, 1, h->loopf.deblock_chroma[1] ); | |
| } | |
| } | |
| @@ -652,120 +666,22 @@ | |
| } | |
| #if HAVE_MMX | |
| -void x264_deblock_v_luma_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_luma_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_chroma_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_chroma_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_mbaff_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_mbaff_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_422_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_422_sse2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_422_avx ( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_luma_intra_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_luma_intra_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_luma_intra_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_luma_intra_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_chroma_intra_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_chroma_intra_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_422_intra_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_422_intra_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_422_intra_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_strength_sse2 ( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| -void x264_deblock_strength_ssse3 ( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| -void x264_deblock_strength_avx ( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| -void x264_deblock_strength_avx2 ( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| -void x264_deblock_strength_avx512( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| - | |
| -void x264_deblock_h_chroma_intra_mbaff_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_mbaff_sse2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_mbaff_avx ( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -#if ARCH_X86 | |
| -void x264_deblock_h_luma_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v8_luma_mmx2( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_chroma_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_mbaff_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_intra_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v8_luma_intra_mmx2( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_chroma_intra_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_mbaff_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| - | |
| -#if HIGH_BIT_DEPTH | |
| -void x264_deblock_v_luma_mmx2( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_luma_intra_mmx2( pixel *pix, intptr_t stride, int alpha, int beta ); | |
| -#else | |
| -// FIXME this wrapper has a significant cpu cost | |
| -static void x264_deblock_v_luma_mmx2( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ) | |
| -{ | |
| - x264_deblock_v8_luma_mmx2( pix, stride, alpha, beta, tc0 ); | |
| - x264_deblock_v8_luma_mmx2( pix+8, stride, alpha, beta, tc0+2 ); | |
| -} | |
| -static void x264_deblock_v_luma_intra_mmx2( uint8_t *pix, intptr_t stride, int alpha, int beta ) | |
| -{ | |
| - x264_deblock_v8_luma_intra_mmx2( pix, stride, alpha, beta ); | |
| - x264_deblock_v8_luma_intra_mmx2( pix+8, stride, alpha, beta ); | |
| -} | |
| -#endif // HIGH_BIT_DEPTH | |
| +#include "x86/deblock.h" | |
| #endif | |
| +#if HAVE_ALTIVEC | |
| +#include "ppc/deblock.h" | |
| #endif | |
| - | |
| -#if ARCH_PPC | |
| -void x264_deblock_v_luma_altivec( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_altivec( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -#endif // ARCH_PPC | |
| - | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| -void x264_deblock_v_luma_neon ( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_neon ( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_chroma_neon( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_neon( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_strength_neon( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], | |
| - int mvy_limit, int bframe ); | |
| -void x264_deblock_h_chroma_422_neon( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_mbaff_neon( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_intra_mbaff_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_422_intra_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_chroma_intra_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_luma_intra_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_luma_intra_neon( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| +#if HAVE_ARMV6 | |
| +#include "arm/deblock.h" | |
| #endif | |
| - | |
| -#if !HIGH_BIT_DEPTH | |
| -#if HAVE_MSA | |
| -void x264_deblock_v_luma_msa( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_luma_msa( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_chroma_msa( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_h_chroma_msa( uint8_t *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ); | |
| -void x264_deblock_v_luma_intra_msa( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_luma_intra_msa( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_v_chroma_intra_msa( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_h_chroma_intra_msa( uint8_t *pix, intptr_t stride, int alpha, int beta ); | |
| -void x264_deblock_strength_msa( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], | |
| - int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], int mvy_limit, | |
| - int bframe ); | |
| +#if HAVE_AARCH64 | |
| +#include "aarch64/deblock.h" | |
| #endif | |
| +#if HAVE_MSA | |
| +#include "mips/deblock.h" | |
| #endif | |
| -void x264_deblock_init( int cpu, x264_deblock_function_t *pf, int b_mbaff ) | |
| +void x264_deblock_init( uint32_t cpu, x264_deblock_function_t *pf, int b_mbaff ) | |
| { | |
| pf->deblock_luma[1] = deblock_v_luma_c; | |
| pf->deblock_luma[0] = deblock_h_luma_c; | |
| @@ -867,7 +783,7 @@ | |
| } | |
| #endif // HAVE_ALTIVEC | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| +#if HAVE_ARMV6 || HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| pf->deblock_luma[1] = x264_deblock_v_luma_neon; | |
| diff -ur x264-go/x264c/external/x264/common/frame.c x264-go.new/x264c/external/x264/common/frame.c | |
| --- x264-go/x264c/external/x264/common/frame.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/frame.c 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * frame.c: frame handling | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -42,37 +42,24 @@ | |
| return x; | |
| } | |
| -static int x264_frame_internal_csp( int external_csp ) | |
| +static int frame_internal_csp( int external_csp ) | |
| { | |
| - switch( external_csp & X264_CSP_MASK ) | |
| - { | |
| - case X264_CSP_NV12: | |
| - case X264_CSP_NV21: | |
| - case X264_CSP_I420: | |
| - case X264_CSP_YV12: | |
| - return X264_CSP_NV12; | |
| - case X264_CSP_NV16: | |
| - case X264_CSP_I422: | |
| - case X264_CSP_YV16: | |
| - case X264_CSP_YUYV: | |
| - case X264_CSP_UYVY: | |
| - case X264_CSP_V210: | |
| - return X264_CSP_NV16; | |
| - case X264_CSP_I444: | |
| - case X264_CSP_YV24: | |
| - case X264_CSP_BGR: | |
| - case X264_CSP_BGRA: | |
| - case X264_CSP_RGB: | |
| - return X264_CSP_I444; | |
| - default: | |
| - return X264_CSP_NONE; | |
| - } | |
| + int csp = external_csp & X264_CSP_MASK; | |
| + if( csp == X264_CSP_I400 ) | |
| + return X264_CSP_I400; | |
| + if( csp >= X264_CSP_I420 && csp < X264_CSP_I422 ) | |
| + return X264_CSP_NV12; | |
| + if( csp >= X264_CSP_I422 && csp < X264_CSP_I444 ) | |
| + return X264_CSP_NV16; | |
| + if( csp >= X264_CSP_I444 && csp <= X264_CSP_RGB ) | |
| + return X264_CSP_I444; | |
| + return X264_CSP_NONE; | |
| } | |
| -static x264_frame_t *x264_frame_new( x264_t *h, int b_fdec ) | |
| +static x264_frame_t *frame_new( x264_t *h, int b_fdec ) | |
| { | |
| x264_frame_t *frame; | |
| - int i_csp = x264_frame_internal_csp( h->param.i_csp ); | |
| + int i_csp = frame_internal_csp( h->param.i_csp ); | |
| int i_mb_count = h->mb.i_mb_count; | |
| int i_stride, i_width, i_lines, luma_plane_count; | |
| int i_padv = PADV << PARAM_INTERLACED; | |
| @@ -89,6 +76,9 @@ | |
| int disalign = 1<<10; | |
| #endif | |
| + /* ensure frame alignment after PADH is added */ | |
| + int padh_align = X264_MAX( align - PADH * SIZEOF_PIXEL, 0 ) / SIZEOF_PIXEL; | |
| + | |
| CHECKED_MALLOCZERO( frame, sizeof(x264_frame_t) ); | |
| PREALLOC_INIT | |
| @@ -119,6 +109,14 @@ | |
| frame->i_stride[i] = i_stride; | |
| } | |
| } | |
| + else if( i_csp == X264_CSP_I400 ) | |
| + { | |
| + luma_plane_count = 1; | |
| + frame->i_plane = 1; | |
| + frame->i_width[0] = i_width; | |
| + frame->i_lines[0] = i_lines; | |
| + frame->i_stride[0] = i_stride; | |
| + } | |
| else | |
| goto fail; | |
| @@ -154,9 +152,9 @@ | |
| { | |
| int chroma_padv = i_padv >> (i_csp == X264_CSP_NV12); | |
| int chroma_plane_size = (frame->i_stride[1] * (frame->i_lines[1] + 2*chroma_padv)); | |
| - PREALLOC( frame->buffer[1], chroma_plane_size * sizeof(pixel) ); | |
| + PREALLOC( frame->buffer[1], (chroma_plane_size + padh_align) * SIZEOF_PIXEL ); | |
| if( PARAM_INTERLACED ) | |
| - PREALLOC( frame->buffer_fld[1], chroma_plane_size * sizeof(pixel) ); | |
| + PREALLOC( frame->buffer_fld[1], (chroma_plane_size + padh_align) * SIZEOF_PIXEL ); | |
| } | |
| /* all 4 luma planes allocated together, since the cacheline split code | |
| @@ -164,20 +162,14 @@ | |
| for( int p = 0; p < luma_plane_count; p++ ) | |
| { | |
| - int luma_plane_size = align_plane_size( frame->i_stride[p] * (frame->i_lines[p] + 2*i_padv), disalign ); | |
| + int64_t luma_plane_size = align_plane_size( frame->i_stride[p] * (frame->i_lines[p] + 2*i_padv), disalign ); | |
| if( h->param.analyse.i_subpel_refine && b_fdec ) | |
| - { | |
| - /* FIXME: Don't allocate both buffers in non-adaptive MBAFF. */ | |
| - PREALLOC( frame->buffer[p], 4*luma_plane_size * sizeof(pixel) ); | |
| - if( PARAM_INTERLACED ) | |
| - PREALLOC( frame->buffer_fld[p], 4*luma_plane_size * sizeof(pixel) ); | |
| - } | |
| - else | |
| - { | |
| - PREALLOC( frame->buffer[p], luma_plane_size * sizeof(pixel) ); | |
| - if( PARAM_INTERLACED ) | |
| - PREALLOC( frame->buffer_fld[p], luma_plane_size * sizeof(pixel) ); | |
| - } | |
| + luma_plane_size *= 4; | |
| + | |
| + /* FIXME: Don't allocate both buffers in non-adaptive MBAFF. */ | |
| + PREALLOC( frame->buffer[p], (luma_plane_size + padh_align) * SIZEOF_PIXEL ); | |
| + if( PARAM_INTERLACED ) | |
| + PREALLOC( frame->buffer_fld[p], (luma_plane_size + padh_align) * SIZEOF_PIXEL ); | |
| } | |
| frame->b_duplicate = 0; | |
| @@ -213,9 +205,9 @@ | |
| { | |
| if( h->frames.b_have_lowres ) | |
| { | |
| - int luma_plane_size = align_plane_size( frame->i_stride_lowres * (frame->i_lines[0]/2 + 2*PADV), disalign ); | |
| + int64_t luma_plane_size = align_plane_size( frame->i_stride_lowres * (frame->i_lines[0]/2 + 2*PADV), disalign ); | |
| - PREALLOC( frame->buffer_lowres[0], 4 * luma_plane_size * sizeof(pixel) ); | |
| + PREALLOC( frame->buffer_lowres, (4 * luma_plane_size + padh_align) * SIZEOF_PIXEL ); | |
| for( int j = 0; j <= !!h->param.i_bframe; j++ ) | |
| for( int i = 0; i <= h->param.i_bframe; i++ ) | |
| @@ -245,28 +237,30 @@ | |
| if( i_csp == X264_CSP_NV12 || i_csp == X264_CSP_NV16 ) | |
| { | |
| int chroma_padv = i_padv >> (i_csp == X264_CSP_NV12); | |
| - frame->plane[1] = frame->buffer[1] + frame->i_stride[1] * chroma_padv + PADH; | |
| + frame->plane[1] = frame->buffer[1] + frame->i_stride[1] * chroma_padv + PADH + padh_align; | |
| if( PARAM_INTERLACED ) | |
| - frame->plane_fld[1] = frame->buffer_fld[1] + frame->i_stride[1] * chroma_padv + PADH; | |
| + frame->plane_fld[1] = frame->buffer_fld[1] + frame->i_stride[1] * chroma_padv + PADH + padh_align; | |
| } | |
| for( int p = 0; p < luma_plane_count; p++ ) | |
| { | |
| - int luma_plane_size = align_plane_size( frame->i_stride[p] * (frame->i_lines[p] + 2*i_padv), disalign ); | |
| + int64_t luma_plane_size = align_plane_size( frame->i_stride[p] * (frame->i_lines[p] + 2*i_padv), disalign ); | |
| if( h->param.analyse.i_subpel_refine && b_fdec ) | |
| { | |
| for( int i = 0; i < 4; i++ ) | |
| { | |
| - frame->filtered[p][i] = frame->buffer[p] + i*luma_plane_size + frame->i_stride[p] * i_padv + PADH; | |
| - frame->filtered_fld[p][i] = frame->buffer_fld[p] + i*luma_plane_size + frame->i_stride[p] * i_padv + PADH; | |
| + frame->filtered[p][i] = frame->buffer[p] + i*luma_plane_size + frame->i_stride[p] * i_padv + PADH + padh_align; | |
| + if( PARAM_INTERLACED ) | |
| + frame->filtered_fld[p][i] = frame->buffer_fld[p] + i*luma_plane_size + frame->i_stride[p] * i_padv + PADH + padh_align; | |
| } | |
| frame->plane[p] = frame->filtered[p][0]; | |
| frame->plane_fld[p] = frame->filtered_fld[p][0]; | |
| } | |
| else | |
| { | |
| - frame->filtered[p][0] = frame->plane[p] = frame->buffer[p] + frame->i_stride[p] * i_padv + PADH; | |
| - frame->filtered_fld[p][0] = frame->plane_fld[p] = frame->buffer_fld[p] + frame->i_stride[p] * i_padv + PADH; | |
| + frame->filtered[p][0] = frame->plane[p] = frame->buffer[p] + frame->i_stride[p] * i_padv + PADH + padh_align; | |
| + if( PARAM_INTERLACED ) | |
| + frame->filtered_fld[p][0] = frame->plane_fld[p] = frame->buffer_fld[p] + frame->i_stride[p] * i_padv + PADH + padh_align; | |
| } | |
| } | |
| @@ -282,9 +276,9 @@ | |
| { | |
| if( h->frames.b_have_lowres ) | |
| { | |
| - int luma_plane_size = align_plane_size( frame->i_stride_lowres * (frame->i_lines[0]/2 + 2*PADV), disalign ); | |
| + int64_t luma_plane_size = align_plane_size( frame->i_stride_lowres * (frame->i_lines[0]/2 + 2*PADV), disalign ); | |
| for( int i = 0; i < 4; i++ ) | |
| - frame->lowres[i] = frame->buffer_lowres[0] + (frame->i_stride_lowres * PADV + PADH) + i * luma_plane_size; | |
| + frame->lowres[i] = frame->buffer_lowres + frame->i_stride_lowres * PADV + PADH + padh_align + i * luma_plane_size; | |
| for( int j = 0; j <= !!h->param.i_bframe; j++ ) | |
| for( int i = 0; i <= h->param.i_bframe; i++ ) | |
| @@ -366,7 +360,7 @@ | |
| int x264_frame_copy_picture( x264_t *h, x264_frame_t *dst, x264_picture_t *src ) | |
| { | |
| int i_csp = src->img.i_csp & X264_CSP_MASK; | |
| - if( dst->i_csp != x264_frame_internal_csp( i_csp ) ) | |
| + if( dst->i_csp != frame_internal_csp( i_csp ) ) | |
| { | |
| x264_log( h, X264_LOG_ERROR, "Invalid input colorspace\n" ); | |
| return -1; | |
| @@ -425,7 +419,7 @@ | |
| h->mc.plane_copy_deinterleave_v210( dst->plane[0], dst->i_stride[0], | |
| dst->plane[1], dst->i_stride[1], | |
| - (uint32_t *)pix[0], stride[0]/sizeof(uint32_t), h->param.i_width, h->param.i_height ); | |
| + (uint32_t *)pix[0], stride[0]/(int)sizeof(uint32_t), h->param.i_width, h->param.i_height ); | |
| } | |
| else if( i_csp >= X264_CSP_BGR ) | |
| { | |
| @@ -440,25 +434,25 @@ | |
| h->mc.plane_copy_deinterleave_rgb( dst->plane[1+b], dst->i_stride[1+b], | |
| dst->plane[0], dst->i_stride[0], | |
| dst->plane[2-b], dst->i_stride[2-b], | |
| - (pixel*)pix[0], stride[0]/sizeof(pixel), i_csp==X264_CSP_BGRA ? 4 : 3, h->param.i_width, h->param.i_height ); | |
| + (pixel*)pix[0], stride[0]/SIZEOF_PIXEL, i_csp==X264_CSP_BGRA ? 4 : 3, h->param.i_width, h->param.i_height ); | |
| } | |
| else | |
| { | |
| int v_shift = CHROMA_V_SHIFT; | |
| get_plane_ptr( h, src, &pix[0], &stride[0], 0, 0, 0 ); | |
| h->mc.plane_copy( dst->plane[0], dst->i_stride[0], (pixel*)pix[0], | |
| - stride[0]/sizeof(pixel), h->param.i_width, h->param.i_height ); | |
| + stride[0]/SIZEOF_PIXEL, h->param.i_width, h->param.i_height ); | |
| if( i_csp == X264_CSP_NV12 || i_csp == X264_CSP_NV16 ) | |
| { | |
| get_plane_ptr( h, src, &pix[1], &stride[1], 1, 0, v_shift ); | |
| h->mc.plane_copy( dst->plane[1], dst->i_stride[1], (pixel*)pix[1], | |
| - stride[1]/sizeof(pixel), h->param.i_width, h->param.i_height>>v_shift ); | |
| + stride[1]/SIZEOF_PIXEL, h->param.i_width, h->param.i_height>>v_shift ); | |
| } | |
| else if( i_csp == X264_CSP_NV21 ) | |
| { | |
| get_plane_ptr( h, src, &pix[1], &stride[1], 1, 0, v_shift ); | |
| h->mc.plane_copy_swap( dst->plane[1], dst->i_stride[1], (pixel*)pix[1], | |
| - stride[1]/sizeof(pixel), h->param.i_width>>1, h->param.i_height>>v_shift ); | |
| + stride[1]/SIZEOF_PIXEL, h->param.i_width>>1, h->param.i_height>>v_shift ); | |
| } | |
| else if( i_csp == X264_CSP_I420 || i_csp == X264_CSP_I422 || i_csp == X264_CSP_YV12 || i_csp == X264_CSP_YV16 ) | |
| { | |
| @@ -466,24 +460,24 @@ | |
| get_plane_ptr( h, src, &pix[1], &stride[1], uv_swap ? 2 : 1, 1, v_shift ); | |
| get_plane_ptr( h, src, &pix[2], &stride[2], uv_swap ? 1 : 2, 1, v_shift ); | |
| h->mc.plane_copy_interleave( dst->plane[1], dst->i_stride[1], | |
| - (pixel*)pix[1], stride[1]/sizeof(pixel), | |
| - (pixel*)pix[2], stride[2]/sizeof(pixel), | |
| + (pixel*)pix[1], stride[1]/SIZEOF_PIXEL, | |
| + (pixel*)pix[2], stride[2]/SIZEOF_PIXEL, | |
| h->param.i_width>>1, h->param.i_height>>v_shift ); | |
| } | |
| - else //if( i_csp == X264_CSP_I444 || i_csp == X264_CSP_YV24 ) | |
| + else if( i_csp == X264_CSP_I444 || i_csp == X264_CSP_YV24 ) | |
| { | |
| get_plane_ptr( h, src, &pix[1], &stride[1], i_csp==X264_CSP_I444 ? 1 : 2, 0, 0 ); | |
| get_plane_ptr( h, src, &pix[2], &stride[2], i_csp==X264_CSP_I444 ? 2 : 1, 0, 0 ); | |
| h->mc.plane_copy( dst->plane[1], dst->i_stride[1], (pixel*)pix[1], | |
| - stride[1]/sizeof(pixel), h->param.i_width, h->param.i_height ); | |
| + stride[1]/SIZEOF_PIXEL, h->param.i_width, h->param.i_height ); | |
| h->mc.plane_copy( dst->plane[2], dst->i_stride[2], (pixel*)pix[2], | |
| - stride[2]/sizeof(pixel), h->param.i_width, h->param.i_height ); | |
| + stride[2]/SIZEOF_PIXEL, h->param.i_width, h->param.i_height ); | |
| } | |
| } | |
| return 0; | |
| } | |
| -static void ALWAYS_INLINE pixel_memset( pixel *dst, pixel *src, int len, int size ) | |
| +static ALWAYS_INLINE void pixel_memset( pixel *dst, pixel *src, int len, int size ) | |
| { | |
| uint8_t *dstp = (uint8_t*)dst; | |
| uint32_t v1 = *src; | |
| @@ -535,24 +529,24 @@ | |
| } | |
| } | |
| -static void ALWAYS_INLINE plane_expand_border( pixel *pix, int i_stride, int i_width, int i_height, int i_padh, int i_padv, int b_pad_top, int b_pad_bottom, int b_chroma ) | |
| +static ALWAYS_INLINE void plane_expand_border( pixel *pix, int i_stride, int i_width, int i_height, int i_padh, int i_padv, int b_pad_top, int b_pad_bottom, int b_chroma ) | |
| { | |
| #define PPIXEL(x, y) ( pix + (x) + (y)*i_stride ) | |
| for( int y = 0; y < i_height; y++ ) | |
| { | |
| /* left band */ | |
| - pixel_memset( PPIXEL(-i_padh, y), PPIXEL(0, y), i_padh>>b_chroma, sizeof(pixel)<<b_chroma ); | |
| + pixel_memset( PPIXEL(-i_padh, y), PPIXEL(0, y), i_padh>>b_chroma, SIZEOF_PIXEL<<b_chroma ); | |
| /* right band */ | |
| - pixel_memset( PPIXEL(i_width, y), PPIXEL(i_width-1-b_chroma, y), i_padh>>b_chroma, sizeof(pixel)<<b_chroma ); | |
| + pixel_memset( PPIXEL(i_width, y), PPIXEL(i_width-1-b_chroma, y), i_padh>>b_chroma, SIZEOF_PIXEL<<b_chroma ); | |
| } | |
| /* upper band */ | |
| if( b_pad_top ) | |
| for( int y = 0; y < i_padv; y++ ) | |
| - memcpy( PPIXEL(-i_padh, -y-1), PPIXEL(-i_padh, 0), (i_width+2*i_padh) * sizeof(pixel) ); | |
| + memcpy( PPIXEL(-i_padh, -y-1), PPIXEL(-i_padh, 0), (i_width+2*i_padh) * SIZEOF_PIXEL ); | |
| /* lower band */ | |
| if( b_pad_bottom ) | |
| for( int y = 0; y < i_padv; y++ ) | |
| - memcpy( PPIXEL(-i_padh, i_height+y), PPIXEL(-i_padh, i_height-1), (i_width+2*i_padh) * sizeof(pixel) ); | |
| + memcpy( PPIXEL(-i_padh, i_height+y), PPIXEL(-i_padh, i_height-1), (i_width+2*i_padh) * SIZEOF_PIXEL ); | |
| #undef PPIXEL | |
| } | |
| @@ -656,14 +650,14 @@ | |
| for( int y = 0; y < i_height; y++ ) | |
| pixel_memset( &frame->plane[i][y*frame->i_stride[i] + i_width], | |
| &frame->plane[i][y*frame->i_stride[i] + i_width - 1-h_shift], | |
| - i_padx>>h_shift, sizeof(pixel)<<h_shift ); | |
| + i_padx>>h_shift, SIZEOF_PIXEL<<h_shift ); | |
| } | |
| if( i_pady ) | |
| { | |
| for( int y = i_height; y < i_height + i_pady; y++ ) | |
| memcpy( &frame->plane[i][y*frame->i_stride[i]], | |
| &frame->plane[i][(i_height-(~y&PARAM_INTERLACED)-1)*frame->i_stride[i]], | |
| - (i_width + i_padx) * sizeof(pixel) ); | |
| + (i_width + i_padx) * SIZEOF_PIXEL ); | |
| } | |
| } | |
| } | |
| @@ -678,7 +672,7 @@ | |
| int pady = (h->mb.i_mb_height * 16 - h->param.i_height) >> v_shift; | |
| pixel *fenc = h->fenc->plane[i] + 16*mb_x; | |
| for( int y = height; y < height + pady; y++ ) | |
| - memcpy( fenc + y*stride, fenc + (height-1)*stride, 16*sizeof(pixel) ); | |
| + memcpy( fenc + y*stride, fenc + (height-1)*stride, 16*SIZEOF_PIXEL ); | |
| } | |
| } | |
| @@ -784,7 +778,7 @@ | |
| if( h->frames.unused[b_fdec][0] ) | |
| frame = x264_frame_pop( h->frames.unused[b_fdec] ); | |
| else | |
| - frame = x264_frame_new( h, b_fdec ); | |
| + frame = frame_new( h, b_fdec ); | |
| if( !frame ) | |
| return NULL; | |
| frame->b_last_minigop_bframe = 0; | |
| diff -ur x264-go/x264c/external/x264/common/frame.h x264-go.new/x264c/external/x264/common/frame.h | |
| --- x264-go/x264c/external/x264/common/frame.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/frame.h 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * frame.h: frame handling | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -86,7 +86,7 @@ | |
| * allocated data are stored in buffer */ | |
| pixel *buffer[4]; | |
| pixel *buffer_fld[4]; | |
| - pixel *buffer_lowres[4]; | |
| + pixel *buffer_lowres; | |
| x264_weight_t weight[X264_REF_MAX][3]; /* [ref_index][plane] */ | |
| pixel *weighted[X264_REF_MAX]; /* plane[0] weighted of the reference frames */ | |
| @@ -216,47 +216,80 @@ | |
| int bframe ); | |
| } x264_deblock_function_t; | |
| +#define x264_frame_delete x264_template(frame_delete) | |
| void x264_frame_delete( x264_frame_t *frame ); | |
| +#define x264_frame_copy_picture x264_template(frame_copy_picture) | |
| int x264_frame_copy_picture( x264_t *h, x264_frame_t *dst, x264_picture_t *src ); | |
| +#define x264_frame_expand_border x264_template(frame_expand_border) | |
| void x264_frame_expand_border( x264_t *h, x264_frame_t *frame, int mb_y ); | |
| +#define x264_frame_expand_border_filtered x264_template(frame_expand_border_filtered) | |
| void x264_frame_expand_border_filtered( x264_t *h, x264_frame_t *frame, int mb_y, int b_end ); | |
| +#define x264_frame_expand_border_lowres x264_template(frame_expand_border_lowres) | |
| void x264_frame_expand_border_lowres( x264_frame_t *frame ); | |
| +#define x264_frame_expand_border_chroma x264_template(frame_expand_border_chroma) | |
| void x264_frame_expand_border_chroma( x264_t *h, x264_frame_t *frame, int plane ); | |
| +#define x264_frame_expand_border_mod16 x264_template(frame_expand_border_mod16) | |
| void x264_frame_expand_border_mod16( x264_t *h, x264_frame_t *frame ); | |
| +#define x264_expand_border_mbpair x264_template(expand_border_mbpair) | |
| void x264_expand_border_mbpair( x264_t *h, int mb_x, int mb_y ); | |
| +#define x264_frame_deblock_row x264_template(frame_deblock_row) | |
| void x264_frame_deblock_row( x264_t *h, int mb_y ); | |
| +#define x264_macroblock_deblock x264_template(macroblock_deblock) | |
| void x264_macroblock_deblock( x264_t *h ); | |
| +#define x264_frame_filter x264_template(frame_filter) | |
| void x264_frame_filter( x264_t *h, x264_frame_t *frame, int mb_y, int b_end ); | |
| +#define x264_frame_init_lowres x264_template(frame_init_lowres) | |
| void x264_frame_init_lowres( x264_t *h, x264_frame_t *frame ); | |
| -void x264_deblock_init( int cpu, x264_deblock_function_t *pf, int b_mbaff ); | |
| +#define x264_deblock_init x264_template(deblock_init) | |
| +void x264_deblock_init( uint32_t cpu, x264_deblock_function_t *pf, int b_mbaff ); | |
| +#define x264_frame_cond_broadcast x264_template(frame_cond_broadcast) | |
| void x264_frame_cond_broadcast( x264_frame_t *frame, int i_lines_completed ); | |
| +#define x264_frame_cond_wait x264_template(frame_cond_wait) | |
| void x264_frame_cond_wait( x264_frame_t *frame, int i_lines_completed ); | |
| +#define x264_frame_new_slice x264_template(frame_new_slice) | |
| int x264_frame_new_slice( x264_t *h, x264_frame_t *frame ); | |
| +#define x264_threadslice_cond_broadcast x264_template(threadslice_cond_broadcast) | |
| void x264_threadslice_cond_broadcast( x264_t *h, int pass ); | |
| +#define x264_threadslice_cond_wait x264_template(threadslice_cond_wait) | |
| void x264_threadslice_cond_wait( x264_t *h, int pass ); | |
| -void x264_frame_push( x264_frame_t **list, x264_frame_t *frame ); | |
| -x264_frame_t *x264_frame_pop( x264_frame_t **list ); | |
| -void x264_frame_unshift( x264_frame_t **list, x264_frame_t *frame ); | |
| -x264_frame_t *x264_frame_shift( x264_frame_t **list ); | |
| +#define x264_frame_push x264_template(frame_push) | |
| +X264_API void x264_frame_push( x264_frame_t **list, x264_frame_t *frame ); | |
| +#define x264_frame_pop x264_template(frame_pop) | |
| +X264_API x264_frame_t *x264_frame_pop( x264_frame_t **list ); | |
| +#define x264_frame_unshift x264_template(frame_unshift) | |
| +X264_API void x264_frame_unshift( x264_frame_t **list, x264_frame_t *frame ); | |
| +#define x264_frame_shift x264_template(frame_shift) | |
| +X264_API x264_frame_t *x264_frame_shift( x264_frame_t **list ); | |
| + | |
| +#define x264_frame_push_unused x264_template(frame_push_unused) | |
| void x264_frame_push_unused( x264_t *h, x264_frame_t *frame ); | |
| +#define x264_frame_push_blank_unused x264_template(frame_push_blank_unused) | |
| void x264_frame_push_blank_unused( x264_t *h, x264_frame_t *frame ); | |
| +#define x264_frame_pop_blank_unused x264_template(frame_pop_blank_unused) | |
| x264_frame_t *x264_frame_pop_blank_unused( x264_t *h ); | |
| +#define x264_weight_scale_plane x264_template(weight_scale_plane) | |
| void x264_weight_scale_plane( x264_t *h, pixel *dst, intptr_t i_dst_stride, pixel *src, intptr_t i_src_stride, | |
| int i_width, int i_height, x264_weight_t *w ); | |
| +#define x264_frame_pop_unused x264_template(frame_pop_unused) | |
| x264_frame_t *x264_frame_pop_unused( x264_t *h, int b_fdec ); | |
| +#define x264_frame_delete_list x264_template(frame_delete_list) | |
| void x264_frame_delete_list( x264_frame_t **list ); | |
| +#define x264_sync_frame_list_init x264_template(sync_frame_list_init) | |
| int x264_sync_frame_list_init( x264_sync_frame_list_t *slist, int nelem ); | |
| +#define x264_sync_frame_list_delete x264_template(sync_frame_list_delete) | |
| void x264_sync_frame_list_delete( x264_sync_frame_list_t *slist ); | |
| +#define x264_sync_frame_list_push x264_template(sync_frame_list_push) | |
| void x264_sync_frame_list_push( x264_sync_frame_list_t *slist, x264_frame_t *frame ); | |
| +#define x264_sync_frame_list_pop x264_template(sync_frame_list_pop) | |
| x264_frame_t *x264_sync_frame_list_pop( x264_sync_frame_list_t *slist ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/macroblock.c x264-go.new/x264c/external/x264/common/macroblock.c | |
| --- x264-go/x264c/external/x264/common/macroblock.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/macroblock.c 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * macroblock.c: macroblock common functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Fiona Glaser <fiona@x264.com> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -34,7 +34,7 @@ | |
| mvx, mvy, 4*width, 4*height, \ | |
| list ? x264_weight_none : &h->sh.weight[i_ref][p] ); | |
| -static NOINLINE void x264_mb_mc_0xywh( x264_t *h, int x, int y, int width, int height ) | |
| +static NOINLINE void mb_mc_0xywh( x264_t *h, int x, int y, int width, int height ) | |
| { | |
| int i8 = x264_scan8[0]+x+8*y; | |
| int i_ref = h->mb.cache.ref[0][i8]; | |
| @@ -48,7 +48,7 @@ | |
| MC_LUMA( 0, 1 ); | |
| MC_LUMA( 0, 2 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| int v_shift = CHROMA_V_SHIFT; | |
| // Chroma in 4:2:0 is offset if MCing from a field of opposite parity | |
| @@ -73,7 +73,7 @@ | |
| &h->sh.weight[i_ref][2], height ); | |
| } | |
| } | |
| -static NOINLINE void x264_mb_mc_1xywh( x264_t *h, int x, int y, int width, int height ) | |
| +static NOINLINE void mb_mc_1xywh( x264_t *h, int x, int y, int width, int height ) | |
| { | |
| int i8 = x264_scan8[0]+x+8*y; | |
| int i_ref = h->mb.cache.ref[1][i8]; | |
| @@ -87,7 +87,7 @@ | |
| MC_LUMA( 1, 1 ); | |
| MC_LUMA( 1, 2 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| int v_shift = CHROMA_V_SHIFT; | |
| if( v_shift & MB_INTERLACED & i_ref ) | |
| @@ -109,7 +109,7 @@ | |
| h->mc.avg[i_mode]( &h->mb.pic.p_fdec[p][4*y*FDEC_STRIDE+4*x], FDEC_STRIDE, \ | |
| src0, i_stride0, src1, i_stride1, weight ); | |
| -static NOINLINE void x264_mb_mc_01xywh( x264_t *h, int x, int y, int width, int height ) | |
| +static NOINLINE void mb_mc_01xywh( x264_t *h, int x, int y, int width, int height ) | |
| { | |
| int i8 = x264_scan8[0]+x+8*y; | |
| int i_ref0 = h->mb.cache.ref[0][i8]; | |
| @@ -132,7 +132,7 @@ | |
| MC_LUMA_BI( 1 ); | |
| MC_LUMA_BI( 2 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| int v_shift = CHROMA_V_SHIFT; | |
| if( v_shift & MB_INTERLACED & i_ref0 ) | |
| @@ -165,21 +165,21 @@ | |
| switch( h->mb.i_sub_partition[i8] ) | |
| { | |
| case D_L0_8x8: | |
| - x264_mb_mc_0xywh( h, x, y, 2, 2 ); | |
| + mb_mc_0xywh( h, x, y, 2, 2 ); | |
| break; | |
| case D_L0_8x4: | |
| - x264_mb_mc_0xywh( h, x, y+0, 2, 1 ); | |
| - x264_mb_mc_0xywh( h, x, y+1, 2, 1 ); | |
| + mb_mc_0xywh( h, x, y+0, 2, 1 ); | |
| + mb_mc_0xywh( h, x, y+1, 2, 1 ); | |
| break; | |
| case D_L0_4x8: | |
| - x264_mb_mc_0xywh( h, x+0, y, 1, 2 ); | |
| - x264_mb_mc_0xywh( h, x+1, y, 1, 2 ); | |
| + mb_mc_0xywh( h, x+0, y, 1, 2 ); | |
| + mb_mc_0xywh( h, x+1, y, 1, 2 ); | |
| break; | |
| case D_L0_4x4: | |
| - x264_mb_mc_0xywh( h, x+0, y+0, 1, 1 ); | |
| - x264_mb_mc_0xywh( h, x+1, y+0, 1, 1 ); | |
| - x264_mb_mc_0xywh( h, x+0, y+1, 1, 1 ); | |
| - x264_mb_mc_0xywh( h, x+1, y+1, 1, 1 ); | |
| + mb_mc_0xywh( h, x+0, y+0, 1, 1 ); | |
| + mb_mc_0xywh( h, x+1, y+0, 1, 1 ); | |
| + mb_mc_0xywh( h, x+0, y+1, 1, 1 ); | |
| + mb_mc_0xywh( h, x+1, y+1, 1, 1 ); | |
| break; | |
| } | |
| } | |
| @@ -189,11 +189,11 @@ | |
| if( h->mb.cache.ref[0][scan8] >= 0 ) | |
| if( h->mb.cache.ref[1][scan8] >= 0 ) | |
| - x264_mb_mc_01xywh( h, x, y, 2, 2 ); | |
| + mb_mc_01xywh( h, x, y, 2, 2 ); | |
| else | |
| - x264_mb_mc_0xywh( h, x, y, 2, 2 ); | |
| + mb_mc_0xywh( h, x, y, 2, 2 ); | |
| else | |
| - x264_mb_mc_1xywh( h, x, y, 2, 2 ); | |
| + mb_mc_1xywh( h, x, y, 2, 2 ); | |
| } | |
| } | |
| @@ -214,33 +214,33 @@ | |
| if( h->mb.i_partition == D_16x16 ) | |
| { | |
| if( ref0a >= 0 ) | |
| - if( ref1a >= 0 ) x264_mb_mc_01xywh( h, 0, 0, 4, 4 ); | |
| - else x264_mb_mc_0xywh ( h, 0, 0, 4, 4 ); | |
| - else x264_mb_mc_1xywh ( h, 0, 0, 4, 4 ); | |
| + if( ref1a >= 0 ) mb_mc_01xywh( h, 0, 0, 4, 4 ); | |
| + else mb_mc_0xywh ( h, 0, 0, 4, 4 ); | |
| + else mb_mc_1xywh ( h, 0, 0, 4, 4 ); | |
| } | |
| else if( h->mb.i_partition == D_16x8 ) | |
| { | |
| if( ref0a >= 0 ) | |
| - if( ref1a >= 0 ) x264_mb_mc_01xywh( h, 0, 0, 4, 2 ); | |
| - else x264_mb_mc_0xywh ( h, 0, 0, 4, 2 ); | |
| - else x264_mb_mc_1xywh ( h, 0, 0, 4, 2 ); | |
| + if( ref1a >= 0 ) mb_mc_01xywh( h, 0, 0, 4, 2 ); | |
| + else mb_mc_0xywh ( h, 0, 0, 4, 2 ); | |
| + else mb_mc_1xywh ( h, 0, 0, 4, 2 ); | |
| if( ref0b >= 0 ) | |
| - if( ref1b >= 0 ) x264_mb_mc_01xywh( h, 0, 2, 4, 2 ); | |
| - else x264_mb_mc_0xywh ( h, 0, 2, 4, 2 ); | |
| - else x264_mb_mc_1xywh ( h, 0, 2, 4, 2 ); | |
| + if( ref1b >= 0 ) mb_mc_01xywh( h, 0, 2, 4, 2 ); | |
| + else mb_mc_0xywh ( h, 0, 2, 4, 2 ); | |
| + else mb_mc_1xywh ( h, 0, 2, 4, 2 ); | |
| } | |
| else if( h->mb.i_partition == D_8x16 ) | |
| { | |
| if( ref0a >= 0 ) | |
| - if( ref1a >= 0 ) x264_mb_mc_01xywh( h, 0, 0, 2, 4 ); | |
| - else x264_mb_mc_0xywh ( h, 0, 0, 2, 4 ); | |
| - else x264_mb_mc_1xywh ( h, 0, 0, 2, 4 ); | |
| + if( ref1a >= 0 ) mb_mc_01xywh( h, 0, 0, 2, 4 ); | |
| + else mb_mc_0xywh ( h, 0, 0, 2, 4 ); | |
| + else mb_mc_1xywh ( h, 0, 0, 2, 4 ); | |
| if( ref0b >= 0 ) | |
| - if( ref1b >= 0 ) x264_mb_mc_01xywh( h, 2, 0, 2, 4 ); | |
| - else x264_mb_mc_0xywh ( h, 2, 0, 2, 4 ); | |
| - else x264_mb_mc_1xywh ( h, 2, 0, 2, 4 ); | |
| + if( ref1b >= 0 ) mb_mc_01xywh( h, 2, 0, 2, 4 ); | |
| + else mb_mc_0xywh ( h, 2, 0, 2, 4 ); | |
| + else mb_mc_1xywh ( h, 2, 0, 2, 4 ); | |
| } | |
| } | |
| } | |
| @@ -260,7 +260,7 @@ | |
| PREALLOC( h->mb.qp, i_mb_count * sizeof(int8_t) ); | |
| PREALLOC( h->mb.cbp, i_mb_count * sizeof(int16_t) ); | |
| PREALLOC( h->mb.mb_transform_size, i_mb_count * sizeof(int8_t) ); | |
| - PREALLOC( h->mb.slice_table, i_mb_count * sizeof(uint32_t) ); | |
| + PREALLOC( h->mb.slice_table, i_mb_count * sizeof(int32_t) ); | |
| /* 0 -> 3 top(4), 4 -> 6 : left(3) */ | |
| PREALLOC( h->mb.intra4x4_pred_mode, i_mb_count * 8 * sizeof(int8_t) ); | |
| @@ -321,12 +321,12 @@ | |
| } | |
| for( int i = 0; i < numweightbuf; i++ ) | |
| - PREALLOC( h->mb.p_weight_buf[i], luma_plane_size * sizeof(pixel) ); | |
| + PREALLOC( h->mb.p_weight_buf[i], luma_plane_size * SIZEOF_PIXEL ); | |
| } | |
| PREALLOC_END( h->mb.base ); | |
| - memset( h->mb.slice_table, -1, i_mb_count * sizeof(uint32_t) ); | |
| + memset( h->mb.slice_table, -1, i_mb_count * sizeof(int32_t) ); | |
| for( int i = 0; i < 2; i++ ) | |
| { | |
| @@ -357,7 +357,7 @@ | |
| for( int i = 0; i < (PARAM_INTERLACED ? 5 : 2); i++ ) | |
| for( int j = 0; j < (CHROMA444 ? 3 : 2); j++ ) | |
| { | |
| - CHECKED_MALLOC( h->intra_border_backup[i][j], (h->sps->i_mb_width*16+32) * sizeof(pixel) ); | |
| + CHECKED_MALLOC( h->intra_border_backup[i][j], (h->sps->i_mb_width*16+32) * SIZEOF_PIXEL ); | |
| h->intra_border_backup[i][j] += 16; | |
| } | |
| for( int i = 0; i <= PARAM_INTERLACED; i++ ) | |
| @@ -531,17 +531,20 @@ | |
| */ | |
| h->mb.pic.p_fenc[0] = h->mb.pic.fenc_buf; | |
| h->mb.pic.p_fdec[0] = h->mb.pic.fdec_buf + 2*FDEC_STRIDE; | |
| - h->mb.pic.p_fenc[1] = h->mb.pic.fenc_buf + 16*FENC_STRIDE; | |
| - h->mb.pic.p_fdec[1] = h->mb.pic.fdec_buf + 20*FDEC_STRIDE; | |
| - if( CHROMA444 ) | |
| + if( CHROMA_FORMAT ) | |
| { | |
| - h->mb.pic.p_fenc[2] = h->mb.pic.fenc_buf + 32*FENC_STRIDE; | |
| - h->mb.pic.p_fdec[2] = h->mb.pic.fdec_buf + 38*FDEC_STRIDE; | |
| - } | |
| - else | |
| - { | |
| - h->mb.pic.p_fenc[2] = h->mb.pic.fenc_buf + 16*FENC_STRIDE + 8; | |
| - h->mb.pic.p_fdec[2] = h->mb.pic.fdec_buf + 20*FDEC_STRIDE + 16; | |
| + h->mb.pic.p_fenc[1] = h->mb.pic.fenc_buf + 16*FENC_STRIDE; | |
| + h->mb.pic.p_fdec[1] = h->mb.pic.fdec_buf + 20*FDEC_STRIDE; | |
| + if( CHROMA444 ) | |
| + { | |
| + h->mb.pic.p_fenc[2] = h->mb.pic.fenc_buf + 32*FENC_STRIDE; | |
| + h->mb.pic.p_fdec[2] = h->mb.pic.fdec_buf + 38*FDEC_STRIDE; | |
| + } | |
| + else | |
| + { | |
| + h->mb.pic.p_fenc[2] = h->mb.pic.fenc_buf + 16*FENC_STRIDE + 8; | |
| + h->mb.pic.p_fdec[2] = h->mb.pic.fdec_buf + 20*FDEC_STRIDE + 16; | |
| + } | |
| } | |
| } | |
| @@ -552,7 +555,7 @@ | |
| int off_y = 16 * i_mb_x + 16 * i_mb_y * stride_y; | |
| int off_uv = 16 * i_mb_x + (16 * i_mb_y * stride_uv >> CHROMA_V_SHIFT); | |
| h->mc.prefetch_fenc( fenc->plane[0]+off_y, stride_y, | |
| - fenc->plane[1]+off_uv, stride_uv, i_mb_x ); | |
| + fenc->plane[1] != NULL ? fenc->plane[1]+off_uv : NULL, stride_uv, i_mb_x ); | |
| } | |
| NOINLINE void x264_copy_column8( pixel *dst, pixel *src ) | |
| @@ -562,7 +565,7 @@ | |
| dst[i*FDEC_STRIDE] = src[i*FDEC_STRIDE]; | |
| } | |
| -static void ALWAYS_INLINE x264_macroblock_load_pic_pointers( x264_t *h, int mb_x, int mb_y, int i, int b_chroma, int b_mbaff ) | |
| +static ALWAYS_INLINE void macroblock_load_pic_pointers( x264_t *h, int mb_x, int mb_y, int i, int b_chroma, int b_mbaff ) | |
| { | |
| int mb_interlaced = b_mbaff && MB_INTERLACED; | |
| int height = b_chroma ? 16 >> CHROMA_V_SHIFT : 16; | |
| @@ -583,15 +586,15 @@ | |
| if( b_chroma ) | |
| { | |
| h->mc.load_deinterleave_chroma_fenc( h->mb.pic.p_fenc[1], h->mb.pic.p_fenc_plane[1], i_stride2, height ); | |
| - memcpy( h->mb.pic.p_fdec[1]-FDEC_STRIDE, intra_fdec, 8*sizeof(pixel) ); | |
| - memcpy( h->mb.pic.p_fdec[2]-FDEC_STRIDE, intra_fdec+8, 8*sizeof(pixel) ); | |
| + memcpy( h->mb.pic.p_fdec[1]-FDEC_STRIDE, intra_fdec, 8*SIZEOF_PIXEL ); | |
| + memcpy( h->mb.pic.p_fdec[2]-FDEC_STRIDE, intra_fdec+8, 8*SIZEOF_PIXEL ); | |
| h->mb.pic.p_fdec[1][-FDEC_STRIDE-1] = intra_fdec[-1-8]; | |
| h->mb.pic.p_fdec[2][-FDEC_STRIDE-1] = intra_fdec[-1]; | |
| } | |
| else | |
| { | |
| h->mc.copy[PIXEL_16x16]( h->mb.pic.p_fenc[i], FENC_STRIDE, h->mb.pic.p_fenc_plane[i], i_stride2, 16 ); | |
| - memcpy( h->mb.pic.p_fdec[i]-FDEC_STRIDE, intra_fdec, 24*sizeof(pixel) ); | |
| + memcpy( h->mb.pic.p_fdec[i]-FDEC_STRIDE, intra_fdec, 24*SIZEOF_PIXEL ); | |
| h->mb.pic.p_fdec[i][-FDEC_STRIDE-1] = intra_fdec[-1]; | |
| } | |
| if( b_mbaff || h->mb.b_reencode_mb ) | |
| @@ -623,8 +626,9 @@ | |
| if( !b_chroma ) | |
| { | |
| - for( int k = 1; k < 4; k++ ) | |
| - h->mb.pic.p_fref[0][j][i*4+k] = filtered_src[k] + ref_pix_offset[j&1]; | |
| + if( h->param.analyse.i_subpel_refine ) | |
| + for( int k = 1; k < 4; k++ ) | |
| + h->mb.pic.p_fref[0][j][i*4+k] = filtered_src[k] + ref_pix_offset[j&1]; | |
| if( !i ) | |
| { | |
| if( h->sh.weight[j][0].weightfn ) | |
| @@ -649,7 +653,7 @@ | |
| } | |
| h->mb.pic.p_fref[1][j][i*4] = plane_src + ref_pix_offset[j&1]; | |
| - if( !b_chroma ) | |
| + if( !b_chroma && h->param.analyse.i_subpel_refine ) | |
| for( int k = 1; k < 4; k++ ) | |
| h->mb.pic.p_fref[1][j][i*4+k] = filtered_src[k] + ref_pix_offset[j&1]; | |
| } | |
| @@ -666,7 +670,7 @@ | |
| {{ 4, 5, 6, 3}, { 3, 7, 11, 15}, {16+1, 16+5, 32+1, 32+5}, {0, 1, 2, 3}, {0, 0, 1, 1}} | |
| }; | |
| -static void ALWAYS_INLINE x264_macroblock_cache_load_neighbours( x264_t *h, int mb_x, int mb_y, int b_interlaced ) | |
| +static ALWAYS_INLINE void macroblock_cache_load_neighbours( x264_t *h, int mb_x, int mb_y, int b_interlaced ) | |
| { | |
| const int mb_interlaced = b_interlaced && MB_INTERLACED; | |
| int top_y = mb_y - (1 << mb_interlaced); | |
| @@ -803,9 +807,9 @@ | |
| x264_prefetch( &h->mb.cbp[top] ); | |
| x264_prefetch( h->mb.intra4x4_pred_mode[top] ); | |
| x264_prefetch( &h->mb.non_zero_count[top][12] ); | |
| - /* These aren't always allocated, but prefetching an invalid address can't hurt. */ | |
| x264_prefetch( &h->mb.mb_transform_size[top] ); | |
| - x264_prefetch( &h->mb.skipbp[top] ); | |
| + if( h->param.b_cabac ) | |
| + x264_prefetch( &h->mb.skipbp[top] ); | |
| } | |
| } | |
| @@ -848,9 +852,9 @@ | |
| # define LBOT 0 | |
| #endif | |
| -static void ALWAYS_INLINE x264_macroblock_cache_load( x264_t *h, int mb_x, int mb_y, int b_mbaff ) | |
| +static ALWAYS_INLINE void macroblock_cache_load( x264_t *h, int mb_x, int mb_y, int b_mbaff ) | |
| { | |
| - x264_macroblock_cache_load_neighbours( h, mb_x, mb_y, b_mbaff ); | |
| + macroblock_cache_load_neighbours( h, mb_x, mb_y, b_mbaff ); | |
| int *left = h->mb.i_mb_left_xy; | |
| int top = h->mb.i_mb_top_xy; | |
| @@ -891,7 +895,8 @@ | |
| * once every 4 MBs, so one extra prefetch is worthwhile */ | |
| x264_prefetch( &h->mb.mv[l][top_4x4+4] ); | |
| x264_prefetch( &h->mb.ref[l][top_8x8-1] ); | |
| - x264_prefetch( &h->mb.mvd[l][top] ); | |
| + if( h->param.b_cabac ) | |
| + x264_prefetch( &h->mb.mvd[l][top] ); | |
| } | |
| } | |
| else | |
| @@ -996,17 +1001,17 @@ | |
| { | |
| x264_copy_column8( h->mb.pic.p_fdec[0]-1+ 4*FDEC_STRIDE, h->mb.pic.p_fdec[0]+15+ 4*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[0]-1+12*FDEC_STRIDE, h->mb.pic.p_fdec[0]+15+12*FDEC_STRIDE ); | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 0, 0, 0 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 0, 0, 0 ); | |
| if( CHROMA444 ) | |
| { | |
| x264_copy_column8( h->mb.pic.p_fdec[1]-1+ 4*FDEC_STRIDE, h->mb.pic.p_fdec[1]+15+ 4*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[1]-1+12*FDEC_STRIDE, h->mb.pic.p_fdec[1]+15+12*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[2]-1+ 4*FDEC_STRIDE, h->mb.pic.p_fdec[2]+15+ 4*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[2]-1+12*FDEC_STRIDE, h->mb.pic.p_fdec[2]+15+12*FDEC_STRIDE ); | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 0, 0 ); | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 2, 0, 0 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 0, 0 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 2, 0, 0 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| x264_copy_column8( h->mb.pic.p_fdec[1]-1+ 4*FDEC_STRIDE, h->mb.pic.p_fdec[1]+ 7+ 4*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[2]-1+ 4*FDEC_STRIDE, h->mb.pic.p_fdec[2]+ 7+ 4*FDEC_STRIDE ); | |
| @@ -1015,19 +1020,19 @@ | |
| x264_copy_column8( h->mb.pic.p_fdec[1]-1+12*FDEC_STRIDE, h->mb.pic.p_fdec[1]+ 7+12*FDEC_STRIDE ); | |
| x264_copy_column8( h->mb.pic.p_fdec[2]-1+12*FDEC_STRIDE, h->mb.pic.p_fdec[2]+ 7+12*FDEC_STRIDE ); | |
| } | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 1, 0 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 1, 0 ); | |
| } | |
| } | |
| else | |
| { | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 0, 0, 1 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 0, 0, 1 ); | |
| if( CHROMA444 ) | |
| { | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 0, 1 ); | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 2, 0, 1 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 0, 1 ); | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 2, 0, 1 ); | |
| } | |
| - else | |
| - x264_macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 1, 1 ); | |
| + else if( CHROMA_FORMAT ) | |
| + macroblock_load_pic_pointers( h, mb_x, mb_y, 1, 1, 1 ); | |
| } | |
| if( h->fdec->integral ) | |
| @@ -1348,15 +1353,15 @@ | |
| void x264_macroblock_cache_load_progressive( x264_t *h, int mb_x, int mb_y ) | |
| { | |
| - x264_macroblock_cache_load( h, mb_x, mb_y, 0 ); | |
| + macroblock_cache_load( h, mb_x, mb_y, 0 ); | |
| } | |
| void x264_macroblock_cache_load_interlaced( x264_t *h, int mb_x, int mb_y ) | |
| { | |
| - x264_macroblock_cache_load( h, mb_x, mb_y, 1 ); | |
| + macroblock_cache_load( h, mb_x, mb_y, 1 ); | |
| } | |
| -static void x264_macroblock_deblock_strength_mbaff( x264_t *h, uint8_t (*bs)[8][4] ) | |
| +static void macroblock_deblock_strength_mbaff( x264_t *h, uint8_t (*bs)[8][4] ) | |
| { | |
| if( (h->mb.i_neighbour & MB_LEFT) && h->mb.field[h->mb.i_mb_left_xy[0]] != MB_INTERLACED ) | |
| { | |
| @@ -1613,10 +1618,10 @@ | |
| bs, 4 >> MB_INTERLACED, h->sh.i_type == SLICE_TYPE_B ); | |
| if( SLICE_MBAFF ) | |
| - x264_macroblock_deblock_strength_mbaff( h, bs ); | |
| + macroblock_deblock_strength_mbaff( h, bs ); | |
| } | |
| -static void ALWAYS_INLINE x264_macroblock_store_pic( x264_t *h, int mb_x, int mb_y, int i, int b_chroma, int b_mbaff ) | |
| +static ALWAYS_INLINE void macroblock_store_pic( x264_t *h, int mb_x, int mb_y, int i, int b_chroma, int b_mbaff ) | |
| { | |
| int height = b_chroma ? 16>>CHROMA_V_SHIFT : 16; | |
| int i_stride = h->fdec->i_stride[i]; | |
| @@ -1630,24 +1635,24 @@ | |
| h->mc.copy[PIXEL_16x16]( &h->fdec->plane[i][i_pix_offset], i_stride2, h->mb.pic.p_fdec[i], FDEC_STRIDE, 16 ); | |
| } | |
| -static void ALWAYS_INLINE x264_macroblock_backup_intra( x264_t *h, int mb_x, int mb_y, int b_mbaff ) | |
| +static ALWAYS_INLINE void macroblock_backup_intra( x264_t *h, int mb_x, int mb_y, int b_mbaff ) | |
| { | |
| /* In MBAFF we store the last two rows in intra_border_backup[0] and [1]. | |
| * For progressive mbs this is the bottom two rows, and for interlaced the | |
| * bottom row of each field. We also store samples needed for the next | |
| * mbpair in intra_border_backup[2]. */ | |
| int backup_dst = !b_mbaff ? (mb_y&1) : (mb_y&1) ? 1 : MB_INTERLACED ? 0 : 2; | |
| - memcpy( &h->intra_border_backup[backup_dst][0][mb_x*16 ], h->mb.pic.p_fdec[0]+FDEC_STRIDE*15, 16*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][0][mb_x*16 ], h->mb.pic.p_fdec[0]+FDEC_STRIDE*15, 16*SIZEOF_PIXEL ); | |
| if( CHROMA444 ) | |
| { | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+FDEC_STRIDE*15, 16*sizeof(pixel) ); | |
| - memcpy( &h->intra_border_backup[backup_dst][2][mb_x*16 ], h->mb.pic.p_fdec[2]+FDEC_STRIDE*15, 16*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+FDEC_STRIDE*15, 16*SIZEOF_PIXEL ); | |
| + memcpy( &h->intra_border_backup[backup_dst][2][mb_x*16 ], h->mb.pic.p_fdec[2]+FDEC_STRIDE*15, 16*SIZEOF_PIXEL ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| int backup_src = (15>>CHROMA_V_SHIFT) * FDEC_STRIDE; | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 8*sizeof(pixel) ); | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16+8], h->mb.pic.p_fdec[2]+backup_src, 8*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 8*SIZEOF_PIXEL ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16+8], h->mb.pic.p_fdec[2]+backup_src, 8*SIZEOF_PIXEL ); | |
| } | |
| if( b_mbaff ) | |
| { | |
| @@ -1655,18 +1660,18 @@ | |
| { | |
| int backup_src = (MB_INTERLACED ? 7 : 14) * FDEC_STRIDE; | |
| backup_dst = MB_INTERLACED ? 2 : 0; | |
| - memcpy( &h->intra_border_backup[backup_dst][0][mb_x*16 ], h->mb.pic.p_fdec[0]+backup_src, 16*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][0][mb_x*16 ], h->mb.pic.p_fdec[0]+backup_src, 16*SIZEOF_PIXEL ); | |
| if( CHROMA444 ) | |
| { | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 16*sizeof(pixel) ); | |
| - memcpy( &h->intra_border_backup[backup_dst][2][mb_x*16 ], h->mb.pic.p_fdec[2]+backup_src, 16*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 16*SIZEOF_PIXEL ); | |
| + memcpy( &h->intra_border_backup[backup_dst][2][mb_x*16 ], h->mb.pic.p_fdec[2]+backup_src, 16*SIZEOF_PIXEL ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| if( CHROMA_FORMAT == CHROMA_420 ) | |
| backup_src = (MB_INTERLACED ? 3 : 6) * FDEC_STRIDE; | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 8*sizeof(pixel) ); | |
| - memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16+8], h->mb.pic.p_fdec[2]+backup_src, 8*sizeof(pixel) ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16 ], h->mb.pic.p_fdec[1]+backup_src, 8*SIZEOF_PIXEL ); | |
| + memcpy( &h->intra_border_backup[backup_dst][1][mb_x*16+8], h->mb.pic.p_fdec[2]+backup_src, 8*SIZEOF_PIXEL ); | |
| } | |
| } | |
| } | |
| @@ -1688,27 +1693,27 @@ | |
| if( SLICE_MBAFF ) | |
| { | |
| - x264_macroblock_backup_intra( h, h->mb.i_mb_x, h->mb.i_mb_y, 1 ); | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 0, 0, 1 ); | |
| + macroblock_backup_intra( h, h->mb.i_mb_x, h->mb.i_mb_y, 1 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 0, 0, 1 ); | |
| if( CHROMA444 ) | |
| { | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 0, 1 ); | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 2, 0, 1 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 0, 1 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 2, 0, 1 ); | |
| } | |
| - else | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 1, 1 ); | |
| + else if( CHROMA_FORMAT ) | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 1, 1 ); | |
| } | |
| else | |
| { | |
| - x264_macroblock_backup_intra( h, h->mb.i_mb_x, h->mb.i_mb_y, 0 ); | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 0, 0, 0 ); | |
| + macroblock_backup_intra( h, h->mb.i_mb_x, h->mb.i_mb_y, 0 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 0, 0, 0 ); | |
| if( CHROMA444 ) | |
| { | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 0, 0 ); | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 2, 0, 0 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 0, 0 ); | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 2, 0, 0 ); | |
| } | |
| - else | |
| - x264_macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 1, 0 ); | |
| + else if( CHROMA_FORMAT ) | |
| + macroblock_store_pic( h, h->mb.i_mb_x, h->mb.i_mb_y, 1, 1, 0 ); | |
| } | |
| x264_prefetch_fenc( h, h->fdec, h->mb.i_mb_x, h->mb.i_mb_y ); | |
| @@ -1776,9 +1781,7 @@ | |
| if( h->sh.i_type != SLICE_TYPE_I ) | |
| { | |
| int16_t (*mv0)[2] = &h->mb.mv[0][i_mb_4x4]; | |
| - int16_t (*mv1)[2] = &h->mb.mv[1][i_mb_4x4]; | |
| int8_t *ref0 = &h->mb.ref[0][i_mb_8x8]; | |
| - int8_t *ref1 = &h->mb.ref[1][i_mb_8x8]; | |
| if( !IS_INTRA( i_mb_type ) ) | |
| { | |
| ref0[0+0*s8x8] = h->mb.cache.ref[0][x264_scan8[0]]; | |
| @@ -1791,6 +1794,8 @@ | |
| CP128( &mv0[3*s4x4], h->mb.cache.mv[0][x264_scan8[0]+8*3] ); | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| { | |
| + int16_t (*mv1)[2] = &h->mb.mv[1][i_mb_4x4]; | |
| + int8_t *ref1 = &h->mb.ref[1][i_mb_8x8]; | |
| ref1[0+0*s8x8] = h->mb.cache.ref[1][x264_scan8[0]]; | |
| ref1[1+0*s8x8] = h->mb.cache.ref[1][x264_scan8[4]]; | |
| ref1[0+1*s8x8] = h->mb.cache.ref[1][x264_scan8[8]]; | |
| @@ -1811,6 +1816,8 @@ | |
| M128( &mv0[3*s4x4] ) = M128_ZERO; | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| { | |
| + int16_t (*mv1)[2] = &h->mb.mv[1][i_mb_4x4]; | |
| + int8_t *ref1 = &h->mb.ref[1][i_mb_8x8]; | |
| M16( &ref1[0*s8x8] ) = (uint8_t)(-1) * 0x0101; | |
| M16( &ref1[1*s8x8] ) = (uint8_t)(-1) * 0x0101; | |
| M128( &mv1[0*s4x4] ) = M128_ZERO; | |
| @@ -1824,7 +1831,6 @@ | |
| if( h->param.b_cabac ) | |
| { | |
| uint8_t (*mvd0)[2] = h->mb.mvd[0][i_mb_xy]; | |
| - uint8_t (*mvd1)[2] = h->mb.mvd[1][i_mb_xy]; | |
| if( IS_INTRA(i_mb_type) && i_mb_type != I_PCM ) | |
| h->mb.chroma_pred_mode[i_mb_xy] = x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode]; | |
| else | |
| @@ -1838,6 +1844,7 @@ | |
| CP16( mvd0[6], h->mb.cache.mvd[0][x264_scan8[13]] ); | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| { | |
| + uint8_t (*mvd1)[2] = h->mb.mvd[1][i_mb_xy]; | |
| CP64( mvd1[0], h->mb.cache.mvd[1][x264_scan8[10]] ); | |
| CP16( mvd1[4], h->mb.cache.mvd[1][x264_scan8[5 ]] ); | |
| CP16( mvd1[5], h->mb.cache.mvd[1][x264_scan8[7 ]] ); | |
| @@ -1848,7 +1855,10 @@ | |
| { | |
| M128( mvd0[0] ) = M128_ZERO; | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| + { | |
| + uint8_t (*mvd1)[2] = h->mb.mvd[1][i_mb_xy]; | |
| M128( mvd1[0] ) = M128_ZERO; | |
| + } | |
| } | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| diff -ur x264-go/x264c/external/x264/common/macroblock.h x264-go.new/x264c/external/x264/common/macroblock.h | |
| --- x264-go/x264c/external/x264/common/macroblock.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/macroblock.h 2020-06-06 15:20:58.687039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * macroblock.h: macroblock common functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -299,38 +299,54 @@ | |
| }; | |
| /* Per-frame allocation: is allocated per-thread only in frame-threads mode. */ | |
| +#define x264_macroblock_cache_allocate x264_template(macroblock_cache_allocate) | |
| int x264_macroblock_cache_allocate( x264_t *h ); | |
| +#define x264_macroblock_cache_free x264_template(macroblock_cache_free) | |
| void x264_macroblock_cache_free( x264_t *h ); | |
| /* Per-thread allocation: is allocated per-thread even in sliced-threads mode. */ | |
| +#define x264_macroblock_thread_allocate x264_template(macroblock_thread_allocate) | |
| int x264_macroblock_thread_allocate( x264_t *h, int b_lookahead ); | |
| +#define x264_macroblock_thread_free x264_template(macroblock_thread_free) | |
| void x264_macroblock_thread_free( x264_t *h, int b_lookahead ); | |
| +#define x264_macroblock_slice_init x264_template(macroblock_slice_init) | |
| void x264_macroblock_slice_init( x264_t *h ); | |
| +#define x264_macroblock_thread_init x264_template(macroblock_thread_init) | |
| void x264_macroblock_thread_init( x264_t *h ); | |
| +#define x264_macroblock_cache_load_interlaced x264_template(macroblock_cache_load_interlaced) | |
| void x264_macroblock_cache_load_progressive( x264_t *h, int mb_x, int mb_y ); | |
| +#define x264_macroblock_cache_load_progressive x264_template(macroblock_cache_load_progressive) | |
| void x264_macroblock_cache_load_interlaced( x264_t *h, int mb_x, int mb_y ); | |
| +#define x264_macroblock_deblock_strength x264_template(macroblock_deblock_strength) | |
| void x264_macroblock_deblock_strength( x264_t *h ); | |
| +#define x264_macroblock_cache_save x264_template(macroblock_cache_save) | |
| void x264_macroblock_cache_save( x264_t *h ); | |
| +#define x264_macroblock_bipred_init x264_template(macroblock_bipred_init) | |
| void x264_macroblock_bipred_init( x264_t *h ); | |
| +#define x264_prefetch_fenc x264_template(prefetch_fenc) | |
| void x264_prefetch_fenc( x264_t *h, x264_frame_t *fenc, int i_mb_x, int i_mb_y ); | |
| +#define x264_copy_column8 x264_template(copy_column8) | |
| void x264_copy_column8( pixel *dst, pixel *src ); | |
| /* x264_mb_predict_mv_16x16: | |
| * set mvp with predicted mv for D_16x16 block | |
| * h->mb. need only valid values from other blocks */ | |
| +#define x264_mb_predict_mv_16x16 x264_template(mb_predict_mv_16x16) | |
| void x264_mb_predict_mv_16x16( x264_t *h, int i_list, int i_ref, int16_t mvp[2] ); | |
| /* x264_mb_predict_mv_pskip: | |
| * set mvp with predicted mv for P_SKIP | |
| * h->mb. need only valid values from other blocks */ | |
| +#define x264_mb_predict_mv_pskip x264_template(mb_predict_mv_pskip) | |
| void x264_mb_predict_mv_pskip( x264_t *h, int16_t mv[2] ); | |
| /* x264_mb_predict_mv: | |
| * set mvp with predicted mv for all blocks except SKIP and DIRECT | |
| * h->mb. need valid ref/partition/sub of current block to be valid | |
| * and valid mv/ref from other blocks. */ | |
| +#define x264_mb_predict_mv x264_template(mb_predict_mv) | |
| void x264_mb_predict_mv( x264_t *h, int i_list, int idx, int i_width, int16_t mvp[2] ); | |
| /* x264_mb_predict_mv_direct16x16: | |
| * set h->mb.cache.mv and h->mb.cache.ref for B_SKIP or B_DIRECT | |
| @@ -338,14 +354,18 @@ | |
| * return 1 on success, 0 on failure. | |
| * if b_changed != NULL, set it to whether refs or mvs differ from | |
| * before this functioncall. */ | |
| +#define x264_mb_predict_mv_direct16x16 x264_template(mb_predict_mv_direct16x16) | |
| int x264_mb_predict_mv_direct16x16( x264_t *h, int *b_changed ); | |
| /* x264_mb_predict_mv_ref16x16: | |
| * set mvc with D_16x16 prediction. | |
| * uses all neighbors, even those that didn't end up using this ref. | |
| * h->mb. need only valid values from other blocks */ | |
| +#define x264_mb_predict_mv_ref16x16 x264_template(mb_predict_mv_ref16x16) | |
| void x264_mb_predict_mv_ref16x16( x264_t *h, int i_list, int i_ref, int16_t mvc[8][2], int *i_mvc ); | |
| +#define x264_mb_mc x264_template(mb_mc) | |
| void x264_mb_mc( x264_t *h ); | |
| +#define x264_mb_mc_8x8 x264_template(mb_mc_8x8) | |
| void x264_mb_mc_8x8( x264_t *h, int i8 ); | |
| static ALWAYS_INLINE uint32_t pack16to32( uint32_t a, uint32_t b ) | |
| @@ -441,4 +461,3 @@ | |
| } | |
| #endif | |
| - | |
| diff -ur x264-go/x264c/external/x264/common/mc.c x264-go.new/x264c/external/x264/common/mc.c | |
| --- x264-go/x264c/external/x264/common/mc.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/mc.c 2020-06-06 15:20:58.688039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc.c: motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -29,16 +29,16 @@ | |
| #if HAVE_MMX | |
| #include "x86/mc.h" | |
| #endif | |
| -#if ARCH_PPC | |
| +#if HAVE_ALTIVEC | |
| #include "ppc/mc.h" | |
| #endif | |
| -#if ARCH_ARM | |
| +#if HAVE_ARMV6 | |
| #include "arm/mc.h" | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| #include "aarch64/mc.h" | |
| #endif | |
| -#if ARCH_MIPS | |
| +#if HAVE_MSA | |
| #include "mips/mc.h" | |
| #endif | |
| @@ -107,7 +107,7 @@ | |
| PIXEL_AVG_C( pixel_avg_2x4, 2, 4 ) | |
| PIXEL_AVG_C( pixel_avg_2x2, 2, 2 ) | |
| -static void x264_weight_cache( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache( x264_t *h, x264_weight_t *w ) | |
| { | |
| w->weightfn = h->mc.weight; | |
| } | |
| @@ -134,7 +134,7 @@ | |
| } | |
| #define MC_WEIGHT_C( name, width ) \ | |
| - static void name( pixel *dst, intptr_t i_dst_stride, pixel *src, intptr_t i_src_stride, const x264_weight_t *weight, int height ) \ | |
| +static void name( pixel *dst, intptr_t i_dst_stride, pixel *src, intptr_t i_src_stride, const x264_weight_t *weight, int height ) \ | |
| { \ | |
| mc_weight( dst, i_dst_stride, src, i_src_stride, weight, width, height );\ | |
| } | |
| @@ -146,7 +146,7 @@ | |
| MC_WEIGHT_C( mc_weight_w4, 4 ) | |
| MC_WEIGHT_C( mc_weight_w2, 2 ) | |
| -static weight_fn_t x264_mc_weight_wtab[6] = | |
| +static weight_fn_t mc_weight_wtab[6] = | |
| { | |
| mc_weight_w2, | |
| mc_weight_w4, | |
| @@ -155,12 +155,12 @@ | |
| mc_weight_w16, | |
| mc_weight_w20, | |
| }; | |
| -const x264_weight_t x264_weight_none[3] = { {{0}} }; | |
| + | |
| static void mc_copy( pixel *src, intptr_t i_src_stride, pixel *dst, intptr_t i_dst_stride, int i_width, int i_height ) | |
| { | |
| for( int y = 0; y < i_height; y++ ) | |
| { | |
| - memcpy( dst, src, i_width * sizeof(pixel) ); | |
| + memcpy( dst, src, i_width * SIZEOF_PIXEL ); | |
| src += i_src_stride; | |
| dst += i_dst_stride; | |
| @@ -192,9 +192,6 @@ | |
| } | |
| } | |
| -const uint8_t x264_hpel_ref0[16] = {0,1,1,1,0,1,1,1,2,3,3,3,0,1,1,1}; | |
| -const uint8_t x264_hpel_ref1[16] = {0,0,1,0,2,2,3,2,2,2,3,2,2,2,3,2}; | |
| - | |
| static void mc_luma( pixel *dst, intptr_t i_dst_stride, | |
| pixel *src[4], intptr_t i_src_stride, | |
| int mvx, int mvy, | |
| @@ -296,7 +293,7 @@ | |
| { | |
| while( h-- ) | |
| { | |
| - memcpy( dst, src, w * sizeof(pixel) ); | |
| + memcpy( dst, src, w * SIZEOF_PIXEL ); | |
| dst += i_dst; | |
| src += i_src; | |
| } | |
| @@ -336,10 +333,10 @@ | |
| } | |
| } | |
| -static void x264_plane_copy_deinterleave_rgb_c( pixel *dsta, intptr_t i_dsta, | |
| - pixel *dstb, intptr_t i_dstb, | |
| - pixel *dstc, intptr_t i_dstc, | |
| - pixel *src, intptr_t i_src, int pw, int w, int h ) | |
| +static void plane_copy_deinterleave_rgb_c( pixel *dsta, intptr_t i_dsta, | |
| + pixel *dstb, intptr_t i_dstb, | |
| + pixel *dstc, intptr_t i_dstc, | |
| + pixel *src, intptr_t i_src, int pw, int w, int h ) | |
| { | |
| for( int y=0; y<h; y++, dsta+=i_dsta, dstb+=i_dstb, dstc+=i_dstc, src+=i_src ) | |
| { | |
| @@ -361,9 +358,9 @@ | |
| #define v210_endian_fix32(x) (x) | |
| #endif | |
| -static void x264_plane_copy_deinterleave_v210_c( pixel *dsty, intptr_t i_dsty, | |
| - pixel *dstc, intptr_t i_dstc, | |
| - uint32_t *src, intptr_t i_src, int w, int h ) | |
| +static void plane_copy_deinterleave_v210_c( pixel *dsty, intptr_t i_dsty, | |
| + pixel *dstc, intptr_t i_dstc, | |
| + uint32_t *src, intptr_t i_src, int w, int h ) | |
| { | |
| for( int l = 0; l < h; l++ ) | |
| { | |
| @@ -465,7 +462,7 @@ | |
| // duplicate last row and column so that their interpolation doesn't have to be special-cased | |
| for( int y = 0; y < i_height; y++ ) | |
| src[i_width+y*i_stride] = src[i_width-1+y*i_stride]; | |
| - memcpy( src+i_stride*i_height, src+i_stride*(i_height-1), (i_width+1) * sizeof(pixel) ); | |
| + memcpy( src+i_stride*i_height, src+i_stride*(i_height-1), (i_width+1) * SIZEOF_PIXEL ); | |
| h->mc.frame_init_lowres_core( src, frame->lowres[0], frame->lowres[1], frame->lowres[2], frame->lowres[3], | |
| i_stride, frame->i_stride_lowres, frame->i_width_lowres, frame->i_lines_lowres ); | |
| x264_frame_expand_border_lowres( frame ); | |
| @@ -532,7 +529,7 @@ | |
| unsigned width = h->mb.i_mb_width; | |
| unsigned height = h->mb.i_mb_height; | |
| - for( unsigned i = 0; i < len; i++ ) | |
| + for( int i = 0; i < len; i++ ) | |
| { | |
| int lists_used = lowres_costs[i]>>LOWRES_COST_SHIFT; | |
| @@ -610,7 +607,7 @@ | |
| dst[i] = (int16_t)endian_fix16( src[i] ) * (1.0f/256.0f); | |
| } | |
| -void x264_mc_init( int cpu, x264_mc_functions_t *pf, int cpu_independent ) | |
| +void x264_mc_init( uint32_t cpu, x264_mc_functions_t *pf, int cpu_independent ) | |
| { | |
| pf->mc_luma = mc_luma; | |
| pf->get_ref = get_ref; | |
| @@ -630,10 +627,10 @@ | |
| pf->avg[PIXEL_2x4] = pixel_avg_2x4; | |
| pf->avg[PIXEL_2x2] = pixel_avg_2x2; | |
| - pf->weight = x264_mc_weight_wtab; | |
| - pf->offsetadd = x264_mc_weight_wtab; | |
| - pf->offsetsub = x264_mc_weight_wtab; | |
| - pf->weight_cache = x264_weight_cache; | |
| + pf->weight = mc_weight_wtab; | |
| + pf->offsetadd = mc_weight_wtab; | |
| + pf->offsetsub = mc_weight_wtab; | |
| + pf->weight_cache = weight_cache; | |
| pf->copy_16x16_unaligned = mc_copy_w16; | |
| pf->copy[PIXEL_16x16] = mc_copy_w16; | |
| @@ -647,13 +644,15 @@ | |
| pf->plane_copy = x264_plane_copy_c; | |
| pf->plane_copy_swap = x264_plane_copy_swap_c; | |
| pf->plane_copy_interleave = x264_plane_copy_interleave_c; | |
| + | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_c; | |
| pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_c; | |
| - pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_c; | |
| - pf->plane_copy_deinterleave_v210 = x264_plane_copy_deinterleave_v210_c; | |
| + pf->plane_copy_deinterleave_rgb = plane_copy_deinterleave_rgb_c; | |
| + pf->plane_copy_deinterleave_v210 = plane_copy_deinterleave_v210_c; | |
| pf->hpel_filter = hpel_filter; | |
| + pf->prefetch_fenc_400 = prefetch_fenc_null; | |
| pf->prefetch_fenc_420 = prefetch_fenc_null; | |
| pf->prefetch_fenc_422 = prefetch_fenc_null; | |
| pf->prefetch_ref = prefetch_ref_null; | |
| @@ -681,7 +680,7 @@ | |
| #if HAVE_ARMV6 | |
| x264_mc_init_arm( cpu, pf ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_mc_init_aarch64( cpu, pf ); | |
| #endif | |
| #if HAVE_MSA | |
| diff -ur x264-go/x264c/external/x264/common/mc.h x264-go.new/x264c/external/x264/common/mc.h | |
| --- x264-go/x264c/external/x264/common/mc.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/mc.h 2020-06-06 15:20:58.688039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc.h: motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2004-2017 x264 project | |
| + * Copyright (C) 2004-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * | |
| @@ -34,14 +34,15 @@ | |
| MC_CLIP_ADD((s)[1], (x)[1]);\ | |
| } while( 0 ) | |
| +#define x264_mbtree_propagate_list_internal_neon x264_template(mbtree_propagate_list_internal_neon) | |
| #define PROPAGATE_LIST(cpu)\ | |
| void x264_mbtree_propagate_list_internal_##cpu( int16_t (*mvs)[2], int16_t *propagate_amount,\ | |
| uint16_t *lowres_costs, int16_t *output,\ | |
| int bipred_weight, int mb_y, int len );\ | |
| \ | |
| -static void x264_mbtree_propagate_list_##cpu( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2],\ | |
| - int16_t *propagate_amount, uint16_t *lowres_costs,\ | |
| - int bipred_weight, int mb_y, int len, int list )\ | |
| +static void mbtree_propagate_list_##cpu( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2],\ | |
| + int16_t *propagate_amount, uint16_t *lowres_costs,\ | |
| + int bipred_weight, int mb_y, int len, int list )\ | |
| {\ | |
| int16_t *current = h->scratch_buffer2;\ | |
| \ | |
| @@ -52,7 +53,7 @@ | |
| unsigned width = h->mb.i_mb_width;\ | |
| unsigned height = h->mb.i_mb_height;\ | |
| \ | |
| - for( unsigned i = 0; i < len; current += 32 )\ | |
| + for( int i = 0; i < len; current += 32 )\ | |
| {\ | |
| int end = X264_MIN( i+8, len );\ | |
| for( ; i < end; i++, current += 2 )\ | |
| @@ -100,12 +101,13 @@ | |
| }\ | |
| } | |
| +#define x264_plane_copy_c x264_template(plane_copy_c) | |
| void x264_plane_copy_c( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| #define PLANE_COPY(align, cpu)\ | |
| -static void x264_plane_copy_##cpu( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h )\ | |
| +static void plane_copy_##cpu( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h )\ | |
| {\ | |
| - int c_w = (align) / sizeof(pixel) - 1;\ | |
| + int c_w = (align) / SIZEOF_PIXEL - 1;\ | |
| if( w < 256 ) /* tiny resolutions don't want non-temporal hints. dunno the exact threshold. */\ | |
| x264_plane_copy_c( dst, i_dst, src, i_src, w, h );\ | |
| else if( !(w&c_w) )\ | |
| @@ -124,16 +126,17 @@ | |
| x264_plane_copy_core_##cpu( dst+i_dst, i_dst, src+i_src, i_src, (w+c_w)&~c_w, h );\ | |
| }\ | |
| /* use plain memcpy on the last line (in memory order) to avoid overreading src. */\ | |
| - memcpy( dst, src, w*sizeof(pixel) );\ | |
| + memcpy( dst, src, w*SIZEOF_PIXEL );\ | |
| }\ | |
| } | |
| +#define x264_plane_copy_swap_c x264_template(plane_copy_swap_c) | |
| void x264_plane_copy_swap_c( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| #define PLANE_COPY_SWAP(align, cpu)\ | |
| -static void x264_plane_copy_swap_##cpu( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h )\ | |
| +static void plane_copy_swap_##cpu( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h )\ | |
| {\ | |
| - int c_w = (align>>1) / sizeof(pixel) - 1;\ | |
| + int c_w = (align>>1) / SIZEOF_PIXEL - 1;\ | |
| if( !(w&c_w) )\ | |
| x264_plane_copy_swap_core_##cpu( dst, i_dst, src, i_src, w, h );\ | |
| else if( w > c_w )\ | |
| @@ -160,16 +163,17 @@ | |
| x264_plane_copy_swap_c( dst, i_dst, src, i_src, w, h );\ | |
| } | |
| +#define x264_plane_copy_deinterleave_c x264_template(plane_copy_deinterleave_c) | |
| void x264_plane_copy_deinterleave_c( pixel *dsta, intptr_t i_dsta, pixel *dstb, intptr_t i_dstb, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| /* We can utilize existing plane_copy_deinterleave() functions for YUYV/UYUV | |
| * input with the additional constraint that we cannot overread src. */ | |
| #define PLANE_COPY_YUYV(align, cpu)\ | |
| -static void x264_plane_copy_deinterleave_yuyv_##cpu( pixel *dsta, intptr_t i_dsta, pixel *dstb, intptr_t i_dstb,\ | |
| - pixel *src, intptr_t i_src, int w, int h )\ | |
| +static void plane_copy_deinterleave_yuyv_##cpu( pixel *dsta, intptr_t i_dsta, pixel *dstb, intptr_t i_dstb,\ | |
| + pixel *src, intptr_t i_src, int w, int h )\ | |
| {\ | |
| - int c_w = (align>>1) / sizeof(pixel) - 1;\ | |
| + int c_w = (align>>1) / SIZEOF_PIXEL - 1;\ | |
| if( !(w&c_w) )\ | |
| x264_plane_copy_deinterleave_##cpu( dsta, i_dsta, dstb, i_dstb, src, i_src, w, h );\ | |
| else if( w > c_w )\ | |
| @@ -193,16 +197,17 @@ | |
| x264_plane_copy_deinterleave_c( dsta, i_dsta, dstb, i_dstb, src, i_src, w, h );\ | |
| } | |
| +#define x264_plane_copy_interleave_c x264_template(plane_copy_interleave_c) | |
| void x264_plane_copy_interleave_c( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| #define PLANE_INTERLEAVE(cpu) \ | |
| -static void x264_plane_copy_interleave_##cpu( pixel *dst, intptr_t i_dst,\ | |
| - pixel *srcu, intptr_t i_srcu,\ | |
| - pixel *srcv, intptr_t i_srcv, int w, int h )\ | |
| +static void plane_copy_interleave_##cpu( pixel *dst, intptr_t i_dst,\ | |
| + pixel *srcu, intptr_t i_srcu,\ | |
| + pixel *srcv, intptr_t i_srcv, int w, int h )\ | |
| {\ | |
| - int c_w = 16 / sizeof(pixel) - 1;\ | |
| + int c_w = 16 / SIZEOF_PIXEL - 1;\ | |
| if( !(w&c_w) )\ | |
| x264_plane_copy_interleave_core_##cpu( dst, i_dst, srcu, i_srcu, srcv, i_srcv, w, h );\ | |
| else if( w > c_w && (i_srcu ^ i_srcv) >= 0 ) /* only works correctly for strides with identical signs */\ | |
| @@ -239,9 +244,7 @@ | |
| weight_fn_t *weightfn; | |
| } ALIGNED_16( x264_weight_t ); | |
| -extern const x264_weight_t x264_weight_none[3]; | |
| -extern const uint8_t x264_hpel_ref0[16]; | |
| -extern const uint8_t x264_hpel_ref1[16]; | |
| +#define x264_weight_none ((const x264_weight_t*)x264_zero) | |
| #define SET_WEIGHT( w, b, s, d, o )\ | |
| {\ | |
| @@ -305,6 +308,7 @@ | |
| /* prefetch the next few macroblocks of fenc or fdec */ | |
| void (*prefetch_fenc) ( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); | |
| + void (*prefetch_fenc_400)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); | |
| void (*prefetch_fenc_420)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); | |
| void (*prefetch_fenc_422)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); | |
| /* prefetch the next few macroblocks of a hpel reference frame */ | |
| @@ -335,6 +339,7 @@ | |
| void (*mbtree_fix8_unpack)( float *dst, uint16_t *src, int count ); | |
| } x264_mc_functions_t; | |
| -void x264_mc_init( int cpu, x264_mc_functions_t *pf, int cpu_independent ); | |
| +#define x264_mc_init x264_template(mc_init) | |
| +void x264_mc_init( uint32_t cpu, x264_mc_functions_t *pf, int cpu_independent ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common: mips | |
| diff -ur x264-go/x264c/external/x264/common/mvpred.c x264-go.new/x264c/external/x264/common/mvpred.c | |
| --- x264-go/x264c/external/x264/common/mvpred.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/mvpred.c 2020-06-06 15:20:58.689039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mvpred.c: motion vector prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -180,7 +180,7 @@ | |
| x264_mb_predict_mv_16x16( h, 0, 0, mv ); | |
| } | |
| -static int x264_mb_predict_mv_direct16x16_temporal( x264_t *h ) | |
| +static int mb_predict_mv_direct16x16_temporal( x264_t *h ) | |
| { | |
| int mb_x = h->mb.i_mb_x; | |
| int mb_y = h->mb.i_mb_y; | |
| @@ -286,7 +286,7 @@ | |
| return 1; | |
| } | |
| -static ALWAYS_INLINE int x264_mb_predict_mv_direct16x16_spatial( x264_t *h, int b_interlaced ) | |
| +static ALWAYS_INLINE int mb_predict_mv_direct16x16_spatial( x264_t *h, int b_interlaced ) | |
| { | |
| int8_t ref[2]; | |
| ALIGNED_ARRAY_8( int16_t, mv,[2],[2] ); | |
| @@ -441,14 +441,14 @@ | |
| } | |
| -static int x264_mb_predict_mv_direct16x16_spatial_interlaced( x264_t *h ) | |
| +static int mb_predict_mv_direct16x16_spatial_interlaced( x264_t *h ) | |
| { | |
| - return x264_mb_predict_mv_direct16x16_spatial( h, 1 ); | |
| + return mb_predict_mv_direct16x16_spatial( h, 1 ); | |
| } | |
| -static int x264_mb_predict_mv_direct16x16_spatial_progressive( x264_t *h ) | |
| +static int mb_predict_mv_direct16x16_spatial_progressive( x264_t *h ) | |
| { | |
| - return x264_mb_predict_mv_direct16x16_spatial( h, 0 ); | |
| + return mb_predict_mv_direct16x16_spatial( h, 0 ); | |
| } | |
| int x264_mb_predict_mv_direct16x16( x264_t *h, int *b_changed ) | |
| @@ -459,12 +459,12 @@ | |
| else if( h->sh.b_direct_spatial_mv_pred ) | |
| { | |
| if( SLICE_MBAFF ) | |
| - b_available = x264_mb_predict_mv_direct16x16_spatial_interlaced( h ); | |
| + b_available = mb_predict_mv_direct16x16_spatial_interlaced( h ); | |
| else | |
| - b_available = x264_mb_predict_mv_direct16x16_spatial_progressive( h ); | |
| + b_available = mb_predict_mv_direct16x16_spatial_progressive( h ); | |
| } | |
| else | |
| - b_available = x264_mb_predict_mv_direct16x16_temporal( h ); | |
| + b_available = mb_predict_mv_direct16x16_temporal( h ); | |
| if( b_changed != NULL && b_available ) | |
| { | |
| Only in x264-go.new/x264c/external/x264/common: opencl | |
| diff -ur x264-go/x264c/external/x264/common/opencl.c x264-go.new/x264c/external/x264/common/opencl.c | |
| --- x264-go/x264c/external/x264/common/opencl.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/opencl.c 2020-06-06 15:20:58.689039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * opencl.c: OpenCL initialization and kernel compilation | |
| ***************************************************************************** | |
| - * Copyright (C) 2012-2017 x264 project | |
| + * Copyright (C) 2012-2020 x264 project | |
| * | |
| * Authors: Steve Borho <sborho@multicorewareinc.com> | |
| * Anton Mitrofanov <BugMaster@narod.ru> | |
| @@ -115,11 +115,11 @@ | |
| /* Requires full include path in case of out-of-tree builds */ | |
| #include "common/oclobj.h" | |
| -static int x264_detect_switchable_graphics( void ); | |
| +static int detect_switchable_graphics( void ); | |
| /* Try to load the cached compiled program binary, verify the device context is | |
| * still valid before reuse */ | |
| -static cl_program x264_opencl_cache_load( x264_t *h, const char *dev_name, const char *dev_vendor, const char *driver_version ) | |
| +static cl_program opencl_cache_load( x264_t *h, const char *dev_name, const char *dev_vendor, const char *driver_version ) | |
| { | |
| /* try to load cached program binary */ | |
| FILE *fp = x264_fopen( h->param.psz_clbin_file, "rb" ); | |
| @@ -131,8 +131,11 @@ | |
| uint8_t *binary = NULL; | |
| fseek( fp, 0, SEEK_END ); | |
| - size_t size = ftell( fp ); | |
| - rewind( fp ); | |
| + int64_t file_size = ftell( fp ); | |
| + fseek( fp, 0, SEEK_SET ); | |
| + if( file_size < 0 || (uint64_t)file_size > SIZE_MAX ) | |
| + goto fail; | |
| + size_t size = file_size; | |
| CHECKED_MALLOC( binary, size ); | |
| if( fread( binary, 1, size, fp ) != size ) | |
| @@ -168,7 +171,7 @@ | |
| /* Save the compiled program binary to a file for later reuse. Device context | |
| * is also saved in the cache file so we do not reuse stale binaries */ | |
| -static void x264_opencl_cache_save( x264_t *h, cl_program program, const char *dev_name, const char *dev_vendor, const char *driver_version ) | |
| +static void opencl_cache_save( x264_t *h, cl_program program, const char *dev_name, const char *dev_vendor, const char *driver_version ) | |
| { | |
| FILE *fp = x264_fopen( h->param.psz_clbin_file, "wb" ); | |
| if( !fp ) | |
| @@ -216,7 +219,7 @@ | |
| * the Makefile. It defines a x264_opencl_source byte array which we will pass | |
| * to clCreateProgramWithSource(). We also attempt to use a cache file for the | |
| * compiled binary, stored in the current working folder. */ | |
| -static cl_program x264_opencl_compile( x264_t *h ) | |
| +static cl_program opencl_compile( x264_t *h ) | |
| { | |
| x264_opencl_function_t *ocl = h->opencl.ocl; | |
| cl_program program = NULL; | |
| @@ -239,7 +242,7 @@ | |
| if( vectorize ) | |
| { | |
| /* Disable OpenCL on Intel/AMD switchable graphics devices */ | |
| - if( x264_detect_switchable_graphics() ) | |
| + if( detect_switchable_graphics() ) | |
| { | |
| x264_log( h, X264_LOG_INFO, "OpenCL acceleration disabled, switchable graphics detected\n" ); | |
| return NULL; | |
| @@ -257,7 +260,7 @@ | |
| x264_log( h, X264_LOG_INFO, "OpenCL acceleration enabled with %s %s %s\n", dev_vendor, dev_name, h->opencl.b_device_AMD_SI ? "(SI)" : "" ); | |
| - program = x264_opencl_cache_load( h, dev_name, dev_vendor, driver_version ); | |
| + program = opencl_cache_load( h, dev_name, dev_vendor, driver_version ); | |
| if( !program ) | |
| { | |
| /* clCreateProgramWithSource() requires a pointer variable, you cannot just use &x264_opencl_source */ | |
| @@ -277,7 +280,7 @@ | |
| status = ocl->clBuildProgram( program, 1, &h->opencl.device, buildopts, NULL, NULL ); | |
| if( status == CL_SUCCESS ) | |
| { | |
| - x264_opencl_cache_save( h, program, dev_name, dev_vendor, driver_version ); | |
| + opencl_cache_save( h, program, dev_name, dev_vendor, driver_version ); | |
| return program; | |
| } | |
| @@ -322,7 +325,7 @@ | |
| return NULL; | |
| } | |
| -static int x264_opencl_lookahead_alloc( x264_t *h ) | |
| +static int opencl_lookahead_alloc( x264_t *h ) | |
| { | |
| if( !h->param.rc.i_lookahead ) | |
| return -1; | |
| @@ -360,11 +363,11 @@ | |
| x264_opencl_function_t *ocl = h->opencl.ocl; | |
| cl_int status; | |
| - h->opencl.lookahead_program = x264_opencl_compile( h ); | |
| + h->opencl.lookahead_program = opencl_compile( h ); | |
| if( !h->opencl.lookahead_program ) | |
| goto fail; | |
| - for( int i = 0; i < ARRAY_SIZE(kernelnames); i++ ) | |
| + for( int i = 0; i < ARRAY_ELEMS(kernelnames); i++ ) | |
| { | |
| *kernels[i] = ocl->clCreateKernel( h->opencl.lookahead_program, kernelnames[i], &status ); | |
| if( status != CL_SUCCESS ) | |
| @@ -394,7 +397,7 @@ | |
| return -1; | |
| } | |
| -static void CL_CALLBACK x264_opencl_error_notify( const char *errinfo, const void *private_info, size_t cb, void *user_data ) | |
| +static void CL_CALLBACK opencl_error_notify( const char *errinfo, const void *private_info, size_t cb, void *user_data ) | |
| { | |
| /* Any error notification can be assumed to be fatal to the OpenCL context. | |
| * We need to stop using it immediately to prevent further damage. */ | |
| @@ -470,7 +473,7 @@ | |
| if( context ) | |
| ocl->clReleaseContext( context ); | |
| - context = ocl->clCreateContext( NULL, 1, &h->opencl.device, (void*)x264_opencl_error_notify, (void*)h, &status ); | |
| + context = ocl->clCreateContext( NULL, 1, &h->opencl.device, (void*)opencl_error_notify, (void*)h, &status ); | |
| if( status != CL_SUCCESS || !context ) | |
| continue; | |
| @@ -540,7 +543,7 @@ | |
| if( ret ) | |
| x264_log( h, X264_LOG_WARNING, "OpenCL: Unable to find a compatible device\n" ); | |
| else | |
| - ret = x264_opencl_lookahead_alloc( h ); | |
| + ret = opencl_lookahead_alloc( h ); | |
| fail: | |
| if( context ) | |
| @@ -551,7 +554,7 @@ | |
| return ret; | |
| } | |
| -static void x264_opencl_lookahead_free( x264_t *h ) | |
| +static void opencl_lookahead_free( x264_t *h ) | |
| { | |
| x264_opencl_function_t *ocl = h->opencl.ocl; | |
| @@ -600,7 +603,7 @@ | |
| if( h->opencl.queue ) | |
| ocl->clFinish( h->opencl.queue ); | |
| - x264_opencl_lookahead_free( h ); | |
| + opencl_lookahead_free( h ); | |
| if( h->opencl.queue ) | |
| { | |
| @@ -663,7 +666,7 @@ | |
| return x264_malloc( iSize ); | |
| } | |
| -static int x264_detect_switchable_graphics( void ) | |
| +static int detect_switchable_graphics( void ) | |
| { | |
| void *hDLL; | |
| ADL_MAIN_CONTROL_CREATE ADL_Main_Control_Create; | |
| diff -ur x264-go/x264c/external/x264/common/opencl.h x264-go.new/x264c/external/x264/common/opencl.h | |
| --- x264-go/x264c/external/x264/common/opencl.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/opencl.h 2020-06-06 15:20:58.689039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * opencl.h: OpenCL structures and defines | |
| ***************************************************************************** | |
| - * Copyright (C) 2012-2017 x264 project | |
| + * Copyright (C) 2012-2020 x264 project | |
| * | |
| * Authors: Steve Borho <sborho@multicorewareinc.com> | |
| * Anton Mitrofanov <BugMaster@narod.ru> | |
| @@ -793,12 +793,17 @@ | |
| typedef struct x264_frame x264_frame; | |
| +#define x264_opencl_load_library x264_template(opencl_load_library) | |
| x264_opencl_function_t *x264_opencl_load_library( void ); | |
| +#define x264_opencl_close_library x264_template(opencl_close_library) | |
| void x264_opencl_close_library( x264_opencl_function_t *ocl ); | |
| +#define x264_opencl_lookahead_init x264_template(opencl_lookahead_init) | |
| int x264_opencl_lookahead_init( x264_t *h ); | |
| +#define x264_opencl_lookahead_delete x264_template(opencl_lookahead_delete) | |
| void x264_opencl_lookahead_delete( x264_t *h ); | |
| +#define x264_opencl_frame_delete x264_template(opencl_frame_delete) | |
| void x264_opencl_frame_delete( x264_frame *frame ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/osdep.c x264-go.new/x264c/external/x264/common/osdep.c | |
| --- x264-go/x264c/external/x264/common/osdep.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/osdep.c 2020-06-06 15:20:58.690039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * osdep.c: platform-specific code | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Steven Walters <kemuri9@gmail.com> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -25,12 +25,7 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#include "common.h" | |
| - | |
| -#ifdef _WIN32 | |
| -#include <windows.h> | |
| -#include <io.h> | |
| -#endif | |
| +#include "osdep.h" | |
| #if SYS_WINDOWS | |
| #include <sys/types.h> | |
| @@ -51,6 +46,10 @@ | |
| struct timeb tb; | |
| ftime( &tb ); | |
| return ((int64_t)tb.time * 1000 + (int64_t)tb.millitm) * 1000; | |
| +#elif HAVE_CLOCK_GETTIME | |
| + struct timespec ts; | |
| + clock_gettime( CLOCK_MONOTONIC, &ts ); | |
| + return (int64_t)ts.tv_sec * 1000000 + (int64_t)ts.tv_nsec / 1000; | |
| #else | |
| struct timeval tv_date; | |
| gettimeofday( &tv_date, NULL ); | |
| @@ -60,9 +59,9 @@ | |
| #if HAVE_WIN32THREAD || PTW32_STATIC_LIB | |
| /* state of the threading library being initialized */ | |
| -static volatile LONG x264_threading_is_init = 0; | |
| +static volatile LONG threading_is_init = 0; | |
| -static void x264_threading_destroy( void ) | |
| +static void threading_destroy( void ) | |
| { | |
| #if PTW32_STATIC_LIB | |
| pthread_win32_thread_detach_np(); | |
| @@ -72,11 +71,8 @@ | |
| #endif | |
| } | |
| -int x264_threading_init( void ) | |
| +static int threading_init( void ) | |
| { | |
| - /* if already init, then do nothing */ | |
| - if( InterlockedCompareExchange( &x264_threading_is_init, 1, 0 ) ) | |
| - return 0; | |
| #if PTW32_STATIC_LIB | |
| /* if static pthread-win32 is already initialized, then do nothing */ | |
| if( ptw32_processInitialized ) | |
| @@ -88,119 +84,25 @@ | |
| return -1; | |
| #endif | |
| /* register cleanup to run at process termination */ | |
| - atexit( x264_threading_destroy ); | |
| - | |
| + atexit( threading_destroy ); | |
| return 0; | |
| } | |
| -#endif | |
| - | |
| -#ifdef _WIN32 | |
| -/* Functions for dealing with Unicode on Windows. */ | |
| -FILE *x264_fopen( const char *filename, const char *mode ) | |
| -{ | |
| - wchar_t filename_utf16[MAX_PATH]; | |
| - wchar_t mode_utf16[16]; | |
| - if( utf8_to_utf16( filename, filename_utf16 ) && utf8_to_utf16( mode, mode_utf16 ) ) | |
| - return _wfopen( filename_utf16, mode_utf16 ); | |
| - return NULL; | |
| -} | |
| -int x264_rename( const char *oldname, const char *newname ) | |
| +int x264_threading_init( void ) | |
| { | |
| - wchar_t oldname_utf16[MAX_PATH]; | |
| - wchar_t newname_utf16[MAX_PATH]; | |
| - if( utf8_to_utf16( oldname, oldname_utf16 ) && utf8_to_utf16( newname, newname_utf16 ) ) | |
| + LONG state; | |
| + while( (state = InterlockedCompareExchange( &threading_is_init, -1, 0 )) != 0 ) | |
| { | |
| - /* POSIX says that rename() removes the destination, but Win32 doesn't. */ | |
| - _wunlink( newname_utf16 ); | |
| - return _wrename( oldname_utf16, newname_utf16 ); | |
| + /* if already init, then do nothing */ | |
| + if( state > 0 ) | |
| + return 0; | |
| } | |
| - return -1; | |
| -} | |
| - | |
| -int x264_stat( const char *path, x264_struct_stat *buf ) | |
| -{ | |
| - wchar_t path_utf16[MAX_PATH]; | |
| - if( utf8_to_utf16( path, path_utf16 ) ) | |
| - return _wstati64( path_utf16, buf ); | |
| - return -1; | |
| -} | |
| - | |
| -#if !HAVE_WINRT | |
| -int x264_vfprintf( FILE *stream, const char *format, va_list arg ) | |
| -{ | |
| - HANDLE console = NULL; | |
| - DWORD mode; | |
| - | |
| - if( stream == stdout ) | |
| - console = GetStdHandle( STD_OUTPUT_HANDLE ); | |
| - else if( stream == stderr ) | |
| - console = GetStdHandle( STD_ERROR_HANDLE ); | |
| - | |
| - /* Only attempt to convert to UTF-16 when writing to a non-redirected console screen buffer. */ | |
| - if( GetConsoleMode( console, &mode ) ) | |
| + if( threading_init() < 0 ) | |
| { | |
| - char buf[4096]; | |
| - wchar_t buf_utf16[4096]; | |
| - va_list arg2; | |
| - | |
| - va_copy( arg2, arg ); | |
| - int length = vsnprintf( buf, sizeof(buf), format, arg2 ); | |
| - va_end( arg2 ); | |
| - | |
| - if( length > 0 && length < sizeof(buf) ) | |
| - { | |
| - /* WriteConsoleW is the most reliable way to output Unicode to a console. */ | |
| - int length_utf16 = MultiByteToWideChar( CP_UTF8, 0, buf, length, buf_utf16, sizeof(buf_utf16)/sizeof(wchar_t) ); | |
| - DWORD written; | |
| - WriteConsoleW( console, buf_utf16, length_utf16, &written, NULL ); | |
| - return length; | |
| - } | |
| + InterlockedExchange( &threading_is_init, 0 ); | |
| + return -1; | |
| } | |
| - return vfprintf( stream, format, arg ); | |
| -} | |
| - | |
| -int x264_is_pipe( const char *path ) | |
| -{ | |
| - wchar_t path_utf16[MAX_PATH]; | |
| - if( utf8_to_utf16( path, path_utf16 ) ) | |
| - return WaitNamedPipeW( path_utf16, 0 ); | |
| + InterlockedExchange( &threading_is_init, 1 ); | |
| return 0; | |
| } | |
| #endif | |
| - | |
| -#if defined(_MSC_VER) && _MSC_VER < 1900 | |
| -/* MSVC pre-VS2015 has broken snprintf/vsnprintf implementations which are incompatible with C99. */ | |
| -int x264_snprintf( char *s, size_t n, const char *fmt, ... ) | |
| -{ | |
| - va_list arg; | |
| - va_start( arg, fmt ); | |
| - int length = x264_vsnprintf( s, n, fmt, arg ); | |
| - va_end( arg ); | |
| - return length; | |
| -} | |
| - | |
| -int x264_vsnprintf( char *s, size_t n, const char *fmt, va_list arg ) | |
| -{ | |
| - int length = -1; | |
| - | |
| - if( n ) | |
| - { | |
| - va_list arg2; | |
| - va_copy( arg2, arg ); | |
| - length = _vsnprintf( s, n, fmt, arg2 ); | |
| - va_end( arg2 ); | |
| - | |
| - /* _(v)snprintf adds a null-terminator only if the length is less than the buffer size. */ | |
| - if( length < 0 || length >= n ) | |
| - s[n-1] = '\0'; | |
| - } | |
| - | |
| - /* _(v)snprintf returns a negative number if the length is greater than the buffer size. */ | |
| - if( length < 0 ) | |
| - return _vscprintf( fmt, arg ); | |
| - | |
| - return length; | |
| -} | |
| -#endif | |
| -#endif | |
| diff -ur x264-go/x264c/external/x264/common/osdep.h x264-go.new/x264c/external/x264/common/osdep.h | |
| --- x264-go/x264c/external/x264/common/osdep.h 2018-02-15 14:40:34.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/osdep.h 2020-06-06 15:27:52.459050342 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * osdep.h: platform-specific code | |
| ***************************************************************************** | |
| - * Copyright (C) 2007-2017 x264 project | |
| + * Copyright (C) 2007-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -43,6 +43,13 @@ | |
| #include <math.h> | |
| #endif | |
| +#ifdef _WIN32 | |
| +#include <windows.h> | |
| +#include <io.h> | |
| +#endif | |
| + | |
| +#include "x264.h" | |
| + | |
| #if !HAVE_LOG2F | |
| #define log2f(x) (logf(x)/0.693147180559945f) | |
| #define log2(x) (log(x)/0.693147180559945) | |
| @@ -54,12 +61,6 @@ | |
| #define strncasecmp _strnicmp | |
| #define strtok_r strtok_s | |
| #define S_ISREG(x) (((x) & S_IFMT) == S_IFREG) | |
| -#if _MSC_VER < 1900 | |
| -int x264_snprintf( char *s, size_t n, const char *fmt, ... ); | |
| -int x264_vsnprintf( char *s, size_t n, const char *fmt, va_list arg ); | |
| -#define snprintf x264_snprintf | |
| -#define vsnprintf x264_vsnprintf | |
| -#endif | |
| #else | |
| #include <strings.h> | |
| #endif | |
| @@ -72,18 +73,85 @@ | |
| #define isfinite finite | |
| #endif | |
| -#ifdef _WIN32 | |
| -#ifndef strtok_r | |
| +#if !HAVE_STRTOK_R && !defined(strtok_r) | |
| #define strtok_r(str,delim,save) strtok(str,delim) | |
| #endif | |
| +#if defined(_MSC_VER) && _MSC_VER < 1900 | |
| +/* MSVC pre-VS2015 has broken snprintf/vsnprintf implementations which are incompatible with C99. */ | |
| +static inline int x264_vsnprintf( char *s, size_t n, const char *fmt, va_list arg ) | |
| +{ | |
| + int length = -1; | |
| + | |
| + if( n ) | |
| + { | |
| + va_list arg2; | |
| + va_copy( arg2, arg ); | |
| + length = _vsnprintf( s, n, fmt, arg2 ); | |
| + va_end( arg2 ); | |
| + | |
| + /* _(v)snprintf adds a null-terminator only if the length is less than the buffer size. */ | |
| + if( length < 0 || length >= n ) | |
| + s[n-1] = '\0'; | |
| + } | |
| + | |
| + /* _(v)snprintf returns a negative number if the length is greater than the buffer size. */ | |
| + if( length < 0 ) | |
| + return _vscprintf( fmt, arg ); | |
| + | |
| + return length; | |
| +} | |
| + | |
| +static inline int x264_snprintf( char *s, size_t n, const char *fmt, ... ) | |
| +{ | |
| + va_list arg; | |
| + va_start( arg, fmt ); | |
| + int length = x264_vsnprintf( s, n, fmt, arg ); | |
| + va_end( arg ); | |
| + return length; | |
| +} | |
| + | |
| +#define snprintf x264_snprintf | |
| +#define vsnprintf x264_vsnprintf | |
| +#endif | |
| + | |
| +#ifdef _WIN32 | |
| #define utf8_to_utf16( utf8, utf16 )\ | |
| MultiByteToWideChar( CP_UTF8, MB_ERR_INVALID_CHARS, utf8, -1, utf16, sizeof(utf16)/sizeof(wchar_t) ) | |
| -FILE *x264_fopen( const char *filename, const char *mode ); | |
| -int x264_rename( const char *oldname, const char *newname ); | |
| + | |
| +/* Functions for dealing with Unicode on Windows. */ | |
| +static inline FILE *x264_fopen( const char *filename, const char *mode ) | |
| +{ | |
| + wchar_t filename_utf16[MAX_PATH]; | |
| + wchar_t mode_utf16[16]; | |
| + if( utf8_to_utf16( filename, filename_utf16 ) && utf8_to_utf16( mode, mode_utf16 ) ) | |
| + return _wfopen( filename_utf16, mode_utf16 ); | |
| + return NULL; | |
| +} | |
| + | |
| +static inline int x264_rename( const char *oldname, const char *newname ) | |
| +{ | |
| + wchar_t oldname_utf16[MAX_PATH]; | |
| + wchar_t newname_utf16[MAX_PATH]; | |
| + if( utf8_to_utf16( oldname, oldname_utf16 ) && utf8_to_utf16( newname, newname_utf16 ) ) | |
| + { | |
| + /* POSIX says that rename() removes the destination, but Win32 doesn't. */ | |
| + _wunlink( newname_utf16 ); | |
| + return _wrename( oldname_utf16, newname_utf16 ); | |
| + } | |
| + return -1; | |
| +} | |
| + | |
| #define x264_struct_stat struct _stati64 | |
| #define x264_fstat _fstati64 | |
| -int x264_stat( const char *path, x264_struct_stat *buf ); | |
| + | |
| +static inline int x264_stat( const char *path, x264_struct_stat *buf ) | |
| +{ | |
| + wchar_t path_utf16[MAX_PATH]; | |
| + if( utf8_to_utf16( path, path_utf16 ) ) | |
| + return _wstati64( path_utf16, buf ); | |
| + return -1; | |
| +} | |
| #else | |
| #define x264_fopen fopen | |
| #define x264_rename rename | |
| @@ -93,16 +161,57 @@ | |
| #endif | |
| /* mdate: return the current date in microsecond */ | |
| -int64_t x264_mdate( void ); | |
| +X264_API int64_t x264_mdate( void ); | |
| #if defined(_WIN32) && !HAVE_WINRT | |
| -int x264_vfprintf( FILE *stream, const char *format, va_list arg ); | |
| -int x264_is_pipe( const char *path ); | |
| +static inline int x264_vfprintf( FILE *stream, const char *format, va_list arg ) | |
| +{ | |
| + HANDLE console = NULL; | |
| + DWORD mode; | |
| + | |
| + if( stream == stdout ) | |
| + console = GetStdHandle( STD_OUTPUT_HANDLE ); | |
| + else if( stream == stderr ) | |
| + console = GetStdHandle( STD_ERROR_HANDLE ); | |
| + | |
| + /* Only attempt to convert to UTF-16 when writing to a non-redirected console screen buffer. */ | |
| + if( GetConsoleMode( console, &mode ) ) | |
| + { | |
| + char buf[4096]; | |
| + wchar_t buf_utf16[4096]; | |
| + va_list arg2; | |
| + | |
| + va_copy( arg2, arg ); | |
| + int length = vsnprintf( buf, sizeof(buf), format, arg2 ); | |
| + va_end( arg2 ); | |
| + | |
| + if( length > 0 && (unsigned)length < sizeof(buf) ) | |
| + { | |
| + /* WriteConsoleW is the most reliable way to output Unicode to a console. */ | |
| + int length_utf16 = MultiByteToWideChar( CP_UTF8, 0, buf, length, buf_utf16, sizeof(buf_utf16)/sizeof(wchar_t) ); | |
| + DWORD written; | |
| + WriteConsoleW( console, buf_utf16, length_utf16, &written, NULL ); | |
| + return length; | |
| + } | |
| + } | |
| + return vfprintf( stream, format, arg ); | |
| +} | |
| + | |
| +static inline int x264_is_pipe( const char *path ) | |
| +{ | |
| + wchar_t path_utf16[MAX_PATH]; | |
| + if( utf8_to_utf16( path, path_utf16 ) ) | |
| + return WaitNamedPipeW( path_utf16, 0 ); | |
| + return 0; | |
| +} | |
| #else | |
| #define x264_vfprintf vfprintf | |
| #define x264_is_pipe(x) 0 | |
| #endif | |
| +#define x264_glue3_expand(x,y,z) x##_##y##_##z | |
| +#define x264_glue3(x,y,z) x264_glue3_expand(x,y,z) | |
| + | |
| #ifdef _MSC_VER | |
| #define DECLARE_ALIGNED( var, n ) __declspec(align(n)) var | |
| #else | |
| @@ -160,6 +269,12 @@ | |
| #define ALIGNED_ARRAY_64 ALIGNED_ARRAY_16 | |
| #endif | |
| +#if STACK_ALIGNMENT > 16 || (ARCH_X86 && STACK_ALIGNMENT > 4) | |
| +#define REALIGN_STACK __attribute__((force_align_arg_pointer)) | |
| +#else | |
| +#define REALIGN_STACK | |
| +#endif | |
| + | |
| #if defined(__GNUC__) && (__GNUC__ > 3 || __GNUC__ == 3 && __GNUC_MINOR__ > 0) | |
| #define UNUSED __attribute__((unused)) | |
| #define ALWAYS_INLINE __attribute__((always_inline)) inline | |
| @@ -244,7 +359,7 @@ | |
| #endif | |
| #if HAVE_WIN32THREAD || PTW32_STATIC_LIB | |
| -int x264_threading_init( void ); | |
| +X264_API int x264_threading_init( void ); | |
| #else | |
| #define x264_threading_init() 0 | |
| #endif | |
| @@ -308,7 +423,7 @@ | |
| return endian_fix32(x>>32) + ((uint64_t)endian_fix32(x)<<32); | |
| } | |
| #endif | |
| -static ALWAYS_INLINE intptr_t endian_fix( intptr_t x ) | |
| +static ALWAYS_INLINE uintptr_t endian_fix( uintptr_t x ) | |
| { | |
| return WORD_SIZE == 8 ? endian_fix64(x) : endian_fix32(x); | |
| } | |
| @@ -319,7 +434,7 @@ | |
| #endif | |
| /* For values with 4 bits or less. */ | |
| -static int ALWAYS_INLINE x264_ctz_4bit( uint32_t x ) | |
| +static ALWAYS_INLINE int x264_ctz_4bit( uint32_t x ) | |
| { | |
| static uint8_t lut[16] = {4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0}; | |
| return lut[x]; | |
| @@ -329,7 +444,7 @@ | |
| #define x264_clz(x) __builtin_clz(x) | |
| #define x264_ctz(x) __builtin_ctz(x) | |
| #else | |
| -static int ALWAYS_INLINE x264_clz( uint32_t x ) | |
| +static ALWAYS_INLINE int x264_clz( uint32_t x ) | |
| { | |
| static uint8_t lut[16] = {4,3,2,2,1,1,1,1,0,0,0,0,0,0,0,0}; | |
| int y, z = (((x >> 16) - 1) >> 27) & 16; | |
| @@ -341,7 +456,7 @@ | |
| return z + lut[x]; | |
| } | |
| -static int ALWAYS_INLINE x264_ctz( uint32_t x ) | |
| +static ALWAYS_INLINE int x264_ctz( uint32_t x ) | |
| { | |
| static uint8_t lut[16] = {4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0}; | |
| int y, z = (((x & 0xffff) - 1) >> 27) & 16; | |
| diff -ur x264-go/x264c/external/x264/common/pixel.c x264-go.new/x264c/external/x264/common/pixel.c | |
| --- x264-go/x264c/external/x264/common/pixel.c 2020-06-05 14:33:54.745687917 +0200 | |
| +++ x264-go.new/x264c/external/x264/common/pixel.c 2020-06-06 15:20:58.690039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * pixel.c: pixel metrics | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -31,18 +31,18 @@ | |
| # include "x86/pixel.h" | |
| # include "x86/predict.h" | |
| #endif | |
| -#if ARCH_PPC | |
| +#if HAVE_ALTIVEC | |
| # include "ppc/pixel.h" | |
| #endif | |
| -#if ARCH_ARM | |
| +#if HAVE_ARMV6 | |
| # include "arm/pixel.h" | |
| # include "arm/predict.h" | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| # include "aarch64/pixel.h" | |
| # include "aarch64/predict.h" | |
| #endif | |
| -#if ARCH_MIPS | |
| +#if HAVE_MSA | |
| # include "mips/pixel.h" | |
| #endif | |
| @@ -194,9 +194,9 @@ | |
| return sum + ((uint64_t)sqr << 32); \ | |
| } | |
| -PIXEL_VAR_C( x264_pixel_var_16x16, 16, 16 ) | |
| -PIXEL_VAR_C( x264_pixel_var_8x16, 8, 16 ) | |
| -PIXEL_VAR_C( x264_pixel_var_8x8, 8, 8 ) | |
| +PIXEL_VAR_C( pixel_var_16x16, 16, 16 ) | |
| +PIXEL_VAR_C( pixel_var_8x16, 8, 16 ) | |
| +PIXEL_VAR_C( pixel_var_8x8, 8, 8 ) | |
| /**************************************************************************** | |
| * pixel_var2_wxh | |
| @@ -225,8 +225,8 @@ | |
| sqr_v - ((int64_t)sum_v * sum_v >> shift); \ | |
| } | |
| -PIXEL_VAR2_C( x264_pixel_var2_8x16, 16, 7 ) | |
| -PIXEL_VAR2_C( x264_pixel_var2_8x8, 8, 6 ) | |
| +PIXEL_VAR2_C( pixel_var2_8x16, 16, 7 ) | |
| +PIXEL_VAR2_C( pixel_var2_8x8, 8, 6 ) | |
| #if BIT_DEPTH > 8 | |
| typedef uint32_t sum_t; | |
| @@ -503,17 +503,18 @@ | |
| SATD_X_DECL7( _sse4 ) | |
| SATD_X_DECL7( _avx ) | |
| SATD_X_DECL7( _xop ) | |
| +SATD_X_DECL7( _avx512 ) | |
| #endif // !HIGH_BIT_DEPTH | |
| #endif | |
| #if !HIGH_BIT_DEPTH | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| +#if HAVE_ARMV6 || HAVE_AARCH64 | |
| SATD_X_DECL7( _neon ) | |
| #endif | |
| #endif // !HIGH_BIT_DEPTH | |
| #define INTRA_MBCMP_8x8( mbcmp, cpu, cpu2 )\ | |
| -void x264_intra_##mbcmp##_x3_8x8##cpu( pixel *fenc, pixel edge[36], int res[3] )\ | |
| +static void intra_##mbcmp##_x3_8x8##cpu( pixel *fenc, pixel edge[36], int res[3] )\ | |
| {\ | |
| ALIGNED_ARRAY_16( pixel, pix, [8*FDEC_STRIDE] );\ | |
| x264_predict_8x8_v##cpu2( pix, edge );\ | |
| @@ -531,13 +532,13 @@ | |
| INTRA_MBCMP_8x8( sad, _mmx2, _c ) | |
| INTRA_MBCMP_8x8(sa8d, _sse2, _sse2 ) | |
| #endif | |
| -#if !HIGH_BIT_DEPTH && (HAVE_ARMV6 || ARCH_AARCH64) | |
| +#if !HIGH_BIT_DEPTH && (HAVE_ARMV6 || HAVE_AARCH64) | |
| INTRA_MBCMP_8x8( sad, _neon, _neon ) | |
| INTRA_MBCMP_8x8(sa8d, _neon, _neon ) | |
| #endif | |
| #define INTRA_MBCMP( mbcmp, size, pred1, pred2, pred3, chroma, cpu, cpu2 )\ | |
| -void x264_intra_##mbcmp##_x3_##size##chroma##cpu( pixel *fenc, pixel *fdec, int res[3] )\ | |
| +static void intra_##mbcmp##_x3_##size##chroma##cpu( pixel *fenc, pixel *fdec, int res[3] )\ | |
| {\ | |
| x264_predict_##size##chroma##_##pred1##cpu2( fdec );\ | |
| res[0] = x264_pixel_##mbcmp##_##size##cpu( fdec, FDEC_STRIDE, fenc, FENC_STRIDE );\ | |
| @@ -601,7 +602,7 @@ | |
| INTRA_MBCMP( sad, 16x16, v, h, dc, , _neon, _neon ) | |
| INTRA_MBCMP(satd, 16x16, v, h, dc, , _neon, _neon ) | |
| #endif | |
| -#if !HIGH_BIT_DEPTH && ARCH_AARCH64 | |
| +#if !HIGH_BIT_DEPTH && HAVE_AARCH64 | |
| INTRA_MBCMP( sad, 4x4, v, h, dc, , _neon, _neon ) | |
| INTRA_MBCMP(satd, 4x4, v, h, dc, , _neon, _neon ) | |
| INTRA_MBCMP( sad, 8x8, dc, h, v, c, _neon, _neon ) | |
| @@ -613,7 +614,7 @@ | |
| #endif | |
| // No C implementation of intra_satd_x9. See checkasm for its behavior, | |
| -// or see x264_mb_analyse_intra for the entirely different algorithm we | |
| +// or see mb_analyse_intra for the entirely different algorithm we | |
| // use when lacking an asm implementation of it. | |
| @@ -803,7 +804,7 @@ | |
| /**************************************************************************** | |
| * x264_pixel_init: | |
| ****************************************************************************/ | |
| -void x264_pixel_init( int cpu, x264_pixel_function_t *pixf ) | |
| +void x264_pixel_init( uint32_t cpu, x264_pixel_function_t *pixf ) | |
| { | |
| memset( pixf, 0, sizeof(*pixf) ); | |
| @@ -851,11 +852,11 @@ | |
| pixf->sa8d[PIXEL_16x16] = x264_pixel_sa8d_16x16; | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8; | |
| - pixf->var[PIXEL_16x16] = x264_pixel_var_16x16; | |
| - pixf->var[PIXEL_8x16] = x264_pixel_var_8x16; | |
| - pixf->var[PIXEL_8x8] = x264_pixel_var_8x8; | |
| - pixf->var2[PIXEL_8x16] = x264_pixel_var2_8x16; | |
| - pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8; | |
| + pixf->var[PIXEL_16x16] = pixel_var_16x16; | |
| + pixf->var[PIXEL_8x16] = pixel_var_8x16; | |
| + pixf->var[PIXEL_8x8] = pixel_var_8x8; | |
| + pixf->var2[PIXEL_8x16] = pixel_var2_8x16; | |
| + pixf->var2[PIXEL_8x8] = pixel_var2_8x8; | |
| pixf->ssd_nv12_core = pixel_ssd_nv12_core; | |
| pixf->ssim_4x4x2_core = ssim_4x4x2_core; | |
| @@ -863,16 +864,16 @@ | |
| pixf->vsad = pixel_vsad; | |
| pixf->asd8 = pixel_asd8; | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4; | |
| - pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4; | |
| - pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8; | |
| - pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c; | |
| - pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16; | |
| - pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16; | |
| + pixf->intra_sad_x3_4x4 = intra_sad_x3_4x4; | |
| + pixf->intra_satd_x3_4x4 = intra_satd_x3_4x4; | |
| + pixf->intra_sad_x3_8x8 = intra_sad_x3_8x8; | |
| + pixf->intra_sa8d_x3_8x8 = intra_sa8d_x3_8x8; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c; | |
| + pixf->intra_satd_x3_8x8c = intra_satd_x3_8x8c; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16; | |
| + pixf->intra_satd_x3_16x16 = intra_satd_x3_16x16; | |
| #if HIGH_BIT_DEPTH | |
| #if HAVE_MMX | |
| @@ -889,14 +890,14 @@ | |
| INIT8( ssd, _mmx2 ); | |
| INIT_ADS( _mmx2 ); | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_mmx2; | |
| + pixf->intra_sad_x3_4x4 = intra_sad_x3_4x4_mmx2; | |
| pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4_mmx2; | |
| - pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_mmx2; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_mmx2; | |
| + pixf->intra_sad_x3_8x8 = intra_sad_x3_8x8_mmx2; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c_mmx2; | |
| pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_mmx2; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_mmx2; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_mmx2; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_mmx2; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_mmx2; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_mmx2; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16_mmx2; | |
| pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_mmx2; | |
| } | |
| if( cpu&X264_CPU_SSE2 ) | |
| @@ -906,21 +907,22 @@ | |
| INIT6( satd, _sse2 ); | |
| pixf->satd[PIXEL_4x16] = x264_pixel_satd_4x16_sse2; | |
| - pixf->sa8d[PIXEL_16x16] = x264_pixel_sa8d_16x16_sse2; | |
| - pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_sse2; | |
| -#if ARCH_X86_64 | |
| - pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8_sse2; | |
| - pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_sse2; | |
| -#endif | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_sse2; | |
| - pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_sse2; | |
| + pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_sse2; | |
| pixf->ssim_4x4x2_core = x264_pixel_ssim_4x4x2_core_sse2; | |
| pixf->ssim_end4 = x264_pixel_ssim_end4_sse2; | |
| pixf->var[PIXEL_16x16] = x264_pixel_var_16x16_sse2; | |
| pixf->var[PIXEL_8x8] = x264_pixel_var_8x8_sse2; | |
| pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8_sse2; | |
| pixf->var2[PIXEL_8x16] = x264_pixel_var2_8x16_sse2; | |
| - pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_sse2; | |
| + | |
| + pixf->sa8d[PIXEL_16x16] = x264_pixel_sa8d_16x16_sse2; | |
| + pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_sse2; | |
| +#if ARCH_X86_64 | |
| + pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_sse2; | |
| +#endif | |
| + pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_sse2; | |
| + pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_sse2; | |
| + pixf->intra_sa8d_x3_8x8 = intra_sa8d_x3_8x8_sse2; | |
| } | |
| if( (cpu&X264_CPU_SSE2) && !(cpu&X264_CPU_SSE2_IS_SLOW) ) | |
| { | |
| @@ -936,10 +938,10 @@ | |
| pixf->vsad = x264_pixel_vsad_sse2; | |
| pixf->asd8 = x264_pixel_asd8_sse2; | |
| pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_sse2; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_sse2; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_sse2; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_sse2; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_sse2; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c_sse2; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_sse2; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_sse2; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16_sse2; | |
| } | |
| if( cpu&X264_CPU_SSE2_IS_FAST ) | |
| { | |
| @@ -971,7 +973,6 @@ | |
| } | |
| pixf->vsad = x264_pixel_vsad_ssse3; | |
| pixf->asd8 = x264_pixel_asd8_ssse3; | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_ssse3; | |
| pixf->sa8d[PIXEL_16x16]= x264_pixel_sa8d_16x16_ssse3; | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_ssse3; | |
| #if ARCH_X86_64 | |
| @@ -979,10 +980,10 @@ | |
| #endif | |
| pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_ssse3; | |
| pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_ssse3; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_ssse3; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_ssse3; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_ssse3; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_ssse3; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c_ssse3; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_ssse3; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_ssse3; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16_ssse3; | |
| } | |
| if( cpu&X264_CPU_SSE4 ) | |
| { | |
| @@ -997,7 +998,7 @@ | |
| #if ARCH_X86_64 | |
| pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_sse4; | |
| #endif | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_sse4; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_sse4; | |
| } | |
| if( cpu&X264_CPU_AVX ) | |
| { | |
| @@ -1022,7 +1023,7 @@ | |
| #if ARCH_X86_64 | |
| pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_avx; | |
| #endif | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_avx; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_avx; | |
| } | |
| if( cpu&X264_CPU_XOP ) | |
| { | |
| @@ -1108,8 +1109,8 @@ | |
| #endif | |
| pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_mmx2; | |
| pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_mmx2; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_mmx2; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_mmx2; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_mmx2; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_mmx2; | |
| pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_mmx2; | |
| pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_mmx2; | |
| pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_mmx2; | |
| @@ -1151,8 +1152,8 @@ | |
| pixf->var[PIXEL_8x8] = x264_pixel_var_8x8_sse2; | |
| pixf->var[PIXEL_8x16] = x264_pixel_var_8x16_sse2; | |
| pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_sse2; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_sse2; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_sse2; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_sse2; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_sse2; | |
| if( cpu&X264_CPU_CACHELINE_64 ) | |
| { | |
| INIT2( ssd, _sse2); /* faster for width 16 on p4 */ | |
| @@ -1231,7 +1232,7 @@ | |
| pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_ssse3; | |
| if( !(cpu&X264_CPU_SLOW_PSHUFB) ) | |
| pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_ssse3; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_ssse3; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_ssse3; | |
| pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_ssse3; | |
| pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_ssse3; | |
| pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8_ssse3; | |
| @@ -1271,7 +1272,7 @@ | |
| } | |
| pixf->sa8d[PIXEL_16x16]= x264_pixel_sa8d_16x16_sse4; | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_sse4; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_sse4; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_sse4; | |
| #if ARCH_X86_64 | |
| pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_sse4; | |
| #endif | |
| @@ -1301,7 +1302,7 @@ | |
| INIT5( ssd, _avx ); | |
| pixf->sa8d[PIXEL_16x16]= x264_pixel_sa8d_16x16_avx; | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_avx; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_avx; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_avx; | |
| pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_avx; | |
| pixf->var[PIXEL_16x16] = x264_pixel_var_16x16_avx; | |
| pixf->var[PIXEL_8x16] = x264_pixel_var_8x16_avx; | |
| @@ -1326,7 +1327,7 @@ | |
| INIT5( ssd, _xop ); | |
| pixf->sa8d[PIXEL_16x16]= x264_pixel_sa8d_16x16_xop; | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_xop; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_xop; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_xop; | |
| pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_xop; | |
| #if ARCH_X86_64 | |
| pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_xop; | |
| @@ -1363,6 +1364,8 @@ | |
| INIT7( sad_x3, _avx512 ); | |
| INIT7( sad_x4, _avx512 ); | |
| INIT8( satd, _avx512 ); | |
| + INIT7( satd_x3, _avx512 ); | |
| + INIT7( satd_x4, _avx512 ); | |
| pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_avx512; | |
| pixf->var[PIXEL_8x8] = x264_pixel_var_8x8_avx512; | |
| pixf->var[PIXEL_8x16] = x264_pixel_var_8x16_avx512; | |
| @@ -1402,16 +1405,16 @@ | |
| pixf->vsad = x264_pixel_vsad_neon; | |
| pixf->asd8 = x264_pixel_asd8_neon; | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_neon; | |
| - pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4_neon; | |
| - pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_neon; | |
| - pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8_neon; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_neon; | |
| - pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_neon; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_neon; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_neon; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_neon; | |
| - pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_neon; | |
| + pixf->intra_sad_x3_4x4 = intra_sad_x3_4x4_neon; | |
| + pixf->intra_satd_x3_4x4 = intra_satd_x3_4x4_neon; | |
| + pixf->intra_sad_x3_8x8 = intra_sad_x3_8x8_neon; | |
| + pixf->intra_sa8d_x3_8x8 = intra_sa8d_x3_8x8_neon; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c_neon; | |
| + pixf->intra_satd_x3_8x8c = intra_satd_x3_8x8c_neon; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_neon; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_neon; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16_neon; | |
| + pixf->intra_satd_x3_16x16 = intra_satd_x3_16x16_neon; | |
| pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_neon; | |
| pixf->ssim_4x4x2_core = x264_pixel_ssim_4x4x2_core_neon; | |
| @@ -1431,7 +1434,7 @@ | |
| } | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| INIT8( sad, _neon ); | |
| @@ -1457,22 +1460,22 @@ | |
| pixf->vsad = x264_pixel_vsad_neon; | |
| pixf->asd8 = x264_pixel_asd8_neon; | |
| - pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_neon; | |
| - pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4_neon; | |
| - pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_neon; | |
| - pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8_neon; | |
| - pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_neon; | |
| - pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_neon; | |
| - pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_neon; | |
| - pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_neon; | |
| - pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_neon; | |
| - pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_neon; | |
| + pixf->intra_sad_x3_4x4 = intra_sad_x3_4x4_neon; | |
| + pixf->intra_satd_x3_4x4 = intra_satd_x3_4x4_neon; | |
| + pixf->intra_sad_x3_8x8 = intra_sad_x3_8x8_neon; | |
| + pixf->intra_sa8d_x3_8x8 = intra_sa8d_x3_8x8_neon; | |
| + pixf->intra_sad_x3_8x8c = intra_sad_x3_8x8c_neon; | |
| + pixf->intra_satd_x3_8x8c = intra_satd_x3_8x8c_neon; | |
| + pixf->intra_sad_x3_8x16c = intra_sad_x3_8x16c_neon; | |
| + pixf->intra_satd_x3_8x16c = intra_satd_x3_8x16c_neon; | |
| + pixf->intra_sad_x3_16x16 = intra_sad_x3_16x16_neon; | |
| + pixf->intra_satd_x3_16x16 = intra_satd_x3_16x16_neon; | |
| pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_neon; | |
| pixf->ssim_4x4x2_core = x264_pixel_ssim_4x4x2_core_neon; | |
| pixf->ssim_end4 = x264_pixel_ssim_end4_neon; | |
| } | |
| -#endif // ARCH_AARCH64 | |
| +#endif // HAVE_AARCH64 | |
| #if HAVE_MSA | |
| if( cpu&X264_CPU_MSA ) | |
| diff -ur x264-go/x264c/external/x264/common/pixel.h x264-go.new/x264c/external/x264/common/pixel.h | |
| --- x264-go/x264c/external/x264/common/pixel.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/pixel.h 2020-06-06 15:20:58.690039437 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * pixel.c: pixel metrics | |
| ***************************************************************************** | |
| - * Copyright (C) 2004-2017 x264 project | |
| + * Copyright (C) 2004-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -143,13 +143,18 @@ | |
| int (*intra_sad_x9_8x8) ( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds ); | |
| } x264_pixel_function_t; | |
| -void x264_pixel_init( int cpu, x264_pixel_function_t *pixf ); | |
| +#define x264_pixel_init x264_template(pixel_init) | |
| +void x264_pixel_init( uint32_t cpu, x264_pixel_function_t *pixf ); | |
| +#define x264_pixel_ssd_nv12 x264_template(pixel_ssd_nv12) | |
| void x264_pixel_ssd_nv12 ( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2, | |
| int i_width, int i_height, uint64_t *ssd_u, uint64_t *ssd_v ); | |
| +#define x264_pixel_ssd_wxh x264_template(pixel_ssd_wxh) | |
| uint64_t x264_pixel_ssd_wxh( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2, | |
| int i_width, int i_height ); | |
| +#define x264_pixel_ssim_wxh x264_template(pixel_ssim_wxh) | |
| float x264_pixel_ssim_wxh ( x264_pixel_function_t *pf, pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2, | |
| int i_width, int i_height, void *buf, int *cnt ); | |
| +#define x264_field_vsad x264_template(field_vsad) | |
| int x264_field_vsad( x264_t *h, int mb_x, int mb_y ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common: ppc | |
| diff -ur x264-go/x264c/external/x264/common/predict.c x264-go.new/x264c/external/x264/common/predict.c | |
| --- x264-go/x264c/external/x264/common/predict.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/predict.c 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.c: intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -34,16 +34,16 @@ | |
| #if HAVE_MMX | |
| # include "x86/predict.h" | |
| #endif | |
| -#if ARCH_PPC | |
| +#if HAVE_ALTIVEC | |
| # include "ppc/predict.h" | |
| #endif | |
| -#if ARCH_ARM | |
| +#if HAVE_ARMV6 | |
| # include "arm/predict.h" | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| # include "aarch64/predict.h" | |
| #endif | |
| -#if ARCH_MIPS | |
| +#if HAVE_MSA | |
| # include "mips/predict.h" | |
| #endif | |
| @@ -74,7 +74,7 @@ | |
| PREDICT_16x16_DC( dcsplat ); | |
| } | |
| -static void x264_predict_16x16_dc_left_c( pixel *src ) | |
| +static void predict_16x16_dc_left_c( pixel *src ) | |
| { | |
| int dc = 0; | |
| @@ -84,7 +84,7 @@ | |
| PREDICT_16x16_DC( dcsplat ); | |
| } | |
| -static void x264_predict_16x16_dc_top_c( pixel *src ) | |
| +static void predict_16x16_dc_top_c( pixel *src ) | |
| { | |
| int dc = 0; | |
| @@ -94,7 +94,7 @@ | |
| PREDICT_16x16_DC( dcsplat ); | |
| } | |
| -static void x264_predict_16x16_dc_128_c( pixel *src ) | |
| +static void predict_16x16_dc_128_c( pixel *src ) | |
| { | |
| PREDICT_16x16_DC( PIXEL_SPLAT_X4( 1 << (BIT_DEPTH-1) ) ); | |
| } | |
| @@ -161,7 +161,7 @@ | |
| * 8x8 prediction for intra chroma block (4:2:0) | |
| ****************************************************************************/ | |
| -static void x264_predict_8x8c_dc_128_c( pixel *src ) | |
| +static void predict_8x8c_dc_128_c( pixel *src ) | |
| { | |
| for( int y = 0; y < 8; y++ ) | |
| { | |
| @@ -170,7 +170,7 @@ | |
| src += FDEC_STRIDE; | |
| } | |
| } | |
| -static void x264_predict_8x8c_dc_left_c( pixel *src ) | |
| +static void predict_8x8c_dc_left_c( pixel *src ) | |
| { | |
| int dc0 = 0, dc1 = 0; | |
| @@ -196,7 +196,7 @@ | |
| } | |
| } | |
| -static void x264_predict_8x8c_dc_top_c( pixel *src ) | |
| +static void predict_8x8c_dc_top_c( pixel *src ) | |
| { | |
| int dc0 = 0, dc1 = 0; | |
| @@ -308,7 +308,7 @@ | |
| * 8x16 prediction for intra chroma block (4:2:2) | |
| ****************************************************************************/ | |
| -static void x264_predict_8x16c_dc_128_c( pixel *src ) | |
| +static void predict_8x16c_dc_128_c( pixel *src ) | |
| { | |
| for( int y = 0; y < 16; y++ ) | |
| { | |
| @@ -317,7 +317,7 @@ | |
| src += FDEC_STRIDE; | |
| } | |
| } | |
| -static void x264_predict_8x16c_dc_left_c( pixel *src ) | |
| +static void predict_8x16c_dc_left_c( pixel *src ) | |
| { | |
| for( int i = 0; i < 4; i++ ) | |
| { | |
| @@ -336,7 +336,7 @@ | |
| } | |
| } | |
| } | |
| -static void x264_predict_8x16c_dc_top_c( pixel *src ) | |
| +static void predict_8x16c_dc_top_c( pixel *src ) | |
| { | |
| int dc0 = 0, dc1 = 0; | |
| @@ -475,16 +475,16 @@ | |
| #define PREDICT_4x4_DC(v)\ | |
| SRC_X4(0,0) = SRC_X4(0,1) = SRC_X4(0,2) = SRC_X4(0,3) = v; | |
| -static void x264_predict_4x4_dc_128_c( pixel *src ) | |
| +static void predict_4x4_dc_128_c( pixel *src ) | |
| { | |
| PREDICT_4x4_DC( PIXEL_SPLAT_X4( 1 << (BIT_DEPTH-1) ) ); | |
| } | |
| -static void x264_predict_4x4_dc_left_c( pixel *src ) | |
| +static void predict_4x4_dc_left_c( pixel *src ) | |
| { | |
| pixel4 dc = PIXEL_SPLAT_X4( (SRC(-1,0) + SRC(-1,1) + SRC(-1,2) + SRC(-1,3) + 2) >> 2 ); | |
| PREDICT_4x4_DC( dc ); | |
| } | |
| -static void x264_predict_4x4_dc_top_c( pixel *src ) | |
| +static void predict_4x4_dc_top_c( pixel *src ) | |
| { | |
| pixel4 dc = PIXEL_SPLAT_X4( (SRC(0,-1) + SRC(1,-1) + SRC(2,-1) + SRC(3,-1) + 2) >> 2 ); | |
| PREDICT_4x4_DC( dc ); | |
| @@ -528,7 +528,7 @@ | |
| #define F1(a,b) (((a)+(b)+1)>>1) | |
| #define F2(a,b,c) (((a)+2*(b)+(c)+2)>>2) | |
| -static void x264_predict_4x4_ddl_c( pixel *src ) | |
| +static void predict_4x4_ddl_c( pixel *src ) | |
| { | |
| PREDICT_4x4_LOAD_TOP | |
| PREDICT_4x4_LOAD_TOP_RIGHT | |
| @@ -540,7 +540,7 @@ | |
| SRC(3,2)=SRC(2,3)= F2(t5,t6,t7); | |
| SRC(3,3)= F2(t6,t7,t7); | |
| } | |
| -static void x264_predict_4x4_ddr_c( pixel *src ) | |
| +static void predict_4x4_ddr_c( pixel *src ) | |
| { | |
| int lt = SRC(-1,-1); | |
| PREDICT_4x4_LOAD_LEFT | |
| @@ -554,7 +554,7 @@ | |
| SRC(0,3)= F2(l1,l2,l3); | |
| } | |
| -static void x264_predict_4x4_vr_c( pixel *src ) | |
| +static void predict_4x4_vr_c( pixel *src ) | |
| { | |
| int lt = SRC(-1,-1); | |
| PREDICT_4x4_LOAD_LEFT | |
| @@ -571,7 +571,7 @@ | |
| SRC(3,0)= F1(t2,t3); | |
| } | |
| -static void x264_predict_4x4_hd_c( pixel *src ) | |
| +static void predict_4x4_hd_c( pixel *src ) | |
| { | |
| int lt= SRC(-1,-1); | |
| PREDICT_4x4_LOAD_LEFT | |
| @@ -588,7 +588,7 @@ | |
| SRC(3,0)= F2(t2,t1,t0); | |
| } | |
| -static void x264_predict_4x4_vl_c( pixel *src ) | |
| +static void predict_4x4_vl_c( pixel *src ) | |
| { | |
| PREDICT_4x4_LOAD_TOP | |
| PREDICT_4x4_LOAD_TOP_RIGHT | |
| @@ -604,7 +604,7 @@ | |
| SRC(3,3)= F2(t4,t5,t6); | |
| } | |
| -static void x264_predict_4x4_hu_c( pixel *src ) | |
| +static void predict_4x4_hu_c( pixel *src ) | |
| { | |
| PREDICT_4x4_LOAD_LEFT | |
| SRC(0,0)= F1(l0,l1); | |
| @@ -626,7 +626,7 @@ | |
| #define PT(x) \ | |
| edge[16+x] = F2(SRC(x-1,-1), SRC(x,-1), SRC(x+1,-1)); | |
| -static void x264_predict_8x8_filter_c( pixel *src, pixel edge[36], int i_neighbor, int i_filters ) | |
| +static void predict_8x8_filter_c( pixel *src, pixel edge[36], int i_neighbor, int i_filters ) | |
| { | |
| /* edge[7..14] = l7..l0 | |
| * edge[15] = lt | |
| @@ -694,17 +694,17 @@ | |
| src += FDEC_STRIDE; \ | |
| } | |
| -static void x264_predict_8x8_dc_128_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_dc_128_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_DC( PIXEL_SPLAT_X4( 1 << (BIT_DEPTH-1) ) ); | |
| } | |
| -static void x264_predict_8x8_dc_left_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_dc_left_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_LEFT | |
| pixel4 dc = PIXEL_SPLAT_X4( (l0+l1+l2+l3+l4+l5+l6+l7+4) >> 3 ); | |
| PREDICT_8x8_DC( dc ); | |
| } | |
| -static void x264_predict_8x8_dc_top_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_dc_top_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| pixel4 dc = PIXEL_SPLAT_X4( (t0+t1+t2+t3+t4+t5+t6+t7+4) >> 3 ); | |
| @@ -735,7 +735,7 @@ | |
| MPIXEL_X4( src+y*FDEC_STRIDE+4 ) = top[1]; | |
| } | |
| } | |
| -static void x264_predict_8x8_ddl_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_ddl_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| PREDICT_8x8_LOAD_TOPRIGHT | |
| @@ -755,7 +755,7 @@ | |
| SRC(6,7)=SRC(7,6)= F2(t13,t14,t15); | |
| SRC(7,7)= F2(t14,t15,t15); | |
| } | |
| -static void x264_predict_8x8_ddr_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_ddr_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| PREDICT_8x8_LOAD_LEFT | |
| @@ -777,7 +777,7 @@ | |
| SRC(7,0)= F2(t5,t6,t7); | |
| } | |
| -static void x264_predict_8x8_vr_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_vr_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| PREDICT_8x8_LOAD_LEFT | |
| @@ -805,7 +805,7 @@ | |
| SRC(7,1)= F2(t5,t6,t7); | |
| SRC(7,0)= F1(t6,t7); | |
| } | |
| -static void x264_predict_8x8_hd_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_hd_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| PREDICT_8x8_LOAD_LEFT | |
| @@ -832,7 +832,7 @@ | |
| SRC_X4(4,1)= pack_pixel_2to4(p9,p10); | |
| SRC_X4(4,0)= pack_pixel_2to4(p10,p11); | |
| } | |
| -static void x264_predict_8x8_vl_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_vl_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_TOP | |
| PREDICT_8x8_LOAD_TOPRIGHT | |
| @@ -859,7 +859,7 @@ | |
| SRC(7,6)= F1(t10,t11); | |
| SRC(7,7)= F2(t10,t11,t12); | |
| } | |
| -static void x264_predict_8x8_hu_c( pixel *src, pixel edge[36] ) | |
| +static void predict_8x8_hu_c( pixel *src, pixel edge[36] ) | |
| { | |
| PREDICT_8x8_LOAD_LEFT | |
| int p1 = pack_pixel_1to2(F1(l0,l1), F2(l0,l1,l2)); | |
| @@ -883,15 +883,15 @@ | |
| /**************************************************************************** | |
| * Exported functions: | |
| ****************************************************************************/ | |
| -void x264_predict_16x16_init( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_16x16_init( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| pf[I_PRED_16x16_V ] = x264_predict_16x16_v_c; | |
| pf[I_PRED_16x16_H ] = x264_predict_16x16_h_c; | |
| pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_c; | |
| pf[I_PRED_16x16_P ] = x264_predict_16x16_p_c; | |
| - pf[I_PRED_16x16_DC_LEFT]= x264_predict_16x16_dc_left_c; | |
| - pf[I_PRED_16x16_DC_TOP ]= x264_predict_16x16_dc_top_c; | |
| - pf[I_PRED_16x16_DC_128 ]= x264_predict_16x16_dc_128_c; | |
| + pf[I_PRED_16x16_DC_LEFT]= predict_16x16_dc_left_c; | |
| + pf[I_PRED_16x16_DC_TOP ]= predict_16x16_dc_top_c; | |
| + pf[I_PRED_16x16_DC_128 ]= predict_16x16_dc_128_c; | |
| #if HAVE_MMX | |
| x264_predict_16x16_init_mmx( cpu, pf ); | |
| @@ -906,7 +906,7 @@ | |
| x264_predict_16x16_init_arm( cpu, pf ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_predict_16x16_init_aarch64( cpu, pf ); | |
| #endif | |
| @@ -926,15 +926,15 @@ | |
| #endif | |
| } | |
| -void x264_predict_8x8c_init( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x8c_init( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| pf[I_PRED_CHROMA_V ] = x264_predict_8x8c_v_c; | |
| pf[I_PRED_CHROMA_H ] = x264_predict_8x8c_h_c; | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x8c_dc_c; | |
| pf[I_PRED_CHROMA_P ] = x264_predict_8x8c_p_c; | |
| - pf[I_PRED_CHROMA_DC_LEFT]= x264_predict_8x8c_dc_left_c; | |
| - pf[I_PRED_CHROMA_DC_TOP ]= x264_predict_8x8c_dc_top_c; | |
| - pf[I_PRED_CHROMA_DC_128 ]= x264_predict_8x8c_dc_128_c; | |
| + pf[I_PRED_CHROMA_DC_LEFT]= predict_8x8c_dc_left_c; | |
| + pf[I_PRED_CHROMA_DC_TOP ]= predict_8x8c_dc_top_c; | |
| + pf[I_PRED_CHROMA_DC_128 ]= predict_8x8c_dc_128_c; | |
| #if HAVE_MMX | |
| x264_predict_8x8c_init_mmx( cpu, pf ); | |
| @@ -949,7 +949,7 @@ | |
| x264_predict_8x8c_init_arm( cpu, pf ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_predict_8x8c_init_aarch64( cpu, pf ); | |
| #endif | |
| @@ -963,15 +963,15 @@ | |
| #endif | |
| } | |
| -void x264_predict_8x16c_init( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x16c_init( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| pf[I_PRED_CHROMA_V ] = x264_predict_8x16c_v_c; | |
| pf[I_PRED_CHROMA_H ] = x264_predict_8x16c_h_c; | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x16c_dc_c; | |
| pf[I_PRED_CHROMA_P ] = x264_predict_8x16c_p_c; | |
| - pf[I_PRED_CHROMA_DC_LEFT]= x264_predict_8x16c_dc_left_c; | |
| - pf[I_PRED_CHROMA_DC_TOP ]= x264_predict_8x16c_dc_top_c; | |
| - pf[I_PRED_CHROMA_DC_128 ]= x264_predict_8x16c_dc_128_c; | |
| + pf[I_PRED_CHROMA_DC_LEFT]= predict_8x16c_dc_left_c; | |
| + pf[I_PRED_CHROMA_DC_TOP ]= predict_8x16c_dc_top_c; | |
| + pf[I_PRED_CHROMA_DC_128 ]= predict_8x16c_dc_128_c; | |
| #if HAVE_MMX | |
| x264_predict_8x16c_init_mmx( cpu, pf ); | |
| @@ -981,26 +981,26 @@ | |
| x264_predict_8x16c_init_arm( cpu, pf ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_predict_8x16c_init_aarch64( cpu, pf ); | |
| #endif | |
| } | |
| -void x264_predict_8x8_init( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| +void x264_predict_8x8_init( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ) | |
| { | |
| pf[I_PRED_8x8_V] = x264_predict_8x8_v_c; | |
| pf[I_PRED_8x8_H] = x264_predict_8x8_h_c; | |
| pf[I_PRED_8x8_DC] = x264_predict_8x8_dc_c; | |
| - pf[I_PRED_8x8_DDL] = x264_predict_8x8_ddl_c; | |
| - pf[I_PRED_8x8_DDR] = x264_predict_8x8_ddr_c; | |
| - pf[I_PRED_8x8_VR] = x264_predict_8x8_vr_c; | |
| - pf[I_PRED_8x8_HD] = x264_predict_8x8_hd_c; | |
| - pf[I_PRED_8x8_VL] = x264_predict_8x8_vl_c; | |
| - pf[I_PRED_8x8_HU] = x264_predict_8x8_hu_c; | |
| - pf[I_PRED_8x8_DC_LEFT]= x264_predict_8x8_dc_left_c; | |
| - pf[I_PRED_8x8_DC_TOP] = x264_predict_8x8_dc_top_c; | |
| - pf[I_PRED_8x8_DC_128] = x264_predict_8x8_dc_128_c; | |
| - *predict_filter = x264_predict_8x8_filter_c; | |
| + pf[I_PRED_8x8_DDL] = predict_8x8_ddl_c; | |
| + pf[I_PRED_8x8_DDR] = predict_8x8_ddr_c; | |
| + pf[I_PRED_8x8_VR] = predict_8x8_vr_c; | |
| + pf[I_PRED_8x8_HD] = predict_8x8_hd_c; | |
| + pf[I_PRED_8x8_VL] = predict_8x8_vl_c; | |
| + pf[I_PRED_8x8_HU] = predict_8x8_hu_c; | |
| + pf[I_PRED_8x8_DC_LEFT]= predict_8x8_dc_left_c; | |
| + pf[I_PRED_8x8_DC_TOP] = predict_8x8_dc_top_c; | |
| + pf[I_PRED_8x8_DC_128] = predict_8x8_dc_128_c; | |
| + *predict_filter = predict_8x8_filter_c; | |
| #if HAVE_MMX | |
| x264_predict_8x8_init_mmx( cpu, pf, predict_filter ); | |
| @@ -1010,7 +1010,7 @@ | |
| x264_predict_8x8_init_arm( cpu, pf, predict_filter ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_predict_8x8_init_aarch64( cpu, pf, predict_filter ); | |
| #endif | |
| @@ -1024,20 +1024,20 @@ | |
| #endif | |
| } | |
| -void x264_predict_4x4_init( int cpu, x264_predict_t pf[12] ) | |
| +void x264_predict_4x4_init( uint32_t cpu, x264_predict_t pf[12] ) | |
| { | |
| pf[I_PRED_4x4_V] = x264_predict_4x4_v_c; | |
| pf[I_PRED_4x4_H] = x264_predict_4x4_h_c; | |
| pf[I_PRED_4x4_DC] = x264_predict_4x4_dc_c; | |
| - pf[I_PRED_4x4_DDL] = x264_predict_4x4_ddl_c; | |
| - pf[I_PRED_4x4_DDR] = x264_predict_4x4_ddr_c; | |
| - pf[I_PRED_4x4_VR] = x264_predict_4x4_vr_c; | |
| - pf[I_PRED_4x4_HD] = x264_predict_4x4_hd_c; | |
| - pf[I_PRED_4x4_VL] = x264_predict_4x4_vl_c; | |
| - pf[I_PRED_4x4_HU] = x264_predict_4x4_hu_c; | |
| - pf[I_PRED_4x4_DC_LEFT]= x264_predict_4x4_dc_left_c; | |
| - pf[I_PRED_4x4_DC_TOP] = x264_predict_4x4_dc_top_c; | |
| - pf[I_PRED_4x4_DC_128] = x264_predict_4x4_dc_128_c; | |
| + pf[I_PRED_4x4_DDL] = predict_4x4_ddl_c; | |
| + pf[I_PRED_4x4_DDR] = predict_4x4_ddr_c; | |
| + pf[I_PRED_4x4_VR] = predict_4x4_vr_c; | |
| + pf[I_PRED_4x4_HD] = predict_4x4_hd_c; | |
| + pf[I_PRED_4x4_VL] = predict_4x4_vl_c; | |
| + pf[I_PRED_4x4_HU] = predict_4x4_hu_c; | |
| + pf[I_PRED_4x4_DC_LEFT]= predict_4x4_dc_left_c; | |
| + pf[I_PRED_4x4_DC_TOP] = predict_4x4_dc_top_c; | |
| + pf[I_PRED_4x4_DC_128] = predict_4x4_dc_128_c; | |
| #if HAVE_MMX | |
| x264_predict_4x4_init_mmx( cpu, pf ); | |
| @@ -1047,7 +1047,7 @@ | |
| x264_predict_4x4_init_arm( cpu, pf ); | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| x264_predict_4x4_init_aarch64( cpu, pf ); | |
| #endif | |
| } | |
| diff -ur x264-go/x264c/external/x264/common/predict.h x264-go.new/x264c/external/x264/common/predict.h | |
| --- x264-go/x264c/external/x264/common/predict.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/predict.h 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.h: intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -109,30 +109,52 @@ | |
| I_PRED_8x8_DC_128 = 11, | |
| }; | |
| +#define x264_predict_8x8_dc_c x264_template(predict_8x8_dc_c) | |
| void x264_predict_8x8_dc_c ( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_h_c x264_template(predict_8x8_h_c) | |
| void x264_predict_8x8_h_c ( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_v_c x264_template(predict_8x8_v_c) | |
| void x264_predict_8x8_v_c ( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_4x4_dc_c x264_template(predict_4x4_dc_c) | |
| void x264_predict_4x4_dc_c ( pixel *src ); | |
| +#define x264_predict_4x4_h_c x264_template(predict_4x4_h_c) | |
| void x264_predict_4x4_h_c ( pixel *src ); | |
| +#define x264_predict_4x4_v_c x264_template(predict_4x4_v_c) | |
| void x264_predict_4x4_v_c ( pixel *src ); | |
| +#define x264_predict_16x16_dc_c x264_template(predict_16x16_dc_c) | |
| void x264_predict_16x16_dc_c( pixel *src ); | |
| +#define x264_predict_16x16_h_c x264_template(predict_16x16_h_c) | |
| void x264_predict_16x16_h_c ( pixel *src ); | |
| +#define x264_predict_16x16_v_c x264_template(predict_16x16_v_c) | |
| void x264_predict_16x16_v_c ( pixel *src ); | |
| +#define x264_predict_16x16_p_c x264_template(predict_16x16_p_c) | |
| void x264_predict_16x16_p_c ( pixel *src ); | |
| +#define x264_predict_8x8c_dc_c x264_template(predict_8x8c_dc_c) | |
| void x264_predict_8x8c_dc_c ( pixel *src ); | |
| +#define x264_predict_8x8c_h_c x264_template(predict_8x8c_h_c) | |
| void x264_predict_8x8c_h_c ( pixel *src ); | |
| +#define x264_predict_8x8c_v_c x264_template(predict_8x8c_v_c) | |
| void x264_predict_8x8c_v_c ( pixel *src ); | |
| +#define x264_predict_8x8c_p_c x264_template(predict_8x8c_p_c) | |
| void x264_predict_8x8c_p_c ( pixel *src ); | |
| +#define x264_predict_8x16c_dc_c x264_template(predict_8x16c_dc_c) | |
| void x264_predict_8x16c_dc_c( pixel *src ); | |
| +#define x264_predict_8x16c_h_c x264_template(predict_8x16c_h_c) | |
| void x264_predict_8x16c_h_c ( pixel *src ); | |
| +#define x264_predict_8x16c_v_c x264_template(predict_8x16c_v_c) | |
| void x264_predict_8x16c_v_c ( pixel *src ); | |
| +#define x264_predict_8x16c_p_c x264_template(predict_8x16c_p_c) | |
| void x264_predict_8x16c_p_c ( pixel *src ); | |
| -void x264_predict_16x16_init ( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x8c_init ( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x16c_init ( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_4x4_init ( int cpu, x264_predict_t pf[12] ); | |
| -void x264_predict_8x8_init ( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| - | |
| +#define x264_predict_16x16_init x264_template(predict_16x16_init) | |
| +void x264_predict_16x16_init ( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x8c_init x264_template(predict_8x8c_init) | |
| +void x264_predict_8x8c_init ( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x16c_init x264_template(predict_8x16c_init) | |
| +void x264_predict_8x16c_init ( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_4x4_init x264_template(predict_4x4_init) | |
| +void x264_predict_4x4_init ( uint32_t cpu, x264_predict_t pf[12] ); | |
| +#define x264_predict_8x8_init x264_template(predict_8x8_init) | |
| +void x264_predict_8x8_init ( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_filter ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/quant.c x264-go.new/x264c/external/x264/common/quant.c | |
| --- x264-go/x264c/external/x264/common/quant.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/quant.c 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * quant.c: quantization and level-run | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -31,16 +31,16 @@ | |
| #if HAVE_MMX | |
| #include "x86/quant.h" | |
| #endif | |
| -#if ARCH_PPC | |
| +#if HAVE_ALTIVEC | |
| # include "ppc/quant.h" | |
| #endif | |
| -#if ARCH_ARM | |
| +#if HAVE_ARMV6 | |
| # include "arm/quant.h" | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| # include "aarch64/quant.h" | |
| #endif | |
| -#if ARCH_MIPS | |
| +#if HAVE_MSA | |
| # include "mips/quant.h" | |
| #endif | |
| @@ -298,7 +298,7 @@ | |
| return optimize_chroma_dc_internal( dct, dequant_mf, 1 ); | |
| } | |
| -static void x264_denoise_dct( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ) | |
| +static void denoise_dct( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ) | |
| { | |
| for( int i = 0; i < size; i++ ) | |
| { | |
| @@ -320,19 +320,7 @@ | |
| * chroma: for the complete mb: if score < 7 -> null | |
| */ | |
| -const uint8_t x264_decimate_table4[16] = | |
| -{ | |
| - 3,2,2,1,1,1,0,0,0,0,0,0,0,0,0,0 | |
| -}; | |
| -const uint8_t x264_decimate_table8[64] = | |
| -{ | |
| - 3,3,3,3,2,2,2,2,2,2,2,2,1,1,1,1, | |
| - 1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0, | |
| - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, | |
| - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 | |
| -}; | |
| - | |
| -static int ALWAYS_INLINE x264_decimate_score_internal( dctcoef *dct, int i_max ) | |
| +static ALWAYS_INLINE int decimate_score_internal( dctcoef *dct, int i_max ) | |
| { | |
| const uint8_t *ds_table = (i_max == 64) ? x264_decimate_table8 : x264_decimate_table4; | |
| int i_score = 0; | |
| @@ -359,21 +347,21 @@ | |
| return i_score; | |
| } | |
| -static int x264_decimate_score15( dctcoef *dct ) | |
| +static int decimate_score15( dctcoef *dct ) | |
| { | |
| - return x264_decimate_score_internal( dct+1, 15 ); | |
| + return decimate_score_internal( dct+1, 15 ); | |
| } | |
| -static int x264_decimate_score16( dctcoef *dct ) | |
| +static int decimate_score16( dctcoef *dct ) | |
| { | |
| - return x264_decimate_score_internal( dct, 16 ); | |
| + return decimate_score_internal( dct, 16 ); | |
| } | |
| -static int x264_decimate_score64( dctcoef *dct ) | |
| +static int decimate_score64( dctcoef *dct ) | |
| { | |
| - return x264_decimate_score_internal( dct, 64 ); | |
| + return decimate_score_internal( dct, 64 ); | |
| } | |
| #define last(num)\ | |
| -static int x264_coeff_last##num( dctcoef *l )\ | |
| +static int coeff_last##num( dctcoef *l )\ | |
| {\ | |
| int i_last = num-1;\ | |
| while( i_last >= 0 && l[i_last] == 0 )\ | |
| @@ -388,9 +376,9 @@ | |
| last(64) | |
| #define level_run(num)\ | |
| -static int x264_coeff_level_run##num( dctcoef *dct, x264_run_level_t *runlevel )\ | |
| +static int coeff_level_run##num( dctcoef *dct, x264_run_level_t *runlevel )\ | |
| {\ | |
| - int i_last = runlevel->last = x264_coeff_last##num(dct);\ | |
| + int i_last = runlevel->last = coeff_last##num(dct);\ | |
| int i_total = 0;\ | |
| int mask = 0;\ | |
| do\ | |
| @@ -420,7 +408,7 @@ | |
| #define INIT_TRELLIS(...) | |
| #endif | |
| -void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf ) | |
| +void x264_quant_init( x264_t *h, uint32_t cpu, x264_quant_function_t *pf ) | |
| { | |
| pf->quant_8x8 = quant_8x8; | |
| pf->quant_4x4 = quant_4x4; | |
| @@ -438,20 +426,20 @@ | |
| pf->optimize_chroma_2x2_dc = optimize_chroma_2x2_dc; | |
| pf->optimize_chroma_2x4_dc = optimize_chroma_2x4_dc; | |
| - pf->denoise_dct = x264_denoise_dct; | |
| - pf->decimate_score15 = x264_decimate_score15; | |
| - pf->decimate_score16 = x264_decimate_score16; | |
| - pf->decimate_score64 = x264_decimate_score64; | |
| - | |
| - pf->coeff_last4 = x264_coeff_last4; | |
| - pf->coeff_last8 = x264_coeff_last8; | |
| - pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15; | |
| - pf->coeff_last[ DCT_LUMA_4x4] = x264_coeff_last16; | |
| - pf->coeff_last[ DCT_LUMA_8x8] = x264_coeff_last64; | |
| - pf->coeff_level_run4 = x264_coeff_level_run4; | |
| - pf->coeff_level_run8 = x264_coeff_level_run8; | |
| - pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15; | |
| - pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16; | |
| + pf->denoise_dct = denoise_dct; | |
| + pf->decimate_score15 = decimate_score15; | |
| + pf->decimate_score16 = decimate_score16; | |
| + pf->decimate_score64 = decimate_score64; | |
| + | |
| + pf->coeff_last4 = coeff_last4; | |
| + pf->coeff_last8 = coeff_last8; | |
| + pf->coeff_last[ DCT_LUMA_AC] = coeff_last15; | |
| + pf->coeff_last[ DCT_LUMA_4x4] = coeff_last16; | |
| + pf->coeff_last[ DCT_LUMA_8x8] = coeff_last64; | |
| + pf->coeff_level_run4 = coeff_level_run4; | |
| + pf->coeff_level_run8 = coeff_level_run8; | |
| + pf->coeff_level_run[ DCT_LUMA_AC] = coeff_level_run15; | |
| + pf->coeff_level_run[ DCT_LUMA_4x4] = coeff_level_run16; | |
| #if HIGH_BIT_DEPTH | |
| #if HAVE_MMX | |
| @@ -753,6 +741,7 @@ | |
| pf->quant_2x2_dc = x264_quant_2x2_dc_altivec; | |
| pf->quant_4x4_dc = x264_quant_4x4_dc_altivec; | |
| pf->quant_4x4 = x264_quant_4x4_altivec; | |
| + pf->quant_4x4x4 = x264_quant_4x4x4_altivec; | |
| pf->quant_8x8 = x264_quant_8x8_altivec; | |
| pf->dequant_4x4 = x264_dequant_4x4_altivec; | |
| @@ -767,7 +756,7 @@ | |
| pf->coeff_last8 = x264_coeff_last8_arm; | |
| } | |
| #endif | |
| -#if HAVE_ARMV6 || ARCH_AARCH64 | |
| +#if HAVE_ARMV6 || HAVE_AARCH64 | |
| if( cpu&X264_CPU_NEON ) | |
| { | |
| pf->quant_2x2_dc = x264_quant_2x2_dc_neon; | |
| @@ -787,7 +776,7 @@ | |
| pf->decimate_score64 = x264_decimate_score64_neon; | |
| } | |
| #endif | |
| -#if ARCH_AARCH64 | |
| +#if HAVE_AARCH64 | |
| if( cpu&X264_CPU_ARMV8 ) | |
| { | |
| pf->coeff_last4 = x264_coeff_last4_aarch64; | |
| diff -ur x264-go/x264c/external/x264/common/quant.h x264-go.new/x264c/external/x264/common/quant.h | |
| --- x264-go/x264c/external/x264/common/quant.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/quant.h 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * quant.h: quantization and level-run | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -69,6 +69,7 @@ | |
| int (*trellis_cabac_chroma_422_dc)( TRELLIS_PARAMS ); | |
| } x264_quant_function_t; | |
| -void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf ); | |
| +#define x264_quant_init x264_template(quant_init) | |
| +void x264_quant_init( x264_t *h, uint32_t cpu, x264_quant_function_t *pf ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/common/rectangle.c x264-go.new/x264c/external/x264/common/rectangle.c | |
| --- x264-go/x264c/external/x264/common/rectangle.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/rectangle.c 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * rectangle.c: rectangle filling | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 x264 project | |
| + * Copyright (C) 2010-2020 x264 project | |
| * | |
| * Authors: Fiona Glaser <fiona@x264.com> | |
| * | |
| @@ -26,7 +26,7 @@ | |
| #include "common.h" | |
| #define CACHE_FUNC(name,size,width,height)\ | |
| -static void x264_macroblock_cache_##name##_##width##_##height( void *target, uint32_t val )\ | |
| +static void macroblock_cache_##name##_##width##_##height( void *target, uint32_t val )\ | |
| {\ | |
| x264_macroblock_cache_rect( target, width*size, height, size, val );\ | |
| } | |
| @@ -41,16 +41,16 @@ | |
| CACHE_FUNC(name,size,1,1)\ | |
| void (*x264_cache_##name##_func_table[10])(void *, uint32_t) =\ | |
| {\ | |
| - x264_macroblock_cache_##name##_1_1,\ | |
| - x264_macroblock_cache_##name##_2_1,\ | |
| - x264_macroblock_cache_##name##_1_2,\ | |
| - x264_macroblock_cache_##name##_2_2,\ | |
| + macroblock_cache_##name##_1_1,\ | |
| + macroblock_cache_##name##_2_1,\ | |
| + macroblock_cache_##name##_1_2,\ | |
| + macroblock_cache_##name##_2_2,\ | |
| NULL,\ | |
| - x264_macroblock_cache_##name##_4_2,\ | |
| + macroblock_cache_##name##_4_2,\ | |
| NULL,\ | |
| - x264_macroblock_cache_##name##_2_4,\ | |
| + macroblock_cache_##name##_2_4,\ | |
| NULL,\ | |
| - x264_macroblock_cache_##name##_4_4\ | |
| + macroblock_cache_##name##_4_4\ | |
| };\ | |
| CACHE_FUNCS(mv, 4) | |
| diff -ur x264-go/x264c/external/x264/common/rectangle.h x264-go.new/x264c/external/x264/common/rectangle.h | |
| --- x264-go/x264c/external/x264/common/rectangle.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/rectangle.h 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * rectangle.h: rectangle filling | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Fiona Glaser <fiona@x264.com> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -118,9 +118,12 @@ | |
| assert(0); | |
| } | |
| -extern void (*x264_cache_mv_func_table[10])(void *, uint32_t);\ | |
| -extern void (*x264_cache_mvd_func_table[10])(void *, uint32_t);\ | |
| -extern void (*x264_cache_ref_func_table[10])(void *, uint32_t);\ | |
| +#define x264_cache_mv_func_table x264_template(cache_mv_func_table) | |
| +extern void (*x264_cache_mv_func_table[10])(void *, uint32_t); | |
| +#define x264_cache_mvd_func_table x264_template(cache_mvd_func_table) | |
| +extern void (*x264_cache_mvd_func_table[10])(void *, uint32_t); | |
| +#define x264_cache_ref_func_table x264_template(cache_ref_func_table) | |
| +extern void (*x264_cache_ref_func_table[10])(void *, uint32_t); | |
| #define x264_macroblock_cache_mv_ptr( a, x, y, w, h, l, mv ) x264_macroblock_cache_mv( a, x, y, w, h, l, M32( mv ) ) | |
| static ALWAYS_INLINE void x264_macroblock_cache_mv( x264_t *h, int x, int y, int width, int height, int i_list, uint32_t mv ) | |
| diff -ur x264-go/x264c/external/x264/common/set.c x264-go.new/x264c/external/x264/common/set.c | |
| --- x264-go/x264c/external/x264/common/set.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/set.c 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * set.c: quantization init | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * | |
| @@ -94,7 +94,7 @@ | |
| int start = w == 8 ? 4 : 0;\ | |
| int j;\ | |
| for( j = 0; j < i; j++ )\ | |
| - if( !memcmp( h->pps->scaling_list[i+start], h->pps->scaling_list[j+start], size*sizeof(uint8_t) ) )\ | |
| + if( !memcmp( h->sps->scaling_list[i+start], h->sps->scaling_list[j+start], size*sizeof(uint8_t) ) )\ | |
| break;\ | |
| if( j < i )\ | |
| {\ | |
| @@ -110,7 +110,7 @@ | |
| }\ | |
| for( j = 0; j < i; j++ )\ | |
| if( deadzone[j] == deadzone[i] &&\ | |
| - !memcmp( h->pps->scaling_list[i+start], h->pps->scaling_list[j+start], size*sizeof(uint8_t) ) )\ | |
| + !memcmp( h->sps->scaling_list[i+start], h->sps->scaling_list[j+start], size*sizeof(uint8_t) ) )\ | |
| break;\ | |
| if( j < i )\ | |
| {\ | |
| @@ -148,14 +148,14 @@ | |
| for( int i_list = 0; i_list < 4; i_list++ ) | |
| for( int i = 0; i < 16; i++ ) | |
| { | |
| - h->dequant4_mf[i_list][q][i] = def_dequant4[q][i] * h->pps->scaling_list[i_list][i]; | |
| - quant4_mf[i_list][q][i] = DIV(def_quant4[q][i] * 16, h->pps->scaling_list[i_list][i]); | |
| + h->dequant4_mf[i_list][q][i] = def_dequant4[q][i] * h->sps->scaling_list[i_list][i]; | |
| + quant4_mf[i_list][q][i] = DIV(def_quant4[q][i] * 16, h->sps->scaling_list[i_list][i]); | |
| } | |
| for( int i_list = 0; i_list < num_8x8_lists; i_list++ ) | |
| for( int i = 0; i < 64; i++ ) | |
| { | |
| - h->dequant8_mf[i_list][q][i] = def_dequant8[q][i] * h->pps->scaling_list[4+i_list][i]; | |
| - quant8_mf[i_list][q][i] = DIV(def_quant8[q][i] * 16, h->pps->scaling_list[4+i_list][i]); | |
| + h->dequant8_mf[i_list][q][i] = def_dequant8[q][i] * h->sps->scaling_list[4+i_list][i]; | |
| + quant8_mf[i_list][q][i] = DIV(def_quant8[q][i] * 16, h->sps->scaling_list[4+i_list][i]); | |
| } | |
| } | |
| for( int q = 0; q <= QP_MAX_SPEC; q++ ) | |
| @@ -300,8 +300,8 @@ | |
| x264_free( h->nr_offset_emergency ); | |
| } | |
| -static int x264_cqm_parse_jmlist( x264_t *h, const char *buf, const char *name, | |
| - uint8_t *cqm, const uint8_t *jvt, int length ) | |
| +static int cqm_parse_jmlist( x264_t *h, const char *buf, const char *name, | |
| + uint8_t *cqm, const uint8_t *jvt, int length ) | |
| { | |
| int i; | |
| @@ -361,16 +361,16 @@ | |
| while( (p = strchr( buf, '#' )) != NULL ) | |
| memset( p, ' ', strcspn( p, "\n" ) ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTRA4X4_LUMA", h->param.cqm_4iy, x264_cqm_jvt4i, 16 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTER4X4_LUMA", h->param.cqm_4py, x264_cqm_jvt4p, 16 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTRA4X4_CHROMA", h->param.cqm_4ic, x264_cqm_jvt4i, 16 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTER4X4_CHROMA", h->param.cqm_4pc, x264_cqm_jvt4p, 16 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTRA8X8_LUMA", h->param.cqm_8iy, x264_cqm_jvt8i, 64 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTER8X8_LUMA", h->param.cqm_8py, x264_cqm_jvt8p, 64 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTRA4X4_LUMA", h->param.cqm_4iy, x264_cqm_jvt4i, 16 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTER4X4_LUMA", h->param.cqm_4py, x264_cqm_jvt4p, 16 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTRA4X4_CHROMA", h->param.cqm_4ic, x264_cqm_jvt4i, 16 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTER4X4_CHROMA", h->param.cqm_4pc, x264_cqm_jvt4p, 16 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTRA8X8_LUMA", h->param.cqm_8iy, x264_cqm_jvt8i, 64 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTER8X8_LUMA", h->param.cqm_8py, x264_cqm_jvt8p, 64 ); | |
| if( CHROMA444 ) | |
| { | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTRA8X8_CHROMA", h->param.cqm_8ic, x264_cqm_jvt8i, 64 ); | |
| - b_error |= x264_cqm_parse_jmlist( h, buf, "INTER8X8_CHROMA", h->param.cqm_8pc, x264_cqm_jvt8p, 64 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTRA8X8_CHROMA", h->param.cqm_8ic, x264_cqm_jvt8i, 64 ); | |
| + b_error |= cqm_parse_jmlist( h, buf, "INTER8X8_CHROMA", h->param.cqm_8pc, x264_cqm_jvt8p, 64 ); | |
| } | |
| x264_free( buf ); | |
| diff -ur x264-go/x264c/external/x264/common/set.h x264-go.new/x264c/external/x264/common/set.h | |
| --- x264-go/x264c/external/x264/common/set.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/set.h 2020-06-06 15:20:58.691039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * set.h: quantization init | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -27,24 +27,6 @@ | |
| #ifndef X264_SET_H | |
| #define X264_SET_H | |
| -enum profile_e | |
| -{ | |
| - PROFILE_BASELINE = 66, | |
| - PROFILE_MAIN = 77, | |
| - PROFILE_HIGH = 100, | |
| - PROFILE_HIGH10 = 110, | |
| - PROFILE_HIGH422 = 122, | |
| - PROFILE_HIGH444_PREDICTIVE = 244, | |
| -}; | |
| - | |
| -enum chroma_format_e | |
| -{ | |
| - CHROMA_400 = 0, | |
| - CHROMA_420 = 1, | |
| - CHROMA_422 = 2, | |
| - CHROMA_444 = 3, | |
| -}; | |
| - | |
| enum cqm4_e | |
| { | |
| CQM_4IY = 0, | |
| @@ -158,6 +140,10 @@ | |
| int b_qpprime_y_zero_transform_bypass; | |
| int i_chroma_format_idc; | |
| + int b_avcintra; | |
| + int i_cqm_preset; | |
| + const uint8_t *scaling_list[8]; /* could be 12, but we don't allow separate Cb/Cr lists */ | |
| + | |
| } x264_sps_t; | |
| typedef struct | |
| @@ -187,161 +173,13 @@ | |
| int b_transform_8x8_mode; | |
| - int i_cqm_preset; | |
| - const uint8_t *scaling_list[8]; /* could be 12, but we don't allow separate Cb/Cr lists */ | |
| - | |
| } x264_pps_t; | |
| -/* default quant matrices */ | |
| -static const uint8_t x264_cqm_jvt4i[16] = | |
| -{ | |
| - 6,13,20,28, | |
| - 13,20,28,32, | |
| - 20,28,32,37, | |
| - 28,32,37,42 | |
| -}; | |
| -static const uint8_t x264_cqm_jvt4p[16] = | |
| -{ | |
| - 10,14,20,24, | |
| - 14,20,24,27, | |
| - 20,24,27,30, | |
| - 24,27,30,34 | |
| -}; | |
| -static const uint8_t x264_cqm_jvt8i[64] = | |
| -{ | |
| - 6,10,13,16,18,23,25,27, | |
| - 10,11,16,18,23,25,27,29, | |
| - 13,16,18,23,25,27,29,31, | |
| - 16,18,23,25,27,29,31,33, | |
| - 18,23,25,27,29,31,33,36, | |
| - 23,25,27,29,31,33,36,38, | |
| - 25,27,29,31,33,36,38,40, | |
| - 27,29,31,33,36,38,40,42 | |
| -}; | |
| -static const uint8_t x264_cqm_jvt8p[64] = | |
| -{ | |
| - 9,13,15,17,19,21,22,24, | |
| - 13,13,17,19,21,22,24,25, | |
| - 15,17,19,21,22,24,25,27, | |
| - 17,19,21,22,24,25,27,28, | |
| - 19,21,22,24,25,27,28,30, | |
| - 21,22,24,25,27,28,30,32, | |
| - 22,24,25,27,28,30,32,33, | |
| - 24,25,27,28,30,32,33,35 | |
| -}; | |
| -static const uint8_t x264_cqm_flat16[64] = | |
| -{ | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16, | |
| - 16,16,16,16,16,16,16,16 | |
| -}; | |
| -static const uint8_t * const x264_cqm_jvt[8] = | |
| -{ | |
| - x264_cqm_jvt4i, x264_cqm_jvt4p, | |
| - x264_cqm_jvt4i, x264_cqm_jvt4p, | |
| - x264_cqm_jvt8i, x264_cqm_jvt8p, | |
| - x264_cqm_jvt8i, x264_cqm_jvt8p | |
| -}; | |
| - | |
| -// 1080i25_avci50, 1080p25_avci50 | |
| -static const uint8_t x264_cqm_avci50_4ic[16] = | |
| -{ | |
| - 16,22,28,40, | |
| - 22,28,40,44, | |
| - 28,40,44,48, | |
| - 40,44,48,60 | |
| -}; | |
| - | |
| -// 1080i25_avci50, | |
| -static const uint8_t x264_cqm_avci50_1080i_8iy[64] = | |
| -{ | |
| - 16,18,19,21,27,33,81,87, | |
| - 18,19,21,24,30,33,81,87, | |
| - 19,21,24,27,30,78,84,90, | |
| - 21,24,27,30,33,78,84,90, | |
| - 24,27,30,33,78,81,84,90, | |
| - 24,27,30,33,78,81,84,93, | |
| - 27,30,33,78,78,81,87,93, | |
| - 30,33,33,78,81,84,87,96 | |
| -}; | |
| - | |
| -// 1080p25_avci50, 720p25_avci50, 720p50_avci50 | |
| -static const uint8_t x264_cqm_avci50_p_8iy[64] = | |
| -{ | |
| - 16,18,19,21,24,27,30,33, | |
| - 18,19,21,24,27,30,33,78, | |
| - 19,21,24,27,30,33,78,81, | |
| - 21,24,27,30,33,78,81,84, | |
| - 24,27,30,33,78,81,84,87, | |
| - 27,30,33,78,81,84,87,90, | |
| - 30,33,78,81,84,87,90,93, | |
| - 33,78,81,84,87,90,93,96 | |
| -}; | |
| - | |
| -// 1080i25_avci100, 1080p25_avci100 | |
| -static const uint8_t x264_cqm_avci100_1080_4ic[16] = | |
| -{ | |
| - 16,20,26,32, | |
| - 20,26,32,38, | |
| - 26,32,38,44, | |
| - 32,38,44,50 | |
| -}; | |
| - | |
| -// 720p25_avci100, 720p50_avci100 | |
| -static const uint8_t x264_cqm_avci100_720p_4ic[16] = | |
| -{ | |
| - 16,21,27,34, | |
| - 21,27,34,41, | |
| - 27,34,41,46, | |
| - 34,41,46,54 | |
| -}; | |
| - | |
| -// 1080i25_avci100, | |
| -static const uint8_t x264_cqm_avci100_1080i_8iy[64] = | |
| -{ | |
| - 16,19,20,23,24,26,32,42, | |
| - 18,19,22,24,26,32,36,42, | |
| - 18,20,23,24,26,32,36,63, | |
| - 19,20,23,26,32,36,42,63, | |
| - 20,22,24,26,32,36,59,63, | |
| - 22,23,24,26,32,36,59,68, | |
| - 22,23,24,26,32,42,59,68, | |
| - 22,23,24,26,36,42,59,72 | |
| -}; | |
| - | |
| -// 1080p25_avci100, | |
| -static const uint8_t x264_cqm_avci100_1080p_8iy[64] = | |
| -{ | |
| - 16,18,19,20,22,23,24,26, | |
| - 18,19,20,22,23,24,26,32, | |
| - 19,20,22,23,24,26,32,36, | |
| - 20,22,23,24,26,32,36,42, | |
| - 22,23,24,26,32,36,42,59, | |
| - 23,24,26,32,36,42,59,63, | |
| - 24,26,32,36,42,59,63,68, | |
| - 26,32,36,42,59,63,68,72 | |
| -}; | |
| - | |
| -// 720p25_avci100, 720p50_avci100 | |
| -static const uint8_t x264_cqm_avci100_720p_8iy[64] = | |
| -{ | |
| - 16,18,19,21,22,24,26,32, | |
| - 18,19,19,21,22,24,26,32, | |
| - 19,19,21,22,22,24,26,32, | |
| - 21,21,22,22,23,24,26,34, | |
| - 22,22,22,23,24,25,26,34, | |
| - 24,24,24,24,25,26,34,36, | |
| - 26,26,26,26,26,34,36,38, | |
| - 32,32,32,34,34,36,38,42 | |
| -}; | |
| - | |
| +#define x264_cqm_init x264_template(cqm_init) | |
| int x264_cqm_init( x264_t *h ); | |
| +#define x264_cqm_delete x264_template(cqm_delete) | |
| void x264_cqm_delete( x264_t *h ); | |
| +#define x264_cqm_parse_file x264_template(cqm_parse_file) | |
| int x264_cqm_parse_file( x264_t *h, const char *filename ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common: tables.c | |
| Only in x264-go.new/x264c/external/x264/common: tables.h | |
| diff -ur x264-go/x264c/external/x264/common/threadpool.c x264-go.new/x264c/external/x264/common/threadpool.c | |
| --- x264-go/x264c/external/x264/common/threadpool.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/threadpool.c 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * threadpool.c: thread pooling | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 x264 project | |
| + * Copyright (C) 2010-2020 x264 project | |
| * | |
| * Authors: Steven Walters <kemuri9@gmail.com> | |
| * | |
| @@ -34,7 +34,7 @@ | |
| struct x264_threadpool_t | |
| { | |
| - int exit; | |
| + volatile int exit; | |
| int threads; | |
| x264_pthread_t *thread_handle; | |
| void (*init_func)(void *); | |
| @@ -47,7 +47,7 @@ | |
| x264_sync_frame_list_t done; /* list of jobs that have finished processing */ | |
| }; | |
| -static void *x264_threadpool_thread( x264_threadpool_t *pool ) | |
| +REALIGN_STACK static void *threadpool_thread( x264_threadpool_t *pool ) | |
| { | |
| if( pool->init_func ) | |
| pool->init_func( pool->init_arg ); | |
| @@ -66,7 +66,7 @@ | |
| x264_pthread_mutex_unlock( &pool->run.mutex ); | |
| if( !job ) | |
| continue; | |
| - job->ret = (void*)x264_stack_align( job->func, job->arg ); /* execute the function */ | |
| + job->ret = job->func( job->arg ); | |
| x264_sync_frame_list_push( &pool->done, (void*)job ); | |
| } | |
| return NULL; | |
| @@ -78,6 +78,9 @@ | |
| if( threads <= 0 ) | |
| return -1; | |
| + if( x264_threading_init() < 0 ) | |
| + return -1; | |
| + | |
| x264_threadpool_t *pool; | |
| CHECKED_MALLOCZERO( pool, sizeof(x264_threadpool_t) ); | |
| *p_pool = pool; | |
| @@ -100,7 +103,7 @@ | |
| x264_sync_frame_list_push( &pool->uninit, (void*)job ); | |
| } | |
| for( int i = 0; i < pool->threads; i++ ) | |
| - if( x264_pthread_create( pool->thread_handle+i, NULL, (void*)x264_threadpool_thread, pool ) ) | |
| + if( x264_pthread_create( pool->thread_handle+i, NULL, (void*)threadpool_thread, pool ) ) | |
| goto fail; | |
| return 0; | |
| @@ -137,7 +140,7 @@ | |
| } | |
| } | |
| -static void x264_threadpool_list_delete( x264_sync_frame_list_t *slist ) | |
| +static void threadpool_list_delete( x264_sync_frame_list_t *slist ) | |
| { | |
| for( int i = 0; slist->list[i]; i++ ) | |
| { | |
| @@ -156,9 +159,9 @@ | |
| for( int i = 0; i < pool->threads; i++ ) | |
| x264_pthread_join( pool->thread_handle[i], NULL ); | |
| - x264_threadpool_list_delete( &pool->uninit ); | |
| - x264_threadpool_list_delete( &pool->run ); | |
| - x264_threadpool_list_delete( &pool->done ); | |
| + threadpool_list_delete( &pool->uninit ); | |
| + threadpool_list_delete( &pool->run ); | |
| + threadpool_list_delete( &pool->done ); | |
| x264_free( pool->thread_handle ); | |
| x264_free( pool ); | |
| } | |
| diff -ur x264-go/x264c/external/x264/common/threadpool.h x264-go.new/x264c/external/x264/common/threadpool.h | |
| --- x264-go/x264c/external/x264/common/threadpool.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/threadpool.h 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * threadpool.h: thread pooling | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 x264 project | |
| + * Copyright (C) 2010-2020 x264 project | |
| * | |
| * Authors: Steven Walters <kemuri9@gmail.com> | |
| * | |
| @@ -29,11 +29,15 @@ | |
| typedef struct x264_threadpool_t x264_threadpool_t; | |
| #if HAVE_THREAD | |
| -int x264_threadpool_init( x264_threadpool_t **p_pool, int threads, | |
| - void (*init_func)(void *), void *init_arg ); | |
| -void x264_threadpool_run( x264_threadpool_t *pool, void *(*func)(void *), void *arg ); | |
| -void *x264_threadpool_wait( x264_threadpool_t *pool, void *arg ); | |
| -void x264_threadpool_delete( x264_threadpool_t *pool ); | |
| +#define x264_threadpool_init x264_template(threadpool_init) | |
| +X264_API int x264_threadpool_init( x264_threadpool_t **p_pool, int threads, | |
| + void (*init_func)(void *), void *init_arg ); | |
| +#define x264_threadpool_run x264_template(threadpool_run) | |
| +X264_API void x264_threadpool_run( x264_threadpool_t *pool, void *(*func)(void *), void *arg ); | |
| +#define x264_threadpool_wait x264_template(threadpool_wait) | |
| +X264_API void *x264_threadpool_wait( x264_threadpool_t *pool, void *arg ); | |
| +#define x264_threadpool_delete x264_template(threadpool_delete) | |
| +X264_API void x264_threadpool_delete( x264_threadpool_t *pool ); | |
| #else | |
| #define x264_threadpool_init(p,t,f,a) -1 | |
| #define x264_threadpool_run(p,f,a) | |
| diff -ur x264-go/x264c/external/x264/common/vlc.c x264-go.new/x264c/external/x264/common/vlc.c | |
| --- x264-go/x264c/external/x264/common/vlc.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/vlc.c 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * vlc.c : vlc tables | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -27,777 +27,6 @@ | |
| #include "common.h" | |
| -/* [nC] */ | |
| -const vlc_t x264_coeff0_token[6] = | |
| -{ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0xf, 4 }, /* str=1111 */ | |
| - { 0x3, 6 }, /* str=000011 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| -}; | |
| - | |
| -/* [nC][i_total_coeff-1][i_trailing] */ | |
| -const vlc_t x264_coeff_token[6][16][4] = | |
| -{ | |
| - { /* table 0 */ | |
| - { /* i_total 1 */ | |
| - { 0x5, 6 }, /* str=000101 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x7, 8 }, /* str=00000111 */ | |
| - { 0x4, 6 }, /* str=000100 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x7, 9 }, /* str=000000111 */ | |
| - { 0x6, 8 }, /* str=00000110 */ | |
| - { 0x5, 7 }, /* str=0000101 */ | |
| - { 0x3, 5 }, /* str=00011 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x7, 10 }, /* str=0000000111 */ | |
| - { 0x6, 9 }, /* str=000000110 */ | |
| - { 0x5, 8 }, /* str=00000101 */ | |
| - { 0x3, 6 }, /* str=000011 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x7, 11 }, /* str=00000000111 */ | |
| - { 0x6, 10 }, /* str=0000000110 */ | |
| - { 0x5, 9 }, /* str=000000101 */ | |
| - { 0x4, 7 }, /* str=0000100 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0xf, 13 }, /* str=0000000001111 */ | |
| - { 0x6, 11 }, /* str=00000000110 */ | |
| - { 0x5, 10 }, /* str=0000000101 */ | |
| - { 0x4, 8 }, /* str=00000100 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0xb, 13 }, /* str=0000000001011 */ | |
| - { 0xe, 13 }, /* str=0000000001110 */ | |
| - { 0x5, 11 }, /* str=00000000101 */ | |
| - { 0x4, 9 }, /* str=000000100 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0x8, 13 }, /* str=0000000001000 */ | |
| - { 0xa, 13 }, /* str=0000000001010 */ | |
| - { 0xd, 13 }, /* str=0000000001101 */ | |
| - { 0x4, 10 }, /* str=0000000100 */ | |
| - }, | |
| - { /* i_total 9 */ | |
| - { 0xf, 14 }, /* str=00000000001111 */ | |
| - { 0xe, 14 }, /* str=00000000001110 */ | |
| - { 0x9, 13 }, /* str=0000000001001 */ | |
| - { 0x4, 11 }, /* str=00000000100 */ | |
| - }, | |
| - { /* i_total 10 */ | |
| - { 0xb, 14 }, /* str=00000000001011 */ | |
| - { 0xa, 14 }, /* str=00000000001010 */ | |
| - { 0xd, 14 }, /* str=00000000001101 */ | |
| - { 0xc, 13 }, /* str=0000000001100 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0xf, 15 }, /* str=000000000001111 */ | |
| - { 0xe, 15 }, /* str=000000000001110 */ | |
| - { 0x9, 14 }, /* str=00000000001001 */ | |
| - { 0xc, 14 }, /* str=00000000001100 */ | |
| - }, | |
| - { /* i_total 12 */ | |
| - { 0xb, 15 }, /* str=000000000001011 */ | |
| - { 0xa, 15 }, /* str=000000000001010 */ | |
| - { 0xd, 15 }, /* str=000000000001101 */ | |
| - { 0x8, 14 }, /* str=00000000001000 */ | |
| - }, | |
| - { /* i_total 13 */ | |
| - { 0xf, 16 }, /* str=0000000000001111 */ | |
| - { 0x1, 15 }, /* str=000000000000001 */ | |
| - { 0x9, 15 }, /* str=000000000001001 */ | |
| - { 0xc, 15 }, /* str=000000000001100 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0xb, 16 }, /* str=0000000000001011 */ | |
| - { 0xe, 16 }, /* str=0000000000001110 */ | |
| - { 0xd, 16 }, /* str=0000000000001101 */ | |
| - { 0x8, 15 }, /* str=000000000001000 */ | |
| - }, | |
| - { /* i_total 15 */ | |
| - { 0x7, 16 }, /* str=0000000000000111 */ | |
| - { 0xa, 16 }, /* str=0000000000001010 */ | |
| - { 0x9, 16 }, /* str=0000000000001001 */ | |
| - { 0xc, 16 }, /* str=0000000000001100 */ | |
| - }, | |
| - { /* i_total 16 */ | |
| - { 0x4, 16 }, /* str=0000000000000100 */ | |
| - { 0x6, 16 }, /* str=0000000000000110 */ | |
| - { 0x5, 16 }, /* str=0000000000000101 */ | |
| - { 0x8, 16 }, /* str=0000000000001000 */ | |
| - }, | |
| - }, | |
| - { /* table 1 */ | |
| - { /* i_total 1 */ | |
| - { 0xb, 6 }, /* str=001011 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x7, 6 }, /* str=000111 */ | |
| - { 0x7, 5 }, /* str=00111 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x7, 7 }, /* str=0000111 */ | |
| - { 0xa, 6 }, /* str=001010 */ | |
| - { 0x9, 6 }, /* str=001001 */ | |
| - { 0x5, 4 }, /* str=0101 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x7, 8 }, /* str=00000111 */ | |
| - { 0x6, 6 }, /* str=000110 */ | |
| - { 0x5, 6 }, /* str=000101 */ | |
| - { 0x4, 4 }, /* str=0100 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x4, 8 }, /* str=00000100 */ | |
| - { 0x6, 7 }, /* str=0000110 */ | |
| - { 0x5, 7 }, /* str=0000101 */ | |
| - { 0x6, 5 }, /* str=00110 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x7, 9 }, /* str=000000111 */ | |
| - { 0x6, 8 }, /* str=00000110 */ | |
| - { 0x5, 8 }, /* str=00000101 */ | |
| - { 0x8, 6 }, /* str=001000 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0xf, 11 }, /* str=00000001111 */ | |
| - { 0x6, 9 }, /* str=000000110 */ | |
| - { 0x5, 9 }, /* str=000000101 */ | |
| - { 0x4, 6 }, /* str=000100 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0xb, 11 }, /* str=00000001011 */ | |
| - { 0xe, 11 }, /* str=00000001110 */ | |
| - { 0xd, 11 }, /* str=00000001101 */ | |
| - { 0x4, 7 }, /* str=0000100 */ | |
| - }, | |
| - { /* i_total 9 */ | |
| - { 0xf, 12 }, /* str=000000001111 */ | |
| - { 0xa, 11 }, /* str=00000001010 */ | |
| - { 0x9, 11 }, /* str=00000001001 */ | |
| - { 0x4, 9 }, /* str=000000100 */ | |
| - }, | |
| - { /* i_total 10 */ | |
| - { 0xb, 12 }, /* str=000000001011 */ | |
| - { 0xe, 12 }, /* str=000000001110 */ | |
| - { 0xd, 12 }, /* str=000000001101 */ | |
| - { 0xc, 11 }, /* str=00000001100 */ | |
| - }, | |
| - { /* i_total 11 */ | |
| - { 0x8, 12 }, /* str=000000001000 */ | |
| - { 0xa, 12 }, /* str=000000001010 */ | |
| - { 0x9, 12 }, /* str=000000001001 */ | |
| - { 0x8, 11 }, /* str=00000001000 */ | |
| - }, | |
| - { /* i_total 12 */ | |
| - { 0xf, 13 }, /* str=0000000001111 */ | |
| - { 0xe, 13 }, /* str=0000000001110 */ | |
| - { 0xd, 13 }, /* str=0000000001101 */ | |
| - { 0xc, 12 }, /* str=000000001100 */ | |
| - }, | |
| - { /* i_total 13 */ | |
| - { 0xb, 13 }, /* str=0000000001011 */ | |
| - { 0xa, 13 }, /* str=0000000001010 */ | |
| - { 0x9, 13 }, /* str=0000000001001 */ | |
| - { 0xc, 13 }, /* str=0000000001100 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0x7, 13 }, /* str=0000000000111 */ | |
| - { 0xb, 14 }, /* str=00000000001011 */ | |
| - { 0x6, 13 }, /* str=0000000000110 */ | |
| - { 0x8, 13 }, /* str=0000000001000 */ | |
| - }, | |
| - { /* i_total 15 */ | |
| - { 0x9, 14 }, /* str=00000000001001 */ | |
| - { 0x8, 14 }, /* str=00000000001000 */ | |
| - { 0xa, 14 }, /* str=00000000001010 */ | |
| - { 0x1, 13 }, /* str=0000000000001 */ | |
| - }, | |
| - { /* i_total 16 */ | |
| - { 0x7, 14 }, /* str=00000000000111 */ | |
| - { 0x6, 14 }, /* str=00000000000110 */ | |
| - { 0x5, 14 }, /* str=00000000000101 */ | |
| - { 0x4, 14 }, /* str=00000000000100 */ | |
| - }, | |
| - }, | |
| - { /* table 2 */ | |
| - { /* i_total 1 */ | |
| - { 0xf, 6 }, /* str=001111 */ | |
| - { 0xe, 4 }, /* str=1110 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0xb, 6 }, /* str=001011 */ | |
| - { 0xf, 5 }, /* str=01111 */ | |
| - { 0xd, 4 }, /* str=1101 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x8, 6 }, /* str=001000 */ | |
| - { 0xc, 5 }, /* str=01100 */ | |
| - { 0xe, 5 }, /* str=01110 */ | |
| - { 0xc, 4 }, /* str=1100 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0xf, 7 }, /* str=0001111 */ | |
| - { 0xa, 5 }, /* str=01010 */ | |
| - { 0xb, 5 }, /* str=01011 */ | |
| - { 0xb, 4 }, /* str=1011 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0xb, 7 }, /* str=0001011 */ | |
| - { 0x8, 5 }, /* str=01000 */ | |
| - { 0x9, 5 }, /* str=01001 */ | |
| - { 0xa, 4 }, /* str=1010 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x9, 7 }, /* str=0001001 */ | |
| - { 0xe, 6 }, /* str=001110 */ | |
| - { 0xd, 6 }, /* str=001101 */ | |
| - { 0x9, 4 }, /* str=1001 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0x8, 7 }, /* str=0001000 */ | |
| - { 0xa, 6 }, /* str=001010 */ | |
| - { 0x9, 6 }, /* str=001001 */ | |
| - { 0x8, 4 }, /* str=1000 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0xf, 8 }, /* str=00001111 */ | |
| - { 0xe, 7 }, /* str=0001110 */ | |
| - { 0xd, 7 }, /* str=0001101 */ | |
| - { 0xd, 5 }, /* str=01101 */ | |
| - }, | |
| - { /* i_total 9 */ | |
| - { 0xb, 8 }, /* str=00001011 */ | |
| - { 0xe, 8 }, /* str=00001110 */ | |
| - { 0xa, 7 }, /* str=0001010 */ | |
| - { 0xc, 6 }, /* str=001100 */ | |
| - }, | |
| - { /* i_total 10 */ | |
| - { 0xf, 9 }, /* str=000001111 */ | |
| - { 0xa, 8 }, /* str=00001010 */ | |
| - { 0xd, 8 }, /* str=00001101 */ | |
| - { 0xc, 7 }, /* str=0001100 */ | |
| - }, | |
| - { /* i_total 11 */ | |
| - { 0xb, 9 }, /* str=000001011 */ | |
| - { 0xe, 9 }, /* str=000001110 */ | |
| - { 0x9, 8 }, /* str=00001001 */ | |
| - { 0xc, 8 }, /* str=00001100 */ | |
| - }, | |
| - { /* i_total 12 */ | |
| - { 0x8, 9 }, /* str=000001000 */ | |
| - { 0xa, 9 }, /* str=000001010 */ | |
| - { 0xd, 9 }, /* str=000001101 */ | |
| - { 0x8, 8 }, /* str=00001000 */ | |
| - }, | |
| - { /* i_total 13 */ | |
| - { 0xd, 10 }, /* str=0000001101 */ | |
| - { 0x7, 9 }, /* str=000000111 */ | |
| - { 0x9, 9 }, /* str=000001001 */ | |
| - { 0xc, 9 }, /* str=000001100 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0x9, 10 }, /* str=0000001001 */ | |
| - { 0xc, 10 }, /* str=0000001100 */ | |
| - { 0xb, 10 }, /* str=0000001011 */ | |
| - { 0xa, 10 }, /* str=0000001010 */ | |
| - }, | |
| - { /* i_total 15 */ | |
| - { 0x5, 10 }, /* str=0000000101 */ | |
| - { 0x8, 10 }, /* str=0000001000 */ | |
| - { 0x7, 10 }, /* str=0000000111 */ | |
| - { 0x6, 10 }, /* str=0000000110 */ | |
| - }, | |
| - { /* i_total 16 */ | |
| - { 0x1, 10 }, /* str=0000000001 */ | |
| - { 0x4, 10 }, /* str=0000000100 */ | |
| - { 0x3, 10 }, /* str=0000000011 */ | |
| - { 0x2, 10 }, /* str=0000000010 */ | |
| - }, | |
| - }, | |
| - { /* table 3 */ | |
| - { /* i_total 1 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x4, 6 }, /* str=000100 */ | |
| - { 0x5, 6 }, /* str=000101 */ | |
| - { 0x6, 6 }, /* str=000110 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x8, 6 }, /* str=001000 */ | |
| - { 0x9, 6 }, /* str=001001 */ | |
| - { 0xa, 6 }, /* str=001010 */ | |
| - { 0xb, 6 }, /* str=001011 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0xc, 6 }, /* str=001100 */ | |
| - { 0xd, 6 }, /* str=001101 */ | |
| - { 0xe, 6 }, /* str=001110 */ | |
| - { 0xf, 6 }, /* str=001111 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x10, 6 }, /* str=010000 */ | |
| - { 0x11, 6 }, /* str=010001 */ | |
| - { 0x12, 6 }, /* str=010010 */ | |
| - { 0x13, 6 }, /* str=010011 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x14, 6 }, /* str=010100 */ | |
| - { 0x15, 6 }, /* str=010101 */ | |
| - { 0x16, 6 }, /* str=010110 */ | |
| - { 0x17, 6 }, /* str=010111 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0x18, 6 }, /* str=011000 */ | |
| - { 0x19, 6 }, /* str=011001 */ | |
| - { 0x1a, 6 }, /* str=011010 */ | |
| - { 0x1b, 6 }, /* str=011011 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0x1c, 6 }, /* str=011100 */ | |
| - { 0x1d, 6 }, /* str=011101 */ | |
| - { 0x1e, 6 }, /* str=011110 */ | |
| - { 0x1f, 6 }, /* str=011111 */ | |
| - }, | |
| - { /* i_total 9 */ | |
| - { 0x20, 6 }, /* str=100000 */ | |
| - { 0x21, 6 }, /* str=100001 */ | |
| - { 0x22, 6 }, /* str=100010 */ | |
| - { 0x23, 6 }, /* str=100011 */ | |
| - }, | |
| - { /* i_total 10 */ | |
| - { 0x24, 6 }, /* str=100100 */ | |
| - { 0x25, 6 }, /* str=100101 */ | |
| - { 0x26, 6 }, /* str=100110 */ | |
| - { 0x27, 6 }, /* str=100111 */ | |
| - }, | |
| - { /* i_total 11 */ | |
| - { 0x28, 6 }, /* str=101000 */ | |
| - { 0x29, 6 }, /* str=101001 */ | |
| - { 0x2a, 6 }, /* str=101010 */ | |
| - { 0x2b, 6 }, /* str=101011 */ | |
| - }, | |
| - { /* i_total 12 */ | |
| - { 0x2c, 6 }, /* str=101100 */ | |
| - { 0x2d, 6 }, /* str=101101 */ | |
| - { 0x2e, 6 }, /* str=101110 */ | |
| - { 0x2f, 6 }, /* str=101111 */ | |
| - }, | |
| - { /* i_total 13 */ | |
| - { 0x30, 6 }, /* str=110000 */ | |
| - { 0x31, 6 }, /* str=110001 */ | |
| - { 0x32, 6 }, /* str=110010 */ | |
| - { 0x33, 6 }, /* str=110011 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0x34, 6 }, /* str=110100 */ | |
| - { 0x35, 6 }, /* str=110101 */ | |
| - { 0x36, 6 }, /* str=110110 */ | |
| - { 0x37, 6 }, /* str=110111 */ | |
| - }, | |
| - { /* i_total 15 */ | |
| - { 0x38, 6 }, /* str=111000 */ | |
| - { 0x39, 6 }, /* str=111001 */ | |
| - { 0x3a, 6 }, /* str=111010 */ | |
| - { 0x3b, 6 }, /* str=111011 */ | |
| - }, | |
| - { /* i_total 16 */ | |
| - { 0x3c, 6 }, /* str=111100 */ | |
| - { 0x3d, 6 }, /* str=111101 */ | |
| - { 0x3e, 6 }, /* str=111110 */ | |
| - { 0x3f, 6 }, /* str=111111 */ | |
| - }, | |
| - }, | |
| - { /* table 4 */ | |
| - { /* i_total 1 */ | |
| - { 0x7, 6 }, /* str=000111 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x4, 6 }, /* str=000100 */ | |
| - { 0x6, 6 }, /* str=000110 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x3, 6 }, /* str=000011 */ | |
| - { 0x3, 7 }, /* str=0000011 */ | |
| - { 0x2, 7 }, /* str=0000010 */ | |
| - { 0x5, 6 }, /* str=000101 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x2, 6 }, /* str=000010 */ | |
| - { 0x3, 8 }, /* str=00000011 */ | |
| - { 0x2, 8 }, /* str=00000010 */ | |
| - { 0x0, 7 }, /* str=0000000 */ | |
| - }, | |
| - }, | |
| - { /* table 5 */ | |
| - { /* i_total 1 */ | |
| - { 0xf, 7 }, /* str=0001111 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0xe, 7 }, /* str=0001110 */ | |
| - { 0xd, 7 }, /* str=0001101 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x7, 9 }, /* str=000000111 */ | |
| - { 0xc, 7 }, /* str=0001100 */ | |
| - { 0xb, 7 }, /* str=0001011 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x6, 9 }, /* str=000000110 */ | |
| - { 0x5, 9 }, /* str=000000101 */ | |
| - { 0xa, 7 }, /* str=0001010 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x7, 10 }, /* str=0000000111 */ | |
| - { 0x6, 10 }, /* str=0000000110 */ | |
| - { 0x4, 9 }, /* str=000000100 */ | |
| - { 0x9, 7 }, /* str=0001001 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x7, 11 }, /* str=00000000111 */ | |
| - { 0x6, 11 }, /* str=00000000110 */ | |
| - { 0x5, 10 }, /* str=0000000101 */ | |
| - { 0x8, 7 }, /* str=0001000 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0x7, 12 }, /* str=000000000111 */ | |
| - { 0x6, 12 }, /* str=000000000110 */ | |
| - { 0x5, 11 }, /* str=00000000101 */ | |
| - { 0x4, 10 }, /* str=0000000100 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0x7, 13 }, /* str=0000000000111 */ | |
| - { 0x5, 12 }, /* str=000000000101 */ | |
| - { 0x4, 12 }, /* str=000000000100 */ | |
| - { 0x4, 11 }, /* str=00000000100 */ | |
| - }, | |
| - }, | |
| -}; | |
| - | |
| -/* [i_total_coeff-1][i_total_zeros] */ | |
| -const vlc_t x264_total_zeros[15][16] = | |
| -{ | |
| - { /* i_total 1 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x3, 5 }, /* str=00011 */ | |
| - { 0x2, 5 }, /* str=00010 */ | |
| - { 0x3, 6 }, /* str=000011 */ | |
| - { 0x2, 6 }, /* str=000010 */ | |
| - { 0x3, 7 }, /* str=0000011 */ | |
| - { 0x2, 7 }, /* str=0000010 */ | |
| - { 0x3, 8 }, /* str=00000011 */ | |
| - { 0x2, 8 }, /* str=00000010 */ | |
| - { 0x3, 9 }, /* str=000000011 */ | |
| - { 0x2, 9 }, /* str=000000010 */ | |
| - { 0x1, 9 }, /* str=000000001 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x5, 4 }, /* str=0101 */ | |
| - { 0x4, 4 }, /* str=0100 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x3, 5 }, /* str=00011 */ | |
| - { 0x2, 5 }, /* str=00010 */ | |
| - { 0x3, 6 }, /* str=000011 */ | |
| - { 0x2, 6 }, /* str=000010 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x5, 4 }, /* str=0101 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 4 }, /* str=0100 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x3, 5 }, /* str=00011 */ | |
| - { 0x2, 5 }, /* str=00010 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x3, 5 }, /* str=00011 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x5, 4 }, /* str=0101 */ | |
| - { 0x4, 4 }, /* str=0100 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x2, 5 }, /* str=00010 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x0, 5 }, /* str=00000 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x5, 4 }, /* str=0101 */ | |
| - { 0x4, 4 }, /* str=0100 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x0, 5 }, /* str=00000 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - }, | |
| - { /* i_total 8 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - }, | |
| - { /* i_total 9 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x0, 6 }, /* str=000000 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - }, | |
| - { /* i_total 10 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x0, 5 }, /* str=00000 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - }, | |
| - { /* i_total 11 */ | |
| - { 0x0, 4 }, /* str=0000 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - }, | |
| - { /* i_total 12 */ | |
| - { 0x0, 4 }, /* str=0000 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - }, | |
| - { /* i_total 13 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - }, | |
| - { /* i_total 14 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - }, | |
| - { /* i_total 15 */ | |
| - { 0x0, 1 }, /* str=0 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - }, | |
| -}; | |
| - | |
| -/* [i_total_coeff-1][i_total_zeros] */ | |
| -const vlc_t x264_total_zeros_2x2_dc[3][4] = | |
| -{ | |
| - { /* i_total 1 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 3 } /* str=000 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x0, 1 }, /* str=0 */ | |
| - }, | |
| -}; | |
| - | |
| -/* [i_total_coeff-1][i_total_zeros] */ | |
| -const vlc_t x264_total_zeros_2x4_dc[7][8] = | |
| -{ | |
| - { /* i_total 1 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 4 }, /* str=0010 */ | |
| - { 0x3, 4 }, /* str=0011 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x0, 5 }, /* str=00000 */ | |
| - }, | |
| - { /* i_total 2 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - }, | |
| - { /* i_total 3 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - }, | |
| - { /* i_total 4 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - }, | |
| - { /* i_total 5 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - }, | |
| - { /* i_total 6 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - }, | |
| - { /* i_total 7 */ | |
| - { 0x0, 1 }, /* str=0 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - } | |
| -}; | |
| - | |
| -/* [MIN( i_zero_left-1, 6 )][run_before] */ | |
| -static const vlc_t run_before[7][16] = | |
| -{ | |
| - { /* i_zero_left 1 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x0, 1 }, /* str=0 */ | |
| - }, | |
| - { /* i_zero_left 2 */ | |
| - { 0x1, 1 }, /* str=1 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - }, | |
| - { /* i_zero_left 3 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x0, 2 }, /* str=00 */ | |
| - }, | |
| - { /* i_zero_left 4 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x1, 2 }, /* str=01 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - }, | |
| - { /* i_zero_left 5 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x2, 2 }, /* str=10 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - }, | |
| - { /* i_zero_left 6 */ | |
| - { 0x3, 2 }, /* str=11 */ | |
| - { 0x0, 3 }, /* str=000 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - }, | |
| - { /* i_zero_left >6 */ | |
| - { 0x7, 3 }, /* str=111 */ | |
| - { 0x6, 3 }, /* str=110 */ | |
| - { 0x5, 3 }, /* str=101 */ | |
| - { 0x4, 3 }, /* str=100 */ | |
| - { 0x3, 3 }, /* str=011 */ | |
| - { 0x2, 3 }, /* str=010 */ | |
| - { 0x1, 3 }, /* str=001 */ | |
| - { 0x1, 4 }, /* str=0001 */ | |
| - { 0x1, 5 }, /* str=00001 */ | |
| - { 0x1, 6 }, /* str=000001 */ | |
| - { 0x1, 7 }, /* str=0000001 */ | |
| - { 0x1, 8 }, /* str=00000001 */ | |
| - { 0x1, 9 }, /* str=000000001 */ | |
| - { 0x1, 10 }, /* str=0000000001 */ | |
| - { 0x1, 11 }, /* str=00000000001 */ | |
| - }, | |
| -}; | |
| - | |
| vlc_large_t x264_level_token[7][LEVEL_TABLE_SIZE]; | |
| uint32_t x264_run_before[1<<16]; | |
| @@ -842,7 +71,9 @@ | |
| vlc->i_next = i_next; | |
| } | |
| - for( int i = 1; i < (1<<16); i++ ) | |
| + x264_run_before[0] = 0; | |
| + x264_run_before[1] = 0; | |
| + for( uint32_t i = 2; i < (1<<16); i++ ) | |
| { | |
| x264_run_level_t runlevel; | |
| ALIGNED_ARRAY_16( dctcoef, dct, [16] ); | |
| @@ -857,10 +88,10 @@ | |
| { | |
| int idx = X264_MIN(zeros, 7) - 1; | |
| int run = x264_clz( mask ); | |
| - int len = run_before[idx][run].i_size; | |
| + int len = x264_run_before_init[idx][run].i_size; | |
| size += len; | |
| bits <<= len; | |
| - bits |= run_before[idx][run].i_bits; | |
| + bits |= x264_run_before_init[idx][run].i_bits; | |
| zeros -= run; | |
| mask <<= run + 1; | |
| } | |
| diff -ur x264-go/x264c/external/x264/common/win32thread.c x264-go.new/x264c/external/x264/common/win32thread.c | |
| --- x264-go/x264c/external/x264/common/win32thread.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/win32thread.c 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * win32thread.c: windows threading | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 x264 project | |
| + * Copyright (C) 2010-2020 x264 project | |
| * | |
| * Authors: Steven Walters <kemuri9@gmail.com> | |
| * Pegasys Inc. <http://www.pegasys-inc.com> | |
| @@ -31,7 +31,7 @@ | |
| /* Based on the agreed standing that x264 does not need to utilize >64 logical cpus, | |
| * this API does not detect nor utilize more than 64 cpus for systems that have them. */ | |
| -#include "common.h" | |
| +#include "base.h" | |
| #if HAVE_WINRT | |
| /* _beginthreadex() is technically the correct option, but it's only available for Desktop applications. | |
| @@ -51,7 +51,7 @@ | |
| static x264_pthread_mutex_t static_mutex; | |
| /* _beginthreadex requires that the start routine is __stdcall */ | |
| -static unsigned __stdcall x264_win32thread_worker( void *arg ) | |
| +static unsigned __stdcall win32thread_worker( void *arg ) | |
| { | |
| x264_pthread_t *h = arg; | |
| *h->p_ret = h->func( h->arg ); | |
| @@ -65,7 +65,7 @@ | |
| thread->arg = arg; | |
| thread->p_ret = &thread->ret; | |
| thread->ret = NULL; | |
| - thread->handle = (void*)_beginthreadex( NULL, 0, x264_win32thread_worker, thread, 0, NULL ); | |
| + thread->handle = (void*)_beginthreadex( NULL, 0, win32thread_worker, thread, 0, NULL ); | |
| return !thread->handle; | |
| } | |
| @@ -95,7 +95,15 @@ | |
| { | |
| static const x264_pthread_mutex_t init = X264_PTHREAD_MUTEX_INITIALIZER; | |
| if( !memcmp( mutex, &init, sizeof(x264_pthread_mutex_t) ) ) | |
| - *mutex = static_mutex; | |
| + { | |
| + int ret = 0; | |
| + EnterCriticalSection( &static_mutex ); | |
| + if( !memcmp( mutex, &init, sizeof(x264_pthread_mutex_t) ) ) | |
| + ret = x264_pthread_mutex_init( mutex, NULL ); | |
| + LeaveCriticalSection( &static_mutex ); | |
| + if( ret ) | |
| + return ret; | |
| + } | |
| EnterCriticalSection( mutex ); | |
| return 0; | |
| } | |
| diff -ur x264-go/x264c/external/x264/common/win32thread.h x264-go.new/x264c/external/x264/common/win32thread.h | |
| --- x264-go/x264c/external/x264/common/win32thread.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/win32thread.h 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * win32thread.h: windows threading | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 x264 project | |
| + * Copyright (C) 2010-2020 x264 project | |
| * | |
| * Authors: Steven Walters <kemuri9@gmail.com> | |
| * | |
| Only in x264-go.new/x264c/external/x264/common/x86: bitstream-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: bitstream.h | |
| Only in x264-go.new/x264c/external/x264/common/x86: cabac-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: const-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: cpu-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: dct-32.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: dct-64.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: dct-a.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/dct.h x264-go.new/x264c/external/x264/common/x86/dct.h | |
| --- x264-go/x264c/external/x264/common/x86/dct.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/dct.h 2020-06-06 15:20:58.692039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * dct.h: x86 transform and zigzag | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -25,120 +25,225 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_I386_DCT_H | |
| -#define X264_I386_DCT_H | |
| +#ifndef X264_X86_DCT_H | |
| +#define X264_X86_DCT_H | |
| +#define x264_sub4x4_dct_mmx x264_template(sub4x4_dct_mmx) | |
| void x264_sub4x4_dct_mmx ( dctcoef dct [16], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x8_dct_mmx x264_template(sub8x8_dct_mmx) | |
| void x264_sub8x8_dct_mmx ( dctcoef dct[ 4][16], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub16x16_dct_mmx x264_template(sub16x16_dct_mmx) | |
| void x264_sub16x16_dct_mmx ( dctcoef dct[16][16], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x8_dct_sse2 x264_template(sub8x8_dct_sse2) | |
| void x264_sub8x8_dct_sse2 ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_sse2 x264_template(sub16x16_dct_sse2) | |
| void x264_sub16x16_dct_sse2 ( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub4x4_dct_ssse3 x264_template(sub4x4_dct_ssse3) | |
| void x264_sub4x4_dct_ssse3 ( int16_t dct [16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub4x4_dct_avx512 x264_template(sub4x4_dct_avx512) | |
| void x264_sub4x4_dct_avx512 ( int16_t dct [16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_ssse3 x264_template(sub8x8_dct_ssse3) | |
| void x264_sub8x8_dct_ssse3 ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_ssse3 x264_template(sub16x16_dct_ssse3) | |
| void x264_sub16x16_dct_ssse3( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_avx x264_template(sub8x8_dct_avx) | |
| void x264_sub8x8_dct_avx ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_avx x264_template(sub16x16_dct_avx) | |
| void x264_sub16x16_dct_avx ( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_xop x264_template(sub8x8_dct_xop) | |
| void x264_sub8x8_dct_xop ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_xop x264_template(sub16x16_dct_xop) | |
| void x264_sub16x16_dct_xop ( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_avx2 x264_template(sub8x8_dct_avx2) | |
| void x264_sub8x8_dct_avx2 ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_avx512 x264_template(sub8x8_dct_avx512) | |
| void x264_sub8x8_dct_avx512 ( int16_t dct[ 4][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_avx2 x264_template(sub16x16_dct_avx2) | |
| void x264_sub16x16_dct_avx2 ( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct_avx512 x264_template(sub16x16_dct_avx512) | |
| void x264_sub16x16_dct_avx512( int16_t dct[16][16], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_dc_mmx2 x264_template(sub8x8_dct_dc_mmx2) | |
| void x264_sub8x8_dct_dc_mmx2 ( int16_t dct [ 4], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct_dc_sse2 x264_template(sub8x8_dct_dc_sse2) | |
| void x264_sub8x8_dct_dc_sse2 ( dctcoef dct [ 4], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x8_dct_dc_avx512 x264_template(sub8x8_dct_dc_avx512) | |
| void x264_sub8x8_dct_dc_avx512 ( int16_t dct [ 4], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x16_dct_dc_sse2 x264_template(sub8x16_dct_dc_sse2) | |
| void x264_sub8x16_dct_dc_sse2 ( dctcoef dct [ 8], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x16_dct_dc_ssse3 x264_template(sub8x16_dct_dc_ssse3) | |
| void x264_sub8x16_dct_dc_ssse3 ( int16_t dct [ 8], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x16_dct_dc_avx x264_template(sub8x16_dct_dc_avx) | |
| void x264_sub8x16_dct_dc_avx ( dctcoef dct [ 8], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x16_dct_dc_avx512 x264_template(sub8x16_dct_dc_avx512) | |
| void x264_sub8x16_dct_dc_avx512( int16_t dct [ 8], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_add4x4_idct_mmx x264_template(add4x4_idct_mmx) | |
| void x264_add4x4_idct_mmx ( uint8_t *p_dst, int16_t dct [16] ); | |
| +#define x264_add4x4_idct_sse2 x264_template(add4x4_idct_sse2) | |
| void x264_add4x4_idct_sse2 ( uint16_t *p_dst, int32_t dct [16] ); | |
| +#define x264_add4x4_idct_sse4 x264_template(add4x4_idct_sse4) | |
| void x264_add4x4_idct_sse4 ( uint8_t *p_dst, int16_t dct [16] ); | |
| +#define x264_add4x4_idct_avx x264_template(add4x4_idct_avx) | |
| void x264_add4x4_idct_avx ( pixel *p_dst, dctcoef dct [16] ); | |
| +#define x264_add8x8_idct_mmx x264_template(add8x8_idct_mmx) | |
| void x264_add8x8_idct_mmx ( uint8_t *p_dst, int16_t dct[ 4][16] ); | |
| +#define x264_add8x8_idct_dc_mmx2 x264_template(add8x8_idct_dc_mmx2) | |
| void x264_add8x8_idct_dc_mmx2 ( uint8_t *p_dst, int16_t dct [ 4] ); | |
| +#define x264_add16x16_idct_mmx x264_template(add16x16_idct_mmx) | |
| void x264_add16x16_idct_mmx ( uint8_t *p_dst, int16_t dct[16][16] ); | |
| +#define x264_add16x16_idct_dc_mmx2 x264_template(add16x16_idct_dc_mmx2) | |
| void x264_add16x16_idct_dc_mmx2 ( uint8_t *p_dst, int16_t dct [16] ); | |
| +#define x264_add8x8_idct_sse2 x264_template(add8x8_idct_sse2) | |
| void x264_add8x8_idct_sse2 ( pixel *p_dst, dctcoef dct[ 4][16] ); | |
| +#define x264_add8x8_idct_avx x264_template(add8x8_idct_avx) | |
| void x264_add8x8_idct_avx ( pixel *p_dst, dctcoef dct[ 4][16] ); | |
| +#define x264_add8x8_idct_avx2 x264_template(add8x8_idct_avx2) | |
| void x264_add8x8_idct_avx2 ( pixel *p_dst, dctcoef dct[ 4][16] ); | |
| +#define x264_add8x8_idct_avx512 x264_template(add8x8_idct_avx512) | |
| void x264_add8x8_idct_avx512 ( uint8_t *p_dst, int16_t dct[ 4][16] ); | |
| +#define x264_add16x16_idct_sse2 x264_template(add16x16_idct_sse2) | |
| void x264_add16x16_idct_sse2 ( pixel *p_dst, dctcoef dct[16][16] ); | |
| +#define x264_add16x16_idct_avx x264_template(add16x16_idct_avx) | |
| void x264_add16x16_idct_avx ( pixel *p_dst, dctcoef dct[16][16] ); | |
| +#define x264_add16x16_idct_avx2 x264_template(add16x16_idct_avx2) | |
| void x264_add16x16_idct_avx2 ( pixel *p_dst, dctcoef dct[16][16] ); | |
| +#define x264_add8x8_idct_dc_sse2 x264_template(add8x8_idct_dc_sse2) | |
| void x264_add8x8_idct_dc_sse2 ( pixel *p_dst, dctcoef dct [ 4] ); | |
| +#define x264_add16x16_idct_dc_sse2 x264_template(add16x16_idct_dc_sse2) | |
| void x264_add16x16_idct_dc_sse2 ( pixel *p_dst, dctcoef dct [16] ); | |
| +#define x264_add8x8_idct_dc_ssse3 x264_template(add8x8_idct_dc_ssse3) | |
| void x264_add8x8_idct_dc_ssse3 ( uint8_t *p_dst, int16_t dct [ 4] ); | |
| +#define x264_add16x16_idct_dc_ssse3 x264_template(add16x16_idct_dc_ssse3) | |
| void x264_add16x16_idct_dc_ssse3( uint8_t *p_dst, int16_t dct [16] ); | |
| +#define x264_add8x8_idct_dc_avx x264_template(add8x8_idct_dc_avx) | |
| void x264_add8x8_idct_dc_avx ( pixel *p_dst, dctcoef dct [ 4] ); | |
| +#define x264_add16x16_idct_dc_avx x264_template(add16x16_idct_dc_avx) | |
| void x264_add16x16_idct_dc_avx ( pixel *p_dst, dctcoef dct [16] ); | |
| +#define x264_add16x16_idct_dc_avx2 x264_template(add16x16_idct_dc_avx2) | |
| void x264_add16x16_idct_dc_avx2 ( uint8_t *p_dst, int16_t dct [16] ); | |
| +#define x264_dct4x4dc_mmx2 x264_template(dct4x4dc_mmx2) | |
| void x264_dct4x4dc_mmx2 ( int16_t d[16] ); | |
| +#define x264_dct4x4dc_sse2 x264_template(dct4x4dc_sse2) | |
| void x264_dct4x4dc_sse2 ( int32_t d[16] ); | |
| +#define x264_dct4x4dc_avx x264_template(dct4x4dc_avx) | |
| void x264_dct4x4dc_avx ( int32_t d[16] ); | |
| +#define x264_idct4x4dc_mmx x264_template(idct4x4dc_mmx) | |
| void x264_idct4x4dc_mmx ( int16_t d[16] ); | |
| +#define x264_idct4x4dc_sse2 x264_template(idct4x4dc_sse2) | |
| void x264_idct4x4dc_sse2 ( int32_t d[16] ); | |
| +#define x264_idct4x4dc_avx x264_template(idct4x4dc_avx) | |
| void x264_idct4x4dc_avx ( int32_t d[16] ); | |
| +#define x264_dct2x4dc_mmx2 x264_template(dct2x4dc_mmx2) | |
| void x264_dct2x4dc_mmx2( dctcoef dct[8], dctcoef dct4x4[8][16] ); | |
| +#define x264_dct2x4dc_sse2 x264_template(dct2x4dc_sse2) | |
| void x264_dct2x4dc_sse2( dctcoef dct[8], dctcoef dct4x4[8][16] ); | |
| +#define x264_dct2x4dc_avx x264_template(dct2x4dc_avx) | |
| void x264_dct2x4dc_avx ( dctcoef dct[8], dctcoef dct4x4[8][16] ); | |
| +#define x264_sub8x8_dct8_mmx x264_template(sub8x8_dct8_mmx) | |
| void x264_sub8x8_dct8_mmx ( int16_t dct [64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct8_mmx x264_template(sub16x16_dct8_mmx) | |
| void x264_sub16x16_dct8_mmx ( int16_t dct[4][64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct8_sse2 x264_template(sub8x8_dct8_sse2) | |
| void x264_sub8x8_dct8_sse2 ( dctcoef dct [64], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub16x16_dct8_sse2 x264_template(sub16x16_dct8_sse2) | |
| void x264_sub16x16_dct8_sse2 ( dctcoef dct[4][64], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub8x8_dct8_ssse3 x264_template(sub8x8_dct8_ssse3) | |
| void x264_sub8x8_dct8_ssse3 ( int16_t dct [64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub16x16_dct8_ssse3 x264_template(sub16x16_dct8_ssse3) | |
| void x264_sub16x16_dct8_ssse3( int16_t dct[4][64], uint8_t *pix1, uint8_t *pix2 ); | |
| +#define x264_sub8x8_dct8_sse4 x264_template(sub8x8_dct8_sse4) | |
| void x264_sub8x8_dct8_sse4 ( int32_t dct [64], uint16_t *pix1, uint16_t *pix2 ); | |
| +#define x264_sub16x16_dct8_sse4 x264_template(sub16x16_dct8_sse4) | |
| void x264_sub16x16_dct8_sse4 ( int32_t dct[4][64], uint16_t *pix1, uint16_t *pix2 ); | |
| +#define x264_sub8x8_dct8_avx x264_template(sub8x8_dct8_avx) | |
| void x264_sub8x8_dct8_avx ( dctcoef dct [64], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub16x16_dct8_avx x264_template(sub16x16_dct8_avx) | |
| void x264_sub16x16_dct8_avx ( dctcoef dct[4][64], pixel *pix1, pixel *pix2 ); | |
| +#define x264_sub16x16_dct8_avx2 x264_template(sub16x16_dct8_avx2) | |
| void x264_sub16x16_dct8_avx2 ( dctcoef dct[4][64], pixel *pix1, pixel *pix2 ); | |
| +#define x264_add8x8_idct8_mmx x264_template(add8x8_idct8_mmx) | |
| void x264_add8x8_idct8_mmx ( uint8_t *dst, int16_t dct [64] ); | |
| +#define x264_add16x16_idct8_mmx x264_template(add16x16_idct8_mmx) | |
| void x264_add16x16_idct8_mmx ( uint8_t *dst, int16_t dct[4][64] ); | |
| +#define x264_add8x8_idct8_sse2 x264_template(add8x8_idct8_sse2) | |
| void x264_add8x8_idct8_sse2 ( pixel *dst, dctcoef dct [64] ); | |
| +#define x264_add16x16_idct8_sse2 x264_template(add16x16_idct8_sse2) | |
| void x264_add16x16_idct8_sse2( pixel *dst, dctcoef dct[4][64] ); | |
| +#define x264_add8x8_idct8_avx x264_template(add8x8_idct8_avx) | |
| void x264_add8x8_idct8_avx ( pixel *dst, dctcoef dct [64] ); | |
| +#define x264_add16x16_idct8_avx x264_template(add16x16_idct8_avx) | |
| void x264_add16x16_idct8_avx ( pixel *dst, dctcoef dct[4][64] ); | |
| +#define x264_zigzag_scan_8x8_frame_mmx2 x264_template(zigzag_scan_8x8_frame_mmx2) | |
| void x264_zigzag_scan_8x8_frame_mmx2 ( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_frame_sse2 x264_template(zigzag_scan_8x8_frame_sse2) | |
| void x264_zigzag_scan_8x8_frame_sse2 ( dctcoef level[64], dctcoef dct[64] ); | |
| +#define x264_zigzag_scan_8x8_frame_ssse3 x264_template(zigzag_scan_8x8_frame_ssse3) | |
| void x264_zigzag_scan_8x8_frame_ssse3 ( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_frame_avx x264_template(zigzag_scan_8x8_frame_avx) | |
| void x264_zigzag_scan_8x8_frame_avx ( dctcoef level[64], dctcoef dct[64] ); | |
| +#define x264_zigzag_scan_8x8_frame_xop x264_template(zigzag_scan_8x8_frame_xop) | |
| void x264_zigzag_scan_8x8_frame_xop ( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_frame_avx512 x264_template(zigzag_scan_8x8_frame_avx512) | |
| void x264_zigzag_scan_8x8_frame_avx512( dctcoef level[64], dctcoef dct[64] ); | |
| +#define x264_zigzag_scan_4x4_frame_mmx x264_template(zigzag_scan_4x4_frame_mmx) | |
| void x264_zigzag_scan_4x4_frame_mmx ( int16_t level[16], int16_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_frame_sse2 x264_template(zigzag_scan_4x4_frame_sse2) | |
| void x264_zigzag_scan_4x4_frame_sse2 ( int32_t level[16], int32_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_frame_ssse3 x264_template(zigzag_scan_4x4_frame_ssse3) | |
| void x264_zigzag_scan_4x4_frame_ssse3 ( int16_t level[16], int16_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_frame_avx x264_template(zigzag_scan_4x4_frame_avx) | |
| void x264_zigzag_scan_4x4_frame_avx ( dctcoef level[16], dctcoef dct[16] ); | |
| +#define x264_zigzag_scan_4x4_frame_xop x264_template(zigzag_scan_4x4_frame_xop) | |
| void x264_zigzag_scan_4x4_frame_xop ( dctcoef level[16], dctcoef dct[16] ); | |
| +#define x264_zigzag_scan_4x4_frame_avx512 x264_template(zigzag_scan_4x4_frame_avx512) | |
| void x264_zigzag_scan_4x4_frame_avx512( dctcoef level[16], dctcoef dct[16] ); | |
| +#define x264_zigzag_scan_4x4_field_sse x264_template(zigzag_scan_4x4_field_sse) | |
| void x264_zigzag_scan_4x4_field_sse ( int16_t level[16], int16_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_field_sse2 x264_template(zigzag_scan_4x4_field_sse2) | |
| void x264_zigzag_scan_4x4_field_sse2 ( int32_t level[16], int32_t dct[16] ); | |
| +#define x264_zigzag_scan_4x4_field_avx512 x264_template(zigzag_scan_4x4_field_avx512) | |
| void x264_zigzag_scan_4x4_field_avx512( dctcoef level[16], dctcoef dct[16] ); | |
| +#define x264_zigzag_scan_8x8_field_mmx2 x264_template(zigzag_scan_8x8_field_mmx2) | |
| void x264_zigzag_scan_8x8_field_mmx2 ( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_field_sse4 x264_template(zigzag_scan_8x8_field_sse4) | |
| void x264_zigzag_scan_8x8_field_sse4 ( int32_t level[64], int32_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_field_avx x264_template(zigzag_scan_8x8_field_avx) | |
| void x264_zigzag_scan_8x8_field_avx ( int32_t level[64], int32_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_field_xop x264_template(zigzag_scan_8x8_field_xop) | |
| void x264_zigzag_scan_8x8_field_xop ( int16_t level[64], int16_t dct[64] ); | |
| +#define x264_zigzag_scan_8x8_field_avx512 x264_template(zigzag_scan_8x8_field_avx512) | |
| void x264_zigzag_scan_8x8_field_avx512( dctcoef level[64], dctcoef dct[64] ); | |
| +#define x264_zigzag_sub_4x4_frame_avx x264_template(zigzag_sub_4x4_frame_avx) | |
| int x264_zigzag_sub_4x4_frame_avx ( int16_t level[16], const uint8_t *src, uint8_t *dst ); | |
| +#define x264_zigzag_sub_4x4_frame_ssse3 x264_template(zigzag_sub_4x4_frame_ssse3) | |
| int x264_zigzag_sub_4x4_frame_ssse3 ( int16_t level[16], const uint8_t *src, uint8_t *dst ); | |
| +#define x264_zigzag_sub_4x4ac_frame_avx x264_template(zigzag_sub_4x4ac_frame_avx) | |
| int x264_zigzag_sub_4x4ac_frame_avx ( int16_t level[16], const uint8_t *src, uint8_t *dst, int16_t *dc ); | |
| +#define x264_zigzag_sub_4x4ac_frame_ssse3 x264_template(zigzag_sub_4x4ac_frame_ssse3) | |
| int x264_zigzag_sub_4x4ac_frame_ssse3( int16_t level[16], const uint8_t *src, uint8_t *dst, int16_t *dc ); | |
| +#define x264_zigzag_sub_4x4_field_avx x264_template(zigzag_sub_4x4_field_avx) | |
| int x264_zigzag_sub_4x4_field_avx ( int16_t level[16], const uint8_t *src, uint8_t *dst ); | |
| +#define x264_zigzag_sub_4x4_field_ssse3 x264_template(zigzag_sub_4x4_field_ssse3) | |
| int x264_zigzag_sub_4x4_field_ssse3 ( int16_t level[16], const uint8_t *src, uint8_t *dst ); | |
| +#define x264_zigzag_sub_4x4ac_field_avx x264_template(zigzag_sub_4x4ac_field_avx) | |
| int x264_zigzag_sub_4x4ac_field_avx ( int16_t level[16], const uint8_t *src, uint8_t *dst, int16_t *dc ); | |
| +#define x264_zigzag_sub_4x4ac_field_ssse3 x264_template(zigzag_sub_4x4ac_field_ssse3) | |
| int x264_zigzag_sub_4x4ac_field_ssse3( int16_t level[16], const uint8_t *src, uint8_t *dst, int16_t *dc ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_mmx x264_template(zigzag_interleave_8x8_cavlc_mmx) | |
| void x264_zigzag_interleave_8x8_cavlc_mmx ( int16_t *dst, int16_t *src, uint8_t *nnz ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_sse2 x264_template(zigzag_interleave_8x8_cavlc_sse2) | |
| void x264_zigzag_interleave_8x8_cavlc_sse2 ( dctcoef *dst, dctcoef *src, uint8_t *nnz ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_avx x264_template(zigzag_interleave_8x8_cavlc_avx) | |
| void x264_zigzag_interleave_8x8_cavlc_avx ( dctcoef *dst, dctcoef *src, uint8_t *nnz ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_avx2 x264_template(zigzag_interleave_8x8_cavlc_avx2) | |
| void x264_zigzag_interleave_8x8_cavlc_avx2 ( int16_t *dst, int16_t *src, uint8_t *nnz ); | |
| +#define x264_zigzag_interleave_8x8_cavlc_avx512 x264_template(zigzag_interleave_8x8_cavlc_avx512) | |
| void x264_zigzag_interleave_8x8_cavlc_avx512( dctcoef *dst, dctcoef *src, uint8_t *nnz ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/x86: deblock-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: deblock.h | |
| Only in x264-go.new/x264c/external/x264/common/x86: mc-a2.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: mc-a.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/mc-c.c x264-go.new/x264c/external/x264/common/x86/mc-c.c | |
| --- x264-go/x264c/external/x264/common/x86/mc-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/mc-c.c 2020-06-06 15:20:58.693039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc-c.c: x86 motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -28,6 +28,40 @@ | |
| #include "common/common.h" | |
| #include "mc.h" | |
| +#define x264_pixel_avg_16x16_avx2 x264_template(pixel_avg_16x16_avx2) | |
| +#define x264_pixel_avg_16x16_avx512 x264_template(pixel_avg_16x16_avx512) | |
| +#define x264_pixel_avg_16x16_mmx2 x264_template(pixel_avg_16x16_mmx2) | |
| +#define x264_pixel_avg_16x16_sse2 x264_template(pixel_avg_16x16_sse2) | |
| +#define x264_pixel_avg_16x16_ssse3 x264_template(pixel_avg_16x16_ssse3) | |
| +#define x264_pixel_avg_16x8_avx2 x264_template(pixel_avg_16x8_avx2) | |
| +#define x264_pixel_avg_16x8_avx512 x264_template(pixel_avg_16x8_avx512) | |
| +#define x264_pixel_avg_16x8_mmx2 x264_template(pixel_avg_16x8_mmx2) | |
| +#define x264_pixel_avg_16x8_sse2 x264_template(pixel_avg_16x8_sse2) | |
| +#define x264_pixel_avg_16x8_ssse3 x264_template(pixel_avg_16x8_ssse3) | |
| +#define x264_pixel_avg_4x16_mmx2 x264_template(pixel_avg_4x16_mmx2) | |
| +#define x264_pixel_avg_4x16_sse2 x264_template(pixel_avg_4x16_sse2) | |
| +#define x264_pixel_avg_4x16_ssse3 x264_template(pixel_avg_4x16_ssse3) | |
| +#define x264_pixel_avg_4x2_mmx2 x264_template(pixel_avg_4x2_mmx2) | |
| +#define x264_pixel_avg_4x2_sse2 x264_template(pixel_avg_4x2_sse2) | |
| +#define x264_pixel_avg_4x2_ssse3 x264_template(pixel_avg_4x2_ssse3) | |
| +#define x264_pixel_avg_4x4_mmx2 x264_template(pixel_avg_4x4_mmx2) | |
| +#define x264_pixel_avg_4x4_sse2 x264_template(pixel_avg_4x4_sse2) | |
| +#define x264_pixel_avg_4x4_ssse3 x264_template(pixel_avg_4x4_ssse3) | |
| +#define x264_pixel_avg_4x8_mmx2 x264_template(pixel_avg_4x8_mmx2) | |
| +#define x264_pixel_avg_4x8_sse2 x264_template(pixel_avg_4x8_sse2) | |
| +#define x264_pixel_avg_4x8_ssse3 x264_template(pixel_avg_4x8_ssse3) | |
| +#define x264_pixel_avg_8x16_avx512 x264_template(pixel_avg_8x16_avx512) | |
| +#define x264_pixel_avg_8x16_mmx2 x264_template(pixel_avg_8x16_mmx2) | |
| +#define x264_pixel_avg_8x16_sse2 x264_template(pixel_avg_8x16_sse2) | |
| +#define x264_pixel_avg_8x16_ssse3 x264_template(pixel_avg_8x16_ssse3) | |
| +#define x264_pixel_avg_8x4_avx512 x264_template(pixel_avg_8x4_avx512) | |
| +#define x264_pixel_avg_8x4_mmx2 x264_template(pixel_avg_8x4_mmx2) | |
| +#define x264_pixel_avg_8x4_sse2 x264_template(pixel_avg_8x4_sse2) | |
| +#define x264_pixel_avg_8x4_ssse3 x264_template(pixel_avg_8x4_ssse3) | |
| +#define x264_pixel_avg_8x8_avx512 x264_template(pixel_avg_8x8_avx512) | |
| +#define x264_pixel_avg_8x8_mmx2 x264_template(pixel_avg_8x8_mmx2) | |
| +#define x264_pixel_avg_8x8_sse2 x264_template(pixel_avg_8x8_sse2) | |
| +#define x264_pixel_avg_8x8_ssse3 x264_template(pixel_avg_8x8_ssse3) | |
| #define DECL_SUF( func, args )\ | |
| void func##_mmx2 args;\ | |
| void func##_sse2 args;\ | |
| @@ -44,10 +78,43 @@ | |
| DECL_SUF( x264_pixel_avg_4x8, ( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t, int )) | |
| DECL_SUF( x264_pixel_avg_4x4, ( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t, int )) | |
| DECL_SUF( x264_pixel_avg_4x2, ( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t, int )) | |
| +#undef DECL_SUF | |
| +#define x264_mc_weight_w12_mmx2 x264_template(mc_weight_w12_mmx2) | |
| +#define x264_mc_weight_w12_sse2 x264_template(mc_weight_w12_sse2) | |
| +#define x264_mc_weight_w16_avx2 x264_template(mc_weight_w16_avx2) | |
| +#define x264_mc_weight_w16_mmx2 x264_template(mc_weight_w16_mmx2) | |
| +#define x264_mc_weight_w16_sse2 x264_template(mc_weight_w16_sse2) | |
| +#define x264_mc_weight_w16_ssse3 x264_template(mc_weight_w16_ssse3) | |
| +#define x264_mc_weight_w20_avx2 x264_template(mc_weight_w20_avx2) | |
| +#define x264_mc_weight_w20_mmx2 x264_template(mc_weight_w20_mmx2) | |
| +#define x264_mc_weight_w20_sse2 x264_template(mc_weight_w20_sse2) | |
| +#define x264_mc_weight_w20_ssse3 x264_template(mc_weight_w20_ssse3) | |
| +#define x264_mc_weight_w4_mmx2 x264_template(mc_weight_w4_mmx2) | |
| +#define x264_mc_weight_w4_ssse3 x264_template(mc_weight_w4_ssse3) | |
| +#define x264_mc_weight_w8_avx2 x264_template(mc_weight_w8_avx2) | |
| +#define x264_mc_weight_w8_mmx2 x264_template(mc_weight_w8_mmx2) | |
| +#define x264_mc_weight_w8_sse2 x264_template(mc_weight_w8_sse2) | |
| +#define x264_mc_weight_w8_ssse3 x264_template(mc_weight_w8_ssse3) | |
| #define MC_WEIGHT(w,type) \ | |
| void x264_mc_weight_w##w##_##type( pixel *, intptr_t, pixel *, intptr_t, const x264_weight_t *, int ); | |
| +#define x264_mc_offsetadd_w12_mmx2 x264_template(mc_offsetadd_w12_mmx2) | |
| +#define x264_mc_offsetadd_w16_mmx2 x264_template(mc_offsetadd_w16_mmx2) | |
| +#define x264_mc_offsetadd_w16_sse2 x264_template(mc_offsetadd_w16_sse2) | |
| +#define x264_mc_offsetadd_w20_mmx2 x264_template(mc_offsetadd_w20_mmx2) | |
| +#define x264_mc_offsetadd_w20_sse2 x264_template(mc_offsetadd_w20_sse2) | |
| +#define x264_mc_offsetadd_w4_mmx2 x264_template(mc_offsetadd_w4_mmx2) | |
| +#define x264_mc_offsetadd_w8_mmx2 x264_template(mc_offsetadd_w8_mmx2) | |
| +#define x264_mc_offsetadd_w8_sse2 x264_template(mc_offsetadd_w8_sse2) | |
| +#define x264_mc_offsetsub_w12_mmx2 x264_template(mc_offsetsub_w12_mmx2) | |
| +#define x264_mc_offsetsub_w16_mmx2 x264_template(mc_offsetsub_w16_mmx2) | |
| +#define x264_mc_offsetsub_w16_sse2 x264_template(mc_offsetsub_w16_sse2) | |
| +#define x264_mc_offsetsub_w20_mmx2 x264_template(mc_offsetsub_w20_mmx2) | |
| +#define x264_mc_offsetsub_w20_sse2 x264_template(mc_offsetsub_w20_sse2) | |
| +#define x264_mc_offsetsub_w4_mmx2 x264_template(mc_offsetsub_w4_mmx2) | |
| +#define x264_mc_offsetsub_w8_mmx2 x264_template(mc_offsetsub_w8_mmx2) | |
| +#define x264_mc_offsetsub_w8_sse2 x264_template(mc_offsetsub_w8_sse2) | |
| #define MC_WEIGHT_OFFSET(w,type) \ | |
| void x264_mc_offsetadd_w##w##_##type( pixel *, intptr_t, pixel *, intptr_t, const x264_weight_t *, int ); \ | |
| void x264_mc_offsetsub_w##w##_##type( pixel *, intptr_t, pixel *, intptr_t, const x264_weight_t *, int ); \ | |
| @@ -73,113 +140,200 @@ | |
| MC_WEIGHT( 8, avx2 ) | |
| MC_WEIGHT( 16, avx2 ) | |
| MC_WEIGHT( 20, avx2 ) | |
| -#undef MC_OFFSET | |
| +#undef MC_WEIGHT_OFFSET | |
| #undef MC_WEIGHT | |
| +#define x264_mc_copy_w4_mmx x264_template(mc_copy_w4_mmx) | |
| void x264_mc_copy_w4_mmx ( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w8_mmx x264_template(mc_copy_w8_mmx) | |
| void x264_mc_copy_w8_mmx ( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w8_sse x264_template(mc_copy_w8_sse) | |
| void x264_mc_copy_w8_sse ( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_mmx x264_template(mc_copy_w16_mmx) | |
| void x264_mc_copy_w16_mmx( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_sse x264_template(mc_copy_w16_sse) | |
| void x264_mc_copy_w16_sse( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_aligned_sse x264_template(mc_copy_w16_aligned_sse) | |
| void x264_mc_copy_w16_aligned_sse( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_avx x264_template(mc_copy_w16_avx) | |
| void x264_mc_copy_w16_avx( uint16_t *, intptr_t, uint16_t *, intptr_t, int ); | |
| +#define x264_mc_copy_w16_aligned_avx x264_template(mc_copy_w16_aligned_avx) | |
| void x264_mc_copy_w16_aligned_avx( uint16_t *, intptr_t, uint16_t *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_400_mmx2 x264_template(prefetch_fenc_400_mmx2) | |
| +void x264_prefetch_fenc_400_mmx2( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_420_mmx2 x264_template(prefetch_fenc_420_mmx2) | |
| void x264_prefetch_fenc_420_mmx2( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_prefetch_fenc_422_mmx2 x264_template(prefetch_fenc_422_mmx2) | |
| void x264_prefetch_fenc_422_mmx2( pixel *, intptr_t, pixel *, intptr_t, int ); | |
| +#define x264_prefetch_ref_mmx2 x264_template(prefetch_ref_mmx2) | |
| void x264_prefetch_ref_mmx2( pixel *, intptr_t, int ); | |
| +#define x264_plane_copy_core_sse x264_template(plane_copy_core_sse) | |
| void x264_plane_copy_core_sse( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_core_avx x264_template(plane_copy_core_avx) | |
| void x264_plane_copy_core_avx( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_avx512 x264_template(plane_copy_avx512) | |
| +void x264_plane_copy_avx512( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_swap_core_ssse3 x264_template(plane_copy_swap_core_ssse3) | |
| void x264_plane_copy_swap_core_ssse3( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_swap_core_avx2 x264_template(plane_copy_swap_core_avx2) | |
| void x264_plane_copy_swap_core_avx2 ( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_swap_avx512 x264_template(plane_copy_swap_avx512) | |
| +void x264_plane_copy_swap_avx512( pixel *, intptr_t, pixel *, intptr_t, int w, int h ); | |
| +#define x264_plane_copy_interleave_core_mmx2 x264_template(plane_copy_interleave_core_mmx2) | |
| void x264_plane_copy_interleave_core_mmx2( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| +#define x264_plane_copy_interleave_core_sse2 x264_template(plane_copy_interleave_core_sse2) | |
| void x264_plane_copy_interleave_core_sse2( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| +#define x264_plane_copy_interleave_core_avx x264_template(plane_copy_interleave_core_avx) | |
| void x264_plane_copy_interleave_core_avx( pixel *dst, intptr_t i_dst, | |
| pixel *srcu, intptr_t i_srcu, | |
| pixel *srcv, intptr_t i_srcv, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_sse2 x264_template(plane_copy_deinterleave_sse2) | |
| void x264_plane_copy_deinterleave_sse2( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_ssse3 x264_template(plane_copy_deinterleave_ssse3) | |
| void x264_plane_copy_deinterleave_ssse3( uint8_t *dsta, intptr_t i_dsta, | |
| uint8_t *dstb, intptr_t i_dstb, | |
| uint8_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_avx x264_template(plane_copy_deinterleave_avx) | |
| void x264_plane_copy_deinterleave_avx( uint16_t *dsta, intptr_t i_dsta, | |
| uint16_t *dstb, intptr_t i_dstb, | |
| uint16_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_avx2 x264_template(plane_copy_deinterleave_avx2) | |
| void x264_plane_copy_deinterleave_avx2( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_rgb_sse2 x264_template(plane_copy_deinterleave_rgb_sse2) | |
| void x264_plane_copy_deinterleave_rgb_sse2 ( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *dstc, intptr_t i_dstc, | |
| pixel *src, intptr_t i_src, int pw, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_rgb_ssse3 x264_template(plane_copy_deinterleave_rgb_ssse3) | |
| void x264_plane_copy_deinterleave_rgb_ssse3( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *dstc, intptr_t i_dstc, | |
| pixel *src, intptr_t i_src, int pw, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_rgb_avx2 x264_template(plane_copy_deinterleave_rgb_avx2) | |
| void x264_plane_copy_deinterleave_rgb_avx2 ( pixel *dsta, intptr_t i_dsta, | |
| pixel *dstb, intptr_t i_dstb, | |
| pixel *dstc, intptr_t i_dstc, | |
| pixel *src, intptr_t i_src, int pw, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_v210_ssse3 x264_template(plane_copy_deinterleave_v210_ssse3) | |
| void x264_plane_copy_deinterleave_v210_ssse3 ( uint16_t *dstu, intptr_t i_dstu, | |
| uint16_t *dstv, intptr_t i_dstv, | |
| uint32_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_v210_avx x264_template(plane_copy_deinterleave_v210_avx) | |
| void x264_plane_copy_deinterleave_v210_avx ( uint16_t *dstu, intptr_t i_dstu, | |
| uint16_t *dstv, intptr_t i_dstv, | |
| uint32_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_v210_avx2 x264_template(plane_copy_deinterleave_v210_avx2) | |
| void x264_plane_copy_deinterleave_v210_avx2 ( uint16_t *dstu, intptr_t i_dstu, | |
| uint16_t *dstv, intptr_t i_dstv, | |
| uint32_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_plane_copy_deinterleave_v210_avx512 x264_template(plane_copy_deinterleave_v210_avx512) | |
| void x264_plane_copy_deinterleave_v210_avx512( uint16_t *dstu, intptr_t i_dstu, | |
| uint16_t *dstv, intptr_t i_dstv, | |
| uint32_t *src, intptr_t i_src, int w, int h ); | |
| +#define x264_store_interleave_chroma_mmx2 x264_template(store_interleave_chroma_mmx2) | |
| void x264_store_interleave_chroma_mmx2( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); | |
| +#define x264_store_interleave_chroma_sse2 x264_template(store_interleave_chroma_sse2) | |
| void x264_store_interleave_chroma_sse2( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); | |
| +#define x264_store_interleave_chroma_avx x264_template(store_interleave_chroma_avx) | |
| void x264_store_interleave_chroma_avx ( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_sse2 x264_template(load_deinterleave_chroma_fenc_sse2) | |
| void x264_load_deinterleave_chroma_fenc_sse2( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_ssse3 x264_template(load_deinterleave_chroma_fenc_ssse3) | |
| void x264_load_deinterleave_chroma_fenc_ssse3( uint8_t *dst, uint8_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_avx x264_template(load_deinterleave_chroma_fenc_avx) | |
| void x264_load_deinterleave_chroma_fenc_avx( uint16_t *dst, uint16_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_avx2 x264_template(load_deinterleave_chroma_fenc_avx2) | |
| void x264_load_deinterleave_chroma_fenc_avx2( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fenc_avx512 x264_template(load_deinterleave_chroma_fenc_avx512) | |
| +void x264_load_deinterleave_chroma_fenc_avx512( uint8_t *dst, uint8_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_sse2 x264_template(load_deinterleave_chroma_fdec_sse2) | |
| void x264_load_deinterleave_chroma_fdec_sse2( pixel *dst, pixel *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_ssse3 x264_template(load_deinterleave_chroma_fdec_ssse3) | |
| void x264_load_deinterleave_chroma_fdec_ssse3( uint8_t *dst, uint8_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_avx x264_template(load_deinterleave_chroma_fdec_avx) | |
| void x264_load_deinterleave_chroma_fdec_avx( uint16_t *dst, uint16_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_avx2 x264_template(load_deinterleave_chroma_fdec_avx2) | |
| void x264_load_deinterleave_chroma_fdec_avx2( uint16_t *dst, uint16_t *src, intptr_t i_src, int height ); | |
| +#define x264_load_deinterleave_chroma_fdec_avx512 x264_template(load_deinterleave_chroma_fdec_avx512) | |
| +void x264_load_deinterleave_chroma_fdec_avx512( uint8_t *dst, uint8_t *src, intptr_t i_src, int height ); | |
| +#define x264_memcpy_aligned_sse x264_template(memcpy_aligned_sse) | |
| void *x264_memcpy_aligned_sse ( void *dst, const void *src, size_t n ); | |
| +#define x264_memcpy_aligned_avx x264_template(memcpy_aligned_avx) | |
| void *x264_memcpy_aligned_avx ( void *dst, const void *src, size_t n ); | |
| +#define x264_memcpy_aligned_avx512 x264_template(memcpy_aligned_avx512) | |
| void *x264_memcpy_aligned_avx512( void *dst, const void *src, size_t n ); | |
| +#define x264_memzero_aligned_sse x264_template(memzero_aligned_sse) | |
| void x264_memzero_aligned_sse ( void *dst, size_t n ); | |
| +#define x264_memzero_aligned_avx x264_template(memzero_aligned_avx) | |
| void x264_memzero_aligned_avx ( void *dst, size_t n ); | |
| +#define x264_memzero_aligned_avx512 x264_template(memzero_aligned_avx512) | |
| void x264_memzero_aligned_avx512( void *dst, size_t n ); | |
| +#define x264_integral_init4h_sse4 x264_template(integral_init4h_sse4) | |
| void x264_integral_init4h_sse4( uint16_t *sum, uint8_t *pix, intptr_t stride ); | |
| +#define x264_integral_init4h_avx2 x264_template(integral_init4h_avx2) | |
| void x264_integral_init4h_avx2( uint16_t *sum, uint8_t *pix, intptr_t stride ); | |
| +#define x264_integral_init8h_sse4 x264_template(integral_init8h_sse4) | |
| void x264_integral_init8h_sse4( uint16_t *sum, uint8_t *pix, intptr_t stride ); | |
| +#define x264_integral_init8h_avx x264_template(integral_init8h_avx) | |
| void x264_integral_init8h_avx ( uint16_t *sum, uint8_t *pix, intptr_t stride ); | |
| +#define x264_integral_init8h_avx2 x264_template(integral_init8h_avx2) | |
| void x264_integral_init8h_avx2( uint16_t *sum, uint8_t *pix, intptr_t stride ); | |
| +#define x264_integral_init4v_mmx x264_template(integral_init4v_mmx) | |
| void x264_integral_init4v_mmx ( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); | |
| +#define x264_integral_init4v_sse2 x264_template(integral_init4v_sse2) | |
| void x264_integral_init4v_sse2 ( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); | |
| +#define x264_integral_init4v_ssse3 x264_template(integral_init4v_ssse3) | |
| void x264_integral_init4v_ssse3( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); | |
| +#define x264_integral_init4v_avx2 x264_template(integral_init4v_avx2) | |
| void x264_integral_init4v_avx2( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); | |
| +#define x264_integral_init8v_mmx x264_template(integral_init8v_mmx) | |
| void x264_integral_init8v_mmx ( uint16_t *sum8, intptr_t stride ); | |
| +#define x264_integral_init8v_sse2 x264_template(integral_init8v_sse2) | |
| void x264_integral_init8v_sse2( uint16_t *sum8, intptr_t stride ); | |
| +#define x264_integral_init8v_avx2 x264_template(integral_init8v_avx2) | |
| void x264_integral_init8v_avx2( uint16_t *sum8, intptr_t stride ); | |
| +#define x264_mbtree_propagate_cost_sse2 x264_template(mbtree_propagate_cost_sse2) | |
| void x264_mbtree_propagate_cost_sse2 ( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, | |
| uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); | |
| +#define x264_mbtree_propagate_cost_avx x264_template(mbtree_propagate_cost_avx) | |
| void x264_mbtree_propagate_cost_avx ( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, | |
| uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); | |
| +#define x264_mbtree_propagate_cost_fma4 x264_template(mbtree_propagate_cost_fma4) | |
| void x264_mbtree_propagate_cost_fma4 ( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, | |
| uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); | |
| +#define x264_mbtree_propagate_cost_avx2 x264_template(mbtree_propagate_cost_avx2) | |
| void x264_mbtree_propagate_cost_avx2 ( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, | |
| uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); | |
| +#define x264_mbtree_propagate_cost_avx512 x264_template(mbtree_propagate_cost_avx512) | |
| void x264_mbtree_propagate_cost_avx512( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, | |
| uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); | |
| +#define x264_mbtree_fix8_pack_ssse3 x264_template(mbtree_fix8_pack_ssse3) | |
| void x264_mbtree_fix8_pack_ssse3( uint16_t *dst, float *src, int count ); | |
| +#define x264_mbtree_fix8_pack_avx2 x264_template(mbtree_fix8_pack_avx2) | |
| void x264_mbtree_fix8_pack_avx2 ( uint16_t *dst, float *src, int count ); | |
| +#define x264_mbtree_fix8_pack_avx512 x264_template(mbtree_fix8_pack_avx512) | |
| +void x264_mbtree_fix8_pack_avx512( uint16_t *dst, float *src, int count ); | |
| +#define x264_mbtree_fix8_unpack_ssse3 x264_template(mbtree_fix8_unpack_ssse3) | |
| void x264_mbtree_fix8_unpack_ssse3( float *dst, uint16_t *src, int count ); | |
| +#define x264_mbtree_fix8_unpack_avx2 x264_template(mbtree_fix8_unpack_avx2) | |
| void x264_mbtree_fix8_unpack_avx2 ( float *dst, uint16_t *src, int count ); | |
| +#define x264_mbtree_fix8_unpack_avx512 x264_template(mbtree_fix8_unpack_avx512) | |
| +void x264_mbtree_fix8_unpack_avx512( float *dst, uint16_t *src, int count ); | |
| +#define x264_mc_chroma_avx x264_template(mc_chroma_avx) | |
| +#define x264_mc_chroma_avx2 x264_template(mc_chroma_avx2) | |
| +#define x264_mc_chroma_cache64_ssse3 x264_template(mc_chroma_cache64_ssse3) | |
| +#define x264_mc_chroma_mmx2 x264_template(mc_chroma_mmx2) | |
| +#define x264_mc_chroma_sse2 x264_template(mc_chroma_sse2) | |
| +#define x264_mc_chroma_ssse3 x264_template(mc_chroma_ssse3) | |
| #define MC_CHROMA(cpu)\ | |
| void x264_mc_chroma_##cpu( pixel *dstu, pixel *dstv, intptr_t i_dst, pixel *src, intptr_t i_src,\ | |
| int dx, int dy, int i_width, int i_height ); | |
| @@ -189,7 +343,15 @@ | |
| MC_CHROMA(cache64_ssse3) | |
| MC_CHROMA(avx) | |
| MC_CHROMA(avx2) | |
| +#undef MC_CHROMA | |
| +#define x264_frame_init_lowres_core_avx x264_template(frame_init_lowres_core_avx) | |
| +#define x264_frame_init_lowres_core_avx2 x264_template(frame_init_lowres_core_avx2) | |
| +#define x264_frame_init_lowres_core_mmx2 x264_template(frame_init_lowres_core_mmx2) | |
| +#define x264_frame_init_lowres_core_cache32_mmx2 x264_template(frame_init_lowres_core_cache32_mmx2) | |
| +#define x264_frame_init_lowres_core_sse2 x264_template(frame_init_lowres_core_sse2) | |
| +#define x264_frame_init_lowres_core_ssse3 x264_template(frame_init_lowres_core_ssse3) | |
| +#define x264_frame_init_lowres_core_xop x264_template(frame_init_lowres_core_xop) | |
| #define LOWRES(cpu)\ | |
| void x264_frame_init_lowres_core_##cpu( pixel *src0, pixel *dst0, pixel *dsth, pixel *dstv, pixel *dstc,\ | |
| intptr_t src_stride, intptr_t dst_stride, int width, int height ); | |
| @@ -200,7 +362,34 @@ | |
| LOWRES(avx) | |
| LOWRES(xop) | |
| LOWRES(avx2) | |
| +#undef LOWRES | |
| +#define x264_pixel_avg2_w10_mmx2 x264_template(pixel_avg2_w10_mmx2) | |
| +#define x264_pixel_avg2_w10_sse2 x264_template(pixel_avg2_w10_sse2) | |
| +#define x264_pixel_avg2_w12_cache32_mmx2 x264_template(pixel_avg2_w12_cache32_mmx2) | |
| +#define x264_pixel_avg2_w12_cache64_mmx2 x264_template(pixel_avg2_w12_cache64_mmx2) | |
| +#define x264_pixel_avg2_w12_mmx2 x264_template(pixel_avg2_w12_mmx2) | |
| +#define x264_pixel_avg2_w16_avx2 x264_template(pixel_avg2_w16_avx2) | |
| +#define x264_pixel_avg2_w16_cache32_mmx2 x264_template(pixel_avg2_w16_cache32_mmx2) | |
| +#define x264_pixel_avg2_w16_cache64_mmx2 x264_template(pixel_avg2_w16_cache64_mmx2) | |
| +#define x264_pixel_avg2_w16_cache64_sse2 x264_template(pixel_avg2_w16_cache64_sse2) | |
| +#define x264_pixel_avg2_w16_cache64_ssse3 x264_template(pixel_avg2_w16_cache64_ssse3) | |
| +#define x264_pixel_avg2_w16_mmx2 x264_template(pixel_avg2_w16_mmx2) | |
| +#define x264_pixel_avg2_w16_sse2 x264_template(pixel_avg2_w16_sse2) | |
| +#define x264_pixel_avg2_w18_avx2 x264_template(pixel_avg2_w18_avx2) | |
| +#define x264_pixel_avg2_w18_mmx2 x264_template(pixel_avg2_w18_mmx2) | |
| +#define x264_pixel_avg2_w18_sse2 x264_template(pixel_avg2_w18_sse2) | |
| +#define x264_pixel_avg2_w20_avx2 x264_template(pixel_avg2_w20_avx2) | |
| +#define x264_pixel_avg2_w20_cache32_mmx2 x264_template(pixel_avg2_w20_cache32_mmx2) | |
| +#define x264_pixel_avg2_w20_cache64_mmx2 x264_template(pixel_avg2_w20_cache64_mmx2) | |
| +#define x264_pixel_avg2_w20_cache64_sse2 x264_template(pixel_avg2_w20_cache64_sse2) | |
| +#define x264_pixel_avg2_w20_mmx2 x264_template(pixel_avg2_w20_mmx2) | |
| +#define x264_pixel_avg2_w20_sse2 x264_template(pixel_avg2_w20_sse2) | |
| +#define x264_pixel_avg2_w4_mmx2 x264_template(pixel_avg2_w4_mmx2) | |
| +#define x264_pixel_avg2_w8_cache32_mmx2 x264_template(pixel_avg2_w8_cache32_mmx2) | |
| +#define x264_pixel_avg2_w8_cache64_mmx2 x264_template(pixel_avg2_w8_cache64_mmx2) | |
| +#define x264_pixel_avg2_w8_mmx2 x264_template(pixel_avg2_w8_mmx2) | |
| +#define x264_pixel_avg2_w8_sse2 x264_template(pixel_avg2_w8_sse2) | |
| #define PIXEL_AVG_W(width,cpu)\ | |
| void x264_pixel_avg2_w##width##_##cpu( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t ); | |
| /* This declares some functions that don't exist, but that isn't a problem. */ | |
| @@ -214,9 +403,11 @@ | |
| PIXEL_AVG_WALL(sse2) | |
| PIXEL_AVG_WALL(cache64_ssse3) | |
| PIXEL_AVG_WALL(avx2) | |
| +#undef PIXEL_AVG_W | |
| +#undef PIXEL_AVG_WALL | |
| #define PIXEL_AVG_WTAB(instr, name1, name2, name3, name4, name5)\ | |
| -static void (* const x264_pixel_avg_wtab_##instr[6])( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t ) =\ | |
| +static void (* const pixel_avg_wtab_##instr[6])( pixel *, intptr_t, pixel *, intptr_t, pixel *, intptr_t ) =\ | |
| {\ | |
| NULL,\ | |
| x264_pixel_avg2_w4_##name1,\ | |
| @@ -228,6 +419,10 @@ | |
| #if HIGH_BIT_DEPTH | |
| /* we can replace w12/w20 with w10/w18 as only 9/17 pixels in fact are important */ | |
| +#undef x264_pixel_avg2_w12_mmx2 | |
| +#undef x264_pixel_avg2_w20_mmx2 | |
| +#undef x264_pixel_avg2_w20_sse2 | |
| +#undef x264_pixel_avg2_w20_avx2 | |
| #define x264_pixel_avg2_w12_mmx2 x264_pixel_avg2_w10_mmx2 | |
| #define x264_pixel_avg2_w20_mmx2 x264_pixel_avg2_w18_mmx2 | |
| #define x264_pixel_avg2_w12_sse2 x264_pixel_avg2_w10_sse2 | |
| @@ -259,7 +454,7 @@ | |
| #endif // HIGH_BIT_DEPTH | |
| #define MC_COPY_WTAB(instr, name1, name2, name3)\ | |
| -static void (* const x264_mc_copy_wtab_##instr[5])( pixel *, intptr_t, pixel *, intptr_t, int ) =\ | |
| +static void (* const mc_copy_wtab_##instr[5])( pixel *, intptr_t, pixel *, intptr_t, int ) =\ | |
| {\ | |
| NULL,\ | |
| x264_mc_copy_w4_##name1,\ | |
| @@ -277,7 +472,7 @@ | |
| #endif | |
| #define MC_WEIGHT_WTAB(function, instr, name1, name2, w12version)\ | |
| - static void (* x264_mc_##function##_wtab_##instr[6])( pixel *, intptr_t, pixel *, intptr_t, const x264_weight_t *, int ) =\ | |
| +static void (* mc_##function##_wtab_##instr[6])( pixel *, intptr_t, pixel *, intptr_t, const x264_weight_t *, int ) =\ | |
| {\ | |
| x264_mc_##function##_w4_##name1,\ | |
| x264_mc_##function##_w4_##name1,\ | |
| @@ -295,7 +490,7 @@ | |
| MC_WEIGHT_WTAB(offsetadd,sse2,mmx2,sse2,16) | |
| MC_WEIGHT_WTAB(offsetsub,sse2,mmx2,sse2,16) | |
| -static void x264_weight_cache_mmx2( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache_mmx2( x264_t *h, x264_weight_t *w ) | |
| { | |
| if( w->i_scale == 1<<w->i_denom ) | |
| { | |
| @@ -327,7 +522,7 @@ | |
| MC_WEIGHT_WTAB(weight,ssse3,ssse3,ssse3,16) | |
| MC_WEIGHT_WTAB(weight,avx2,ssse3,avx2,16) | |
| -static void x264_weight_cache_mmx2( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache_mmx2( x264_t *h, x264_weight_t *w ) | |
| { | |
| int i; | |
| int16_t den1; | |
| @@ -342,7 +537,7 @@ | |
| return; | |
| } | |
| w->weightfn = h->mc.weight; | |
| - den1 = 1 << (w->i_denom - 1) | w->i_offset << w->i_denom; | |
| + den1 = w->i_offset << w->i_denom | (w->i_denom ? 1 << (w->i_denom - 1) : 0); | |
| for( i = 0; i < 8; i++ ) | |
| { | |
| w->cachea[i] = w->i_scale; | |
| @@ -350,7 +545,7 @@ | |
| } | |
| } | |
| -static void x264_weight_cache_ssse3( x264_t *h, x264_weight_t *w ) | |
| +static void weight_cache_ssse3( x264_t *h, x264_weight_t *w ) | |
| { | |
| int i, den1; | |
| if( w->i_scale == 1<<w->i_denom ) | |
| @@ -385,7 +580,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */\ | |
| {\ | |
| pixel *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3);\ | |
| - x264_pixel_avg_wtab_##instr1[i_width>>2](\ | |
| + pixel_avg_wtab_##instr1[i_width>>2](\ | |
| dst, i_dst_stride, src1, i_src_stride,\ | |
| src2, i_height );\ | |
| if( weight->weightfn )\ | |
| @@ -394,7 +589,7 @@ | |
| else if( weight->weightfn )\ | |
| weight->weightfn[i_width>>2]( dst, i_dst_stride, src1, i_src_stride, weight, i_height );\ | |
| else\ | |
| - x264_mc_copy_wtab_##instr2[i_width>>2](dst, i_dst_stride, src1, i_src_stride, i_height );\ | |
| + mc_copy_wtab_##instr2[i_width>>2](dst, i_dst_stride, src1, i_src_stride, i_height );\ | |
| } | |
| MC_LUMA(mmx2,mmx2,mmx) | |
| @@ -423,7 +618,7 @@ | |
| if( qpel_idx & 5 ) /* qpel interpolation needed */\ | |
| {\ | |
| pixel *src2 = src[x264_hpel_ref1[qpel_idx]] + offset + ((mvx&3) == 3);\ | |
| - x264_pixel_avg_wtab_##name[i_width>>2](\ | |
| + pixel_avg_wtab_##name[i_width>>2](\ | |
| dst, *i_dst_stride, src1, i_src_stride,\ | |
| src2, i_height );\ | |
| if( weight->weightfn )\ | |
| @@ -455,6 +650,25 @@ | |
| GET_REF(cache64_ssse3_atom) | |
| #endif // !HIGH_BIT_DEPTH | |
| +#define x264_hpel_filter_avx x264_template(hpel_filter_avx) | |
| +#define x264_hpel_filter_avx2 x264_template(hpel_filter_avx2) | |
| +#define x264_hpel_filter_c_mmx2 x264_template(hpel_filter_c_mmx2) | |
| +#define x264_hpel_filter_c_sse2 x264_template(hpel_filter_c_sse2) | |
| +#define x264_hpel_filter_c_ssse3 x264_template(hpel_filter_c_ssse3) | |
| +#define x264_hpel_filter_c_avx x264_template(hpel_filter_c_avx) | |
| +#define x264_hpel_filter_c_avx2 x264_template(hpel_filter_c_avx2) | |
| +#define x264_hpel_filter_h_mmx2 x264_template(hpel_filter_h_mmx2) | |
| +#define x264_hpel_filter_h_sse2 x264_template(hpel_filter_h_sse2) | |
| +#define x264_hpel_filter_h_ssse3 x264_template(hpel_filter_h_ssse3) | |
| +#define x264_hpel_filter_h_avx x264_template(hpel_filter_h_avx) | |
| +#define x264_hpel_filter_h_avx2 x264_template(hpel_filter_h_avx2) | |
| +#define x264_hpel_filter_sse2 x264_template(hpel_filter_sse2) | |
| +#define x264_hpel_filter_ssse3 x264_template(hpel_filter_ssse3) | |
| +#define x264_hpel_filter_v_mmx2 x264_template(hpel_filter_v_mmx2) | |
| +#define x264_hpel_filter_v_sse2 x264_template(hpel_filter_v_sse2) | |
| +#define x264_hpel_filter_v_ssse3 x264_template(hpel_filter_v_ssse3) | |
| +#define x264_hpel_filter_v_avx x264_template(hpel_filter_v_avx) | |
| +#define x264_hpel_filter_v_avx2 x264_template(hpel_filter_v_avx2) | |
| #define HPEL(align, cpu, cpuv, cpuc, cpuh)\ | |
| void x264_hpel_filter_v_##cpuv( pixel *dst, pixel *src, int16_t *buf, intptr_t stride, intptr_t width);\ | |
| void x264_hpel_filter_c_##cpuc( pixel *dst, int16_t *buf, intptr_t width );\ | |
| @@ -525,43 +739,51 @@ | |
| #define MC_CLIP_ADD(s,x)\ | |
| do\ | |
| {\ | |
| - int temp;\ | |
| + int temp_s = s;\ | |
| + int temp_x = x;\ | |
| asm("movd %0, %%xmm0 \n"\ | |
| - "movd %2, %%xmm1 \n"\ | |
| + "movd %1, %%xmm1 \n"\ | |
| "paddsw %%xmm1, %%xmm0 \n"\ | |
| - "movd %%xmm0, %1 \n"\ | |
| - :"+m"(s), "=&r"(temp)\ | |
| - :"m"(x)\ | |
| + "movd %%xmm0, %0 \n"\ | |
| + :"+&r"(temp_s)\ | |
| + :"r"(temp_x)\ | |
| );\ | |
| - s = temp;\ | |
| + s = temp_s;\ | |
| } while( 0 ) | |
| #undef MC_CLIP_ADD2 | |
| #define MC_CLIP_ADD2(s,x)\ | |
| do\ | |
| {\ | |
| + x264_union32_t temp = { .w={ (s)[0], (s)[1] } };\ | |
| asm("movd %0, %%xmm0 \n"\ | |
| "movd %1, %%xmm1 \n"\ | |
| "paddsw %%xmm1, %%xmm0 \n"\ | |
| "movd %%xmm0, %0 \n"\ | |
| - :"+m"(M32(s))\ | |
| + :"+&r"(temp)\ | |
| :"m"(M32(x))\ | |
| );\ | |
| + (s)[0] = temp.w[0];\ | |
| + (s)[1] = temp.w[1];\ | |
| } while( 0 ) | |
| #endif | |
| +#define x264_mbtree_propagate_list_internal_ssse3 x264_template(mbtree_propagate_list_internal_ssse3) | |
| PROPAGATE_LIST(ssse3) | |
| +#define x264_mbtree_propagate_list_internal_avx x264_template(mbtree_propagate_list_internal_avx) | |
| PROPAGATE_LIST(avx) | |
| +#define x264_mbtree_propagate_list_internal_avx2 x264_template(mbtree_propagate_list_internal_avx2) | |
| PROPAGATE_LIST(avx2) | |
| #if ARCH_X86_64 | |
| +#define x264_mbtree_propagate_list_internal_avx512 x264_template(mbtree_propagate_list_internal_avx512) | |
| void x264_mbtree_propagate_list_internal_avx512( size_t len, uint16_t *ref_costs, int16_t (*mvs)[2], int16_t *propagate_amount, | |
| uint16_t *lowres_costs, int bipred_weight, int mb_y, | |
| int width, int height, int stride, int list_mask ); | |
| -static void x264_mbtree_propagate_list_avx512( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2], | |
| - int16_t *propagate_amount, uint16_t *lowres_costs, | |
| - int bipred_weight, int mb_y, int len, int list ) | |
| +static void mbtree_propagate_list_avx512( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2], | |
| + int16_t *propagate_amount, uint16_t *lowres_costs, | |
| + int bipred_weight, int mb_y, int len, int list ) | |
| { | |
| x264_mbtree_propagate_list_internal_avx512( len, ref_costs, mvs, propagate_amount, lowres_costs, bipred_weight << 9, | |
| mb_y << 16, h->mb.i_mb_width, h->mb.i_mb_height, h->mb.i_mb_stride, | |
| @@ -569,7 +791,7 @@ | |
| } | |
| #endif | |
| -void x264_mc_init_mmx( int cpu, x264_mc_functions_t *pf ) | |
| +void x264_mc_init_mmx( uint32_t cpu, x264_mc_functions_t *pf ) | |
| { | |
| if( !(cpu&X264_CPU_MMX) ) | |
| return; | |
| @@ -584,11 +806,12 @@ | |
| if( !(cpu&X264_CPU_MMX2) ) | |
| return; | |
| + pf->prefetch_fenc_400 = x264_prefetch_fenc_400_mmx2; | |
| pf->prefetch_fenc_420 = x264_prefetch_fenc_420_mmx2; | |
| pf->prefetch_fenc_422 = x264_prefetch_fenc_422_mmx2; | |
| pf->prefetch_ref = x264_prefetch_ref_mmx2; | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_mmx2; | |
| + pf->plane_copy_interleave = plane_copy_interleave_mmx2; | |
| pf->store_interleave_chroma = x264_store_interleave_chroma_mmx2; | |
| pf->avg[PIXEL_16x16] = x264_pixel_avg_16x16_mmx2; | |
| @@ -605,10 +828,10 @@ | |
| pf->get_ref = get_ref_mmx2; | |
| pf->mc_chroma = x264_mc_chroma_mmx2; | |
| pf->hpel_filter = x264_hpel_filter_mmx2; | |
| - pf->weight = x264_mc_weight_wtab_mmx2; | |
| - pf->weight_cache = x264_weight_cache_mmx2; | |
| - pf->offsetadd = x264_mc_offsetadd_wtab_mmx2; | |
| - pf->offsetsub = x264_mc_offsetsub_wtab_mmx2; | |
| + pf->weight = mc_weight_wtab_mmx2; | |
| + pf->weight_cache = weight_cache_mmx2; | |
| + pf->offsetadd = mc_offsetadd_wtab_mmx2; | |
| + pf->offsetsub = mc_offsetsub_wtab_mmx2; | |
| pf->frame_init_lowres_core = x264_frame_init_lowres_core_mmx2; | |
| @@ -616,7 +839,7 @@ | |
| { | |
| pf->memcpy_aligned = x264_memcpy_aligned_sse; | |
| pf->memzero_aligned = x264_memzero_aligned_sse; | |
| - pf->plane_copy = x264_plane_copy_sse; | |
| + pf->plane_copy = plane_copy_sse; | |
| } | |
| #if HIGH_BIT_DEPTH | |
| @@ -633,9 +856,9 @@ | |
| pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_sse2; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_sse2; | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_sse2; | |
| + pf->plane_copy_interleave = plane_copy_interleave_sse2; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_sse2; | |
| - pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_yuyv_sse2; | |
| + pf->plane_copy_deinterleave_yuyv = plane_copy_deinterleave_yuyv_sse2; | |
| if( cpu&X264_CPU_SSE2_IS_FAST ) | |
| { | |
| @@ -648,8 +871,8 @@ | |
| pf->integral_init8v = x264_integral_init8v_sse2; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_sse2; | |
| pf->store_interleave_chroma = x264_store_interleave_chroma_sse2; | |
| - pf->offsetadd = x264_mc_offsetadd_wtab_sse2; | |
| - pf->offsetsub = x264_mc_offsetsub_wtab_sse2; | |
| + pf->offsetadd = mc_offsetadd_wtab_sse2; | |
| + pf->offsetsub = mc_offsetsub_wtab_sse2; | |
| if( cpu&X264_CPU_SSE2_IS_SLOW ) | |
| return; | |
| @@ -665,7 +888,7 @@ | |
| pf->avg[PIXEL_4x2] = x264_pixel_avg_4x2_sse2; | |
| pf->copy[PIXEL_16x16] = x264_mc_copy_w16_aligned_sse; | |
| - pf->weight = x264_mc_weight_wtab_sse2; | |
| + pf->weight = mc_weight_wtab_sse2; | |
| if( !(cpu&X264_CPU_STACK_MOD4) ) | |
| pf->mc_chroma = x264_mc_chroma_sse2; | |
| @@ -674,9 +897,9 @@ | |
| return; | |
| pf->frame_init_lowres_core = x264_frame_init_lowres_core_ssse3; | |
| - pf->plane_copy_swap = x264_plane_copy_swap_ssse3; | |
| + pf->plane_copy_swap = plane_copy_swap_ssse3; | |
| pf->plane_copy_deinterleave_v210 = x264_plane_copy_deinterleave_v210_ssse3; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_ssse3; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_ssse3; | |
| pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_ssse3; | |
| pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_ssse3; | |
| @@ -689,9 +912,9 @@ | |
| pf->frame_init_lowres_core = x264_frame_init_lowres_core_avx; | |
| pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_avx; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_avx; | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_avx; | |
| + pf->plane_copy_interleave = plane_copy_interleave_avx; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_avx; | |
| - pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_yuyv_avx; | |
| + pf->plane_copy_deinterleave_yuyv = plane_copy_deinterleave_yuyv_avx; | |
| pf->plane_copy_deinterleave_v210 = x264_plane_copy_deinterleave_v210_avx; | |
| pf->store_interleave_chroma = x264_store_interleave_chroma_avx; | |
| pf->copy[PIXEL_16x16] = x264_mc_copy_w16_aligned_avx; | |
| @@ -706,6 +929,7 @@ | |
| { | |
| pf->mc_luma = mc_luma_avx2; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_avx2; | |
| + pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_avx2; | |
| pf->plane_copy_deinterleave_v210 = x264_plane_copy_deinterleave_v210_avx2; | |
| } | |
| @@ -738,18 +962,18 @@ | |
| pf->hpel_filter = x264_hpel_filter_sse2_amd; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_sse2; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_sse2; | |
| - pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_yuyv_sse2; | |
| + pf->plane_copy_deinterleave_yuyv = plane_copy_deinterleave_yuyv_sse2; | |
| pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_sse2; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_sse2; | |
| pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_sse2; | |
| if( !(cpu&X264_CPU_SSE2_IS_SLOW) ) | |
| { | |
| - pf->weight = x264_mc_weight_wtab_sse2; | |
| + pf->weight = mc_weight_wtab_sse2; | |
| if( !(cpu&X264_CPU_SLOW_ATOM) ) | |
| { | |
| - pf->offsetadd = x264_mc_offsetadd_wtab_sse2; | |
| - pf->offsetsub = x264_mc_offsetsub_wtab_sse2; | |
| + pf->offsetadd = mc_offsetadd_wtab_sse2; | |
| + pf->offsetsub = mc_offsetsub_wtab_sse2; | |
| } | |
| pf->copy[PIXEL_16x16] = x264_mc_copy_w16_aligned_sse; | |
| @@ -766,7 +990,7 @@ | |
| if( cpu&X264_CPU_SSE2_IS_FAST ) | |
| { | |
| pf->store_interleave_chroma = x264_store_interleave_chroma_sse2; // FIXME sse2fast? sse2medium? | |
| - pf->plane_copy_interleave = x264_plane_copy_interleave_sse2; | |
| + pf->plane_copy_interleave = plane_copy_interleave_sse2; | |
| pf->mc_luma = mc_luma_sse2; | |
| pf->get_ref = get_ref_sse2; | |
| if( cpu&X264_CPU_CACHELINE_64 ) | |
| @@ -789,9 +1013,9 @@ | |
| pf->avg[PIXEL_4x8] = x264_pixel_avg_4x8_ssse3; | |
| pf->avg[PIXEL_4x4] = x264_pixel_avg_4x4_ssse3; | |
| pf->avg[PIXEL_4x2] = x264_pixel_avg_4x2_ssse3; | |
| - pf->plane_copy_swap = x264_plane_copy_swap_ssse3; | |
| + pf->plane_copy_swap = plane_copy_swap_ssse3; | |
| pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_ssse3; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_ssse3; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_ssse3; | |
| pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_ssse3; | |
| pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_ssse3; | |
| @@ -800,7 +1024,7 @@ | |
| pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_ssse3; | |
| pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_ssse3; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_ssse3; | |
| - pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_yuyv_ssse3; | |
| + pf->plane_copy_deinterleave_yuyv = plane_copy_deinterleave_yuyv_ssse3; | |
| } | |
| if( !(cpu&X264_CPU_SLOW_PALIGNR) ) | |
| @@ -827,8 +1051,8 @@ | |
| } | |
| } | |
| - pf->weight_cache = x264_weight_cache_ssse3; | |
| - pf->weight = x264_mc_weight_wtab_ssse3; | |
| + pf->weight_cache = weight_cache_ssse3; | |
| + pf->weight = mc_weight_wtab_ssse3; | |
| if( !(cpu&(X264_CPU_SLOW_SHUFFLE|X264_CPU_SLOW_ATOM|X264_CPU_SLOW_PALIGNR)) ) | |
| pf->integral_init4v = x264_integral_init4v_ssse3; | |
| @@ -856,7 +1080,7 @@ | |
| { | |
| pf->hpel_filter = x264_hpel_filter_avx2; | |
| pf->mc_chroma = x264_mc_chroma_avx2; | |
| - pf->weight = x264_mc_weight_wtab_avx2; | |
| + pf->weight = mc_weight_wtab_avx2; | |
| pf->avg[PIXEL_16x16] = x264_pixel_avg_16x16_avx2; | |
| pf->avg[PIXEL_16x8] = x264_pixel_avg_16x8_avx2; | |
| pf->integral_init8v = x264_integral_init8v_avx2; | |
| @@ -865,6 +1089,7 @@ | |
| pf->integral_init4h = x264_integral_init4h_avx2; | |
| pf->frame_init_lowres_core = x264_frame_init_lowres_core_avx2; | |
| pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_avx2; | |
| + pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_avx2; | |
| } | |
| if( cpu&X264_CPU_AVX512 ) | |
| @@ -874,6 +1099,8 @@ | |
| pf->avg[PIXEL_8x16] = x264_pixel_avg_8x16_avx512; | |
| pf->avg[PIXEL_8x8] = x264_pixel_avg_8x8_avx512; | |
| pf->avg[PIXEL_8x4] = x264_pixel_avg_8x4_avx512; | |
| + pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_avx512; | |
| + pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_avx512; | |
| } | |
| #endif // HIGH_BIT_DEPTH | |
| @@ -881,22 +1108,21 @@ | |
| return; | |
| pf->memcpy_aligned = x264_memcpy_aligned_avx; | |
| pf->memzero_aligned = x264_memzero_aligned_avx; | |
| - pf->plane_copy = x264_plane_copy_avx; | |
| + pf->plane_copy = plane_copy_avx; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_avx; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_avx; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_avx; | |
| if( cpu&X264_CPU_FMA4 ) | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_fma4; | |
| if( !(cpu&X264_CPU_AVX2) ) | |
| return; | |
| - pf->plane_copy_swap = x264_plane_copy_swap_avx2; | |
| + pf->plane_copy_swap = plane_copy_swap_avx2; | |
| pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_avx2; | |
| - pf->plane_copy_deinterleave_yuyv = x264_plane_copy_deinterleave_yuyv_avx2; | |
| - pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_avx2; | |
| + pf->plane_copy_deinterleave_yuyv = plane_copy_deinterleave_yuyv_avx2; | |
| pf->get_ref = get_ref_avx2; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_avx2; | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_avx2; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_avx2; | |
| pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_avx2; | |
| pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_avx2; | |
| @@ -904,8 +1130,12 @@ | |
| return; | |
| pf->memcpy_aligned = x264_memcpy_aligned_avx512; | |
| pf->memzero_aligned = x264_memzero_aligned_avx512; | |
| + pf->plane_copy = x264_plane_copy_avx512; | |
| + pf->plane_copy_swap = x264_plane_copy_swap_avx512; | |
| pf->mbtree_propagate_cost = x264_mbtree_propagate_cost_avx512; | |
| #if ARCH_X86_64 | |
| - pf->mbtree_propagate_list = x264_mbtree_propagate_list_avx512; | |
| + pf->mbtree_propagate_list = mbtree_propagate_list_avx512; | |
| #endif | |
| + pf->mbtree_fix8_pack = x264_mbtree_fix8_pack_avx512; | |
| + pf->mbtree_fix8_unpack = x264_mbtree_fix8_unpack_avx512; | |
| } | |
| diff -ur x264-go/x264c/external/x264/common/x86/mc.h x264-go.new/x264c/external/x264/common/x86/mc.h | |
| --- x264-go/x264c/external/x264/common/x86/mc.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/mc.h 2020-06-06 15:20:58.693039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * mc.h: x86 motion compensation | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -24,9 +24,10 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_I386_MC_H | |
| -#define X264_I386_MC_H | |
| +#ifndef X264_X86_MC_H | |
| +#define X264_X86_MC_H | |
| -void x264_mc_init_mmx( int cpu, x264_mc_functions_t *pf ); | |
| +#define x264_mc_init_mmx x264_template(mc_init_mmx) | |
| +void x264_mc_init_mmx( uint32_t cpu, x264_mc_functions_t *pf ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/x86: pixel-32.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: pixel-a.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/pixel.h x264-go.new/x264c/external/x264/common/x86/pixel.h | |
| --- x264-go/x264c/external/x264/common/x86/pixel.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/pixel.h 2020-06-06 15:20:58.694039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * pixel.h: x86 pixel metrics | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -25,9 +25,345 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_I386_PIXEL_H | |
| -#define X264_I386_PIXEL_H | |
| +#ifndef X264_X86_PIXEL_H | |
| +#define X264_X86_PIXEL_H | |
| +#define x264_pixel_ads1_avx x264_template(pixel_ads1_avx) | |
| +#define x264_pixel_ads1_avx2 x264_template(pixel_ads1_avx2) | |
| +#define x264_pixel_ads1_mmx2 x264_template(pixel_ads1_mmx2) | |
| +#define x264_pixel_ads1_sse2 x264_template(pixel_ads1_sse2) | |
| +#define x264_pixel_ads1_ssse3 x264_template(pixel_ads1_ssse3) | |
| +#define x264_pixel_ads2_avx x264_template(pixel_ads2_avx) | |
| +#define x264_pixel_ads2_avx2 x264_template(pixel_ads2_avx2) | |
| +#define x264_pixel_ads2_mmx2 x264_template(pixel_ads2_mmx2) | |
| +#define x264_pixel_ads2_sse2 x264_template(pixel_ads2_sse2) | |
| +#define x264_pixel_ads2_ssse3 x264_template(pixel_ads2_ssse3) | |
| +#define x264_pixel_ads4_avx x264_template(pixel_ads4_avx) | |
| +#define x264_pixel_ads4_avx2 x264_template(pixel_ads4_avx2) | |
| +#define x264_pixel_ads4_mmx2 x264_template(pixel_ads4_mmx2) | |
| +#define x264_pixel_ads4_sse2 x264_template(pixel_ads4_sse2) | |
| +#define x264_pixel_ads4_ssse3 x264_template(pixel_ads4_ssse3) | |
| +#define x264_pixel_hadamard_ac_16x16_avx x264_template(pixel_hadamard_ac_16x16_avx) | |
| +#define x264_pixel_hadamard_ac_16x16_avx2 x264_template(pixel_hadamard_ac_16x16_avx2) | |
| +#define x264_pixel_hadamard_ac_16x16_mmx2 x264_template(pixel_hadamard_ac_16x16_mmx2) | |
| +#define x264_pixel_hadamard_ac_16x16_sse2 x264_template(pixel_hadamard_ac_16x16_sse2) | |
| +#define x264_pixel_hadamard_ac_16x16_sse4 x264_template(pixel_hadamard_ac_16x16_sse4) | |
| +#define x264_pixel_hadamard_ac_16x16_ssse3 x264_template(pixel_hadamard_ac_16x16_ssse3) | |
| +#define x264_pixel_hadamard_ac_16x16_ssse3_atom x264_template(pixel_hadamard_ac_16x16_ssse3_atom) | |
| +#define x264_pixel_hadamard_ac_16x16_xop x264_template(pixel_hadamard_ac_16x16_xop) | |
| +#define x264_pixel_hadamard_ac_16x8_avx x264_template(pixel_hadamard_ac_16x8_avx) | |
| +#define x264_pixel_hadamard_ac_16x8_avx2 x264_template(pixel_hadamard_ac_16x8_avx2) | |
| +#define x264_pixel_hadamard_ac_16x8_mmx2 x264_template(pixel_hadamard_ac_16x8_mmx2) | |
| +#define x264_pixel_hadamard_ac_16x8_sse2 x264_template(pixel_hadamard_ac_16x8_sse2) | |
| +#define x264_pixel_hadamard_ac_16x8_sse4 x264_template(pixel_hadamard_ac_16x8_sse4) | |
| +#define x264_pixel_hadamard_ac_16x8_ssse3 x264_template(pixel_hadamard_ac_16x8_ssse3) | |
| +#define x264_pixel_hadamard_ac_16x8_ssse3_atom x264_template(pixel_hadamard_ac_16x8_ssse3_atom) | |
| +#define x264_pixel_hadamard_ac_16x8_xop x264_template(pixel_hadamard_ac_16x8_xop) | |
| +#define x264_pixel_hadamard_ac_8x16_avx x264_template(pixel_hadamard_ac_8x16_avx) | |
| +#define x264_pixel_hadamard_ac_8x16_mmx2 x264_template(pixel_hadamard_ac_8x16_mmx2) | |
| +#define x264_pixel_hadamard_ac_8x16_sse2 x264_template(pixel_hadamard_ac_8x16_sse2) | |
| +#define x264_pixel_hadamard_ac_8x16_sse4 x264_template(pixel_hadamard_ac_8x16_sse4) | |
| +#define x264_pixel_hadamard_ac_8x16_ssse3 x264_template(pixel_hadamard_ac_8x16_ssse3) | |
| +#define x264_pixel_hadamard_ac_8x16_ssse3_atom x264_template(pixel_hadamard_ac_8x16_ssse3_atom) | |
| +#define x264_pixel_hadamard_ac_8x16_xop x264_template(pixel_hadamard_ac_8x16_xop) | |
| +#define x264_pixel_hadamard_ac_8x8_avx x264_template(pixel_hadamard_ac_8x8_avx) | |
| +#define x264_pixel_hadamard_ac_8x8_mmx2 x264_template(pixel_hadamard_ac_8x8_mmx2) | |
| +#define x264_pixel_hadamard_ac_8x8_sse2 x264_template(pixel_hadamard_ac_8x8_sse2) | |
| +#define x264_pixel_hadamard_ac_8x8_sse4 x264_template(pixel_hadamard_ac_8x8_sse4) | |
| +#define x264_pixel_hadamard_ac_8x8_ssse3 x264_template(pixel_hadamard_ac_8x8_ssse3) | |
| +#define x264_pixel_hadamard_ac_8x8_ssse3_atom x264_template(pixel_hadamard_ac_8x8_ssse3_atom) | |
| +#define x264_pixel_hadamard_ac_8x8_xop x264_template(pixel_hadamard_ac_8x8_xop) | |
| +#define x264_pixel_sa8d_16x16_mmx2 x264_template(pixel_sa8d_16x16_mmx2) | |
| +#define x264_pixel_sa8d_16x16_avx x264_template(pixel_sa8d_16x16_avx) | |
| +#define x264_pixel_sa8d_16x16_sse2 x264_template(pixel_sa8d_16x16_sse2) | |
| +#define x264_pixel_sa8d_16x16_sse4 x264_template(pixel_sa8d_16x16_sse4) | |
| +#define x264_pixel_sa8d_16x16_ssse3 x264_template(pixel_sa8d_16x16_ssse3) | |
| +#define x264_pixel_sa8d_16x16_ssse3_atom x264_template(pixel_sa8d_16x16_ssse3_atom) | |
| +#define x264_pixel_sa8d_16x16_xop x264_template(pixel_sa8d_16x16_xop) | |
| +#define x264_pixel_sa8d_8x8_mmx2 x264_template(pixel_sa8d_8x8_mmx2) | |
| +#define x264_pixel_sa8d_8x8_avx x264_template(pixel_sa8d_8x8_avx) | |
| +#define x264_pixel_sa8d_8x8_avx2 x264_template(pixel_sa8d_8x8_avx2) | |
| +#define x264_pixel_sa8d_8x8_avx512 x264_template(pixel_sa8d_8x8_avx512) | |
| +#define x264_pixel_sa8d_8x8_sse2 x264_template(pixel_sa8d_8x8_sse2) | |
| +#define x264_pixel_sa8d_8x8_sse4 x264_template(pixel_sa8d_8x8_sse4) | |
| +#define x264_pixel_sa8d_8x8_ssse3 x264_template(pixel_sa8d_8x8_ssse3) | |
| +#define x264_pixel_sa8d_8x8_ssse3_atom x264_template(pixel_sa8d_8x8_ssse3_atom) | |
| +#define x264_pixel_sa8d_8x8_xop x264_template(pixel_sa8d_8x8_xop) | |
| +#define x264_pixel_sad_16x16_avx2 x264_template(pixel_sad_16x16_avx2) | |
| +#define x264_pixel_sad_16x16_avx512 x264_template(pixel_sad_16x16_avx512) | |
| +#define x264_pixel_sad_16x16_cache32_mmx2 x264_template(pixel_sad_16x16_cache32_mmx2) | |
| +#define x264_pixel_sad_16x16_cache64_mmx2 x264_template(pixel_sad_16x16_cache64_mmx2) | |
| +#define x264_pixel_sad_16x16_cache64_sse2 x264_template(pixel_sad_16x16_cache64_sse2) | |
| +#define x264_pixel_sad_16x16_cache64_ssse3 x264_template(pixel_sad_16x16_cache64_ssse3) | |
| +#define x264_pixel_sad_16x16_mmx2 x264_template(pixel_sad_16x16_mmx2) | |
| +#define x264_pixel_sad_16x16_sse2 x264_template(pixel_sad_16x16_sse2) | |
| +#define x264_pixel_sad_16x16_sse2_aligned x264_template(pixel_sad_16x16_sse2_aligned) | |
| +#define x264_pixel_sad_16x16_sse3 x264_template(pixel_sad_16x16_sse3) | |
| +#define x264_pixel_sad_16x16_ssse3 x264_template(pixel_sad_16x16_ssse3) | |
| +#define x264_pixel_sad_16x16_ssse3_aligned x264_template(pixel_sad_16x16_ssse3_aligned) | |
| +#define x264_pixel_sad_16x8_avx2 x264_template(pixel_sad_16x8_avx2) | |
| +#define x264_pixel_sad_16x8_avx512 x264_template(pixel_sad_16x8_avx512) | |
| +#define x264_pixel_sad_16x8_cache32_mmx2 x264_template(pixel_sad_16x8_cache32_mmx2) | |
| +#define x264_pixel_sad_16x8_cache64_mmx2 x264_template(pixel_sad_16x8_cache64_mmx2) | |
| +#define x264_pixel_sad_16x8_cache64_sse2 x264_template(pixel_sad_16x8_cache64_sse2) | |
| +#define x264_pixel_sad_16x8_cache64_ssse3 x264_template(pixel_sad_16x8_cache64_ssse3) | |
| +#define x264_pixel_sad_16x8_mmx2 x264_template(pixel_sad_16x8_mmx2) | |
| +#define x264_pixel_sad_16x8_sse2 x264_template(pixel_sad_16x8_sse2) | |
| +#define x264_pixel_sad_16x8_sse2_aligned x264_template(pixel_sad_16x8_sse2_aligned) | |
| +#define x264_pixel_sad_16x8_sse3 x264_template(pixel_sad_16x8_sse3) | |
| +#define x264_pixel_sad_16x8_ssse3 x264_template(pixel_sad_16x8_ssse3) | |
| +#define x264_pixel_sad_16x8_ssse3_aligned x264_template(pixel_sad_16x8_ssse3_aligned) | |
| +#define x264_pixel_sad_4x16_avx512 x264_template(pixel_sad_4x16_avx512) | |
| +#define x264_pixel_sad_4x16_mmx2 x264_template(pixel_sad_4x16_mmx2) | |
| +#define x264_pixel_sad_4x4_avx512 x264_template(pixel_sad_4x4_avx512) | |
| +#define x264_pixel_sad_4x4_mmx2 x264_template(pixel_sad_4x4_mmx2) | |
| +#define x264_pixel_sad_4x4_ssse3 x264_template(pixel_sad_4x4_ssse3) | |
| +#define x264_pixel_sad_4x8_avx512 x264_template(pixel_sad_4x8_avx512) | |
| +#define x264_pixel_sad_4x8_mmx2 x264_template(pixel_sad_4x8_mmx2) | |
| +#define x264_pixel_sad_4x8_ssse3 x264_template(pixel_sad_4x8_ssse3) | |
| +#define x264_pixel_sad_8x16_avx512 x264_template(pixel_sad_8x16_avx512) | |
| +#define x264_pixel_sad_8x16_cache32_mmx2 x264_template(pixel_sad_8x16_cache32_mmx2) | |
| +#define x264_pixel_sad_8x16_cache64_mmx2 x264_template(pixel_sad_8x16_cache64_mmx2) | |
| +#define x264_pixel_sad_8x16_mmx2 x264_template(pixel_sad_8x16_mmx2) | |
| +#define x264_pixel_sad_8x16_sse2 x264_template(pixel_sad_8x16_sse2) | |
| +#define x264_pixel_sad_8x16_sse2_aligned x264_template(pixel_sad_8x16_sse2_aligned) | |
| +#define x264_pixel_sad_8x16_ssse3 x264_template(pixel_sad_8x16_ssse3) | |
| +#define x264_pixel_sad_8x16_ssse3_aligned x264_template(pixel_sad_8x16_ssse3_aligned) | |
| +#define x264_pixel_sad_8x4_avx512 x264_template(pixel_sad_8x4_avx512) | |
| +#define x264_pixel_sad_8x4_cache32_mmx2 x264_template(pixel_sad_8x4_cache32_mmx2) | |
| +#define x264_pixel_sad_8x4_cache64_mmx2 x264_template(pixel_sad_8x4_cache64_mmx2) | |
| +#define x264_pixel_sad_8x4_mmx2 x264_template(pixel_sad_8x4_mmx2) | |
| +#define x264_pixel_sad_8x4_sse2 x264_template(pixel_sad_8x4_sse2) | |
| +#define x264_pixel_sad_8x4_ssse3 x264_template(pixel_sad_8x4_ssse3) | |
| +#define x264_pixel_sad_8x8_avx512 x264_template(pixel_sad_8x8_avx512) | |
| +#define x264_pixel_sad_8x8_cache32_mmx2 x264_template(pixel_sad_8x8_cache32_mmx2) | |
| +#define x264_pixel_sad_8x8_cache64_mmx2 x264_template(pixel_sad_8x8_cache64_mmx2) | |
| +#define x264_pixel_sad_8x8_mmx2 x264_template(pixel_sad_8x8_mmx2) | |
| +#define x264_pixel_sad_8x8_sse2 x264_template(pixel_sad_8x8_sse2) | |
| +#define x264_pixel_sad_8x8_sse2_aligned x264_template(pixel_sad_8x8_sse2_aligned) | |
| +#define x264_pixel_sad_8x8_ssse3 x264_template(pixel_sad_8x8_ssse3) | |
| +#define x264_pixel_sad_8x8_ssse3_aligned x264_template(pixel_sad_8x8_ssse3_aligned) | |
| +#define x264_pixel_sad_x3_16x16_avx x264_template(pixel_sad_x3_16x16_avx) | |
| +#define x264_pixel_sad_x3_16x16_avx2 x264_template(pixel_sad_x3_16x16_avx2) | |
| +#define x264_pixel_sad_x3_16x16_avx512 x264_template(pixel_sad_x3_16x16_avx512) | |
| +#define x264_pixel_sad_x3_16x16_cache32_mmx2 x264_template(pixel_sad_x3_16x16_cache32_mmx2) | |
| +#define x264_pixel_sad_x3_16x16_cache64_mmx2 x264_template(pixel_sad_x3_16x16_cache64_mmx2) | |
| +#define x264_pixel_sad_x3_16x16_cache64_sse2 x264_template(pixel_sad_x3_16x16_cache64_sse2) | |
| +#define x264_pixel_sad_x3_16x16_cache64_ssse3 x264_template(pixel_sad_x3_16x16_cache64_ssse3) | |
| +#define x264_pixel_sad_x3_16x16_mmx2 x264_template(pixel_sad_x3_16x16_mmx2) | |
| +#define x264_pixel_sad_x3_16x16_sse2 x264_template(pixel_sad_x3_16x16_sse2) | |
| +#define x264_pixel_sad_x3_16x16_sse3 x264_template(pixel_sad_x3_16x16_sse3) | |
| +#define x264_pixel_sad_x3_16x16_ssse3 x264_template(pixel_sad_x3_16x16_ssse3) | |
| +#define x264_pixel_sad_x3_16x16_xop x264_template(pixel_sad_x3_16x16_xop) | |
| +#define x264_pixel_sad_x3_16x8_avx x264_template(pixel_sad_x3_16x8_avx) | |
| +#define x264_pixel_sad_x3_16x8_avx2 x264_template(pixel_sad_x3_16x8_avx2) | |
| +#define x264_pixel_sad_x3_16x8_avx512 x264_template(pixel_sad_x3_16x8_avx512) | |
| +#define x264_pixel_sad_x3_16x8_cache32_mmx2 x264_template(pixel_sad_x3_16x8_cache32_mmx2) | |
| +#define x264_pixel_sad_x3_16x8_cache64_mmx2 x264_template(pixel_sad_x3_16x8_cache64_mmx2) | |
| +#define x264_pixel_sad_x3_16x8_cache64_sse2 x264_template(pixel_sad_x3_16x8_cache64_sse2) | |
| +#define x264_pixel_sad_x3_16x8_cache64_ssse3 x264_template(pixel_sad_x3_16x8_cache64_ssse3) | |
| +#define x264_pixel_sad_x3_16x8_mmx2 x264_template(pixel_sad_x3_16x8_mmx2) | |
| +#define x264_pixel_sad_x3_16x8_sse2 x264_template(pixel_sad_x3_16x8_sse2) | |
| +#define x264_pixel_sad_x3_16x8_sse3 x264_template(pixel_sad_x3_16x8_sse3) | |
| +#define x264_pixel_sad_x3_16x8_ssse3 x264_template(pixel_sad_x3_16x8_ssse3) | |
| +#define x264_pixel_sad_x3_16x8_xop x264_template(pixel_sad_x3_16x8_xop) | |
| +#define x264_pixel_sad_x3_4x4_avx512 x264_template(pixel_sad_x3_4x4_avx512) | |
| +#define x264_pixel_sad_x3_4x4_mmx2 x264_template(pixel_sad_x3_4x4_mmx2) | |
| +#define x264_pixel_sad_x3_4x4_ssse3 x264_template(pixel_sad_x3_4x4_ssse3) | |
| +#define x264_pixel_sad_x3_4x8_avx512 x264_template(pixel_sad_x3_4x8_avx512) | |
| +#define x264_pixel_sad_x3_4x8_mmx2 x264_template(pixel_sad_x3_4x8_mmx2) | |
| +#define x264_pixel_sad_x3_4x8_ssse3 x264_template(pixel_sad_x3_4x8_ssse3) | |
| +#define x264_pixel_sad_x3_8x16_avx512 x264_template(pixel_sad_x3_8x16_avx512) | |
| +#define x264_pixel_sad_x3_8x16_cache32_mmx2 x264_template(pixel_sad_x3_8x16_cache32_mmx2) | |
| +#define x264_pixel_sad_x3_8x16_cache64_mmx2 x264_template(pixel_sad_x3_8x16_cache64_mmx2) | |
| +#define x264_pixel_sad_x3_8x16_cache64_sse2 x264_template(pixel_sad_x3_8x16_cache64_sse2) | |
| +#define x264_pixel_sad_x3_8x16_mmx2 x264_template(pixel_sad_x3_8x16_mmx2) | |
| +#define x264_pixel_sad_x3_8x16_sse2 x264_template(pixel_sad_x3_8x16_sse2) | |
| +#define x264_pixel_sad_x3_8x16_ssse3 x264_template(pixel_sad_x3_8x16_ssse3) | |
| +#define x264_pixel_sad_x3_8x16_xop x264_template(pixel_sad_x3_8x16_xop) | |
| +#define x264_pixel_sad_x3_8x4_avx512 x264_template(pixel_sad_x3_8x4_avx512) | |
| +#define x264_pixel_sad_x3_8x4_mmx2 x264_template(pixel_sad_x3_8x4_mmx2) | |
| +#define x264_pixel_sad_x3_8x4_sse2 x264_template(pixel_sad_x3_8x4_sse2) | |
| +#define x264_pixel_sad_x3_8x4_ssse3 x264_template(pixel_sad_x3_8x4_ssse3) | |
| +#define x264_pixel_sad_x3_8x4_xop x264_template(pixel_sad_x3_8x4_xop) | |
| +#define x264_pixel_sad_x3_8x8_avx512 x264_template(pixel_sad_x3_8x8_avx512) | |
| +#define x264_pixel_sad_x3_8x8_cache32_mmx2 x264_template(pixel_sad_x3_8x8_cache32_mmx2) | |
| +#define x264_pixel_sad_x3_8x8_cache64_mmx2 x264_template(pixel_sad_x3_8x8_cache64_mmx2) | |
| +#define x264_pixel_sad_x3_8x8_mmx2 x264_template(pixel_sad_x3_8x8_mmx2) | |
| +#define x264_pixel_sad_x3_8x8_sse2 x264_template(pixel_sad_x3_8x8_sse2) | |
| +#define x264_pixel_sad_x3_8x8_ssse3 x264_template(pixel_sad_x3_8x8_ssse3) | |
| +#define x264_pixel_sad_x3_8x8_xop x264_template(pixel_sad_x3_8x8_xop) | |
| +#define x264_pixel_sad_x4_16x16_avx x264_template(pixel_sad_x4_16x16_avx) | |
| +#define x264_pixel_sad_x4_16x16_avx2 x264_template(pixel_sad_x4_16x16_avx2) | |
| +#define x264_pixel_sad_x4_16x16_avx512 x264_template(pixel_sad_x4_16x16_avx512) | |
| +#define x264_pixel_sad_x4_16x16_cache32_mmx2 x264_template(pixel_sad_x4_16x16_cache32_mmx2) | |
| +#define x264_pixel_sad_x4_16x16_cache64_mmx2 x264_template(pixel_sad_x4_16x16_cache64_mmx2) | |
| +#define x264_pixel_sad_x4_16x16_cache64_sse2 x264_template(pixel_sad_x4_16x16_cache64_sse2) | |
| +#define x264_pixel_sad_x4_16x16_cache64_ssse3 x264_template(pixel_sad_x4_16x16_cache64_ssse3) | |
| +#define x264_pixel_sad_x4_16x16_mmx2 x264_template(pixel_sad_x4_16x16_mmx2) | |
| +#define x264_pixel_sad_x4_16x16_sse2 x264_template(pixel_sad_x4_16x16_sse2) | |
| +#define x264_pixel_sad_x4_16x16_sse3 x264_template(pixel_sad_x4_16x16_sse3) | |
| +#define x264_pixel_sad_x4_16x16_ssse3 x264_template(pixel_sad_x4_16x16_ssse3) | |
| +#define x264_pixel_sad_x4_16x16_xop x264_template(pixel_sad_x4_16x16_xop) | |
| +#define x264_pixel_sad_x4_16x8_avx x264_template(pixel_sad_x4_16x8_avx) | |
| +#define x264_pixel_sad_x4_16x8_avx2 x264_template(pixel_sad_x4_16x8_avx2) | |
| +#define x264_pixel_sad_x4_16x8_avx512 x264_template(pixel_sad_x4_16x8_avx512) | |
| +#define x264_pixel_sad_x4_16x8_cache32_mmx2 x264_template(pixel_sad_x4_16x8_cache32_mmx2) | |
| +#define x264_pixel_sad_x4_16x8_cache64_mmx2 x264_template(pixel_sad_x4_16x8_cache64_mmx2) | |
| +#define x264_pixel_sad_x4_16x8_cache64_sse2 x264_template(pixel_sad_x4_16x8_cache64_sse2) | |
| +#define x264_pixel_sad_x4_16x8_cache64_ssse3 x264_template(pixel_sad_x4_16x8_cache64_ssse3) | |
| +#define x264_pixel_sad_x4_16x8_mmx2 x264_template(pixel_sad_x4_16x8_mmx2) | |
| +#define x264_pixel_sad_x4_16x8_sse2 x264_template(pixel_sad_x4_16x8_sse2) | |
| +#define x264_pixel_sad_x4_16x8_sse3 x264_template(pixel_sad_x4_16x8_sse3) | |
| +#define x264_pixel_sad_x4_16x8_ssse3 x264_template(pixel_sad_x4_16x8_ssse3) | |
| +#define x264_pixel_sad_x4_16x8_xop x264_template(pixel_sad_x4_16x8_xop) | |
| +#define x264_pixel_sad_x4_4x4_avx512 x264_template(pixel_sad_x4_4x4_avx512) | |
| +#define x264_pixel_sad_x4_4x4_mmx2 x264_template(pixel_sad_x4_4x4_mmx2) | |
| +#define x264_pixel_sad_x4_4x4_ssse3 x264_template(pixel_sad_x4_4x4_ssse3) | |
| +#define x264_pixel_sad_x4_4x8_avx512 x264_template(pixel_sad_x4_4x8_avx512) | |
| +#define x264_pixel_sad_x4_4x8_mmx2 x264_template(pixel_sad_x4_4x8_mmx2) | |
| +#define x264_pixel_sad_x4_4x8_ssse3 x264_template(pixel_sad_x4_4x8_ssse3) | |
| +#define x264_pixel_sad_x4_8x16_avx512 x264_template(pixel_sad_x4_8x16_avx512) | |
| +#define x264_pixel_sad_x4_8x16_cache32_mmx2 x264_template(pixel_sad_x4_8x16_cache32_mmx2) | |
| +#define x264_pixel_sad_x4_8x16_cache64_mmx2 x264_template(pixel_sad_x4_8x16_cache64_mmx2) | |
| +#define x264_pixel_sad_x4_8x16_cache64_sse2 x264_template(pixel_sad_x4_8x16_cache64_sse2) | |
| +#define x264_pixel_sad_x4_8x16_mmx2 x264_template(pixel_sad_x4_8x16_mmx2) | |
| +#define x264_pixel_sad_x4_8x16_sse2 x264_template(pixel_sad_x4_8x16_sse2) | |
| +#define x264_pixel_sad_x4_8x16_ssse3 x264_template(pixel_sad_x4_8x16_ssse3) | |
| +#define x264_pixel_sad_x4_8x16_xop x264_template(pixel_sad_x4_8x16_xop) | |
| +#define x264_pixel_sad_x4_8x4_avx512 x264_template(pixel_sad_x4_8x4_avx512) | |
| +#define x264_pixel_sad_x4_8x4_mmx2 x264_template(pixel_sad_x4_8x4_mmx2) | |
| +#define x264_pixel_sad_x4_8x4_sse2 x264_template(pixel_sad_x4_8x4_sse2) | |
| +#define x264_pixel_sad_x4_8x4_ssse3 x264_template(pixel_sad_x4_8x4_ssse3) | |
| +#define x264_pixel_sad_x4_8x4_xop x264_template(pixel_sad_x4_8x4_xop) | |
| +#define x264_pixel_sad_x4_8x8_avx512 x264_template(pixel_sad_x4_8x8_avx512) | |
| +#define x264_pixel_sad_x4_8x8_cache32_mmx2 x264_template(pixel_sad_x4_8x8_cache32_mmx2) | |
| +#define x264_pixel_sad_x4_8x8_cache64_mmx2 x264_template(pixel_sad_x4_8x8_cache64_mmx2) | |
| +#define x264_pixel_sad_x4_8x8_mmx2 x264_template(pixel_sad_x4_8x8_mmx2) | |
| +#define x264_pixel_sad_x4_8x8_sse2 x264_template(pixel_sad_x4_8x8_sse2) | |
| +#define x264_pixel_sad_x4_8x8_ssse3 x264_template(pixel_sad_x4_8x8_ssse3) | |
| +#define x264_pixel_sad_x4_8x8_xop x264_template(pixel_sad_x4_8x8_xop) | |
| +#define x264_pixel_satd_16x16_avx x264_template(pixel_satd_16x16_avx) | |
| +#define x264_pixel_satd_16x16_avx2 x264_template(pixel_satd_16x16_avx2) | |
| +#define x264_pixel_satd_16x16_avx512 x264_template(pixel_satd_16x16_avx512) | |
| +#define x264_pixel_satd_16x16_mmx2 x264_template(pixel_satd_16x16_mmx2) | |
| +#define x264_pixel_satd_16x16_sse2 x264_template(pixel_satd_16x16_sse2) | |
| +#define x264_pixel_satd_16x16_sse4 x264_template(pixel_satd_16x16_sse4) | |
| +#define x264_pixel_satd_16x16_ssse3 x264_template(pixel_satd_16x16_ssse3) | |
| +#define x264_pixel_satd_16x16_ssse3_atom x264_template(pixel_satd_16x16_ssse3_atom) | |
| +#define x264_pixel_satd_16x16_xop x264_template(pixel_satd_16x16_xop) | |
| +#define x264_pixel_satd_16x8_avx x264_template(pixel_satd_16x8_avx) | |
| +#define x264_pixel_satd_16x8_avx2 x264_template(pixel_satd_16x8_avx2) | |
| +#define x264_pixel_satd_16x8_avx512 x264_template(pixel_satd_16x8_avx512) | |
| +#define x264_pixel_satd_16x8_mmx2 x264_template(pixel_satd_16x8_mmx2) | |
| +#define x264_pixel_satd_16x8_sse2 x264_template(pixel_satd_16x8_sse2) | |
| +#define x264_pixel_satd_16x8_sse4 x264_template(pixel_satd_16x8_sse4) | |
| +#define x264_pixel_satd_16x8_ssse3 x264_template(pixel_satd_16x8_ssse3) | |
| +#define x264_pixel_satd_16x8_ssse3_atom x264_template(pixel_satd_16x8_ssse3_atom) | |
| +#define x264_pixel_satd_16x8_xop x264_template(pixel_satd_16x8_xop) | |
| +#define x264_pixel_satd_4x16_avx x264_template(pixel_satd_4x16_avx) | |
| +#define x264_pixel_satd_4x16_avx512 x264_template(pixel_satd_4x16_avx512) | |
| +#define x264_pixel_satd_4x16_mmx2 x264_template(pixel_satd_4x16_mmx2) | |
| +#define x264_pixel_satd_4x16_sse2 x264_template(pixel_satd_4x16_sse2) | |
| +#define x264_pixel_satd_4x16_sse4 x264_template(pixel_satd_4x16_sse4) | |
| +#define x264_pixel_satd_4x16_ssse3 x264_template(pixel_satd_4x16_ssse3) | |
| +#define x264_pixel_satd_4x16_ssse3_atom x264_template(pixel_satd_4x16_ssse3_atom) | |
| +#define x264_pixel_satd_4x4_avx x264_template(pixel_satd_4x4_avx) | |
| +#define x264_pixel_satd_4x4_avx512 x264_template(pixel_satd_4x4_avx512) | |
| +#define x264_pixel_satd_4x4_mmx2 x264_template(pixel_satd_4x4_mmx2) | |
| +#define x264_pixel_satd_4x4_sse4 x264_template(pixel_satd_4x4_sse4) | |
| +#define x264_pixel_satd_4x4_ssse3 x264_template(pixel_satd_4x4_ssse3) | |
| +#define x264_pixel_satd_4x4_xop x264_template(pixel_satd_4x4_xop) | |
| +#define x264_pixel_satd_4x8_avx x264_template(pixel_satd_4x8_avx) | |
| +#define x264_pixel_satd_4x8_avx512 x264_template(pixel_satd_4x8_avx512) | |
| +#define x264_pixel_satd_4x8_mmx2 x264_template(pixel_satd_4x8_mmx2) | |
| +#define x264_pixel_satd_4x8_sse2 x264_template(pixel_satd_4x8_sse2) | |
| +#define x264_pixel_satd_4x8_sse4 x264_template(pixel_satd_4x8_sse4) | |
| +#define x264_pixel_satd_4x8_ssse3 x264_template(pixel_satd_4x8_ssse3) | |
| +#define x264_pixel_satd_4x8_ssse3_atom x264_template(pixel_satd_4x8_ssse3_atom) | |
| +#define x264_pixel_satd_4x8_xop x264_template(pixel_satd_4x8_xop) | |
| +#define x264_pixel_satd_8x16_avx x264_template(pixel_satd_8x16_avx) | |
| +#define x264_pixel_satd_8x16_avx2 x264_template(pixel_satd_8x16_avx2) | |
| +#define x264_pixel_satd_8x16_avx512 x264_template(pixel_satd_8x16_avx512) | |
| +#define x264_pixel_satd_8x16_mmx2 x264_template(pixel_satd_8x16_mmx2) | |
| +#define x264_pixel_satd_8x16_sse2 x264_template(pixel_satd_8x16_sse2) | |
| +#define x264_pixel_satd_8x16_sse4 x264_template(pixel_satd_8x16_sse4) | |
| +#define x264_pixel_satd_8x16_ssse3 x264_template(pixel_satd_8x16_ssse3) | |
| +#define x264_pixel_satd_8x16_ssse3_atom x264_template(pixel_satd_8x16_ssse3_atom) | |
| +#define x264_pixel_satd_8x16_xop x264_template(pixel_satd_8x16_xop) | |
| +#define x264_pixel_satd_8x4_avx x264_template(pixel_satd_8x4_avx) | |
| +#define x264_pixel_satd_8x4_avx512 x264_template(pixel_satd_8x4_avx512) | |
| +#define x264_pixel_satd_8x4_mmx2 x264_template(pixel_satd_8x4_mmx2) | |
| +#define x264_pixel_satd_8x4_sse2 x264_template(pixel_satd_8x4_sse2) | |
| +#define x264_pixel_satd_8x4_sse4 x264_template(pixel_satd_8x4_sse4) | |
| +#define x264_pixel_satd_8x4_ssse3 x264_template(pixel_satd_8x4_ssse3) | |
| +#define x264_pixel_satd_8x4_ssse3_atom x264_template(pixel_satd_8x4_ssse3_atom) | |
| +#define x264_pixel_satd_8x4_xop x264_template(pixel_satd_8x4_xop) | |
| +#define x264_pixel_satd_8x8_avx x264_template(pixel_satd_8x8_avx) | |
| +#define x264_pixel_satd_8x8_avx2 x264_template(pixel_satd_8x8_avx2) | |
| +#define x264_pixel_satd_8x8_avx512 x264_template(pixel_satd_8x8_avx512) | |
| +#define x264_pixel_satd_8x8_mmx2 x264_template(pixel_satd_8x8_mmx2) | |
| +#define x264_pixel_satd_8x8_sse2 x264_template(pixel_satd_8x8_sse2) | |
| +#define x264_pixel_satd_8x8_sse4 x264_template(pixel_satd_8x8_sse4) | |
| +#define x264_pixel_satd_8x8_ssse3 x264_template(pixel_satd_8x8_ssse3) | |
| +#define x264_pixel_satd_8x8_ssse3_atom x264_template(pixel_satd_8x8_ssse3_atom) | |
| +#define x264_pixel_satd_8x8_xop x264_template(pixel_satd_8x8_xop) | |
| +#define x264_pixel_ssd_16x16_avx x264_template(pixel_ssd_16x16_avx) | |
| +#define x264_pixel_ssd_16x16_avx2 x264_template(pixel_ssd_16x16_avx2) | |
| +#define x264_pixel_ssd_16x16_mmx x264_template(pixel_ssd_16x16_mmx) | |
| +#define x264_pixel_ssd_16x16_mmx2 x264_template(pixel_ssd_16x16_mmx2) | |
| +#define x264_pixel_ssd_16x16_sse2 x264_template(pixel_ssd_16x16_sse2) | |
| +#define x264_pixel_ssd_16x16_sse2slow x264_template(pixel_ssd_16x16_sse2slow) | |
| +#define x264_pixel_ssd_16x16_ssse3 x264_template(pixel_ssd_16x16_ssse3) | |
| +#define x264_pixel_ssd_16x16_xop x264_template(pixel_ssd_16x16_xop) | |
| +#define x264_pixel_ssd_16x8_avx x264_template(pixel_ssd_16x8_avx) | |
| +#define x264_pixel_ssd_16x8_avx2 x264_template(pixel_ssd_16x8_avx2) | |
| +#define x264_pixel_ssd_16x8_mmx x264_template(pixel_ssd_16x8_mmx) | |
| +#define x264_pixel_ssd_16x8_mmx2 x264_template(pixel_ssd_16x8_mmx2) | |
| +#define x264_pixel_ssd_16x8_sse2 x264_template(pixel_ssd_16x8_sse2) | |
| +#define x264_pixel_ssd_16x8_sse2slow x264_template(pixel_ssd_16x8_sse2slow) | |
| +#define x264_pixel_ssd_16x8_ssse3 x264_template(pixel_ssd_16x8_ssse3) | |
| +#define x264_pixel_ssd_16x8_xop x264_template(pixel_ssd_16x8_xop) | |
| +#define x264_pixel_ssd_4x16_mmx x264_template(pixel_ssd_4x16_mmx) | |
| +#define x264_pixel_ssd_4x16_mmx2 x264_template(pixel_ssd_4x16_mmx2) | |
| +#define x264_pixel_ssd_4x16_ssse3 x264_template(pixel_ssd_4x16_ssse3) | |
| +#define x264_pixel_ssd_4x4_mmx x264_template(pixel_ssd_4x4_mmx) | |
| +#define x264_pixel_ssd_4x4_mmx2 x264_template(pixel_ssd_4x4_mmx2) | |
| +#define x264_pixel_ssd_4x4_ssse3 x264_template(pixel_ssd_4x4_ssse3) | |
| +#define x264_pixel_ssd_4x8_mmx x264_template(pixel_ssd_4x8_mmx) | |
| +#define x264_pixel_ssd_4x8_mmx2 x264_template(pixel_ssd_4x8_mmx2) | |
| +#define x264_pixel_ssd_4x8_ssse3 x264_template(pixel_ssd_4x8_ssse3) | |
| +#define x264_pixel_ssd_8x16_avx x264_template(pixel_ssd_8x16_avx) | |
| +#define x264_pixel_ssd_8x16_mmx x264_template(pixel_ssd_8x16_mmx) | |
| +#define x264_pixel_ssd_8x16_mmx2 x264_template(pixel_ssd_8x16_mmx2) | |
| +#define x264_pixel_ssd_8x16_sse2 x264_template(pixel_ssd_8x16_sse2) | |
| +#define x264_pixel_ssd_8x16_sse2slow x264_template(pixel_ssd_8x16_sse2slow) | |
| +#define x264_pixel_ssd_8x16_ssse3 x264_template(pixel_ssd_8x16_ssse3) | |
| +#define x264_pixel_ssd_8x16_xop x264_template(pixel_ssd_8x16_xop) | |
| +#define x264_pixel_ssd_8x4_avx x264_template(pixel_ssd_8x4_avx) | |
| +#define x264_pixel_ssd_8x4_mmx x264_template(pixel_ssd_8x4_mmx) | |
| +#define x264_pixel_ssd_8x4_mmx2 x264_template(pixel_ssd_8x4_mmx2) | |
| +#define x264_pixel_ssd_8x4_sse2 x264_template(pixel_ssd_8x4_sse2) | |
| +#define x264_pixel_ssd_8x4_sse2slow x264_template(pixel_ssd_8x4_sse2slow) | |
| +#define x264_pixel_ssd_8x4_ssse3 x264_template(pixel_ssd_8x4_ssse3) | |
| +#define x264_pixel_ssd_8x4_xop x264_template(pixel_ssd_8x4_xop) | |
| +#define x264_pixel_ssd_8x8_avx x264_template(pixel_ssd_8x8_avx) | |
| +#define x264_pixel_ssd_8x8_mmx x264_template(pixel_ssd_8x8_mmx) | |
| +#define x264_pixel_ssd_8x8_mmx2 x264_template(pixel_ssd_8x8_mmx2) | |
| +#define x264_pixel_ssd_8x8_sse2 x264_template(pixel_ssd_8x8_sse2) | |
| +#define x264_pixel_ssd_8x8_sse2slow x264_template(pixel_ssd_8x8_sse2slow) | |
| +#define x264_pixel_ssd_8x8_ssse3 x264_template(pixel_ssd_8x8_ssse3) | |
| +#define x264_pixel_ssd_8x8_xop x264_template(pixel_ssd_8x8_xop) | |
| +#define x264_pixel_var_16x16_avx x264_template(pixel_var_16x16_avx) | |
| +#define x264_pixel_var_16x16_avx2 x264_template(pixel_var_16x16_avx2) | |
| +#define x264_pixel_var_16x16_avx512 x264_template(pixel_var_16x16_avx512) | |
| +#define x264_pixel_var_16x16_sse2 x264_template(pixel_var_16x16_sse2) | |
| +#define x264_pixel_var_8x16_avx x264_template(pixel_var_8x16_avx) | |
| +#define x264_pixel_var_8x16_avx512 x264_template(pixel_var_8x16_avx512) | |
| +#define x264_pixel_var_8x16_sse2 x264_template(pixel_var_8x16_sse2) | |
| +#define x264_pixel_var_8x8_avx x264_template(pixel_var_8x8_avx) | |
| +#define x264_pixel_var_8x8_avx512 x264_template(pixel_var_8x8_avx512) | |
| +#define x264_pixel_var_8x8_sse2 x264_template(pixel_var_8x8_sse2) | |
| #define DECL_PIXELS( ret, name, suffix, args ) \ | |
| ret x264_pixel_##name##_16x16_##suffix args;\ | |
| ret x264_pixel_##name##_16x8_##suffix args;\ | |
| @@ -110,86 +446,153 @@ | |
| DECL_PIXELS( uint64_t, hadamard_ac, avx2, ( pixel *pix, intptr_t i_stride )) | |
| +#define x264_intra_satd_x3_4x4_mmx2 x264_template(intra_satd_x3_4x4_mmx2) | |
| void x264_intra_satd_x3_4x4_mmx2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_4x4_mmx2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_4x4_sse2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_4x4_ssse3 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_4x4_avx ( pixel *, pixel *, int * ); | |
| +#define x264_intra_sad_x3_4x4_mmx2 x264_template(intra_sad_x3_4x4_mmx2) | |
| +void x264_intra_sad_x3_4x4_mmx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_4x4_sse2 x264_template(intra_sad_x3_4x4_sse2) | |
| +void x264_intra_sad_x3_4x4_sse2 ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_sad_x3_4x4_ssse3 x264_template(intra_sad_x3_4x4_ssse3) | |
| +void x264_intra_sad_x3_4x4_ssse3 ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_sad_x3_4x4_avx x264_template(intra_sad_x3_4x4_avx) | |
| +void x264_intra_sad_x3_4x4_avx ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_satd_x3_8x8c_mmx2 x264_template(intra_satd_x3_8x8c_mmx2) | |
| void x264_intra_satd_x3_8x8c_mmx2 ( pixel *, pixel *, int * ); | |
| +#define x264_intra_satd_x3_8x8c_ssse3 x264_template(intra_satd_x3_8x8c_ssse3) | |
| void x264_intra_satd_x3_8x8c_ssse3 ( uint8_t *, uint8_t *, int * ); | |
| -void x264_intra_sad_x3_8x8c_mmx2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8c_sse2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8c_ssse3 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8c_avx2 ( pixel *, pixel *, int * ); | |
| +#define x264_intra_sad_x3_8x8c_mmx2 x264_template(intra_sad_x3_8x8c_mmx2) | |
| +void x264_intra_sad_x3_8x8c_mmx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_8x8c_ssse3 x264_template(intra_sad_x3_8x8c_ssse3) | |
| +void x264_intra_sad_x3_8x8c_ssse3 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_8x8c_avx2 x264_template(intra_sad_x3_8x8c_avx2) | |
| +void x264_intra_sad_x3_8x8c_avx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_satd_x3_16x16_mmx2 x264_template(intra_satd_x3_16x16_mmx2) | |
| void x264_intra_satd_x3_16x16_mmx2 ( pixel *, pixel *, int * ); | |
| +#define x264_intra_satd_x3_16x16_ssse3 x264_template(intra_satd_x3_16x16_ssse3) | |
| void x264_intra_satd_x3_16x16_ssse3( uint8_t *, uint8_t *, int * ); | |
| -void x264_intra_sad_x3_16x16_mmx2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_16x16_sse2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_16x16_ssse3 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_16x16_avx2 ( pixel *, pixel *, int * ); | |
| +#define x264_intra_sad_x3_16x16_mmx2 x264_template(intra_sad_x3_16x16_mmx2) | |
| +void x264_intra_sad_x3_16x16_mmx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_16x16_sse2 x264_template(intra_sad_x3_16x16_sse2) | |
| +void x264_intra_sad_x3_16x16_sse2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_16x16_ssse3 x264_template(intra_sad_x3_16x16_ssse3) | |
| +void x264_intra_sad_x3_16x16_ssse3 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_16x16_avx2 x264_template(intra_sad_x3_16x16_avx2) | |
| +void x264_intra_sad_x3_16x16_avx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sa8d_x3_8x8_mmx2 x264_template(intra_sa8d_x3_8x8_mmx2) | |
| void x264_intra_sa8d_x3_8x8_mmx2 ( uint8_t *, uint8_t *, int * ); | |
| -void x264_intra_sa8d_x3_8x8_sse2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8_mmx2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8_sse2 ( pixel *, pixel *, int * ); | |
| -void x264_intra_sad_x3_8x8_ssse3 ( pixel *, pixel *, int * ); | |
| +#define x264_intra_sa8d_x3_8x8_sse2 x264_template(intra_sa8d_x3_8x8_sse2) | |
| +void x264_intra_sa8d_x3_8x8_sse2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_8x8_mmx2 x264_template(intra_sad_x3_8x8_mmx2) | |
| +void x264_intra_sad_x3_8x8_mmx2 ( uint8_t *, uint8_t *, int * ); | |
| +#define x264_intra_sad_x3_8x8_sse2 x264_template(intra_sad_x3_8x8_sse2) | |
| +void x264_intra_sad_x3_8x8_sse2 ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_sad_x3_8x8_ssse3 x264_template(intra_sad_x3_8x8_ssse3) | |
| +void x264_intra_sad_x3_8x8_ssse3 ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_sad_x3_8x8_avx2 x264_template(intra_sad_x3_8x8_avx2) | |
| void x264_intra_sad_x3_8x8_avx2 ( uint16_t*, uint16_t*, int * ); | |
| +#define x264_intra_satd_x9_4x4_ssse3 x264_template(intra_satd_x9_4x4_ssse3) | |
| int x264_intra_satd_x9_4x4_ssse3( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_satd_x9_4x4_sse4 x264_template(intra_satd_x9_4x4_sse4) | |
| int x264_intra_satd_x9_4x4_sse4 ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_satd_x9_4x4_avx x264_template(intra_satd_x9_4x4_avx) | |
| int x264_intra_satd_x9_4x4_avx ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_satd_x9_4x4_xop x264_template(intra_satd_x9_4x4_xop) | |
| int x264_intra_satd_x9_4x4_xop ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_4x4_ssse3 x264_template(intra_sad_x9_4x4_ssse3) | |
| int x264_intra_sad_x9_4x4_ssse3 ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_4x4_sse4 x264_template(intra_sad_x9_4x4_sse4) | |
| int x264_intra_sad_x9_4x4_sse4 ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_4x4_avx x264_template(intra_sad_x9_4x4_avx) | |
| int x264_intra_sad_x9_4x4_avx ( uint8_t *, uint8_t *, uint16_t * ); | |
| +#define x264_intra_sa8d_x9_8x8_ssse3 x264_template(intra_sa8d_x9_8x8_ssse3) | |
| int x264_intra_sa8d_x9_8x8_ssse3( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sa8d_x9_8x8_sse4 x264_template(intra_sa8d_x9_8x8_sse4) | |
| int x264_intra_sa8d_x9_8x8_sse4 ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sa8d_x9_8x8_avx x264_template(intra_sa8d_x9_8x8_avx) | |
| int x264_intra_sa8d_x9_8x8_avx ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_8x8_ssse3 x264_template(intra_sad_x9_8x8_ssse3) | |
| int x264_intra_sad_x9_8x8_ssse3 ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_8x8_sse4 x264_template(intra_sad_x9_8x8_sse4) | |
| int x264_intra_sad_x9_8x8_sse4 ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_8x8_avx x264_template(intra_sad_x9_8x8_avx) | |
| int x264_intra_sad_x9_8x8_avx ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_intra_sad_x9_8x8_avx2 x264_template(intra_sad_x9_8x8_avx2) | |
| int x264_intra_sad_x9_8x8_avx2 ( uint8_t *, uint8_t *, uint8_t *, uint16_t *, uint16_t * ); | |
| +#define x264_pixel_ssd_nv12_core_sse2 x264_template(pixel_ssd_nv12_core_sse2) | |
| void x264_pixel_ssd_nv12_core_sse2( pixel *pixuv1, intptr_t stride1, | |
| pixel *pixuv2, intptr_t stride2, int width, | |
| int height, uint64_t *ssd_u, uint64_t *ssd_v ); | |
| +#define x264_pixel_ssd_nv12_core_avx x264_template(pixel_ssd_nv12_core_avx) | |
| void x264_pixel_ssd_nv12_core_avx ( pixel *pixuv1, intptr_t stride1, | |
| pixel *pixuv2, intptr_t stride2, int width, | |
| int height, uint64_t *ssd_u, uint64_t *ssd_v ); | |
| +#define x264_pixel_ssd_nv12_core_xop x264_template(pixel_ssd_nv12_core_xop) | |
| void x264_pixel_ssd_nv12_core_xop ( pixel *pixuv1, intptr_t stride1, | |
| pixel *pixuv2, intptr_t stride2, int width, | |
| int height, uint64_t *ssd_u, uint64_t *ssd_v ); | |
| +#define x264_pixel_ssd_nv12_core_avx2 x264_template(pixel_ssd_nv12_core_avx2) | |
| void x264_pixel_ssd_nv12_core_avx2( pixel *pixuv1, intptr_t stride1, | |
| pixel *pixuv2, intptr_t stride2, int width, | |
| int height, uint64_t *ssd_u, uint64_t *ssd_v ); | |
| +#define x264_pixel_ssim_4x4x2_core_mmx2 x264_template(pixel_ssim_4x4x2_core_mmx2) | |
| void x264_pixel_ssim_4x4x2_core_mmx2( const uint8_t *pix1, intptr_t stride1, | |
| const uint8_t *pix2, intptr_t stride2, int sums[2][4] ); | |
| +#define x264_pixel_ssim_4x4x2_core_sse2 x264_template(pixel_ssim_4x4x2_core_sse2) | |
| void x264_pixel_ssim_4x4x2_core_sse2( const pixel *pix1, intptr_t stride1, | |
| const pixel *pix2, intptr_t stride2, int sums[2][4] ); | |
| +#define x264_pixel_ssim_4x4x2_core_avx x264_template(pixel_ssim_4x4x2_core_avx) | |
| void x264_pixel_ssim_4x4x2_core_avx ( const pixel *pix1, intptr_t stride1, | |
| const pixel *pix2, intptr_t stride2, int sums[2][4] ); | |
| +#define x264_pixel_ssim_end4_sse2 x264_template(pixel_ssim_end4_sse2) | |
| float x264_pixel_ssim_end4_sse2( int sum0[5][4], int sum1[5][4], int width ); | |
| +#define x264_pixel_ssim_end4_avx x264_template(pixel_ssim_end4_avx) | |
| float x264_pixel_ssim_end4_avx ( int sum0[5][4], int sum1[5][4], int width ); | |
| +#define x264_pixel_var2_8x8_sse2 x264_template(pixel_var2_8x8_sse2) | |
| int x264_pixel_var2_8x8_sse2 ( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x8_ssse3 x264_template(pixel_var2_8x8_ssse3) | |
| int x264_pixel_var2_8x8_ssse3 ( uint8_t *fenc, uint8_t *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x8_avx2 x264_template(pixel_var2_8x8_avx2) | |
| int x264_pixel_var2_8x8_avx2 ( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x8_avx512 x264_template(pixel_var2_8x8_avx512) | |
| int x264_pixel_var2_8x8_avx512 ( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x16_sse2 x264_template(pixel_var2_8x16_sse2) | |
| int x264_pixel_var2_8x16_sse2 ( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x16_ssse3 x264_template(pixel_var2_8x16_ssse3) | |
| int x264_pixel_var2_8x16_ssse3 ( uint8_t *fenc, uint8_t *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x16_avx2 x264_template(pixel_var2_8x16_avx2) | |
| int x264_pixel_var2_8x16_avx2 ( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_var2_8x16_avx512 x264_template(pixel_var2_8x16_avx512) | |
| int x264_pixel_var2_8x16_avx512( pixel *fenc, pixel *fdec, int ssd[2] ); | |
| +#define x264_pixel_vsad_mmx2 x264_template(pixel_vsad_mmx2) | |
| int x264_pixel_vsad_mmx2 ( pixel *src, intptr_t stride, int height ); | |
| +#define x264_pixel_vsad_sse2 x264_template(pixel_vsad_sse2) | |
| int x264_pixel_vsad_sse2 ( pixel *src, intptr_t stride, int height ); | |
| +#define x264_pixel_vsad_ssse3 x264_template(pixel_vsad_ssse3) | |
| int x264_pixel_vsad_ssse3( pixel *src, intptr_t stride, int height ); | |
| +#define x264_pixel_vsad_xop x264_template(pixel_vsad_xop) | |
| int x264_pixel_vsad_xop ( pixel *src, intptr_t stride, int height ); | |
| +#define x264_pixel_vsad_avx2 x264_template(pixel_vsad_avx2) | |
| int x264_pixel_vsad_avx2 ( uint16_t *src, intptr_t stride, int height ); | |
| +#define x264_pixel_asd8_sse2 x264_template(pixel_asd8_sse2) | |
| int x264_pixel_asd8_sse2 ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int height ); | |
| +#define x264_pixel_asd8_ssse3 x264_template(pixel_asd8_ssse3) | |
| int x264_pixel_asd8_ssse3( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int height ); | |
| +#define x264_pixel_asd8_xop x264_template(pixel_asd8_xop) | |
| int x264_pixel_asd8_xop ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int height ); | |
| +#define x264_pixel_sa8d_satd_16x16_sse2 x264_template(pixel_sa8d_satd_16x16_sse2) | |
| uint64_t x264_pixel_sa8d_satd_16x16_sse2 ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_ssse3 x264_template(pixel_sa8d_satd_16x16_ssse3) | |
| uint64_t x264_pixel_sa8d_satd_16x16_ssse3 ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_ssse3_atom x264_template(pixel_sa8d_satd_16x16_ssse3_atom) | |
| uint64_t x264_pixel_sa8d_satd_16x16_ssse3_atom( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_sse4 x264_template(pixel_sa8d_satd_16x16_sse4) | |
| uint64_t x264_pixel_sa8d_satd_16x16_sse4 ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_avx x264_template(pixel_sa8d_satd_16x16_avx) | |
| uint64_t x264_pixel_sa8d_satd_16x16_avx ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_xop x264_template(pixel_sa8d_satd_16x16_xop) | |
| uint64_t x264_pixel_sa8d_satd_16x16_xop ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| +#define x264_pixel_sa8d_satd_16x16_avx2 x264_template(pixel_sa8d_satd_16x16_avx2) | |
| uint64_t x264_pixel_sa8d_satd_16x16_avx2 ( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); | |
| Only in x264-go.new/x264c/external/x264/common/x86: predict-a.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/predict-c.c x264-go.new/x264c/external/x264/common/x86/predict-c.c | |
| --- x264-go/x264c/external/x264/common/x86/predict-c.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/predict-c.c 2020-06-06 15:20:58.694039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict-c.c: intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -70,7 +70,7 @@ | |
| x264_predict_16x16_p_core_##name( src, i00, b, c ); | |
| #define PREDICT_16x16_P(name, name2)\ | |
| -static void x264_predict_16x16_p_##name( pixel *src )\ | |
| +static void predict_16x16_p_##name( pixel *src )\ | |
| {\ | |
| PREDICT_16x16_P_CORE\ | |
| PREDICT_16x16_P_END(name2)\ | |
| @@ -128,7 +128,7 @@ | |
| + 1 * ( src[ 8*FDEC_STRIDE-1] - src[ 6*FDEC_STRIDE-1] ); | |
| #define PREDICT_16x16_P_INLINE(name, name2)\ | |
| -static void x264_predict_16x16_p_##name( pixel *src )\ | |
| +static void predict_16x16_p_##name( pixel *src )\ | |
| {\ | |
| PREDICT_16x16_P_CORE_INLINE\ | |
| PREDICT_16x16_P_END(name2)\ | |
| @@ -174,7 +174,7 @@ | |
| #endif // HIGH_BIT_DEPTH | |
| #define PREDICT_8x16C_P(name)\ | |
| -static void x264_predict_8x16c_p_##name( pixel *src )\ | |
| +static void predict_8x16c_p_##name( pixel *src )\ | |
| {\ | |
| PREDICT_8x16C_P_CORE\ | |
| PREDICT_8x16C_P_END(name)\ | |
| @@ -211,7 +211,7 @@ | |
| #endif // HIGH_BIT_DEPTH | |
| #define PREDICT_8x8C_P(name, name2)\ | |
| -static void x264_predict_8x8c_p_##name( pixel *src )\ | |
| +static void predict_8x8c_p_##name( pixel *src )\ | |
| {\ | |
| PREDICT_8x8C_P_CORE\ | |
| PREDICT_8x8C_P_END(name2)\ | |
| @@ -257,7 +257,7 @@ | |
| H += -4 * src[-1*FDEC_STRIDE -1]; | |
| #define PREDICT_8x8C_P_INLINE(name, name2)\ | |
| -static void x264_predict_8x8c_p_##name( pixel *src )\ | |
| +static void predict_8x8c_p_##name( pixel *src )\ | |
| {\ | |
| PREDICT_8x8C_P_CORE_INLINE\ | |
| PREDICT_8x8C_P_END(name2)\ | |
| @@ -281,7 +281,7 @@ | |
| PREDICT_8x8C_P_INLINE( avx2, avx2 ) | |
| #if ARCH_X86_64 && !HIGH_BIT_DEPTH | |
| -static void x264_predict_8x8c_dc_left( uint8_t *src ) | |
| +static void predict_8x8c_dc_left( uint8_t *src ) | |
| { | |
| int y; | |
| uint32_t s0 = 0, s1 = 0; | |
| @@ -311,7 +311,7 @@ | |
| /**************************************************************************** | |
| * Exported functions: | |
| ****************************************************************************/ | |
| -void x264_predict_16x16_init_mmx( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_16x16_init_mmx( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_MMX2) ) | |
| return; | |
| @@ -327,7 +327,7 @@ | |
| pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_sse2; | |
| pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_sse2; | |
| pf[I_PRED_16x16_H] = x264_predict_16x16_h_sse2; | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_sse2; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_sse2; | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| pf[I_PRED_16x16_V] = x264_predict_16x16_v_avx; | |
| @@ -336,7 +336,7 @@ | |
| pf[I_PRED_16x16_H] = x264_predict_16x16_h_avx2; | |
| #else | |
| #if !ARCH_X86_64 | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_mmx2; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_mmx2; | |
| #endif | |
| if( !(cpu&X264_CPU_SSE) ) | |
| return; | |
| @@ -348,29 +348,29 @@ | |
| return; | |
| pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_sse2; | |
| pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_sse2; | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_sse2; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_sse2; | |
| if( !(cpu&X264_CPU_SSSE3) ) | |
| return; | |
| if( !(cpu&X264_CPU_SLOW_PSHUFB) ) | |
| pf[I_PRED_16x16_H] = x264_predict_16x16_h_ssse3; | |
| #if HAVE_X86_INLINE_ASM | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_ssse3; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_ssse3; | |
| #endif | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_avx; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_avx; | |
| #endif // HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_AVX2 ) | |
| { | |
| - pf[I_PRED_16x16_P] = x264_predict_16x16_p_avx2; | |
| + pf[I_PRED_16x16_P] = predict_16x16_p_avx2; | |
| pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_avx2; | |
| pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_avx2; | |
| pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_avx2; | |
| } | |
| } | |
| -void x264_predict_8x8c_init_mmx( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x8c_init_mmx( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_MMX) ) | |
| return; | |
| @@ -388,16 +388,16 @@ | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x8c_dc_sse2; | |
| pf[I_PRED_CHROMA_DC_TOP] = x264_predict_8x8c_dc_top_sse2; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x8c_h_sse2; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_sse2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_sse2; | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_avx; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_avx; | |
| if( !(cpu&X264_CPU_AVX2) ) | |
| return; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x8c_h_avx2; | |
| #else | |
| #if ARCH_X86_64 | |
| - pf[I_PRED_CHROMA_DC_LEFT] = x264_predict_8x8c_dc_left; | |
| + pf[I_PRED_CHROMA_DC_LEFT] = predict_8x8c_dc_left; | |
| #endif | |
| pf[I_PRED_CHROMA_V] = x264_predict_8x8c_v_mmx; | |
| if( !(cpu&X264_CPU_MMX2) ) | |
| @@ -405,30 +405,30 @@ | |
| pf[I_PRED_CHROMA_DC_TOP] = x264_predict_8x8c_dc_top_mmx2; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x8c_h_mmx2; | |
| #if !ARCH_X86_64 | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_mmx2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_mmx2; | |
| #endif | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x8c_dc_mmx2; | |
| if( !(cpu&X264_CPU_SSE2) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_sse2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_sse2; | |
| if( !(cpu&X264_CPU_SSSE3) ) | |
| return; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x8c_h_ssse3; | |
| #if HAVE_X86_INLINE_ASM | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_ssse3; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_ssse3; | |
| #endif | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_avx; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_avx; | |
| #endif // HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_AVX2 ) | |
| { | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x8c_p_avx2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x8c_p_avx2; | |
| } | |
| } | |
| -void x264_predict_8x16c_init_mmx( int cpu, x264_predict_t pf[7] ) | |
| +void x264_predict_8x16c_init_mmx( uint32_t cpu, x264_predict_t pf[7] ) | |
| { | |
| if( !(cpu&X264_CPU_MMX) ) | |
| return; | |
| @@ -445,10 +445,10 @@ | |
| pf[I_PRED_CHROMA_DC_TOP] = x264_predict_8x16c_dc_top_sse2; | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x16c_dc_sse2; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x16c_h_sse2; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_sse2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_sse2; | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_avx; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_avx; | |
| if( !(cpu&X264_CPU_AVX2) ) | |
| return; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x16c_h_avx2; | |
| @@ -460,26 +460,26 @@ | |
| pf[I_PRED_CHROMA_DC] = x264_predict_8x16c_dc_mmx2; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x16c_h_mmx2; | |
| #if !ARCH_X86_64 | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_mmx2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_mmx2; | |
| #endif | |
| if( !(cpu&X264_CPU_SSE2) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_sse2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_sse2; | |
| if( !(cpu&X264_CPU_SSSE3) ) | |
| return; | |
| pf[I_PRED_CHROMA_H] = x264_predict_8x16c_h_ssse3; | |
| if( !(cpu&X264_CPU_AVX) ) | |
| return; | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_avx; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_avx; | |
| #endif // HIGH_BIT_DEPTH | |
| if( cpu&X264_CPU_AVX2 ) | |
| { | |
| - pf[I_PRED_CHROMA_P] = x264_predict_8x16c_p_avx2; | |
| + pf[I_PRED_CHROMA_P] = predict_8x16c_p_avx2; | |
| } | |
| } | |
| -void x264_predict_8x8_init_mmx( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_8x8_filter ) | |
| +void x264_predict_8x8_init_mmx( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_8x8_filter ) | |
| { | |
| if( !(cpu&X264_CPU_MMX2) ) | |
| return; | |
| @@ -563,7 +563,7 @@ | |
| #endif // HIGH_BIT_DEPTH | |
| } | |
| -void x264_predict_4x4_init_mmx( int cpu, x264_predict_t pf[12] ) | |
| +void x264_predict_4x4_init_mmx( uint32_t cpu, x264_predict_t pf[12] ) | |
| { | |
| if( !(cpu&X264_CPU_MMX2) ) | |
| return; | |
| diff -ur x264-go/x264c/external/x264/common/x86/predict.h x264-go.new/x264c/external/x264/common/x86/predict.h | |
| --- x264-go/x264c/external/x264/common/x86/predict.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/predict.h 2020-06-06 15:20:58.694039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * predict.h: x86 intra prediction | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -24,121 +24,233 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_I386_PREDICT_H | |
| -#define X264_I386_PREDICT_H | |
| +#ifndef X264_X86_PREDICT_H | |
| +#define X264_X86_PREDICT_H | |
| -void x264_predict_16x16_init_mmx( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x16c_init_mmx( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_8x8c_init_mmx ( int cpu, x264_predict_t pf[7] ); | |
| -void x264_predict_4x4_init_mmx ( int cpu, x264_predict_t pf[12] ); | |
| -void x264_predict_8x8_init_mmx ( int cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_8x8_filter ); | |
| +#define x264_predict_16x16_init_mmx x264_template(predict_16x16_init_mmx) | |
| +void x264_predict_16x16_init_mmx( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x16c_init_mmx x264_template(predict_8x16c_init_mmx) | |
| +void x264_predict_8x16c_init_mmx( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_8x8c_init_mmx x264_template(predict_8x8c_init_mmx) | |
| +void x264_predict_8x8c_init_mmx ( uint32_t cpu, x264_predict_t pf[7] ); | |
| +#define x264_predict_4x4_init_mmx x264_template(predict_4x4_init_mmx) | |
| +void x264_predict_4x4_init_mmx ( uint32_t cpu, x264_predict_t pf[12] ); | |
| +#define x264_predict_8x8_init_mmx x264_template(predict_8x8_init_mmx) | |
| +void x264_predict_8x8_init_mmx ( uint32_t cpu, x264_predict8x8_t pf[12], x264_predict_8x8_filter_t *predict_8x8_filter ); | |
| +#define x264_predict_16x16_v_mmx2 x264_template(predict_16x16_v_mmx2) | |
| void x264_predict_16x16_v_mmx2( pixel *src ); | |
| +#define x264_predict_16x16_v_sse x264_template(predict_16x16_v_sse) | |
| void x264_predict_16x16_v_sse ( pixel *src ); | |
| +#define x264_predict_16x16_v_avx x264_template(predict_16x16_v_avx) | |
| void x264_predict_16x16_v_avx ( uint16_t *src ); | |
| +#define x264_predict_16x16_h_mmx2 x264_template(predict_16x16_h_mmx2) | |
| void x264_predict_16x16_h_mmx2( pixel *src ); | |
| +#define x264_predict_16x16_h_sse2 x264_template(predict_16x16_h_sse2) | |
| void x264_predict_16x16_h_sse2( uint16_t *src ); | |
| +#define x264_predict_16x16_h_ssse3 x264_template(predict_16x16_h_ssse3) | |
| void x264_predict_16x16_h_ssse3( uint8_t *src ); | |
| +#define x264_predict_16x16_h_avx2 x264_template(predict_16x16_h_avx2) | |
| void x264_predict_16x16_h_avx2( uint16_t *src ); | |
| +#define x264_predict_16x16_dc_sse2 x264_template(predict_16x16_dc_sse2) | |
| void x264_predict_16x16_dc_sse2( pixel *src ); | |
| +#define x264_predict_16x16_dc_avx2 x264_template(predict_16x16_dc_avx2) | |
| void x264_predict_16x16_dc_avx2( pixel *src ); | |
| +#define x264_predict_16x16_dc_left_sse2 x264_template(predict_16x16_dc_left_sse2) | |
| void x264_predict_16x16_dc_left_sse2( pixel *src ); | |
| +#define x264_predict_16x16_dc_left_avx2 x264_template(predict_16x16_dc_left_avx2) | |
| void x264_predict_16x16_dc_left_avx2( pixel *src ); | |
| +#define x264_predict_16x16_dc_top_sse2 x264_template(predict_16x16_dc_top_sse2) | |
| void x264_predict_16x16_dc_top_sse2( pixel *src ); | |
| +#define x264_predict_16x16_dc_top_avx2 x264_template(predict_16x16_dc_top_avx2) | |
| void x264_predict_16x16_dc_top_avx2( pixel *src ); | |
| +#define x264_predict_16x16_p_core_mmx2 x264_template(predict_16x16_p_core_mmx2) | |
| void x264_predict_16x16_p_core_mmx2( uint8_t *src, int i00, int b, int c ); | |
| +#define x264_predict_16x16_p_core_sse2 x264_template(predict_16x16_p_core_sse2) | |
| void x264_predict_16x16_p_core_sse2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_16x16_p_core_avx x264_template(predict_16x16_p_core_avx) | |
| void x264_predict_16x16_p_core_avx( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_16x16_p_core_avx2 x264_template(predict_16x16_p_core_avx2) | |
| void x264_predict_16x16_p_core_avx2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x16c_dc_mmx2 x264_template(predict_8x16c_dc_mmx2) | |
| void x264_predict_8x16c_dc_mmx2( pixel *src ); | |
| +#define x264_predict_8x16c_dc_sse2 x264_template(predict_8x16c_dc_sse2) | |
| void x264_predict_8x16c_dc_sse2( uint16_t *src ); | |
| +#define x264_predict_8x16c_dc_top_mmx2 x264_template(predict_8x16c_dc_top_mmx2) | |
| void x264_predict_8x16c_dc_top_mmx2( uint8_t *src ); | |
| +#define x264_predict_8x16c_dc_top_sse2 x264_template(predict_8x16c_dc_top_sse2) | |
| void x264_predict_8x16c_dc_top_sse2( uint16_t *src ); | |
| +#define x264_predict_8x16c_v_mmx x264_template(predict_8x16c_v_mmx) | |
| void x264_predict_8x16c_v_mmx( uint8_t *src ); | |
| +#define x264_predict_8x16c_v_sse x264_template(predict_8x16c_v_sse) | |
| void x264_predict_8x16c_v_sse( uint16_t *src ); | |
| +#define x264_predict_8x16c_h_mmx2 x264_template(predict_8x16c_h_mmx2) | |
| void x264_predict_8x16c_h_mmx2( pixel *src ); | |
| +#define x264_predict_8x16c_h_sse2 x264_template(predict_8x16c_h_sse2) | |
| void x264_predict_8x16c_h_sse2( uint16_t *src ); | |
| +#define x264_predict_8x16c_h_ssse3 x264_template(predict_8x16c_h_ssse3) | |
| void x264_predict_8x16c_h_ssse3( uint8_t *src ); | |
| +#define x264_predict_8x16c_h_avx2 x264_template(predict_8x16c_h_avx2) | |
| void x264_predict_8x16c_h_avx2( uint16_t *src ); | |
| +#define x264_predict_8x16c_p_core_mmx2 x264_template(predict_8x16c_p_core_mmx2) | |
| void x264_predict_8x16c_p_core_mmx2( uint8_t *src, int i00, int b, int c ); | |
| +#define x264_predict_8x16c_p_core_sse2 x264_template(predict_8x16c_p_core_sse2) | |
| void x264_predict_8x16c_p_core_sse2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x16c_p_core_avx x264_template(predict_8x16c_p_core_avx) | |
| void x264_predict_8x16c_p_core_avx ( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x16c_p_core_avx2 x264_template(predict_8x16c_p_core_avx2) | |
| void x264_predict_8x16c_p_core_avx2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x8c_p_core_mmx2 x264_template(predict_8x8c_p_core_mmx2) | |
| void x264_predict_8x8c_p_core_mmx2( uint8_t *src, int i00, int b, int c ); | |
| +#define x264_predict_8x8c_p_core_sse2 x264_template(predict_8x8c_p_core_sse2) | |
| void x264_predict_8x8c_p_core_sse2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x8c_p_core_avx x264_template(predict_8x8c_p_core_avx) | |
| void x264_predict_8x8c_p_core_avx ( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x8c_p_core_avx2 x264_template(predict_8x8c_p_core_avx2) | |
| void x264_predict_8x8c_p_core_avx2( pixel *src, int i00, int b, int c ); | |
| +#define x264_predict_8x8c_dc_mmx2 x264_template(predict_8x8c_dc_mmx2) | |
| void x264_predict_8x8c_dc_mmx2( pixel *src ); | |
| +#define x264_predict_8x8c_dc_sse2 x264_template(predict_8x8c_dc_sse2) | |
| void x264_predict_8x8c_dc_sse2( uint16_t *src ); | |
| +#define x264_predict_8x8c_dc_top_mmx2 x264_template(predict_8x8c_dc_top_mmx2) | |
| void x264_predict_8x8c_dc_top_mmx2( uint8_t *src ); | |
| +#define x264_predict_8x8c_dc_top_sse2 x264_template(predict_8x8c_dc_top_sse2) | |
| void x264_predict_8x8c_dc_top_sse2( uint16_t *src ); | |
| +#define x264_predict_8x8c_v_mmx x264_template(predict_8x8c_v_mmx) | |
| void x264_predict_8x8c_v_mmx( pixel *src ); | |
| +#define x264_predict_8x8c_v_sse x264_template(predict_8x8c_v_sse) | |
| void x264_predict_8x8c_v_sse( uint16_t *src ); | |
| +#define x264_predict_8x8c_h_mmx2 x264_template(predict_8x8c_h_mmx2) | |
| void x264_predict_8x8c_h_mmx2( pixel *src ); | |
| +#define x264_predict_8x8c_h_sse2 x264_template(predict_8x8c_h_sse2) | |
| void x264_predict_8x8c_h_sse2( uint16_t *src ); | |
| +#define x264_predict_8x8c_h_ssse3 x264_template(predict_8x8c_h_ssse3) | |
| void x264_predict_8x8c_h_ssse3( uint8_t *src ); | |
| +#define x264_predict_8x8c_h_avx2 x264_template(predict_8x8c_h_avx2) | |
| void x264_predict_8x8c_h_avx2( uint16_t *src ); | |
| +#define x264_predict_8x8_v_mmx2 x264_template(predict_8x8_v_mmx2) | |
| void x264_predict_8x8_v_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_v_sse x264_template(predict_8x8_v_sse) | |
| void x264_predict_8x8_v_sse ( uint16_t *src, uint16_t edge[36] ); | |
| +#define x264_predict_8x8_h_mmx2 x264_template(predict_8x8_h_mmx2) | |
| void x264_predict_8x8_h_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_h_sse2 x264_template(predict_8x8_h_sse2) | |
| void x264_predict_8x8_h_sse2( uint16_t *src, uint16_t edge[36] ); | |
| +#define x264_predict_8x8_hd_mmx2 x264_template(predict_8x8_hd_mmx2) | |
| void x264_predict_8x8_hd_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_hu_mmx2 x264_template(predict_8x8_hu_mmx2) | |
| void x264_predict_8x8_hu_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_dc_mmx2 x264_template(predict_8x8_dc_mmx2) | |
| void x264_predict_8x8_dc_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_dc_sse2 x264_template(predict_8x8_dc_sse2) | |
| void x264_predict_8x8_dc_sse2( uint16_t *src, uint16_t edge[36] ); | |
| +#define x264_predict_8x8_dc_top_mmx2 x264_template(predict_8x8_dc_top_mmx2) | |
| void x264_predict_8x8_dc_top_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_dc_top_sse2 x264_template(predict_8x8_dc_top_sse2) | |
| void x264_predict_8x8_dc_top_sse2( uint16_t *src, uint16_t edge[36] ); | |
| +#define x264_predict_8x8_dc_left_mmx2 x264_template(predict_8x8_dc_left_mmx2) | |
| void x264_predict_8x8_dc_left_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_dc_left_sse2 x264_template(predict_8x8_dc_left_sse2) | |
| void x264_predict_8x8_dc_left_sse2( uint16_t *src, uint16_t edge[36] ); | |
| +#define x264_predict_8x8_ddl_mmx2 x264_template(predict_8x8_ddl_mmx2) | |
| void x264_predict_8x8_ddl_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_ddl_sse2 x264_template(predict_8x8_ddl_sse2) | |
| void x264_predict_8x8_ddl_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddl_ssse3 x264_template(predict_8x8_ddl_ssse3) | |
| void x264_predict_8x8_ddl_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddl_cache64_ssse3 x264_template(predict_8x8_ddl_cache64_ssse3) | |
| void x264_predict_8x8_ddl_cache64_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddl_avx x264_template(predict_8x8_ddl_avx) | |
| void x264_predict_8x8_ddl_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddr_mmx2 x264_template(predict_8x8_ddr_mmx2) | |
| void x264_predict_8x8_ddr_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_ddr_sse2 x264_template(predict_8x8_ddr_sse2) | |
| void x264_predict_8x8_ddr_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddr_ssse3 x264_template(predict_8x8_ddr_ssse3) | |
| void x264_predict_8x8_ddr_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddr_cache64_ssse3 x264_template(predict_8x8_ddr_cache64_ssse3) | |
| void x264_predict_8x8_ddr_cache64_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_ddr_avx x264_template(predict_8x8_ddr_avx) | |
| void x264_predict_8x8_ddr_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vl_sse2 x264_template(predict_8x8_vl_sse2) | |
| void x264_predict_8x8_vl_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vl_ssse3 x264_template(predict_8x8_vl_ssse3) | |
| void x264_predict_8x8_vl_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vl_avx x264_template(predict_8x8_vl_avx) | |
| void x264_predict_8x8_vl_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vl_mmx2 x264_template(predict_8x8_vl_mmx2) | |
| void x264_predict_8x8_vl_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vr_mmx2 x264_template(predict_8x8_vr_mmx2) | |
| void x264_predict_8x8_vr_mmx2( uint8_t *src, uint8_t edge[36] ); | |
| +#define x264_predict_8x8_vr_sse2 x264_template(predict_8x8_vr_sse2) | |
| void x264_predict_8x8_vr_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vr_ssse3 x264_template(predict_8x8_vr_ssse3) | |
| void x264_predict_8x8_vr_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_vr_avx x264_template(predict_8x8_vr_avx) | |
| void x264_predict_8x8_vr_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hu_sse2 x264_template(predict_8x8_hu_sse2) | |
| void x264_predict_8x8_hu_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hu_ssse3 x264_template(predict_8x8_hu_ssse3) | |
| void x264_predict_8x8_hu_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hu_avx x264_template(predict_8x8_hu_avx) | |
| void x264_predict_8x8_hu_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hd_sse2 x264_template(predict_8x8_hd_sse2) | |
| void x264_predict_8x8_hd_sse2( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hd_ssse3 x264_template(predict_8x8_hd_ssse3) | |
| void x264_predict_8x8_hd_ssse3( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_hd_avx x264_template(predict_8x8_hd_avx) | |
| void x264_predict_8x8_hd_avx( pixel *src, pixel edge[36] ); | |
| +#define x264_predict_8x8_filter_mmx2 x264_template(predict_8x8_filter_mmx2) | |
| void x264_predict_8x8_filter_mmx2( uint8_t *src, uint8_t edge[36], int i_neighbor, int i_filters ); | |
| +#define x264_predict_8x8_filter_sse2 x264_template(predict_8x8_filter_sse2) | |
| void x264_predict_8x8_filter_sse2( uint16_t *src, uint16_t edge[36], int i_neighbor, int i_filters ); | |
| +#define x264_predict_8x8_filter_ssse3 x264_template(predict_8x8_filter_ssse3) | |
| void x264_predict_8x8_filter_ssse3( pixel *src, pixel edge[36], int i_neighbor, int i_filters ); | |
| +#define x264_predict_8x8_filter_avx x264_template(predict_8x8_filter_avx) | |
| void x264_predict_8x8_filter_avx( uint16_t *src, uint16_t edge[36], int i_neighbor, int i_filters ); | |
| +#define x264_predict_4x4_h_avx2 x264_template(predict_4x4_h_avx2) | |
| void x264_predict_4x4_h_avx2( uint16_t *src ); | |
| +#define x264_predict_4x4_ddl_mmx2 x264_template(predict_4x4_ddl_mmx2) | |
| void x264_predict_4x4_ddl_mmx2( pixel *src ); | |
| +#define x264_predict_4x4_ddl_sse2 x264_template(predict_4x4_ddl_sse2) | |
| void x264_predict_4x4_ddl_sse2( uint16_t *src ); | |
| +#define x264_predict_4x4_ddl_avx x264_template(predict_4x4_ddl_avx) | |
| void x264_predict_4x4_ddl_avx( uint16_t *src ); | |
| +#define x264_predict_4x4_ddr_mmx2 x264_template(predict_4x4_ddr_mmx2) | |
| void x264_predict_4x4_ddr_mmx2( pixel *src ); | |
| +#define x264_predict_4x4_vl_mmx2 x264_template(predict_4x4_vl_mmx2) | |
| void x264_predict_4x4_vl_mmx2( pixel *src ); | |
| +#define x264_predict_4x4_vl_sse2 x264_template(predict_4x4_vl_sse2) | |
| void x264_predict_4x4_vl_sse2( uint16_t *src ); | |
| +#define x264_predict_4x4_vl_avx x264_template(predict_4x4_vl_avx) | |
| void x264_predict_4x4_vl_avx( uint16_t *src ); | |
| +#define x264_predict_4x4_vr_mmx2 x264_template(predict_4x4_vr_mmx2) | |
| void x264_predict_4x4_vr_mmx2( uint8_t *src ); | |
| +#define x264_predict_4x4_vr_sse2 x264_template(predict_4x4_vr_sse2) | |
| void x264_predict_4x4_vr_sse2( uint16_t *src ); | |
| +#define x264_predict_4x4_vr_ssse3 x264_template(predict_4x4_vr_ssse3) | |
| void x264_predict_4x4_vr_ssse3( pixel *src ); | |
| +#define x264_predict_4x4_vr_cache64_ssse3 x264_template(predict_4x4_vr_cache64_ssse3) | |
| void x264_predict_4x4_vr_cache64_ssse3( uint8_t *src ); | |
| +#define x264_predict_4x4_vr_avx x264_template(predict_4x4_vr_avx) | |
| void x264_predict_4x4_vr_avx( uint16_t *src ); | |
| +#define x264_predict_4x4_hd_mmx2 x264_template(predict_4x4_hd_mmx2) | |
| void x264_predict_4x4_hd_mmx2( pixel *src ); | |
| +#define x264_predict_4x4_hd_sse2 x264_template(predict_4x4_hd_sse2) | |
| void x264_predict_4x4_hd_sse2( uint16_t *src ); | |
| +#define x264_predict_4x4_hd_ssse3 x264_template(predict_4x4_hd_ssse3) | |
| void x264_predict_4x4_hd_ssse3( pixel *src ); | |
| +#define x264_predict_4x4_hd_avx x264_template(predict_4x4_hd_avx) | |
| void x264_predict_4x4_hd_avx( uint16_t *src ); | |
| +#define x264_predict_4x4_dc_mmx2 x264_template(predict_4x4_dc_mmx2) | |
| void x264_predict_4x4_dc_mmx2( pixel *src ); | |
| +#define x264_predict_4x4_ddr_sse2 x264_template(predict_4x4_ddr_sse2) | |
| void x264_predict_4x4_ddr_sse2( uint16_t *src ); | |
| +#define x264_predict_4x4_ddr_ssse3 x264_template(predict_4x4_ddr_ssse3) | |
| void x264_predict_4x4_ddr_ssse3( pixel *src ); | |
| +#define x264_predict_4x4_ddr_avx x264_template(predict_4x4_ddr_avx) | |
| void x264_predict_4x4_ddr_avx( uint16_t *src ); | |
| +#define x264_predict_4x4_hu_mmx2 x264_template(predict_4x4_hu_mmx2) | |
| void x264_predict_4x4_hu_mmx2( pixel *src ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/x86: quant-a.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/quant.h x264-go.new/x264c/external/x264/common/x86/quant.h | |
| --- x264-go/x264c/external/x264/common/x86/quant.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/quant.h 2020-06-06 15:20:58.694039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * quant.h: x86 quantization and level-run | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -25,132 +25,254 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_I386_QUANT_H | |
| -#define X264_I386_QUANT_H | |
| +#ifndef X264_X86_QUANT_H | |
| +#define X264_X86_QUANT_H | |
| +#define x264_quant_2x2_dc_mmx2 x264_template(quant_2x2_dc_mmx2) | |
| int x264_quant_2x2_dc_mmx2( dctcoef dct[4], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_mmx2 x264_template(quant_4x4_dc_mmx2) | |
| int x264_quant_4x4_dc_mmx2( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_mmx2 x264_template(quant_4x4_mmx2) | |
| int x264_quant_4x4_mmx2( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_8x8_mmx2 x264_template(quant_8x8_mmx2) | |
| int x264_quant_8x8_mmx2( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); | |
| +#define x264_quant_2x2_dc_sse2 x264_template(quant_2x2_dc_sse2) | |
| int x264_quant_2x2_dc_sse2( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_sse2 x264_template(quant_4x4_dc_sse2) | |
| int x264_quant_4x4_dc_sse2( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_sse2 x264_template(quant_4x4_sse2) | |
| int x264_quant_4x4_sse2( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_4x4x4_sse2 x264_template(quant_4x4x4_sse2) | |
| int x264_quant_4x4x4_sse2( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_8x8_sse2 x264_template(quant_8x8_sse2) | |
| int x264_quant_8x8_sse2( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); | |
| +#define x264_quant_2x2_dc_ssse3 x264_template(quant_2x2_dc_ssse3) | |
| int x264_quant_2x2_dc_ssse3( dctcoef dct[4], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_ssse3 x264_template(quant_4x4_dc_ssse3) | |
| int x264_quant_4x4_dc_ssse3( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_ssse3 x264_template(quant_4x4_ssse3) | |
| int x264_quant_4x4_ssse3( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_4x4x4_ssse3 x264_template(quant_4x4x4_ssse3) | |
| int x264_quant_4x4x4_ssse3( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_8x8_ssse3 x264_template(quant_8x8_ssse3) | |
| int x264_quant_8x8_ssse3( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); | |
| +#define x264_quant_2x2_dc_sse4 x264_template(quant_2x2_dc_sse4) | |
| int x264_quant_2x2_dc_sse4( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_dc_sse4 x264_template(quant_4x4_dc_sse4) | |
| int x264_quant_4x4_dc_sse4( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_4x4_sse4 x264_template(quant_4x4_sse4) | |
| int x264_quant_4x4_sse4( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_4x4x4_sse4 x264_template(quant_4x4x4_sse4) | |
| int x264_quant_4x4x4_sse4( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_8x8_sse4 x264_template(quant_8x8_sse4) | |
| int x264_quant_8x8_sse4( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); | |
| +#define x264_quant_4x4_avx2 x264_template(quant_4x4_avx2) | |
| int x264_quant_4x4_avx2( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_quant_4x4_dc_avx2 x264_template(quant_4x4_dc_avx2) | |
| int x264_quant_4x4_dc_avx2( dctcoef dct[16], int mf, int bias ); | |
| +#define x264_quant_8x8_avx2 x264_template(quant_8x8_avx2) | |
| int x264_quant_8x8_avx2( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); | |
| +#define x264_quant_4x4x4_avx2 x264_template(quant_4x4x4_avx2) | |
| int x264_quant_4x4x4_avx2( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ); | |
| +#define x264_dequant_4x4_mmx x264_template(dequant_4x4_mmx) | |
| void x264_dequant_4x4_mmx( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4dc_mmx2 x264_template(dequant_4x4dc_mmx2) | |
| void x264_dequant_4x4dc_mmx2( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_mmx x264_template(dequant_8x8_mmx) | |
| void x264_dequant_8x8_mmx( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_sse2 x264_template(dequant_4x4_sse2) | |
| void x264_dequant_4x4_sse2( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4dc_sse2 x264_template(dequant_4x4dc_sse2) | |
| void x264_dequant_4x4dc_sse2( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_sse2 x264_template(dequant_8x8_sse2) | |
| void x264_dequant_8x8_sse2( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_avx x264_template(dequant_4x4_avx) | |
| void x264_dequant_4x4_avx( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4dc_avx x264_template(dequant_4x4dc_avx) | |
| void x264_dequant_4x4dc_avx( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_avx x264_template(dequant_8x8_avx) | |
| void x264_dequant_8x8_avx( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_xop x264_template(dequant_4x4_xop) | |
| void x264_dequant_4x4_xop( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4dc_xop x264_template(dequant_4x4dc_xop) | |
| void x264_dequant_4x4dc_xop( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_xop x264_template(dequant_8x8_xop) | |
| void x264_dequant_8x8_xop( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_avx2 x264_template(dequant_4x4_avx2) | |
| void x264_dequant_4x4_avx2( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_4x4dc_avx2 x264_template(dequant_4x4dc_avx2) | |
| void x264_dequant_4x4dc_avx2( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_avx2 x264_template(dequant_8x8_avx2) | |
| void x264_dequant_8x8_avx2( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_avx512 x264_template(dequant_4x4_avx512) | |
| void x264_dequant_4x4_avx512( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_avx512 x264_template(dequant_8x8_avx512) | |
| void x264_dequant_8x8_avx512( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_flat16_mmx x264_template(dequant_4x4_flat16_mmx) | |
| void x264_dequant_4x4_flat16_mmx( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_flat16_mmx x264_template(dequant_8x8_flat16_mmx) | |
| void x264_dequant_8x8_flat16_mmx( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_flat16_sse2 x264_template(dequant_4x4_flat16_sse2) | |
| void x264_dequant_4x4_flat16_sse2( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_flat16_sse2 x264_template(dequant_8x8_flat16_sse2) | |
| void x264_dequant_8x8_flat16_sse2( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_4x4_flat16_avx2 x264_template(dequant_4x4_flat16_avx2) | |
| void x264_dequant_4x4_flat16_avx2( int16_t dct[16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_dequant_8x8_flat16_avx2 x264_template(dequant_8x8_flat16_avx2) | |
| void x264_dequant_8x8_flat16_avx2( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_dequant_8x8_flat16_avx512 x264_template(dequant_8x8_flat16_avx512) | |
| void x264_dequant_8x8_flat16_avx512( int16_t dct[64], int dequant_mf[6][64], int i_qp ); | |
| +#define x264_idct_dequant_2x4_dc_sse2 x264_template(idct_dequant_2x4_dc_sse2) | |
| void x264_idct_dequant_2x4_dc_sse2( dctcoef dct[8], dctcoef dct4x4[8][16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_idct_dequant_2x4_dc_avx x264_template(idct_dequant_2x4_dc_avx) | |
| void x264_idct_dequant_2x4_dc_avx ( dctcoef dct[8], dctcoef dct4x4[8][16], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_idct_dequant_2x4_dconly_sse2 x264_template(idct_dequant_2x4_dconly_sse2) | |
| void x264_idct_dequant_2x4_dconly_sse2( dctcoef dct[8], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_idct_dequant_2x4_dconly_avx x264_template(idct_dequant_2x4_dconly_avx) | |
| void x264_idct_dequant_2x4_dconly_avx ( dctcoef dct[8], int dequant_mf[6][16], int i_qp ); | |
| +#define x264_optimize_chroma_2x2_dc_sse2 x264_template(optimize_chroma_2x2_dc_sse2) | |
| int x264_optimize_chroma_2x2_dc_sse2( dctcoef dct[4], int dequant_mf ); | |
| +#define x264_optimize_chroma_2x2_dc_ssse3 x264_template(optimize_chroma_2x2_dc_ssse3) | |
| int x264_optimize_chroma_2x2_dc_ssse3( dctcoef dct[4], int dequant_mf ); | |
| +#define x264_optimize_chroma_2x2_dc_sse4 x264_template(optimize_chroma_2x2_dc_sse4) | |
| int x264_optimize_chroma_2x2_dc_sse4( dctcoef dct[4], int dequant_mf ); | |
| +#define x264_optimize_chroma_2x2_dc_avx x264_template(optimize_chroma_2x2_dc_avx) | |
| int x264_optimize_chroma_2x2_dc_avx( dctcoef dct[4], int dequant_mf ); | |
| +#define x264_denoise_dct_mmx x264_template(denoise_dct_mmx) | |
| void x264_denoise_dct_mmx ( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); | |
| +#define x264_denoise_dct_sse2 x264_template(denoise_dct_sse2) | |
| void x264_denoise_dct_sse2 ( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); | |
| +#define x264_denoise_dct_ssse3 x264_template(denoise_dct_ssse3) | |
| void x264_denoise_dct_ssse3( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); | |
| +#define x264_denoise_dct_avx x264_template(denoise_dct_avx) | |
| void x264_denoise_dct_avx ( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); | |
| +#define x264_denoise_dct_avx2 x264_template(denoise_dct_avx2) | |
| void x264_denoise_dct_avx2 ( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); | |
| +#define x264_decimate_score15_sse2 x264_template(decimate_score15_sse2) | |
| int x264_decimate_score15_sse2( dctcoef *dct ); | |
| +#define x264_decimate_score15_ssse3 x264_template(decimate_score15_ssse3) | |
| int x264_decimate_score15_ssse3( dctcoef *dct ); | |
| +#define x264_decimate_score15_avx512 x264_template(decimate_score15_avx512) | |
| int x264_decimate_score15_avx512( dctcoef *dct ); | |
| +#define x264_decimate_score16_sse2 x264_template(decimate_score16_sse2) | |
| int x264_decimate_score16_sse2( dctcoef *dct ); | |
| +#define x264_decimate_score16_ssse3 x264_template(decimate_score16_ssse3) | |
| int x264_decimate_score16_ssse3( dctcoef *dct ); | |
| +#define x264_decimate_score16_avx512 x264_template(decimate_score16_avx512) | |
| int x264_decimate_score16_avx512( dctcoef *dct ); | |
| +#define x264_decimate_score64_sse2 x264_template(decimate_score64_sse2) | |
| int x264_decimate_score64_sse2( dctcoef *dct ); | |
| +#define x264_decimate_score64_ssse3 x264_template(decimate_score64_ssse3) | |
| int x264_decimate_score64_ssse3( dctcoef *dct ); | |
| +#define x264_decimate_score64_avx2 x264_template(decimate_score64_avx2) | |
| int x264_decimate_score64_avx2( int16_t *dct ); | |
| +#define x264_decimate_score64_avx512 x264_template(decimate_score64_avx512) | |
| int x264_decimate_score64_avx512( dctcoef *dct ); | |
| +#define x264_coeff_last4_mmx2 x264_template(coeff_last4_mmx2) | |
| int x264_coeff_last4_mmx2( dctcoef *dct ); | |
| +#define x264_coeff_last8_mmx2 x264_template(coeff_last8_mmx2) | |
| int x264_coeff_last8_mmx2( dctcoef *dct ); | |
| +#define x264_coeff_last15_mmx2 x264_template(coeff_last15_mmx2) | |
| int x264_coeff_last15_mmx2( dctcoef *dct ); | |
| +#define x264_coeff_last16_mmx2 x264_template(coeff_last16_mmx2) | |
| int x264_coeff_last16_mmx2( dctcoef *dct ); | |
| +#define x264_coeff_last64_mmx2 x264_template(coeff_last64_mmx2) | |
| int x264_coeff_last64_mmx2( dctcoef *dct ); | |
| +#define x264_coeff_last8_sse2 x264_template(coeff_last8_sse2) | |
| int x264_coeff_last8_sse2( dctcoef *dct ); | |
| +#define x264_coeff_last15_sse2 x264_template(coeff_last15_sse2) | |
| int x264_coeff_last15_sse2( dctcoef *dct ); | |
| +#define x264_coeff_last16_sse2 x264_template(coeff_last16_sse2) | |
| int x264_coeff_last16_sse2( dctcoef *dct ); | |
| +#define x264_coeff_last64_sse2 x264_template(coeff_last64_sse2) | |
| int x264_coeff_last64_sse2( dctcoef *dct ); | |
| +#define x264_coeff_last4_lzcnt x264_template(coeff_last4_lzcnt) | |
| int x264_coeff_last4_lzcnt( dctcoef *dct ); | |
| +#define x264_coeff_last8_lzcnt x264_template(coeff_last8_lzcnt) | |
| int x264_coeff_last8_lzcnt( dctcoef *dct ); | |
| +#define x264_coeff_last15_lzcnt x264_template(coeff_last15_lzcnt) | |
| int x264_coeff_last15_lzcnt( dctcoef *dct ); | |
| +#define x264_coeff_last16_lzcnt x264_template(coeff_last16_lzcnt) | |
| int x264_coeff_last16_lzcnt( dctcoef *dct ); | |
| +#define x264_coeff_last64_lzcnt x264_template(coeff_last64_lzcnt) | |
| int x264_coeff_last64_lzcnt( dctcoef *dct ); | |
| +#define x264_coeff_last64_avx2 x264_template(coeff_last64_avx2) | |
| int x264_coeff_last64_avx2 ( dctcoef *dct ); | |
| +#define x264_coeff_last4_avx512 x264_template(coeff_last4_avx512) | |
| int x264_coeff_last4_avx512( int32_t *dct ); | |
| +#define x264_coeff_last8_avx512 x264_template(coeff_last8_avx512) | |
| int x264_coeff_last8_avx512( dctcoef *dct ); | |
| +#define x264_coeff_last15_avx512 x264_template(coeff_last15_avx512) | |
| int x264_coeff_last15_avx512( dctcoef *dct ); | |
| +#define x264_coeff_last16_avx512 x264_template(coeff_last16_avx512) | |
| int x264_coeff_last16_avx512( dctcoef *dct ); | |
| +#define x264_coeff_last64_avx512 x264_template(coeff_last64_avx512) | |
| int x264_coeff_last64_avx512( dctcoef *dct ); | |
| +#define x264_coeff_level_run16_mmx2 x264_template(coeff_level_run16_mmx2) | |
| int x264_coeff_level_run16_mmx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run16_sse2 x264_template(coeff_level_run16_sse2) | |
| int x264_coeff_level_run16_sse2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run16_lzcnt x264_template(coeff_level_run16_lzcnt) | |
| int x264_coeff_level_run16_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run16_ssse3 x264_template(coeff_level_run16_ssse3) | |
| int x264_coeff_level_run16_ssse3( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run16_ssse3_lzcnt x264_template(coeff_level_run16_ssse3_lzcnt) | |
| int x264_coeff_level_run16_ssse3_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run16_avx2 x264_template(coeff_level_run16_avx2) | |
| int x264_coeff_level_run16_avx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_mmx2 x264_template(coeff_level_run15_mmx2) | |
| int x264_coeff_level_run15_mmx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_sse2 x264_template(coeff_level_run15_sse2) | |
| int x264_coeff_level_run15_sse2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_lzcnt x264_template(coeff_level_run15_lzcnt) | |
| int x264_coeff_level_run15_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_ssse3 x264_template(coeff_level_run15_ssse3) | |
| int x264_coeff_level_run15_ssse3( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_ssse3_lzcnt x264_template(coeff_level_run15_ssse3_lzcnt) | |
| int x264_coeff_level_run15_ssse3_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run15_avx2 x264_template(coeff_level_run15_avx2) | |
| int x264_coeff_level_run15_avx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run4_mmx2 x264_template(coeff_level_run4_mmx2) | |
| int x264_coeff_level_run4_mmx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run4_lzcnt x264_template(coeff_level_run4_lzcnt) | |
| int x264_coeff_level_run4_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run4_ssse3 x264_template(coeff_level_run4_ssse3) | |
| int x264_coeff_level_run4_ssse3( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run4_ssse3_lzcnt x264_template(coeff_level_run4_ssse3_lzcnt) | |
| int x264_coeff_level_run4_ssse3_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run8_mmx2 x264_template(coeff_level_run8_mmx2) | |
| int x264_coeff_level_run8_mmx2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run8_lzcnt x264_template(coeff_level_run8_lzcnt) | |
| int x264_coeff_level_run8_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run8_sse2 x264_template(coeff_level_run8_sse2) | |
| int x264_coeff_level_run8_sse2( dctcoef *dct, x264_run_level_t *runlevel ); | |
| -int x264_coeff_level_run8_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run8_ssse3 x264_template(coeff_level_run8_ssse3) | |
| int x264_coeff_level_run8_ssse3( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_coeff_level_run8_ssse3_lzcnt x264_template(coeff_level_run8_ssse3_lzcnt) | |
| int x264_coeff_level_run8_ssse3_lzcnt( dctcoef *dct, x264_run_level_t *runlevel ); | |
| +#define x264_trellis_cabac_4x4_sse2 x264_template(trellis_cabac_4x4_sse2) | |
| int x264_trellis_cabac_4x4_sse2 ( TRELLIS_PARAMS, int b_ac ); | |
| +#define x264_trellis_cabac_4x4_ssse3 x264_template(trellis_cabac_4x4_ssse3) | |
| int x264_trellis_cabac_4x4_ssse3( TRELLIS_PARAMS, int b_ac ); | |
| +#define x264_trellis_cabac_8x8_sse2 x264_template(trellis_cabac_8x8_sse2) | |
| int x264_trellis_cabac_8x8_sse2 ( TRELLIS_PARAMS, int b_interlaced ); | |
| +#define x264_trellis_cabac_8x8_ssse3 x264_template(trellis_cabac_8x8_ssse3) | |
| int x264_trellis_cabac_8x8_ssse3( TRELLIS_PARAMS, int b_interlaced ); | |
| +#define x264_trellis_cabac_4x4_psy_sse2 x264_template(trellis_cabac_4x4_psy_sse2) | |
| int x264_trellis_cabac_4x4_psy_sse2 ( TRELLIS_PARAMS, int b_ac, dctcoef *fenc_dct, int i_psy_trellis ); | |
| +#define x264_trellis_cabac_4x4_psy_ssse3 x264_template(trellis_cabac_4x4_psy_ssse3) | |
| int x264_trellis_cabac_4x4_psy_ssse3( TRELLIS_PARAMS, int b_ac, dctcoef *fenc_dct, int i_psy_trellis ); | |
| +#define x264_trellis_cabac_8x8_psy_sse2 x264_template(trellis_cabac_8x8_psy_sse2) | |
| int x264_trellis_cabac_8x8_psy_sse2 ( TRELLIS_PARAMS, int b_interlaced, dctcoef *fenc_dct, int i_psy_trellis ); | |
| +#define x264_trellis_cabac_8x8_psy_ssse3 x264_template(trellis_cabac_8x8_psy_ssse3) | |
| int x264_trellis_cabac_8x8_psy_ssse3( TRELLIS_PARAMS, int b_interlaced, dctcoef *fenc_dct, int i_psy_trellis ); | |
| +#define x264_trellis_cabac_dc_sse2 x264_template(trellis_cabac_dc_sse2) | |
| int x264_trellis_cabac_dc_sse2 ( TRELLIS_PARAMS, int i_coefs ); | |
| +#define x264_trellis_cabac_dc_ssse3 x264_template(trellis_cabac_dc_ssse3) | |
| int x264_trellis_cabac_dc_ssse3( TRELLIS_PARAMS, int i_coefs ); | |
| +#define x264_trellis_cabac_chroma_422_dc_sse2 x264_template(trellis_cabac_chroma_422_dc_sse2) | |
| int x264_trellis_cabac_chroma_422_dc_sse2 ( TRELLIS_PARAMS ); | |
| +#define x264_trellis_cabac_chroma_422_dc_ssse3 x264_template(trellis_cabac_chroma_422_dc_ssse3) | |
| int x264_trellis_cabac_chroma_422_dc_ssse3( TRELLIS_PARAMS ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/common/x86: sad16-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: sad-a.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: trellis-64.asm | |
| diff -ur x264-go/x264c/external/x264/common/x86/util.h x264-go.new/x264c/external/x264/common/x86/util.h | |
| --- x264-go/x264c/external/x264/common/x86/util.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/common/x86/util.h 2020-06-06 15:20:58.695039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * util.h: x86 inline asm | |
| ***************************************************************************** | |
| - * Copyright (C) 2008-2017 x264 project | |
| + * Copyright (C) 2008-2020 x264 project | |
| * | |
| * Authors: Fiona Glaser <fiona@x264.com> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -33,7 +33,7 @@ | |
| #undef M128_ZERO | |
| #define M128_ZERO ((__m128){0,0,0,0}) | |
| #define x264_union128_t x264_union128_sse_t | |
| -typedef union { __m128 i; uint64_t a[2]; uint32_t b[4]; uint16_t c[8]; uint8_t d[16]; } MAY_ALIAS x264_union128_sse_t; | |
| +typedef union { __m128 i; uint64_t q[2]; uint32_t d[4]; uint16_t w[8]; uint8_t b[16]; } MAY_ALIAS x264_union128_sse_t; | |
| #if HAVE_VECTOREXT | |
| typedef uint32_t v4si __attribute__((vector_size (16))); | |
| #endif | |
| @@ -122,7 +122,7 @@ | |
| } | |
| #define x264_predictor_clip x264_predictor_clip_mmx2 | |
| -static int ALWAYS_INLINE x264_predictor_clip_mmx2( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| +static ALWAYS_INLINE int x264_predictor_clip_mmx2( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| { | |
| static const uint32_t pd_32 = 0x20; | |
| intptr_t tmp = (intptr_t)mv_limit, mvc_max = i_mvc, i = 0; | |
| @@ -184,7 +184,7 @@ | |
| /* Same as the above, except we do (mv + 2) >> 2 on the input. */ | |
| #define x264_predictor_roundclip x264_predictor_roundclip_mmx2 | |
| -static int ALWAYS_INLINE x264_predictor_roundclip_mmx2( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| +static ALWAYS_INLINE int x264_predictor_roundclip_mmx2( int16_t (*dst)[2], int16_t (*mvc)[2], int i_mvc, int16_t mv_limit[2][2], uint32_t pmv ) | |
| { | |
| static const uint64_t pw_2 = 0x0002000200020002ULL; | |
| static const uint32_t pd_32 = 0x20; | |
| Only in x264-go.new/x264c/external/x264/common/x86: x86inc.asm | |
| Only in x264-go.new/x264c/external/x264/common/x86: x86util.asm | |
| Only in x264-go.new/x264c/external/x264: common_ | |
| diff -ur x264-go/x264c/external/x264/encoder/analyse.c x264-go.new/x264c/external/x264/encoder/analyse.c | |
| --- x264-go/x264c/external/x264/encoder/analyse.c 2020-08-25 18:16:05.835874815 +0200 | |
| +++ x264-go.new/x264c/external/x264/encoder/analyse.c 2020-06-06 15:20:58.696039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * analyse.c: macroblock analysis | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -49,8 +49,8 @@ | |
| int i_cost4x8[4]; /* cost per 8x8 partition */ | |
| int i_cost16x8; | |
| int i_cost8x16; | |
| - /* [ref][0] is 16x16 mv, [ref][1..4] are 8x8 mv from partition [0..3] */ | |
| - ALIGNED_4( int16_t mvc[32][5][2] ); | |
| + /* [ref][0] is 16x16 mv, [ref][1..4] are 8x8 mv from partition [0..3], [ref][5] is for alignment */ | |
| + ALIGNED_8( int16_t mvc[32][6][2] ); | |
| } x264_mb_analysis_list_t; | |
| typedef struct | |
| @@ -120,124 +120,6 @@ | |
| } x264_mb_analysis_t; | |
| -/* lambda = pow(2,qp/6-2) */ | |
| -const uint16_t x264_lambda_tab[QP_MAX_MAX+1] = | |
| -{ | |
| - 1, 1, 1, 1, 1, 1, 1, 1, /* 0- 7 */ | |
| - 1, 1, 1, 1, 1, 1, 1, 1, /* 8-15 */ | |
| - 2, 2, 2, 2, 3, 3, 3, 4, /* 16-23 */ | |
| - 4, 4, 5, 6, 6, 7, 8, 9, /* 24-31 */ | |
| - 10, 11, 13, 14, 16, 18, 20, 23, /* 32-39 */ | |
| - 25, 29, 32, 36, 40, 45, 51, 57, /* 40-47 */ | |
| - 64, 72, 81, 91, 102, 114, 128, 144, /* 48-55 */ | |
| - 161, 181, 203, 228, 256, 287, 323, 362, /* 56-63 */ | |
| - 406, 456, 512, 575, 645, 724, 813, 912, /* 64-71 */ | |
| -1024,1149,1290,1448,1625,1825,2048,2299, /* 72-79 */ | |
| -2580,2896, /* 80-81 */ | |
| -}; | |
| - | |
| -/* lambda2 = pow(lambda,2) * .9 * 256 */ | |
| -/* Capped to avoid overflow */ | |
| -const int x264_lambda2_tab[QP_MAX_MAX+1] = | |
| -{ | |
| - 14, 18, 22, 28, 36, 45, 57, 72, /* 0- 7 */ | |
| - 91, 115, 145, 182, 230, 290, 365, 460, /* 8-15 */ | |
| - 580, 731, 921, 1161, 1462, 1843, 2322, 2925, /* 16-23 */ | |
| - 3686, 4644, 5851, 7372, 9289, 11703, 14745, 18578, /* 24-31 */ | |
| - 23407, 29491, 37156, 46814, 58982, 74313, 93628, 117964, /* 32-39 */ | |
| - 148626, 187257, 235929, 297252, 374514, 471859, 594505, 749029, /* 40-47 */ | |
| - 943718, 1189010, 1498059, 1887436, 2378021, 2996119, 3774873, 4756042, /* 48-55 */ | |
| - 5992238, 7549747, 9512085, 11984476, 15099494, 19024170,23968953,30198988, /* 56-63 */ | |
| - 38048341, 47937906, 60397977, 76096683, 95875813,120795955, /* 64-69 */ | |
| -134217727,134217727,134217727,134217727,134217727,134217727, /* 70-75 */ | |
| -134217727,134217727,134217727,134217727,134217727,134217727, /* 76-81 */ | |
| -}; | |
| - | |
| -const uint8_t x264_exp2_lut[64] = | |
| -{ | |
| - 0, 3, 6, 8, 11, 14, 17, 20, 23, 26, 29, 32, 36, 39, 42, 45, | |
| - 48, 52, 55, 58, 62, 65, 69, 72, 76, 80, 83, 87, 91, 94, 98, 102, | |
| - 106, 110, 114, 118, 122, 126, 130, 135, 139, 143, 147, 152, 156, 161, 165, 170, | |
| - 175, 179, 184, 189, 194, 198, 203, 208, 214, 219, 224, 229, 234, 240, 245, 250 | |
| -}; | |
| - | |
| -const float x264_log2_lut[128] = | |
| -{ | |
| - 0.00000, 0.01123, 0.02237, 0.03342, 0.04439, 0.05528, 0.06609, 0.07682, | |
| - 0.08746, 0.09803, 0.10852, 0.11894, 0.12928, 0.13955, 0.14975, 0.15987, | |
| - 0.16993, 0.17991, 0.18982, 0.19967, 0.20945, 0.21917, 0.22882, 0.23840, | |
| - 0.24793, 0.25739, 0.26679, 0.27612, 0.28540, 0.29462, 0.30378, 0.31288, | |
| - 0.32193, 0.33092, 0.33985, 0.34873, 0.35755, 0.36632, 0.37504, 0.38370, | |
| - 0.39232, 0.40088, 0.40939, 0.41785, 0.42626, 0.43463, 0.44294, 0.45121, | |
| - 0.45943, 0.46761, 0.47573, 0.48382, 0.49185, 0.49985, 0.50779, 0.51570, | |
| - 0.52356, 0.53138, 0.53916, 0.54689, 0.55459, 0.56224, 0.56986, 0.57743, | |
| - 0.58496, 0.59246, 0.59991, 0.60733, 0.61471, 0.62205, 0.62936, 0.63662, | |
| - 0.64386, 0.65105, 0.65821, 0.66534, 0.67243, 0.67948, 0.68650, 0.69349, | |
| - 0.70044, 0.70736, 0.71425, 0.72110, 0.72792, 0.73471, 0.74147, 0.74819, | |
| - 0.75489, 0.76155, 0.76818, 0.77479, 0.78136, 0.78790, 0.79442, 0.80090, | |
| - 0.80735, 0.81378, 0.82018, 0.82655, 0.83289, 0.83920, 0.84549, 0.85175, | |
| - 0.85798, 0.86419, 0.87036, 0.87652, 0.88264, 0.88874, 0.89482, 0.90087, | |
| - 0.90689, 0.91289, 0.91886, 0.92481, 0.93074, 0.93664, 0.94251, 0.94837, | |
| - 0.95420, 0.96000, 0.96578, 0.97154, 0.97728, 0.98299, 0.98868, 0.99435, | |
| -}; | |
| - | |
| -/* Avoid an int/float conversion. */ | |
| -const float x264_log2_lz_lut[32] = | |
| -{ | |
| - 31,30,29,28,27,26,25,24,23,22,21,20,19,18,17,16,15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0 | |
| -}; | |
| - | |
| -// should the intra and inter lambdas be different? | |
| -// I'm just matching the behaviour of deadzone quant. | |
| -static const int x264_trellis_lambda2_tab[2][QP_MAX_MAX+1] = | |
| -{ | |
| - // inter lambda = .85 * .85 * 2**(qp/3. + 10 - LAMBDA_BITS) | |
| - { | |
| - 46, 58, 73, 92, 117, 147, | |
| - 185, 233, 294, 370, 466, 587, | |
| - 740, 932, 1174, 1480, 1864, 2349, | |
| - 2959, 3728, 4697, 5918, 7457, 9395, | |
| - 11837, 14914, 18790, 23674, 29828, 37581, | |
| - 47349, 59656, 75163, 94699, 119313, 150326, | |
| - 189399, 238627, 300652, 378798, 477255, 601304, | |
| - 757596, 954511, 1202608, 1515192, 1909022, 2405217, | |
| - 3030384, 3818045, 4810435, 6060769, 7636091, 9620872, | |
| - 12121539, 15272182, 19241743, 24243077, 30544363, 38483486, | |
| - 48486154, 61088726, 76966972, 96972308, | |
| - 122177453,134217727,134217727,134217727,134217727,134217727, | |
| - 134217727,134217727,134217727,134217727,134217727,134217727, | |
| - }, | |
| - // intra lambda = .65 * .65 * 2**(qp/3. + 10 - LAMBDA_BITS) | |
| - { | |
| - 27, 34, 43, 54, 68, 86, | |
| - 108, 136, 172, 216, 273, 343, | |
| - 433, 545, 687, 865, 1090, 1374, | |
| - 1731, 2180, 2747, 3461, 4361, 5494, | |
| - 6922, 8721, 10988, 13844, 17442, 21976, | |
| - 27688, 34885, 43953, 55377, 69771, 87906, | |
| - 110755, 139543, 175813, 221511, 279087, 351627, | |
| - 443023, 558174, 703255, 886046, 1116348, 1406511, | |
| - 1772093, 2232697, 2813022, 3544186, 4465396, 5626046, | |
| - 7088374, 8930791, 11252092, 14176748, 17861583, 22504184, | |
| - 28353495, 35723165, 45008368, 56706990, | |
| - 71446330, 90016736,113413980,134217727,134217727,134217727, | |
| - 134217727,134217727,134217727,134217727,134217727,134217727, | |
| - 134217727,134217727,134217727,134217727,134217727,134217727, | |
| - } | |
| -}; | |
| - | |
| -#define MAX_CHROMA_LAMBDA_OFFSET 36 | |
| -static const uint16_t x264_chroma_lambda2_offset_tab[MAX_CHROMA_LAMBDA_OFFSET+1] = | |
| -{ | |
| - 16, 20, 25, 32, 40, 50, | |
| - 64, 80, 101, 128, 161, 203, | |
| - 256, 322, 406, 512, 645, 812, | |
| - 1024, 1290, 1625, 2048, 2580, 3250, | |
| - 4096, 5160, 6501, 8192, 10321, 13003, | |
| - 16384, 20642, 26007, 32768, 41285, 52015, | |
| - 65535 | |
| -}; | |
| - | |
| /* TODO: calculate CABAC costs */ | |
| static const uint8_t i_mb_b_cost_table[X264_MBTYPE_MAX] = | |
| { | |
| @@ -256,18 +138,14 @@ | |
| 5, 3, 3, 1 | |
| }; | |
| -static void x264_analyse_update_cache( x264_t *h, x264_mb_analysis_t *a ); | |
| - | |
| -static uint16_t x264_cost_ref[QP_MAX+1][3][33]; | |
| -static UNUSED x264_pthread_mutex_t cost_ref_mutex = X264_PTHREAD_MUTEX_INITIALIZER; | |
| -static uint16_t x264_cost_i4x4_mode[(QP_MAX+2)*32]; | |
| +static void analyse_update_cache( x264_t *h, x264_mb_analysis_t *a ); | |
| static int init_costs( x264_t *h, float *logs, int qp ) | |
| { | |
| if( h->cost_mv[qp] ) | |
| return 0; | |
| - int mv_range = h->param.analyse.i_mv_range; | |
| + int mv_range = h->param.analyse.i_mv_range << PARAM_INTERLACED; | |
| int lambda = x264_lambda_tab[qp]; | |
| /* factor of 4 from qpel, 2 from sign, and 2 because mv can be opposite from mvp */ | |
| CHECKED_MALLOC( h->cost_mv[qp], (4*4*mv_range + 1) * sizeof(uint16_t) ); | |
| @@ -277,11 +155,9 @@ | |
| h->cost_mv[qp][-i] = | |
| h->cost_mv[qp][i] = X264_MIN( (int)(lambda * logs[i] + .5f), UINT16_MAX ); | |
| } | |
| - x264_pthread_mutex_lock( &cost_ref_mutex ); | |
| for( int i = 0; i < 3; i++ ) | |
| for( int j = 0; j < 33; j++ ) | |
| - x264_cost_ref[qp][i][j] = i ? X264_MIN( lambda * bs_size_te( i, j ), UINT16_MAX ) : 0; | |
| - x264_pthread_mutex_unlock( &cost_ref_mutex ); | |
| + h->cost_table->ref[qp][i][j] = i ? X264_MIN( lambda * bs_size_te( i, j ), UINT16_MAX ) : 0; | |
| if( h->param.analyse.i_me_method >= X264_ME_ESA && !h->cost_mv_fpel[qp][0] ) | |
| { | |
| for( int j = 0; j < 4; j++ ) | |
| @@ -292,7 +168,7 @@ | |
| h->cost_mv_fpel[qp][j][i] = h->cost_mv[qp][i*4+j]; | |
| } | |
| } | |
| - uint16_t *cost_i4x4_mode = (uint16_t*)ALIGN((intptr_t)x264_cost_i4x4_mode,64) + qp*32; | |
| + uint16_t *cost_i4x4_mode = h->cost_table->i4x4_mode[qp]; | |
| for( int i = 0; i < 17; i++ ) | |
| cost_i4x4_mode[i] = 3*lambda*(i!=8); | |
| return 0; | |
| @@ -302,7 +178,7 @@ | |
| int x264_analyse_init_costs( x264_t *h ) | |
| { | |
| - int mv_range = h->param.analyse.i_mv_range; | |
| + int mv_range = h->param.analyse.i_mv_range << PARAM_INTERLACED; | |
| float *logs = x264_malloc( (2*4*mv_range+1) * sizeof(float) ); | |
| if( !logs ) | |
| return -1; | |
| @@ -327,14 +203,16 @@ | |
| void x264_analyse_free_costs( x264_t *h ) | |
| { | |
| - int mv_range = h->param.analyse.i_mv_range; | |
| + int mv_range = h->param.analyse.i_mv_range << PARAM_INTERLACED; | |
| for( int i = 0; i < QP_MAX+1; i++ ) | |
| { | |
| if( h->cost_mv[i] ) | |
| x264_free( h->cost_mv[i] - 2*4*mv_range ); | |
| - if( h->cost_mv_fpel[i][0] ) | |
| - for( int j = 0; j < 4; j++ ) | |
| + for( int j = 0; j < 4; j++ ) | |
| + { | |
| + if( h->cost_mv_fpel[i][j] ) | |
| x264_free( h->cost_mv_fpel[i][j] - 2*mv_range ); | |
| + } | |
| } | |
| } | |
| @@ -367,14 +245,14 @@ | |
| } | |
| /* initialize an array of lambda*nbits for all possible mvs */ | |
| -static void x264_mb_analyse_load_costs( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_load_costs( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| a->p_cost_mv = h->cost_mv[a->i_qp]; | |
| - a->p_cost_ref[0] = x264_cost_ref[a->i_qp][x264_clip3(h->sh.i_num_ref_idx_l0_active-1,0,2)]; | |
| - a->p_cost_ref[1] = x264_cost_ref[a->i_qp][x264_clip3(h->sh.i_num_ref_idx_l1_active-1,0,2)]; | |
| + a->p_cost_ref[0] = h->cost_table->ref[a->i_qp][x264_clip3(h->sh.i_num_ref_idx_l0_active-1,0,2)]; | |
| + a->p_cost_ref[1] = h->cost_table->ref[a->i_qp][x264_clip3(h->sh.i_num_ref_idx_l1_active-1,0,2)]; | |
| } | |
| -static void x264_mb_analyse_init_qp( x264_t *h, x264_mb_analysis_t *a, int qp ) | |
| +static void mb_analyse_init_qp( x264_t *h, x264_mb_analysis_t *a, int qp ) | |
| { | |
| int effective_chroma_qp = h->chroma_qp_table[SPEC_QP(qp)] + X264_MAX( qp - QP_MAX_SPEC, 0 ); | |
| a->i_lambda = x264_lambda_tab[qp]; | |
| @@ -413,7 +291,7 @@ | |
| h->mb.i_chroma_qp = h->chroma_qp_table[qp]; | |
| } | |
| -static void x264_mb_analyse_init( x264_t *h, x264_mb_analysis_t *a, int qp ) | |
| +static void mb_analyse_init( x264_t *h, x264_mb_analysis_t *a, int qp ) | |
| { | |
| int subme = h->param.analyse.i_subpel_refine - (h->sh.i_type == SLICE_TYPE_B); | |
| @@ -424,15 +302,15 @@ | |
| h->mb.b_deblock_rdo = h->param.analyse.i_subpel_refine >= 9 && h->sh.i_disable_deblocking_filter_idc != 1; | |
| a->b_early_terminate = h->param.analyse.i_subpel_refine < 11; | |
| - x264_mb_analyse_init_qp( h, a, qp ); | |
| + mb_analyse_init_qp( h, a, qp ); | |
| h->mb.b_transform_8x8 = 0; | |
| /* I: Intra part */ | |
| a->i_satd_i16x16 = | |
| a->i_satd_i8x8 = | |
| - a->i_satd_i4x4 = | |
| - a->i_satd_chroma = COST_MAX; | |
| + a->i_satd_i4x4 = COST_MAX; | |
| + a->i_satd_chroma = CHROMA_FORMAT ? COST_MAX : 0; | |
| /* non-RD PCM decision is inaccurate (as is psy-rd), so don't do it. | |
| * PCM cost can overflow with high lambda2, so cap it at COST_MAX. */ | |
| @@ -567,14 +445,12 @@ | |
| /* Fast intra decision */ | |
| if( a->b_early_terminate && h->mb.i_mb_xy - h->sh.i_first_mb > 4 ) | |
| { | |
| - /* Always run in fast-intra mode for subme < 3 */ | |
| - if( h->mb.i_subpel_refine > 2 && | |
| - ( IS_INTRA( h->mb.i_mb_type_left[0] ) || | |
| + if( IS_INTRA( h->mb.i_mb_type_left[0] ) || | |
| IS_INTRA( h->mb.i_mb_type_top ) || | |
| IS_INTRA( h->mb.i_mb_type_topleft ) || | |
| IS_INTRA( h->mb.i_mb_type_topright ) || | |
| (h->sh.i_type == SLICE_TYPE_P && IS_INTRA( h->fref[0][0]->mb_type[h->mb.i_mb_xy] )) || | |
| - (h->mb.i_mb_xy - h->sh.i_first_mb < 3*(h->stat.frame.i_mb_count[I_4x4] + h->stat.frame.i_mb_count[I_8x8] + h->stat.frame.i_mb_count[I_16x16])) ) ) | |
| + (h->mb.i_mb_xy - h->sh.i_first_mb < 3*(h->stat.frame.i_mb_count[I_4x4] + h->stat.frame.i_mb_count[I_8x8] + h->stat.frame.i_mb_count[I_16x16])) ) | |
| { /* intra is likely */ } | |
| else | |
| { | |
| @@ -682,21 +558,19 @@ | |
| } | |
| /* For trellis=2, we need to do this for both sizes of DCT, for trellis=1 we only need to use it on the chosen mode. */ | |
| -static void inline x264_psy_trellis_init( x264_t *h, int do_both_dct ) | |
| +static inline void psy_trellis_init( x264_t *h, int do_both_dct ) | |
| { | |
| - ALIGNED_16( static pixel zero[16*FDEC_STRIDE] ) = {0}; | |
| - | |
| if( do_both_dct || h->mb.b_transform_8x8 ) | |
| - h->dctf.sub16x16_dct8( h->mb.pic.fenc_dct8, h->mb.pic.p_fenc[0], zero ); | |
| + h->dctf.sub16x16_dct8( h->mb.pic.fenc_dct8, h->mb.pic.p_fenc[0], (pixel*)x264_zero ); | |
| if( do_both_dct || !h->mb.b_transform_8x8 ) | |
| - h->dctf.sub16x16_dct( h->mb.pic.fenc_dct4, h->mb.pic.p_fenc[0], zero ); | |
| + h->dctf.sub16x16_dct( h->mb.pic.fenc_dct4, h->mb.pic.p_fenc[0], (pixel*)x264_zero ); | |
| } | |
| /* Reset fenc satd scores cache for psy RD */ | |
| -static inline void x264_mb_init_fenc_cache( x264_t *h, int b_satd ) | |
| +static inline void mb_init_fenc_cache( x264_t *h, int b_satd ) | |
| { | |
| if( h->param.analyse.i_trellis == 2 && h->mb.i_psy_trellis ) | |
| - x264_psy_trellis_init( h, h->param.analyse.b_transform_8x8 ); | |
| + psy_trellis_init( h, h->param.analyse.b_transform_8x8 ); | |
| if( !h->mb.i_psy_rd ) | |
| return; | |
| @@ -709,7 +583,7 @@ | |
| h->mc.memzero_aligned( h->mb.pic.fenc_satd_cache, sizeof(h->mb.pic.fenc_satd_cache) ); | |
| } | |
| -static void x264_mb_analyse_intra_chroma( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_intra_chroma( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| if( a->i_satd_chroma < COST_MAX ) | |
| return; | |
| @@ -791,7 +665,7 @@ | |
| } | |
| /* FIXME: should we do any sort of merged chroma analysis with 4:4:4? */ | |
| -static void x264_mb_analyse_intra( x264_t *h, x264_mb_analysis_t *a, int i_satd_inter ) | |
| +static void mb_analyse_intra( x264_t *h, x264_mb_analysis_t *a, int i_satd_inter ) | |
| { | |
| const unsigned int flags = h->sh.i_type == SLICE_TYPE_I ? h->param.analyse.intra : h->param.analyse.inter; | |
| pixel *p_src = h->mb.pic.p_fenc[0]; | |
| @@ -867,7 +741,7 @@ | |
| return; | |
| } | |
| - uint16_t *cost_i4x4_mode = (uint16_t*)ALIGN((intptr_t)x264_cost_i4x4_mode,64) + a->i_qp*32 + 8; | |
| + uint16_t *cost_i4x4_mode = h->cost_table->i4x4_mode[a->i_qp] + 8; | |
| /* 8x8 prediction selection */ | |
| if( flags & X264_ANALYSE_I8x8 ) | |
| { | |
| @@ -909,10 +783,11 @@ | |
| { | |
| if( !h->mb.b_lossless && predict_mode[5] >= 0 ) | |
| { | |
| - ALIGNED_ARRAY_16( int32_t, satd,[9] ); | |
| + ALIGNED_ARRAY_16( int32_t, satd,[4] ); | |
| h->pixf.intra_mbcmp_x3_8x8( p_src_by, edge, satd ); | |
| int favor_vertical = satd[I_PRED_4x4_H] > satd[I_PRED_4x4_V]; | |
| - satd[i_pred_mode] -= 3 * lambda; | |
| + if( i_pred_mode < 3 ) | |
| + satd[i_pred_mode] -= 3 * lambda; | |
| for( int i = 2; i >= 0; i-- ) | |
| { | |
| int cost = satd[i]; | |
| @@ -1027,10 +902,11 @@ | |
| { | |
| if( !h->mb.b_lossless && predict_mode[5] >= 0 ) | |
| { | |
| - ALIGNED_ARRAY_16( int32_t, satd,[9] ); | |
| + ALIGNED_ARRAY_16( int32_t, satd,[4] ); | |
| h->pixf.intra_mbcmp_x3_4x4( p_src_by, p_dst_by, satd ); | |
| int favor_vertical = satd[I_PRED_4x4_H] > satd[I_PRED_4x4_V]; | |
| - satd[i_pred_mode] -= 3 * lambda; | |
| + if( i_pred_mode < 3 ) | |
| + satd[i_pred_mode] -= 3 * lambda; | |
| i_best = satd[I_PRED_4x4_DC]; a->i_predict4x4[idx] = I_PRED_4x4_DC; | |
| COPY2_IF_LT( i_best, satd[I_PRED_4x4_H], a->i_predict4x4[idx], I_PRED_4x4_H ); | |
| COPY2_IF_LT( i_best, satd[I_PRED_4x4_V], a->i_predict4x4[idx], I_PRED_4x4_V ); | |
| @@ -1103,7 +979,7 @@ | |
| } | |
| } | |
| -static void x264_intra_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd_thresh ) | |
| +static void intra_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd_thresh ) | |
| { | |
| if( !a->b_early_terminate ) | |
| i_satd_thresh = COST_MAX; | |
| @@ -1111,8 +987,8 @@ | |
| if( a->i_satd_i16x16 < i_satd_thresh ) | |
| { | |
| h->mb.i_type = I_16x16; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_satd_i16x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_satd_i16x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| else | |
| a->i_satd_i16x16 = COST_MAX; | |
| @@ -1120,8 +996,8 @@ | |
| if( a->i_satd_i4x4 < i_satd_thresh ) | |
| { | |
| h->mb.i_type = I_4x4; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_satd_i4x4 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_satd_i4x4 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| else | |
| a->i_satd_i4x4 = COST_MAX; | |
| @@ -1129,15 +1005,15 @@ | |
| if( a->i_satd_i8x8 < i_satd_thresh ) | |
| { | |
| h->mb.i_type = I_8x8; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_satd_i8x8 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_satd_i8x8 = rd_cost_mb( h, a->i_lambda2 ); | |
| a->i_cbp_i8x8_luma = h->mb.i_cbp_luma; | |
| } | |
| else | |
| a->i_satd_i8x8 = COST_MAX; | |
| } | |
| -static void x264_intra_rd_refine( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void intra_rd_refine( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| uint64_t i_satd, i_best; | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| @@ -1155,13 +1031,13 @@ | |
| if( i_mode == old_pred_mode || a->i_satd_i16x16_dir[i_mode] > i_thresh ) | |
| continue; | |
| h->mb.i_intra16x16_pred_mode = i_mode; | |
| - i_satd = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + i_satd = rd_cost_mb( h, a->i_lambda2 ); | |
| COPY2_IF_LT( i_best, i_satd, a->i_predict16x16, i_mode ); | |
| } | |
| } | |
| /* RD selection for chroma prediction */ | |
| - if( !CHROMA444 ) | |
| + if( CHROMA_FORMAT == CHROMA_420 || CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| const int8_t *predict_mode = predict_chroma_mode_available( h->mb.i_neighbour_intra ); | |
| if( predict_mode[1] >= 0 ) | |
| @@ -1181,10 +1057,10 @@ | |
| { | |
| int i_cbp_chroma_best = h->mb.i_cbp_chroma; | |
| int i_chroma_lambda = x264_lambda2_tab[h->mb.i_chroma_qp]; | |
| - /* the previous thing encoded was x264_intra_rd(), so the pixels and | |
| + /* the previous thing encoded was intra_rd(), so the pixels and | |
| * coefs for the current chroma mode are still around, so we only | |
| * have to recount the bits. */ | |
| - i_best = x264_rd_cost_chroma( h, i_chroma_lambda, a->i_predict8x8chroma, 0 ); | |
| + i_best = rd_cost_chroma( h, i_chroma_lambda, a->i_predict8x8chroma, 0 ); | |
| for( int i = 0; i < i_max; i++ ) | |
| { | |
| int i_mode = predict_mode_sorted[i]; | |
| @@ -1198,7 +1074,7 @@ | |
| /* if we've already found a mode that needs no residual, then | |
| * probably any mode with a residual will be worse. | |
| * so avoid dct on the remaining modes to improve speed. */ | |
| - i_satd = x264_rd_cost_chroma( h, i_chroma_lambda, i_mode, h->mb.i_cbp_chroma != 0x00 ); | |
| + i_satd = rd_cost_chroma( h, i_chroma_lambda, i_mode, h->mb.i_cbp_chroma != 0x00 ); | |
| COPY3_IF_LT( i_best, i_satd, a->i_predict8x8chroma, i_mode, i_cbp_chroma_best, h->mb.i_cbp_chroma ); | |
| } | |
| h->mb.i_chroma_pred_mode = a->i_predict8x8chroma; | |
| @@ -1214,8 +1090,8 @@ | |
| for( int idx = 0; idx < 16; idx++ ) | |
| { | |
| pixel *dst[3] = {h->mb.pic.p_fdec[0] + block_idx_xy_fdec[idx], | |
| - h->mb.pic.p_fdec[1] + block_idx_xy_fdec[idx], | |
| - h->mb.pic.p_fdec[2] + block_idx_xy_fdec[idx]}; | |
| + CHROMA_FORMAT ? h->mb.pic.p_fdec[1] + block_idx_xy_fdec[idx] : NULL, | |
| + CHROMA_FORMAT ? h->mb.pic.p_fdec[2] + block_idx_xy_fdec[idx] : NULL}; | |
| i_best = COST_MAX64; | |
| const int8_t *predict_mode = predict_4x4_mode_available( a->b_avoid_topright, h->mb.i_neighbour4[idx], idx ); | |
| @@ -1228,7 +1104,7 @@ | |
| for( ; *predict_mode >= 0; predict_mode++ ) | |
| { | |
| int i_mode = *predict_mode; | |
| - i_satd = x264_rd_cost_i4x4( h, a->i_lambda2, idx, i_mode ); | |
| + i_satd = rd_cost_i4x4( h, a->i_lambda2, idx, i_mode ); | |
| if( i_best > i_satd ) | |
| { | |
| @@ -1269,8 +1145,8 @@ | |
| int y = idx>>1; | |
| int s8 = X264_SCAN8_0 + 2*x + 16*y; | |
| pixel *dst[3] = {h->mb.pic.p_fdec[0] + 8*x + 8*y*FDEC_STRIDE, | |
| - h->mb.pic.p_fdec[1] + 8*x + 8*y*FDEC_STRIDE, | |
| - h->mb.pic.p_fdec[2] + 8*x + 8*y*FDEC_STRIDE}; | |
| + CHROMA_FORMAT ? h->mb.pic.p_fdec[1] + 8*x + 8*y*FDEC_STRIDE : NULL, | |
| + CHROMA_FORMAT ? h->mb.pic.p_fdec[2] + 8*x + 8*y*FDEC_STRIDE : NULL}; | |
| int cbp_luma_new = 0; | |
| int i_thresh = a->b_early_terminate ? a->i_satd_i8x8_dir[idx][a->i_predict8x8[idx]] * 11/8 : COST_MAX; | |
| @@ -1287,7 +1163,7 @@ | |
| continue; | |
| h->mb.i_cbp_luma = a->i_cbp_i8x8_luma; | |
| - i_satd = x264_rd_cost_i8x8( h, a->i_lambda2, idx, i_mode, edge ); | |
| + i_satd = rd_cost_i8x8( h, a->i_lambda2, idx, i_mode, edge ); | |
| if( i_best > i_satd ) | |
| { | |
| @@ -1331,30 +1207,40 @@ | |
| (m)->i_stride[1] = h->mb.pic.i_stride[1]; \ | |
| (m)->i_stride[2] = h->mb.pic.i_stride[2]; \ | |
| (m)->p_fenc[0] = &(src)[0][(xoff)+(yoff)*FENC_STRIDE]; \ | |
| - (m)->p_fenc[1] = &(src)[1][((xoff)>>CHROMA_H_SHIFT)+((yoff)>>CHROMA_V_SHIFT)*FENC_STRIDE]; \ | |
| - (m)->p_fenc[2] = &(src)[2][((xoff)>>CHROMA_H_SHIFT)+((yoff)>>CHROMA_V_SHIFT)*FENC_STRIDE]; \ | |
| + if( CHROMA_FORMAT ) \ | |
| + { \ | |
| + (m)->p_fenc[1] = &(src)[1][((xoff)>>CHROMA_H_SHIFT)+((yoff)>>CHROMA_V_SHIFT)*FENC_STRIDE]; \ | |
| + (m)->p_fenc[2] = &(src)[2][((xoff)>>CHROMA_H_SHIFT)+((yoff)>>CHROMA_V_SHIFT)*FENC_STRIDE]; \ | |
| + } \ | |
| } | |
| #define LOAD_HPELS(m, src, list, ref, xoff, yoff) \ | |
| { \ | |
| (m)->p_fref_w = (m)->p_fref[0] = &(src)[0][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| - (m)->p_fref[1] = &(src)[1][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| - (m)->p_fref[2] = &(src)[2][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| - (m)->p_fref[3] = &(src)[3][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| + if( h->param.analyse.i_subpel_refine ) \ | |
| + { \ | |
| + (m)->p_fref[1] = &(src)[1][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| + (m)->p_fref[2] = &(src)[2][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| + (m)->p_fref[3] = &(src)[3][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| + } \ | |
| if( CHROMA444 ) \ | |
| { \ | |
| (m)->p_fref[ 4] = &(src)[ 4][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| - (m)->p_fref[ 5] = &(src)[ 5][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| - (m)->p_fref[ 6] = &(src)[ 6][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| - (m)->p_fref[ 7] = &(src)[ 7][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| (m)->p_fref[ 8] = &(src)[ 8][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| - (m)->p_fref[ 9] = &(src)[ 9][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| - (m)->p_fref[10] = &(src)[10][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| - (m)->p_fref[11] = &(src)[11][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| + if( h->param.analyse.i_subpel_refine ) \ | |
| + { \ | |
| + (m)->p_fref[ 5] = &(src)[ 5][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| + (m)->p_fref[ 6] = &(src)[ 6][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| + (m)->p_fref[ 7] = &(src)[ 7][(xoff)+(yoff)*(m)->i_stride[1]]; \ | |
| + (m)->p_fref[ 9] = &(src)[ 9][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| + (m)->p_fref[10] = &(src)[10][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| + (m)->p_fref[11] = &(src)[11][(xoff)+(yoff)*(m)->i_stride[2]]; \ | |
| + } \ | |
| } \ | |
| - else \ | |
| + else if( CHROMA_FORMAT ) \ | |
| (m)->p_fref[4] = &(src)[4][(xoff)+((yoff)>>CHROMA_V_SHIFT)*(m)->i_stride[1]]; \ | |
| - (m)->integral = &h->mb.pic.p_integral[list][ref][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| + if( h->param.analyse.i_me_method >= X264_ME_ESA ) \ | |
| + (m)->integral = &h->mb.pic.p_integral[list][ref][(xoff)+(yoff)*(m)->i_stride[0]]; \ | |
| (m)->weight = x264_weight_none; \ | |
| (m)->i_ref = ref; \ | |
| } | |
| @@ -1366,11 +1252,11 @@ | |
| #define REF_COST(list, ref) \ | |
| (a->p_cost_ref[list][ref]) | |
| -static void x264_mb_analyse_inter_p16x16( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_p16x16( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| x264_me_t m; | |
| int i_mvc; | |
| - ALIGNED_4( int16_t mvc[8][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[8],[2] ); | |
| int i_halfpel_thresh = INT_MAX; | |
| int *p_halfpel_thresh = (a->b_early_terminate && h->mb.pic.i_fref[0]>1) ? &i_halfpel_thresh : NULL; | |
| @@ -1415,7 +1301,7 @@ | |
| && x264_macroblock_probe_pskip( h ) ) | |
| { | |
| h->mb.i_type = P_SKIP; | |
| - x264_analyse_update_cache( h, a ); | |
| + analyse_update_cache( h, a ); | |
| assert( h->mb.cache.pskip_mv[1] <= h->mb.mv_max_spel[1] || h->i_thread_frames == 1 ); | |
| return; | |
| } | |
| @@ -1433,19 +1319,19 @@ | |
| h->mb.i_type = P_L0; | |
| if( a->i_mbrd ) | |
| { | |
| - x264_mb_init_fenc_cache( h, a->i_mbrd >= 2 || h->param.analyse.inter & X264_ANALYSE_PSUB8x8 ); | |
| + mb_init_fenc_cache( h, a->i_mbrd >= 2 || h->param.analyse.inter & X264_ANALYSE_PSUB8x8 ); | |
| if( a->l0.me16x16.i_ref == 0 && M32( a->l0.me16x16.mv ) == M32( h->mb.cache.pskip_mv ) && !a->b_force_intra ) | |
| { | |
| h->mb.i_partition = D_16x16; | |
| x264_macroblock_cache_mv_ptr( h, 0, 0, 4, 4, 0, a->l0.me16x16.mv ); | |
| - a->l0.i_rd16x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + a->l0.i_rd16x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| if( !(h->mb.i_cbp_luma|h->mb.i_cbp_chroma) ) | |
| h->mb.i_type = P_SKIP; | |
| } | |
| } | |
| } | |
| -static void x264_mb_analyse_inter_p8x8_mixed_ref( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_p8x8_mixed_ref( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| x264_me_t m; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| @@ -1536,7 +1422,7 @@ | |
| M32( h->mb.i_sub_partition ) = D_L0_8x8 * 0x01010101; | |
| } | |
| -static void x264_mb_analyse_inter_p8x8( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_p8x8( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| /* Duplicate refs are rarely useful in p8x8 due to the high cost of the | |
| * reference frame flags. Thus, if we're not doing mixedrefs, just | |
| @@ -1591,11 +1477,11 @@ | |
| M32( h->mb.i_sub_partition ) = D_L0_8x8 * 0x01010101; | |
| } | |
| -static void x264_mb_analyse_inter_p16x8( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| +static void mb_analyse_inter_p16x8( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| { | |
| x264_me_t m; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| - ALIGNED_4( int16_t mvc[3][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[3],[2] ); | |
| /* XXX Needed for x264_mb_predict_mv */ | |
| h->mb.i_partition = D_16x8; | |
| @@ -1657,11 +1543,11 @@ | |
| a->l0.i_cost16x8 = a->l0.me16x8[0].cost + a->l0.me16x8[1].cost; | |
| } | |
| -static void x264_mb_analyse_inter_p8x16( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| +static void mb_analyse_inter_p8x16( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| { | |
| x264_me_t m; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| - ALIGNED_4( int16_t mvc[3][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[3],[2] ); | |
| /* XXX Needed for x264_mb_predict_mv */ | |
| h->mb.i_partition = D_8x16; | |
| @@ -1722,8 +1608,8 @@ | |
| a->l0.i_cost8x16 = a->l0.me8x16[0].cost + a->l0.me8x16[1].cost; | |
| } | |
| -static ALWAYS_INLINE int x264_mb_analyse_inter_p4x4_chroma_internal( x264_t *h, x264_mb_analysis_t *a, | |
| - pixel **p_fref, int i8x8, int size, int chroma ) | |
| +static ALWAYS_INLINE int mb_analyse_inter_p4x4_chroma_internal( x264_t *h, x264_mb_analysis_t *a, | |
| + pixel **p_fref, int i8x8, int size, int chroma ) | |
| { | |
| ALIGNED_ARRAY_32( pixel, pix1,[16*16] ); | |
| pixel *pix2 = pix1+8; | |
| @@ -1786,17 +1672,17 @@ | |
| + h->pixf.mbcmp[chromapix]( &h->mb.pic.p_fenc[2][oe], FENC_STRIDE, pix2, 16 ); | |
| } | |
| -static int x264_mb_analyse_inter_p4x4_chroma( x264_t *h, x264_mb_analysis_t *a, pixel **p_fref, int i8x8, int size ) | |
| +static int mb_analyse_inter_p4x4_chroma( x264_t *h, x264_mb_analysis_t *a, pixel **p_fref, int i8x8, int size ) | |
| { | |
| if( CHROMA_FORMAT == CHROMA_444 ) | |
| - return x264_mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_444 ); | |
| + return mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_444 ); | |
| else if( CHROMA_FORMAT == CHROMA_422 ) | |
| - return x264_mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_422 ); | |
| + return mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_422 ); | |
| else | |
| - return x264_mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_420 ); | |
| + return mb_analyse_inter_p4x4_chroma_internal( h, a, p_fref, i8x8, size, CHROMA_420 ); | |
| } | |
| -static void x264_mb_analyse_inter_p4x4( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| +static void mb_analyse_inter_p4x4( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| { | |
| pixel **p_fref = h->mb.pic.p_fref[0][a->l0.me8x8[i8x8].i_ref]; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| @@ -1832,10 +1718,10 @@ | |
| REF_COST( 0, i_ref ) + | |
| a->i_lambda * i_sub_mb_p_cost_table[D_L0_4x4]; | |
| if( h->mb.b_chroma_me && !CHROMA444 ) | |
| - a->l0.i_cost4x4[i8x8] += x264_mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_4x4 ); | |
| + a->l0.i_cost4x4[i8x8] += mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_4x4 ); | |
| } | |
| -static void x264_mb_analyse_inter_p8x4( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| +static void mb_analyse_inter_p8x4( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| { | |
| pixel **p_fref = h->mb.pic.p_fref[0][a->l0.me8x8[i8x8].i_ref]; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| @@ -1868,10 +1754,10 @@ | |
| REF_COST( 0, i_ref ) + | |
| a->i_lambda * i_sub_mb_p_cost_table[D_L0_8x4]; | |
| if( h->mb.b_chroma_me && !CHROMA444 ) | |
| - a->l0.i_cost8x4[i8x8] += x264_mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_8x4 ); | |
| + a->l0.i_cost8x4[i8x8] += mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_8x4 ); | |
| } | |
| -static void x264_mb_analyse_inter_p4x8( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| +static void mb_analyse_inter_p4x8( x264_t *h, x264_mb_analysis_t *a, int i8x8 ) | |
| { | |
| pixel **p_fref = h->mb.pic.p_fref[0][a->l0.me8x8[i8x8].i_ref]; | |
| pixel **p_fenc = h->mb.pic.p_fenc; | |
| @@ -1904,10 +1790,10 @@ | |
| REF_COST( 0, i_ref ) + | |
| a->i_lambda * i_sub_mb_p_cost_table[D_L0_4x8]; | |
| if( h->mb.b_chroma_me && !CHROMA444 ) | |
| - a->l0.i_cost4x8[i8x8] += x264_mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_4x8 ); | |
| + a->l0.i_cost4x8[i8x8] += mb_analyse_inter_p4x4_chroma( h, a, p_fref, i8x8, PIXEL_4x8 ); | |
| } | |
| -static ALWAYS_INLINE int x264_analyse_bi_chroma( x264_t *h, x264_mb_analysis_t *a, int idx, int i_pixel ) | |
| +static ALWAYS_INLINE int analyse_bi_chroma( x264_t *h, x264_mb_analysis_t *a, int idx, int i_pixel ) | |
| { | |
| ALIGNED_ARRAY_32( pixel, pix, [4],[16*16] ); | |
| ALIGNED_ARRAY_32( pixel, bi, [2],[16*16] ); | |
| @@ -1955,7 +1841,7 @@ | |
| return i_chroma_cost; | |
| } | |
| -static void x264_mb_analyse_inter_direct( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_direct( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| /* Assumes that fdec still contains the results of | |
| * x264_mb_predict_mv_direct16x16 and x264_mb_mc */ | |
| @@ -2001,14 +1887,14 @@ | |
| } | |
| } | |
| -static void x264_mb_analyse_inter_b16x16( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_b16x16( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| ALIGNED_ARRAY_32( pixel, pix0,[16*16] ); | |
| ALIGNED_ARRAY_32( pixel, pix1,[16*16] ); | |
| pixel *src0, *src1; | |
| intptr_t stride0 = 16, stride1 = 16; | |
| int i_ref, i_mvc; | |
| - ALIGNED_4( int16_t mvc[9][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[9],[2] ); | |
| int try_skip = a->b_try_skip; | |
| int list1_skipped = 0; | |
| int i_halfpel_thresh[2] = {INT_MAX, INT_MAX}; | |
| @@ -2073,7 +1959,7 @@ | |
| { | |
| /* We already tested skip */ | |
| h->mb.i_type = B_SKIP; | |
| - x264_analyse_update_cache( h, a ); | |
| + analyse_update_cache( h, a ); | |
| return; | |
| } | |
| } | |
| @@ -2105,7 +1991,7 @@ | |
| + a->l1.bi16x16.cost_mv; | |
| if( h->mb.b_chroma_me ) | |
| - a->i_cost16x16bi += x264_analyse_bi_chroma( h, a, 0, PIXEL_16x16 ); | |
| + a->i_cost16x16bi += analyse_bi_chroma( h, a, 0, PIXEL_16x16 ); | |
| /* Always try the 0,0,0,0 vector; helps avoid errant motion vectors in fades */ | |
| if( M32( a->l0.bi16x16.mv ) | M32( a->l1.bi16x16.mv ) ) | |
| @@ -2137,7 +2023,7 @@ | |
| } | |
| else | |
| { | |
| - ALIGNED_ARRAY_32( pixel, pixuv, [2],[16*FENC_STRIDE] ); | |
| + ALIGNED_ARRAY_64( pixel, pixuv, [2],[16*FENC_STRIDE] ); | |
| int chromapix = h->luma2chroma_pixel[PIXEL_16x16]; | |
| int v_shift = CHROMA_V_SHIFT; | |
| @@ -2187,7 +2073,7 @@ | |
| a->l1.me16x16.cost += a->i_lambda * i_mb_b_cost_table[B_L1_L1]; | |
| } | |
| -static inline void x264_mb_cache_mv_p8x8( x264_t *h, x264_mb_analysis_t *a, int i ) | |
| +static inline void mb_cache_mv_p8x8( x264_t *h, x264_mb_analysis_t *a, int i ) | |
| { | |
| int x = 2*(i&1); | |
| int y = i&2; | |
| @@ -2217,7 +2103,7 @@ | |
| } | |
| } | |
| -static void x264_mb_load_mv_direct8x8( x264_t *h, int idx ) | |
| +static void mb_load_mv_direct8x8( x264_t *h, int idx ) | |
| { | |
| int x = 2*(idx&1); | |
| int y = idx&2; | |
| @@ -2253,13 +2139,13 @@ | |
| x264_macroblock_cache_mvd( h, x,y,dx,dy, 1, 0 ); \ | |
| } | |
| -static inline void x264_mb_cache_mv_b8x8( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| +static inline void mb_cache_mv_b8x8( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| { | |
| int x = 2*(i&1); | |
| int y = i&2; | |
| if( h->mb.i_sub_partition[i] == D_DIRECT_8x8 ) | |
| { | |
| - x264_mb_load_mv_direct8x8( h, i ); | |
| + mb_load_mv_direct8x8( h, i ); | |
| if( b_mvd ) | |
| { | |
| x264_macroblock_cache_mvd( h, x, y, 2, 2, 0, 0 ); | |
| @@ -2272,17 +2158,17 @@ | |
| CACHE_MV_BI( x, y, 2, 2, a->l0.me8x8[i], a->l1.me8x8[i], h->mb.i_sub_partition[i] ); | |
| } | |
| } | |
| -static inline void x264_mb_cache_mv_b16x8( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| +static inline void mb_cache_mv_b16x8( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| { | |
| CACHE_MV_BI( 0, 2*i, 4, 2, a->l0.me16x8[i], a->l1.me16x8[i], a->i_mb_partition16x8[i] ); | |
| } | |
| -static inline void x264_mb_cache_mv_b8x16( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| +static inline void mb_cache_mv_b8x16( x264_t *h, x264_mb_analysis_t *a, int i, int b_mvd ) | |
| { | |
| CACHE_MV_BI( 2*i, 0, 2, 4, a->l0.me8x16[i], a->l1.me8x16[i], a->i_mb_partition8x16[i] ); | |
| } | |
| #undef CACHE_MV_BI | |
| -static void x264_mb_analyse_inter_b8x8_mixed_ref( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_b8x8_mixed_ref( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| ALIGNED_ARRAY_16( pixel, pix,[2],[8*8] ); | |
| int i_maxref[2] = {h->mb.pic.i_fref[0]-1, h->mb.pic.i_fref[1]-1}; | |
| @@ -2371,7 +2257,7 @@ | |
| if( h->mb.b_chroma_me ) | |
| { | |
| - int i_chroma_cost = x264_analyse_bi_chroma( h, a, i, PIXEL_8x8 ); | |
| + int i_chroma_cost = analyse_bi_chroma( h, a, i, PIXEL_8x8 ); | |
| i_part_cost_bi += i_chroma_cost; | |
| a->i_satd8x8[2][i] += i_chroma_cost; | |
| } | |
| @@ -2387,14 +2273,14 @@ | |
| a->i_cost8x8bi += i_part_cost; | |
| /* XXX Needed for x264_mb_predict_mv */ | |
| - x264_mb_cache_mv_b8x8( h, a, i, 0 ); | |
| + mb_cache_mv_b8x8( h, a, i, 0 ); | |
| } | |
| /* mb type cost */ | |
| a->i_cost8x8bi += a->i_lambda * i_mb_b_cost_table[B_8x8]; | |
| } | |
| -static void x264_mb_analyse_inter_b8x8( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void mb_analyse_inter_b8x8( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| pixel **p_fref[2] = | |
| { h->mb.pic.p_fref[0][a->l0.me16x16.i_ref], | |
| @@ -2451,7 +2337,7 @@ | |
| if( h->mb.b_chroma_me ) | |
| { | |
| - int i_chroma_cost = x264_analyse_bi_chroma( h, a, i, PIXEL_8x8 ); | |
| + int i_chroma_cost = analyse_bi_chroma( h, a, i, PIXEL_8x8 ); | |
| i_part_cost_bi += i_chroma_cost; | |
| a->i_satd8x8[2][i] += i_chroma_cost; | |
| } | |
| @@ -2464,17 +2350,17 @@ | |
| a->i_cost8x8bi += i_part_cost; | |
| /* XXX Needed for x264_mb_predict_mv */ | |
| - x264_mb_cache_mv_b8x8( h, a, i, 0 ); | |
| + mb_cache_mv_b8x8( h, a, i, 0 ); | |
| } | |
| /* mb type cost */ | |
| a->i_cost8x8bi += a->i_lambda * i_mb_b_cost_table[B_8x8]; | |
| } | |
| -static void x264_mb_analyse_inter_b16x8( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| +static void mb_analyse_inter_b16x8( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| { | |
| ALIGNED_ARRAY_32( pixel, pix,[2],[16*8] ); | |
| - ALIGNED_4( int16_t mvc[3][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[3],[2] ); | |
| h->mb.i_partition = D_16x8; | |
| a->i_cost16x8bi = 0; | |
| @@ -2529,7 +2415,7 @@ | |
| + a->l1.me16x8[i].i_ref_cost; | |
| if( h->mb.b_chroma_me ) | |
| - i_part_cost_bi += x264_analyse_bi_chroma( h, a, i, PIXEL_16x8 ); | |
| + i_part_cost_bi += analyse_bi_chroma( h, a, i, PIXEL_16x8 ); | |
| i_part_cost = a->l0.me16x8[i].cost; | |
| a->i_mb_partition16x8[i] = D_L0_8x8; /* not actually 8x8, only the L0 matters */ | |
| @@ -2555,7 +2441,7 @@ | |
| return; | |
| } | |
| - x264_mb_cache_mv_b16x8( h, a, i, 0 ); | |
| + mb_cache_mv_b16x8( h, a, i, 0 ); | |
| } | |
| /* mb type cost */ | |
| @@ -2565,10 +2451,10 @@ | |
| a->i_cost16x8bi += a->i_lambda * i_mb_b16x8_cost_table[a->i_mb_type16x8]; | |
| } | |
| -static void x264_mb_analyse_inter_b8x16( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| +static void mb_analyse_inter_b8x16( x264_t *h, x264_mb_analysis_t *a, int i_best_satd ) | |
| { | |
| ALIGNED_ARRAY_16( pixel, pix,[2],[8*16] ); | |
| - ALIGNED_4( int16_t mvc[3][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[3],[2] ); | |
| h->mb.i_partition = D_8x16; | |
| a->i_cost8x16bi = 0; | |
| @@ -2622,7 +2508,7 @@ | |
| + a->l1.me8x16[i].i_ref_cost; | |
| if( h->mb.b_chroma_me ) | |
| - i_part_cost_bi += x264_analyse_bi_chroma( h, a, i, PIXEL_8x16 ); | |
| + i_part_cost_bi += analyse_bi_chroma( h, a, i, PIXEL_8x16 ); | |
| i_part_cost = a->l0.me8x16[i].cost; | |
| a->i_mb_partition8x16[i] = D_L0_8x8; | |
| @@ -2648,7 +2534,7 @@ | |
| return; | |
| } | |
| - x264_mb_cache_mv_b8x16( h, a, i, 0 ); | |
| + mb_cache_mv_b8x16( h, a, i, 0 ); | |
| } | |
| /* mb type cost */ | |
| @@ -2658,7 +2544,7 @@ | |
| a->i_cost8x16bi += a->i_lambda * i_mb_b16x8_cost_table[a->i_mb_type8x16]; | |
| } | |
| -static void x264_mb_analyse_p_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd ) | |
| +static void mb_analyse_p_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd ) | |
| { | |
| int thresh = a->b_early_terminate ? i_satd * 5/4 + 1 : COST_MAX; | |
| @@ -2666,15 +2552,15 @@ | |
| if( a->l0.i_rd16x16 == COST_MAX && (!a->b_early_terminate || a->l0.me16x16.cost <= i_satd * 3/2) ) | |
| { | |
| h->mb.i_partition = D_16x16; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l0.i_rd16x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l0.i_rd16x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| if( a->l0.i_cost16x8 < thresh ) | |
| { | |
| h->mb.i_partition = D_16x8; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l0.i_cost16x8 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l0.i_cost16x8 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| else | |
| a->l0.i_cost16x8 = COST_MAX; | |
| @@ -2682,8 +2568,8 @@ | |
| if( a->l0.i_cost8x16 < thresh ) | |
| { | |
| h->mb.i_partition = D_8x16; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l0.i_cost8x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l0.i_cost8x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| else | |
| a->l0.i_cost8x16 = COST_MAX; | |
| @@ -2712,7 +2598,7 @@ | |
| if( costs[subtype] > sub8x8_thresh ) | |
| continue; | |
| h->mb.i_sub_partition[i] = subtype; | |
| - x264_mb_cache_mv_p8x8( h, a, i ); | |
| + mb_cache_mv_p8x8( h, a, i ); | |
| if( subtype == btype ) | |
| continue; | |
| cost = x264_rd_cost_part( h, a->i_lambda2, i<<2, PIXEL_8x8 ); | |
| @@ -2721,19 +2607,19 @@ | |
| if( h->mb.i_sub_partition[i] != btype ) | |
| { | |
| h->mb.i_sub_partition[i] = btype; | |
| - x264_mb_cache_mv_p8x8( h, a, i ); | |
| + mb_cache_mv_p8x8( h, a, i ); | |
| } | |
| } | |
| } | |
| else | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l0.i_cost8x8 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l0.i_cost8x8 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| else | |
| a->l0.i_cost8x8 = COST_MAX; | |
| } | |
| -static void x264_mb_analyse_b_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd_inter ) | |
| +static void mb_analyse_b_rd( x264_t *h, x264_mb_analysis_t *a, int i_satd_inter ) | |
| { | |
| int thresh = a->b_early_terminate ? i_satd_inter * (17 + (!!h->mb.i_psy_rd))/16 + 1 : COST_MAX; | |
| @@ -2743,8 +2629,8 @@ | |
| /* Assumes direct/skip MC is still in fdec */ | |
| /* Requires b-rdo to be done before intra analysis */ | |
| h->mb.b_skip_mc = 1; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_rd16x16direct = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_rd16x16direct = rd_cost_mb( h, a->i_lambda2 ); | |
| h->mb.b_skip_mc = 0; | |
| } | |
| @@ -2754,24 +2640,24 @@ | |
| if( a->l0.me16x16.cost < thresh && a->l0.i_rd16x16 == COST_MAX ) | |
| { | |
| h->mb.i_type = B_L0_L0; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l0.i_rd16x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l0.i_rd16x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| /* L1 */ | |
| if( a->l1.me16x16.cost < thresh && a->l1.i_rd16x16 == COST_MAX ) | |
| { | |
| h->mb.i_type = B_L1_L1; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->l1.i_rd16x16 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->l1.i_rd16x16 = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| /* BI */ | |
| if( a->i_cost16x16bi < thresh && a->i_rd16x16bi == COST_MAX ) | |
| { | |
| h->mb.i_type = B_BI_BI; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_rd16x16bi = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_rd16x16bi = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| /* 8x8 */ | |
| @@ -2779,8 +2665,8 @@ | |
| { | |
| h->mb.i_type = B_8x8; | |
| h->mb.i_partition = D_8x8; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_rd8x8bi = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_rd8x8bi = rd_cost_mb( h, a->i_lambda2 ); | |
| x264_macroblock_cache_skip( h, 0, 0, 4, 4, 0 ); | |
| } | |
| @@ -2789,8 +2675,8 @@ | |
| { | |
| h->mb.i_type = a->i_mb_type16x8; | |
| h->mb.i_partition = D_16x8; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_rd16x8bi = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_rd16x8bi = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| /* 8x16 */ | |
| @@ -2798,12 +2684,12 @@ | |
| { | |
| h->mb.i_type = a->i_mb_type8x16; | |
| h->mb.i_partition = D_8x16; | |
| - x264_analyse_update_cache( h, a ); | |
| - a->i_rd8x16bi = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + analyse_update_cache( h, a ); | |
| + a->i_rd8x16bi = rd_cost_mb( h, a->i_lambda2 ); | |
| } | |
| } | |
| -static void x264_refine_bidir( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void refine_bidir( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| int i_biweight; | |
| @@ -2846,7 +2732,7 @@ | |
| } | |
| } | |
| -static inline void x264_mb_analyse_transform( x264_t *h ) | |
| +static inline void mb_analyse_transform( x264_t *h ) | |
| { | |
| if( x264_mb_transform_8x8_allowed( h ) && h->param.analyse.b_transform_8x8 && !h->mb.b_lossless ) | |
| { | |
| @@ -2884,7 +2770,7 @@ | |
| } | |
| } | |
| -static inline void x264_mb_analyse_transform_rd( x264_t *h, x264_mb_analysis_t *a, int *i_satd, int *i_rd ) | |
| +static inline void mb_analyse_transform_rd( x264_t *h, x264_mb_analysis_t *a, int *i_satd, int *i_rd ) | |
| { | |
| if( h->param.analyse.b_transform_8x8 && h->pps->b_transform_8x8_mode ) | |
| { | |
| @@ -2895,10 +2781,10 @@ | |
| else if( !x264_transform_allowed[h->mb.i_type] ) | |
| return; | |
| - x264_analyse_update_cache( h, a ); | |
| + analyse_update_cache( h, a ); | |
| h->mb.b_transform_8x8 ^= 1; | |
| /* FIXME only luma is needed for 4:2:0, but the score for comparison already includes chroma */ | |
| - int i_rd8 = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + int i_rd8 = rd_cost_mb( h, a->i_lambda2 ); | |
| if( *i_rd >= i_rd8 ) | |
| { | |
| @@ -2921,12 +2807,12 @@ | |
| * There must be a more efficient way to get that portion of the benefit | |
| * without doing full QP-RD, but RD-decimation doesn't seem to do the | |
| * trick. */ | |
| -static inline void x264_mb_analyse_qp_rd( x264_t *h, x264_mb_analysis_t *a ) | |
| +static inline void mb_analyse_qp_rd( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| int bcost, cost, failures, prevcost, origcost; | |
| int orig_qp = h->mb.i_qp, bqp = h->mb.i_qp; | |
| int last_qp_tried = 0; | |
| - origcost = bcost = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + origcost = bcost = rd_cost_mb( h, a->i_lambda2 ); | |
| int origcbp = h->mb.cbp[h->mb.i_mb_xy]; | |
| /* If CBP is already zero, don't raise the quantizer any higher. */ | |
| @@ -2959,7 +2845,7 @@ | |
| { | |
| h->mb.i_qp = X264_MAX( h->mb.i_qp - threshold - 1, SPEC_QP( h->param.rc.i_qp_min ) ); | |
| h->mb.i_chroma_qp = h->chroma_qp_table[h->mb.i_qp]; | |
| - already_checked_cost = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + already_checked_cost = rd_cost_mb( h, a->i_lambda2 ); | |
| if( !h->mb.cbp[h->mb.i_mb_xy] ) | |
| { | |
| /* If our empty-CBP block is lower QP than the last QP, | |
| @@ -2983,7 +2869,7 @@ | |
| else | |
| { | |
| h->mb.i_chroma_qp = h->chroma_qp_table[h->mb.i_qp]; | |
| - cost = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + cost = rd_cost_mb( h, a->i_lambda2 ); | |
| COPY2_IF_LT( bcost, cost, bqp, h->mb.i_qp ); | |
| } | |
| @@ -3008,7 +2894,7 @@ | |
| { | |
| h->mb.i_qp = h->mb.i_last_qp; | |
| h->mb.i_chroma_qp = h->chroma_qp_table[h->mb.i_qp]; | |
| - cost = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + cost = rd_cost_mb( h, a->i_lambda2 ); | |
| COPY2_IF_LT( bcost, cost, bqp, h->mb.i_qp ); | |
| } | |
| @@ -3020,7 +2906,7 @@ | |
| x264_mb_transform_8x8_allowed( h ) ) | |
| { | |
| h->mb.b_transform_8x8 ^= 1; | |
| - cost = x264_rd_cost_mb( h, a->i_lambda2 ); | |
| + cost = rd_cost_mb( h, a->i_lambda2 ); | |
| if( cost > bcost ) | |
| h->mb.b_transform_8x8 ^= 1; | |
| } | |
| @@ -3042,17 +2928,17 @@ | |
| if( h->param.analyse.b_mb_info ) | |
| h->fdec->effective_qp[h->mb.i_mb_xy] = h->mb.i_qp; /* Store the real analysis QP. */ | |
| - x264_mb_analyse_init( h, &analysis, h->mb.i_qp ); | |
| + mb_analyse_init( h, &analysis, h->mb.i_qp ); | |
| /*--------------------------- Do the analysis ---------------------------*/ | |
| if( h->sh.i_type == SLICE_TYPE_I ) | |
| { | |
| intra_analysis: | |
| if( analysis.i_mbrd ) | |
| - x264_mb_init_fenc_cache( h, analysis.i_mbrd >= 2 ); | |
| - x264_mb_analyse_intra( h, &analysis, COST_MAX ); | |
| + mb_init_fenc_cache( h, analysis.i_mbrd >= 2 ); | |
| + mb_analyse_intra( h, &analysis, COST_MAX ); | |
| if( analysis.i_mbrd ) | |
| - x264_intra_rd( h, &analysis, COST_MAX ); | |
| + intra_rd( h, &analysis, COST_MAX ); | |
| i_cost = analysis.i_satd_i16x16; | |
| h->mb.i_type = I_16x16; | |
| @@ -3062,7 +2948,7 @@ | |
| h->mb.i_type = I_PCM; | |
| else if( analysis.i_mbrd >= 2 ) | |
| - x264_intra_rd_refine( h, &analysis ); | |
| + intra_rd_refine( h, &analysis ); | |
| } | |
| else if( h->sh.i_type == SLICE_TYPE_P ) | |
| { | |
| @@ -3075,7 +2961,7 @@ | |
| { | |
| if( !h->param.analyse.b_psy ) | |
| { | |
| - x264_mb_analyse_init_qp( h, &analysis, X264_MAX( h->mb.i_qp - h->mb.ip_offset, h->param.rc.i_qp_min ) ); | |
| + mb_analyse_init_qp( h, &analysis, X264_MAX( h->mb.i_qp - h->mb.ip_offset, h->param.rc.i_qp_min ) ); | |
| goto intra_analysis; | |
| } | |
| } | |
| @@ -3147,9 +3033,9 @@ | |
| int i_partition; | |
| int i_satd_inter, i_satd_intra; | |
| - x264_mb_analyse_load_costs( h, &analysis ); | |
| + mb_analyse_load_costs( h, &analysis ); | |
| - x264_mb_analyse_inter_p16x16( h, &analysis ); | |
| + mb_analyse_inter_p16x16( h, &analysis ); | |
| if( h->mb.i_type == P_SKIP ) | |
| { | |
| @@ -3161,9 +3047,9 @@ | |
| if( flags & X264_ANALYSE_PSUB16x16 ) | |
| { | |
| if( h->param.analyse.b_mixed_references ) | |
| - x264_mb_analyse_inter_p8x8_mixed_ref( h, &analysis ); | |
| + mb_analyse_inter_p8x8_mixed_ref( h, &analysis ); | |
| else | |
| - x264_mb_analyse_inter_p8x8( h, &analysis ); | |
| + mb_analyse_inter_p8x8( h, &analysis ); | |
| } | |
| /* Select best inter mode */ | |
| @@ -3183,24 +3069,24 @@ | |
| { | |
| for( int i = 0; i < 4; i++ ) | |
| { | |
| - x264_mb_analyse_inter_p4x4( h, &analysis, i ); | |
| + mb_analyse_inter_p4x4( h, &analysis, i ); | |
| int i_thresh8x4 = analysis.l0.me4x4[i][1].cost_mv + analysis.l0.me4x4[i][2].cost_mv; | |
| if( !analysis.b_early_terminate || analysis.l0.i_cost4x4[i] < analysis.l0.me8x8[i].cost + i_thresh8x4 ) | |
| { | |
| int i_cost8x8 = analysis.l0.i_cost4x4[i]; | |
| h->mb.i_sub_partition[i] = D_L0_4x4; | |
| - x264_mb_analyse_inter_p8x4( h, &analysis, i ); | |
| + mb_analyse_inter_p8x4( h, &analysis, i ); | |
| COPY2_IF_LT( i_cost8x8, analysis.l0.i_cost8x4[i], | |
| h->mb.i_sub_partition[i], D_L0_8x4 ); | |
| - x264_mb_analyse_inter_p4x8( h, &analysis, i ); | |
| + mb_analyse_inter_p4x8( h, &analysis, i ); | |
| COPY2_IF_LT( i_cost8x8, analysis.l0.i_cost4x8[i], | |
| h->mb.i_sub_partition[i], D_L0_4x8 ); | |
| i_cost += i_cost8x8 - analysis.l0.me8x8[i].cost; | |
| } | |
| - x264_mb_cache_mv_p8x8( h, &analysis, i ); | |
| + mb_cache_mv_p8x8( h, &analysis, i ); | |
| } | |
| analysis.l0.i_cost8x8 = i_cost; | |
| } | |
| @@ -3215,14 +3101,14 @@ | |
| + analysis.l0.me8x8[3].cost_mv + analysis.l0.me8x8[3].i_ref_cost + 1) >> 1; | |
| analysis.i_cost_est16x8[1] = analysis.i_satd8x8[0][2] + analysis.i_satd8x8[0][3] + i_avg_mv_ref_cost; | |
| - x264_mb_analyse_inter_p16x8( h, &analysis, i_cost ); | |
| + mb_analyse_inter_p16x8( h, &analysis, i_cost ); | |
| COPY3_IF_LT( i_cost, analysis.l0.i_cost16x8, i_type, P_L0, i_partition, D_16x8 ); | |
| i_avg_mv_ref_cost = (analysis.l0.me8x8[1].cost_mv + analysis.l0.me8x8[1].i_ref_cost | |
| + analysis.l0.me8x8[3].cost_mv + analysis.l0.me8x8[3].i_ref_cost + 1) >> 1; | |
| analysis.i_cost_est8x16[1] = analysis.i_satd8x8[0][1] + analysis.i_satd8x8[0][3] + i_avg_mv_ref_cost; | |
| - x264_mb_analyse_inter_p8x16( h, &analysis, i_cost ); | |
| + mb_analyse_inter_p8x16( h, &analysis, i_cost ); | |
| COPY3_IF_LT( i_cost, analysis.l0.i_cost8x16, i_type, P_L0, i_partition, D_8x16 ); | |
| } | |
| @@ -3296,20 +3182,20 @@ | |
| { | |
| if( CHROMA444 ) | |
| { | |
| - x264_mb_analyse_intra( h, &analysis, i_cost ); | |
| - x264_mb_analyse_intra_chroma( h, &analysis ); | |
| + mb_analyse_intra( h, &analysis, i_cost ); | |
| + mb_analyse_intra_chroma( h, &analysis ); | |
| } | |
| else | |
| { | |
| - x264_mb_analyse_intra_chroma( h, &analysis ); | |
| - x264_mb_analyse_intra( h, &analysis, i_cost - analysis.i_satd_chroma ); | |
| + mb_analyse_intra_chroma( h, &analysis ); | |
| + mb_analyse_intra( h, &analysis, i_cost - analysis.i_satd_chroma ); | |
| } | |
| analysis.i_satd_i16x16 += analysis.i_satd_chroma; | |
| analysis.i_satd_i8x8 += analysis.i_satd_chroma; | |
| analysis.i_satd_i4x4 += analysis.i_satd_chroma; | |
| } | |
| else | |
| - x264_mb_analyse_intra( h, &analysis, i_cost ); | |
| + mb_analyse_intra( h, &analysis, i_cost ); | |
| i_satd_inter = i_cost; | |
| i_satd_intra = X264_MIN3( analysis.i_satd_i16x16, | |
| @@ -3318,7 +3204,7 @@ | |
| if( analysis.i_mbrd ) | |
| { | |
| - x264_mb_analyse_p_rd( h, &analysis, X264_MIN(i_satd_inter, i_satd_intra) ); | |
| + mb_analyse_p_rd( h, &analysis, X264_MIN(i_satd_inter, i_satd_intra) ); | |
| i_type = P_L0; | |
| i_partition = D_16x16; | |
| i_cost = analysis.l0.i_rd16x16; | |
| @@ -3328,8 +3214,8 @@ | |
| h->mb.i_type = i_type; | |
| h->mb.i_partition = i_partition; | |
| if( i_cost < COST_MAX ) | |
| - x264_mb_analyse_transform_rd( h, &analysis, &i_satd_inter, &i_cost ); | |
| - x264_intra_rd( h, &analysis, i_satd_inter * 5/4 + 1 ); | |
| + mb_analyse_transform_rd( h, &analysis, &i_satd_inter, &i_cost ); | |
| + intra_rd( h, &analysis, i_satd_inter * 5/4 + 1 ); | |
| } | |
| COPY2_IF_LT( i_cost, analysis.i_satd_i16x16, i_type, I_16x16 ); | |
| @@ -3343,7 +3229,7 @@ | |
| { | |
| /* Intra masking: copy fdec to fenc and re-encode the block as intra in order to make it appear as if | |
| * it was an inter block. */ | |
| - x264_analyse_update_cache( h, &analysis ); | |
| + analyse_update_cache( h, &analysis ); | |
| x264_macroblock_encode( h ); | |
| for( int p = 0; p < (CHROMA444 ? 3 : 1); p++ ) | |
| h->mc.copy[PIXEL_16x16]( h->mb.pic.p_fenc[p], FENC_STRIDE, h->mb.pic.p_fdec[p], FDEC_STRIDE, 16 ); | |
| @@ -3353,7 +3239,7 @@ | |
| h->mc.copy[PIXEL_8x8] ( h->mb.pic.p_fenc[1], FENC_STRIDE, h->mb.pic.p_fdec[1], FDEC_STRIDE, height ); | |
| h->mc.copy[PIXEL_8x8] ( h->mb.pic.p_fenc[2], FENC_STRIDE, h->mb.pic.p_fdec[2], FDEC_STRIDE, height ); | |
| } | |
| - x264_mb_analyse_init_qp( h, &analysis, X264_MAX( h->mb.i_qp - h->mb.ip_offset, h->param.rc.i_qp_min ) ); | |
| + mb_analyse_init_qp( h, &analysis, X264_MAX( h->mb.i_qp - h->mb.ip_offset, h->param.rc.i_qp_min ) ); | |
| goto intra_analysis; | |
| } | |
| @@ -3361,7 +3247,7 @@ | |
| { | |
| if( IS_INTRA( h->mb.i_type ) ) | |
| { | |
| - x264_intra_rd_refine( h, &analysis ); | |
| + intra_rd_refine( h, &analysis ); | |
| } | |
| else if( i_partition == D_16x16 ) | |
| { | |
| @@ -3387,7 +3273,7 @@ | |
| } | |
| else if( i_partition == D_8x8 ) | |
| { | |
| - x264_analyse_update_cache( h, &analysis ); | |
| + analyse_update_cache( h, &analysis ); | |
| for( int i8x8 = 0; i8x8 < 4; i8x8++ ) | |
| { | |
| if( h->mb.i_sub_partition[i8x8] == D_L0_8x8 ) | |
| @@ -3422,7 +3308,7 @@ | |
| int b_skip = 0; | |
| if( analysis.i_mbrd ) | |
| - x264_mb_init_fenc_cache( h, analysis.i_mbrd >= 2 ); | |
| + mb_init_fenc_cache( h, analysis.i_mbrd >= 2 ); | |
| h->mb.i_type = B_SKIP; | |
| if( h->mb.b_direct_auto_write ) | |
| @@ -3490,14 +3376,14 @@ | |
| h->mb.b_skip_mc = 0; | |
| h->mb.i_type = B_DIRECT; | |
| - x264_mb_analyse_load_costs( h, &analysis ); | |
| + mb_analyse_load_costs( h, &analysis ); | |
| /* select best inter mode */ | |
| /* direct must be first */ | |
| if( analysis.b_direct_available ) | |
| - x264_mb_analyse_inter_direct( h, &analysis ); | |
| + mb_analyse_inter_direct( h, &analysis ); | |
| - x264_mb_analyse_inter_b16x16( h, &analysis ); | |
| + mb_analyse_inter_b16x16( h, &analysis ); | |
| if( h->mb.i_type == B_SKIP ) | |
| { | |
| @@ -3517,14 +3403,14 @@ | |
| if( analysis.i_mbrd && analysis.b_early_terminate && analysis.i_cost16x16direct <= i_cost * 33/32 ) | |
| { | |
| - x264_mb_analyse_b_rd( h, &analysis, i_cost ); | |
| + mb_analyse_b_rd( h, &analysis, i_cost ); | |
| if( i_bskip_cost < analysis.i_rd16x16direct && | |
| i_bskip_cost < analysis.i_rd16x16bi && | |
| i_bskip_cost < analysis.l0.i_rd16x16 && | |
| i_bskip_cost < analysis.l1.i_rd16x16 ) | |
| { | |
| h->mb.i_type = B_SKIP; | |
| - x264_analyse_update_cache( h, &analysis ); | |
| + analyse_update_cache( h, &analysis ); | |
| return; | |
| } | |
| } | |
| @@ -3532,9 +3418,9 @@ | |
| if( flags & X264_ANALYSE_BSUB16x16 ) | |
| { | |
| if( h->param.analyse.b_mixed_references ) | |
| - x264_mb_analyse_inter_b8x8_mixed_ref( h, &analysis ); | |
| + mb_analyse_inter_b8x8_mixed_ref( h, &analysis ); | |
| else | |
| - x264_mb_analyse_inter_b8x8( h, &analysis ); | |
| + mb_analyse_inter_b8x8( h, &analysis ); | |
| COPY3_IF_LT( i_cost, analysis.i_cost8x8bi, i_type, B_8x8, i_partition, D_8x8 ); | |
| @@ -3584,17 +3470,17 @@ | |
| int try_16x8_first = i_cost_est16x8bi_total < i_cost_est8x16bi_total; | |
| if( try_16x8_first && (!analysis.b_early_terminate || i_cost_est16x8bi_total < i_cost) ) | |
| { | |
| - x264_mb_analyse_inter_b16x8( h, &analysis, i_cost ); | |
| + mb_analyse_inter_b16x8( h, &analysis, i_cost ); | |
| COPY3_IF_LT( i_cost, analysis.i_cost16x8bi, i_type, analysis.i_mb_type16x8, i_partition, D_16x8 ); | |
| } | |
| if( !analysis.b_early_terminate || i_cost_est8x16bi_total < i_cost ) | |
| { | |
| - x264_mb_analyse_inter_b8x16( h, &analysis, i_cost ); | |
| + mb_analyse_inter_b8x16( h, &analysis, i_cost ); | |
| COPY3_IF_LT( i_cost, analysis.i_cost8x16bi, i_type, analysis.i_mb_type8x16, i_partition, D_8x16 ); | |
| } | |
| if( !try_16x8_first && (!analysis.b_early_terminate || i_cost_est16x8bi_total < i_cost) ) | |
| { | |
| - x264_mb_analyse_inter_b16x8( h, &analysis, i_cost ); | |
| + mb_analyse_inter_b16x8( h, &analysis, i_cost ); | |
| COPY3_IF_LT( i_cost, analysis.i_cost16x8bi, i_type, analysis.i_mb_type16x8, i_partition, D_16x8 ); | |
| } | |
| } | |
| @@ -3686,7 +3572,7 @@ | |
| if( analysis.i_mbrd ) | |
| { | |
| - x264_mb_analyse_b_rd( h, &analysis, i_satd_inter ); | |
| + mb_analyse_b_rd( h, &analysis, i_satd_inter ); | |
| i_type = B_SKIP; | |
| i_cost = i_bskip_cost; | |
| i_partition = D_16x16; | |
| @@ -3706,25 +3592,25 @@ | |
| { | |
| if( CHROMA444 ) | |
| { | |
| - x264_mb_analyse_intra( h, &analysis, i_satd_inter ); | |
| - x264_mb_analyse_intra_chroma( h, &analysis ); | |
| + mb_analyse_intra( h, &analysis, i_satd_inter ); | |
| + mb_analyse_intra_chroma( h, &analysis ); | |
| } | |
| else | |
| { | |
| - x264_mb_analyse_intra_chroma( h, &analysis ); | |
| - x264_mb_analyse_intra( h, &analysis, i_satd_inter - analysis.i_satd_chroma ); | |
| + mb_analyse_intra_chroma( h, &analysis ); | |
| + mb_analyse_intra( h, &analysis, i_satd_inter - analysis.i_satd_chroma ); | |
| } | |
| analysis.i_satd_i16x16 += analysis.i_satd_chroma; | |
| analysis.i_satd_i8x8 += analysis.i_satd_chroma; | |
| analysis.i_satd_i4x4 += analysis.i_satd_chroma; | |
| } | |
| else | |
| - x264_mb_analyse_intra( h, &analysis, i_satd_inter ); | |
| + mb_analyse_intra( h, &analysis, i_satd_inter ); | |
| if( analysis.i_mbrd ) | |
| { | |
| - x264_mb_analyse_transform_rd( h, &analysis, &i_satd_inter, &i_cost ); | |
| - x264_intra_rd( h, &analysis, i_satd_inter * 17/16 + 1 ); | |
| + mb_analyse_transform_rd( h, &analysis, &i_satd_inter, &i_cost ); | |
| + intra_rd( h, &analysis, i_satd_inter * 17/16 + 1 ); | |
| } | |
| COPY2_IF_LT( i_cost, analysis.i_satd_i16x16, i_type, I_16x16 ); | |
| @@ -3736,14 +3622,14 @@ | |
| h->mb.i_partition = i_partition; | |
| if( analysis.i_mbrd >= 2 && IS_INTRA( i_type ) && i_type != I_PCM ) | |
| - x264_intra_rd_refine( h, &analysis ); | |
| + intra_rd_refine( h, &analysis ); | |
| if( h->mb.i_subpel_refine >= 5 ) | |
| - x264_refine_bidir( h, &analysis ); | |
| + refine_bidir( h, &analysis ); | |
| if( analysis.i_mbrd >= 2 && i_type > B_DIRECT && i_type < B_SKIP ) | |
| { | |
| int i_biweight; | |
| - x264_analyse_update_cache( h, &analysis ); | |
| + analyse_update_cache( h, &analysis ); | |
| if( i_partition == D_16x16 ) | |
| { | |
| @@ -3814,7 +3700,7 @@ | |
| } | |
| } | |
| - x264_analyse_update_cache( h, &analysis ); | |
| + analyse_update_cache( h, &analysis ); | |
| /* In rare cases we can end up qpel-RDing our way back to a larger partition size | |
| * without realizing it. Check for this and account for it if necessary. */ | |
| @@ -3830,22 +3716,22 @@ | |
| } | |
| if( !analysis.i_mbrd ) | |
| - x264_mb_analyse_transform( h ); | |
| + mb_analyse_transform( h ); | |
| if( analysis.i_mbrd == 3 && !IS_SKIP(h->mb.i_type) ) | |
| - x264_mb_analyse_qp_rd( h, &analysis ); | |
| + mb_analyse_qp_rd( h, &analysis ); | |
| h->mb.b_trellis = h->param.analyse.i_trellis; | |
| h->mb.b_noise_reduction = h->mb.b_noise_reduction || (!!h->param.analyse.i_noise_reduction && !IS_INTRA( h->mb.i_type )); | |
| if( !IS_SKIP(h->mb.i_type) && h->mb.i_psy_trellis && h->param.analyse.i_trellis == 1 ) | |
| - x264_psy_trellis_init( h, 0 ); | |
| + psy_trellis_init( h, 0 ); | |
| if( h->mb.b_trellis == 1 || h->mb.b_noise_reduction ) | |
| h->mb.i_skip_intra = 0; | |
| } | |
| /*-------------------- Update MB from the analysis ----------------------*/ | |
| -static void x264_analyse_update_cache( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void analyse_update_cache( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| switch( h->mb.i_type ) | |
| { | |
| @@ -3853,17 +3739,17 @@ | |
| for( int i = 0; i < 16; i++ ) | |
| h->mb.cache.intra4x4_pred_mode[x264_scan8[i]] = a->i_predict4x4[i]; | |
| - x264_mb_analyse_intra_chroma( h, a ); | |
| + mb_analyse_intra_chroma( h, a ); | |
| break; | |
| case I_8x8: | |
| for( int i = 0; i < 4; i++ ) | |
| x264_macroblock_cache_intra8x8_pred( h, 2*(i&1), 2*(i>>1), a->i_predict8x8[i] ); | |
| - x264_mb_analyse_intra_chroma( h, a ); | |
| + mb_analyse_intra_chroma( h, a ); | |
| break; | |
| case I_16x16: | |
| h->mb.i_intra16x16_pred_mode = a->i_predict16x16; | |
| - x264_mb_analyse_intra_chroma( h, a ); | |
| + mb_analyse_intra_chroma( h, a ); | |
| break; | |
| case I_PCM: | |
| @@ -3903,7 +3789,7 @@ | |
| x264_macroblock_cache_ref( h, 0, 2, 2, 2, 0, a->l0.me8x8[2].i_ref ); | |
| x264_macroblock_cache_ref( h, 2, 2, 2, 2, 0, a->l0.me8x8[3].i_ref ); | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_mb_cache_mv_p8x8( h, a, i ); | |
| + mb_cache_mv_p8x8( h, a, i ); | |
| break; | |
| case P_SKIP: | |
| @@ -3917,16 +3803,16 @@ | |
| case B_SKIP: | |
| case B_DIRECT: | |
| h->mb.i_partition = h->mb.cache.direct_partition; | |
| - x264_mb_load_mv_direct8x8( h, 0 ); | |
| - x264_mb_load_mv_direct8x8( h, 1 ); | |
| - x264_mb_load_mv_direct8x8( h, 2 ); | |
| - x264_mb_load_mv_direct8x8( h, 3 ); | |
| + mb_load_mv_direct8x8( h, 0 ); | |
| + mb_load_mv_direct8x8( h, 1 ); | |
| + mb_load_mv_direct8x8( h, 2 ); | |
| + mb_load_mv_direct8x8( h, 3 ); | |
| break; | |
| case B_8x8: | |
| /* optimize: cache might not need to be rewritten */ | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_mb_cache_mv_b8x8( h, a, i, 1 ); | |
| + mb_cache_mv_b8x8( h, a, i, 1 ); | |
| break; | |
| default: /* the rest of the B types */ | |
| @@ -3961,12 +3847,12 @@ | |
| } | |
| break; | |
| case D_16x8: | |
| - x264_mb_cache_mv_b16x8( h, a, 0, 1 ); | |
| - x264_mb_cache_mv_b16x8( h, a, 1, 1 ); | |
| + mb_cache_mv_b16x8( h, a, 0, 1 ); | |
| + mb_cache_mv_b16x8( h, a, 1, 1 ); | |
| break; | |
| case D_8x16: | |
| - x264_mb_cache_mv_b8x16( h, a, 0, 1 ); | |
| - x264_mb_cache_mv_b8x16( h, a, 1, 1 ); | |
| + mb_cache_mv_b8x16( h, a, 0, 1 ); | |
| + mb_cache_mv_b8x16( h, a, 1, 1 ); | |
| break; | |
| default: | |
| x264_log( h, X264_LOG_ERROR, "internal error (invalid MB type)\n" ); | |
| @@ -3995,10 +3881,10 @@ | |
| x264_log( h, X264_LOG_DEBUG, "mb_xy: %d,%d \n", h->mb.i_mb_x, h->mb.i_mb_y); | |
| x264_log( h, X264_LOG_DEBUG, "completed: %d \n", completed ); | |
| x264_log( h, X264_LOG_WARNING, "recovering by using intra mode\n"); | |
| - x264_mb_analyse_intra( h, a, COST_MAX ); | |
| + mb_analyse_intra( h, a, COST_MAX ); | |
| h->mb.i_type = I_16x16; | |
| h->mb.i_intra16x16_pred_mode = a->i_predict16x16; | |
| - x264_mb_analyse_intra_chroma( h, a ); | |
| + mb_analyse_intra_chroma( h, a ); | |
| } | |
| } | |
| } | |
| diff -ur x264-go/x264c/external/x264/encoder/analyse.h x264-go.new/x264c/external/x264/encoder/analyse.h | |
| --- x264-go/x264c/external/x264/encoder/analyse.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/analyse.h 2020-06-06 15:20:58.697039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * analyse.h: macroblock analysis | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -24,21 +24,32 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_ANALYSE_H | |
| -#define X264_ANALYSE_H | |
| +#ifndef X264_ENCODER_ANALYSE_H | |
| +#define X264_ENCODER_ANALYSE_H | |
| +#define x264_analyse_init_costs x264_template(analyse_init_costs) | |
| int x264_analyse_init_costs( x264_t *h ); | |
| +#define x264_analyse_free_costs x264_template(analyse_free_costs) | |
| void x264_analyse_free_costs( x264_t *h ); | |
| +#define x264_analyse_weight_frame x264_template(analyse_weight_frame) | |
| void x264_analyse_weight_frame( x264_t *h, int end ); | |
| +#define x264_macroblock_analyse x264_template(macroblock_analyse) | |
| void x264_macroblock_analyse( x264_t *h ); | |
| +#define x264_slicetype_decide x264_template(slicetype_decide) | |
| void x264_slicetype_decide( x264_t *h ); | |
| +#define x264_slicetype_analyse x264_template(slicetype_analyse) | |
| void x264_slicetype_analyse( x264_t *h, int intra_minigop ); | |
| +#define x264_lookahead_init x264_template(lookahead_init) | |
| int x264_lookahead_init( x264_t *h, int i_slicetype_length ); | |
| +#define x264_lookahead_is_empty x264_template(lookahead_is_empty) | |
| int x264_lookahead_is_empty( x264_t *h ); | |
| +#define x264_lookahead_put_frame x264_template(lookahead_put_frame) | |
| void x264_lookahead_put_frame( x264_t *h, x264_frame_t *frame ); | |
| +#define x264_lookahead_get_frames x264_template(lookahead_get_frames) | |
| void x264_lookahead_get_frames( x264_t *h ); | |
| +#define x264_lookahead_delete x264_template(lookahead_delete) | |
| void x264_lookahead_delete( x264_t *h ); | |
| #endif | |
| Only in x264-go.new/x264c/external/x264/encoder: api.c | |
| diff -ur x264-go/x264c/external/x264/encoder/cabac.c x264-go.new/x264c/external/x264/encoder/cabac.c | |
| --- x264-go/x264c/external/x264/encoder/cabac.c 2018-02-15 15:58:53.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/cabac.c 2020-06-06 15:20:58.697039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cabac.c: cabac bitstream writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -32,8 +32,8 @@ | |
| #define RDO_SKIP_BS 0 | |
| #endif | |
| -static inline void x264_cabac_mb_type_intra( x264_t *h, x264_cabac_t *cb, int i_mb_type, | |
| - int ctx0, int ctx1, int ctx2, int ctx3, int ctx4, int ctx5 ) | |
| +static inline void cabac_mb_type_intra( x264_t *h, x264_cabac_t *cb, int i_mb_type, | |
| + int ctx0, int ctx1, int ctx2, int ctx3, int ctx4, int ctx5 ) | |
| { | |
| if( i_mb_type == I_4x4 || i_mb_type == I_8x8 ) | |
| { | |
| @@ -67,7 +67,7 @@ | |
| } | |
| #if !RDO_SKIP_BS | |
| -static void x264_cabac_field_decoding_flag( x264_t *h, x264_cabac_t *cb ) | |
| +static void cabac_field_decoding_flag( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int ctx = 0; | |
| ctx += h->mb.field_decoding_flag & !!h->mb.i_mb_x; | |
| @@ -80,7 +80,7 @@ | |
| } | |
| #endif | |
| -static void x264_cabac_intra4x4_pred_mode( x264_cabac_t *cb, int i_pred, int i_mode ) | |
| +static void cabac_intra4x4_pred_mode( x264_cabac_t *cb, int i_pred, int i_mode ) | |
| { | |
| if( i_pred == i_mode ) | |
| x264_cabac_encode_decision( cb, 68, 1 ); | |
| @@ -95,7 +95,7 @@ | |
| } | |
| } | |
| -static void x264_cabac_intra_chroma_pred_mode( x264_t *h, x264_cabac_t *cb ) | |
| +static void cabac_intra_chroma_pred_mode( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int i_mode = x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode]; | |
| int ctx = 0; | |
| @@ -115,7 +115,7 @@ | |
| } | |
| } | |
| -static void x264_cabac_cbp_luma( x264_t *h, x264_cabac_t *cb ) | |
| +static void cabac_cbp_luma( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int cbp = h->mb.i_cbp_luma; | |
| int cbp_l = h->mb.cache.i_cbp_left; | |
| @@ -126,7 +126,7 @@ | |
| x264_cabac_encode_decision_noup( cb, 76 - ((cbp >> 2) & 1) - ((cbp >> 0) & 2), (cbp >> 3) & 1 ); | |
| } | |
| -static void x264_cabac_cbp_chroma( x264_t *h, x264_cabac_t *cb ) | |
| +static void cabac_cbp_chroma( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int cbp_a = h->mb.cache.i_cbp_left & 0x30; | |
| int cbp_b = h->mb.cache.i_cbp_top & 0x30; | |
| @@ -147,7 +147,7 @@ | |
| } | |
| } | |
| -static void x264_cabac_qp_delta( x264_t *h, x264_cabac_t *cb ) | |
| +static void cabac_qp_delta( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int i_dqp = h->mb.i_qp - h->mb.i_last_qp; | |
| int ctx; | |
| @@ -195,7 +195,7 @@ | |
| } | |
| #endif | |
| -static inline void x264_cabac_subpartition_p( x264_cabac_t *cb, int i_sub ) | |
| +static inline void cabac_subpartition_p( x264_cabac_t *cb, int i_sub ) | |
| { | |
| if( i_sub == D_L0_8x8 ) | |
| { | |
| @@ -212,7 +212,7 @@ | |
| } | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_subpartition_b( x264_cabac_t *cb, int i_sub ) | |
| +static ALWAYS_INLINE void cabac_subpartition_b( x264_cabac_t *cb, int i_sub ) | |
| { | |
| if( i_sub == D_DIRECT_8x8 ) | |
| { | |
| @@ -232,13 +232,13 @@ | |
| x264_cabac_encode_decision( cb, 39, i_sub == D_L1_8x8 ); | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_transform_size( x264_t *h, x264_cabac_t *cb ) | |
| +static ALWAYS_INLINE void cabac_transform_size( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| int ctx = 399 + h->mb.cache.i_neighbour_transform_size; | |
| x264_cabac_encode_decision_noup( cb, ctx, h->mb.b_transform_8x8 ); | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_ref_internal( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int bframe ) | |
| +static ALWAYS_INLINE void cabac_ref_internal( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int bframe ) | |
| { | |
| const int i8 = x264_scan8[idx]; | |
| const int i_refa = h->mb.cache.ref[i_list][i8 - 1]; | |
| @@ -258,16 +258,16 @@ | |
| x264_cabac_encode_decision( cb, 54 + ctx, 0 ); | |
| } | |
| -static NOINLINE void x264_cabac_ref_p( x264_t *h, x264_cabac_t *cb, int idx ) | |
| +static NOINLINE void cabac_ref_p( x264_t *h, x264_cabac_t *cb, int idx ) | |
| { | |
| - x264_cabac_ref_internal( h, cb, 0, idx, 0 ); | |
| + cabac_ref_internal( h, cb, 0, idx, 0 ); | |
| } | |
| -static NOINLINE void x264_cabac_ref_b( x264_t *h, x264_cabac_t *cb, int i_list, int idx ) | |
| +static NOINLINE void cabac_ref_b( x264_t *h, x264_cabac_t *cb, int i_list, int idx ) | |
| { | |
| - x264_cabac_ref_internal( h, cb, i_list, idx, 1 ); | |
| + cabac_ref_internal( h, cb, i_list, idx, 1 ); | |
| } | |
| -static ALWAYS_INLINE int x264_cabac_mvd_cpn( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int l, int mvd, int ctx ) | |
| +static ALWAYS_INLINE int cabac_mvd_cpn( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int l, int mvd, int ctx ) | |
| { | |
| int ctxbase = l ? 47 : 40; | |
| @@ -326,7 +326,7 @@ | |
| return X264_MIN( i_abs, 66 ); | |
| } | |
| -static NOINLINE uint16_t x264_cabac_mvd( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int width ) | |
| +static NOINLINE uint16_t cabac_mvd( x264_t *h, x264_cabac_t *cb, int i_list, int idx, int width ) | |
| { | |
| ALIGNED_4( int16_t mvp[2] ); | |
| int mdx, mdy; | |
| @@ -339,46 +339,46 @@ | |
| h->mb.cache.mvd[i_list][x264_scan8[idx] - 8]); | |
| /* encode */ | |
| - mdx = x264_cabac_mvd_cpn( h, cb, i_list, idx, 0, mdx, amvd&0xFF ); | |
| - mdy = x264_cabac_mvd_cpn( h, cb, i_list, idx, 1, mdy, amvd>>8 ); | |
| + mdx = cabac_mvd_cpn( h, cb, i_list, idx, 0, mdx, amvd&0xFF ); | |
| + mdy = cabac_mvd_cpn( h, cb, i_list, idx, 1, mdy, amvd>>8 ); | |
| return pack8to16(mdx,mdy); | |
| } | |
| -#define x264_cabac_mvd(h,cb,i_list,idx,width,height)\ | |
| +#define cabac_mvd(h,cb,i_list,idx,width,height)\ | |
| do\ | |
| {\ | |
| - uint16_t mvd = x264_cabac_mvd(h,cb,i_list,idx,width);\ | |
| + uint16_t mvd = cabac_mvd(h,cb,i_list,idx,width);\ | |
| x264_macroblock_cache_mvd( h, block_idx_x[idx], block_idx_y[idx], width, height, i_list, mvd );\ | |
| } while( 0 ) | |
| -static inline void x264_cabac_8x8_mvd( x264_t *h, x264_cabac_t *cb, int i ) | |
| +static inline void cabac_8x8_mvd( x264_t *h, x264_cabac_t *cb, int i ) | |
| { | |
| switch( h->mb.i_sub_partition[i] ) | |
| { | |
| case D_L0_8x8: | |
| - x264_cabac_mvd( h, cb, 0, 4*i, 2, 2 ); | |
| + cabac_mvd( h, cb, 0, 4*i, 2, 2 ); | |
| break; | |
| case D_L0_8x4: | |
| - x264_cabac_mvd( h, cb, 0, 4*i+0, 2, 1 ); | |
| - x264_cabac_mvd( h, cb, 0, 4*i+2, 2, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+0, 2, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+2, 2, 1 ); | |
| break; | |
| case D_L0_4x8: | |
| - x264_cabac_mvd( h, cb, 0, 4*i+0, 1, 2 ); | |
| - x264_cabac_mvd( h, cb, 0, 4*i+1, 1, 2 ); | |
| + cabac_mvd( h, cb, 0, 4*i+0, 1, 2 ); | |
| + cabac_mvd( h, cb, 0, 4*i+1, 1, 2 ); | |
| break; | |
| case D_L0_4x4: | |
| - x264_cabac_mvd( h, cb, 0, 4*i+0, 1, 1 ); | |
| - x264_cabac_mvd( h, cb, 0, 4*i+1, 1, 1 ); | |
| - x264_cabac_mvd( h, cb, 0, 4*i+2, 1, 1 ); | |
| - x264_cabac_mvd( h, cb, 0, 4*i+3, 1, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+0, 1, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+1, 1, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+2, 1, 1 ); | |
| + cabac_mvd( h, cb, 0, 4*i+3, 1, 1 ); | |
| break; | |
| default: | |
| assert(0); | |
| } | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_mb_header_i( x264_t *h, x264_cabac_t *cb, int i_mb_type, int slice_type, int chroma ) | |
| +static ALWAYS_INLINE void cabac_mb_header_i( x264_t *h, x264_cabac_t *cb, int i_mb_type, int slice_type, int chroma ) | |
| { | |
| if( slice_type == SLICE_TYPE_I ) | |
| { | |
| @@ -388,7 +388,7 @@ | |
| if( (h->mb.i_neighbour & MB_TOP) && h->mb.i_mb_type_top != I_4x4 ) | |
| ctx++; | |
| - x264_cabac_mb_type_intra( h, cb, i_mb_type, 3+ctx, 3+3, 3+4, 3+5, 3+6, 3+7 ); | |
| + cabac_mb_type_intra( h, cb, i_mb_type, 3+ctx, 3+3, 3+4, 3+5, 3+6, 3+7 ); | |
| } | |
| else if( slice_type == SLICE_TYPE_P ) | |
| { | |
| @@ -396,7 +396,7 @@ | |
| x264_cabac_encode_decision_noup( cb, 14, 1 ); | |
| /* suffix */ | |
| - x264_cabac_mb_type_intra( h, cb, i_mb_type, 17+0, 17+1, 17+2, 17+2, 17+3, 17+3 ); | |
| + cabac_mb_type_intra( h, cb, i_mb_type, 17+0, 17+1, 17+2, 17+2, 17+3, 17+3 ); | |
| } | |
| else if( slice_type == SLICE_TYPE_B ) | |
| { | |
| @@ -408,7 +408,7 @@ | |
| x264_cabac_encode_decision( cb, 27+5, 1 ); | |
| /* suffix */ | |
| - x264_cabac_mb_type_intra( h, cb, i_mb_type, 32+0, 32+1, 32+2, 32+2, 32+3, 32+3 ); | |
| + cabac_mb_type_intra( h, cb, i_mb_type, 32+0, 32+1, 32+2, 32+2, 32+3, 32+3 ); | |
| } | |
| if( i_mb_type == I_PCM ) | |
| @@ -417,22 +417,22 @@ | |
| if( i_mb_type != I_16x16 ) | |
| { | |
| if( h->pps->b_transform_8x8_mode ) | |
| - x264_cabac_transform_size( h, cb ); | |
| + cabac_transform_size( h, cb ); | |
| int di = h->mb.b_transform_8x8 ? 4 : 1; | |
| for( int i = 0; i < 16; i += di ) | |
| { | |
| const int i_pred = x264_mb_predict_intra4x4_mode( h, i ); | |
| const int i_mode = x264_mb_pred_mode4x4_fix( h->mb.cache.intra4x4_pred_mode[x264_scan8[i]] ); | |
| - x264_cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| + cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| } | |
| } | |
| if( chroma ) | |
| - x264_cabac_intra_chroma_pred_mode( h, cb ); | |
| + cabac_intra_chroma_pred_mode( h, cb ); | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_mb_header_p( x264_t *h, x264_cabac_t *cb, int i_mb_type, int chroma ) | |
| +static ALWAYS_INLINE void cabac_mb_header_p( x264_t *h, x264_cabac_t *cb, int i_mb_type, int chroma ) | |
| { | |
| if( i_mb_type == P_L0 ) | |
| { | |
| @@ -442,8 +442,8 @@ | |
| x264_cabac_encode_decision_noup( cb, 15, 0 ); | |
| x264_cabac_encode_decision_noup( cb, 16, 0 ); | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| - x264_cabac_ref_p( h, cb, 0 ); | |
| - x264_cabac_mvd( h, cb, 0, 0, 4, 4 ); | |
| + cabac_ref_p( h, cb, 0 ); | |
| + cabac_mvd( h, cb, 0, 0, 4, 4 ); | |
| } | |
| else if( h->mb.i_partition == D_16x8 ) | |
| { | |
| @@ -451,11 +451,11 @@ | |
| x264_cabac_encode_decision_noup( cb, 17, 1 ); | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| { | |
| - x264_cabac_ref_p( h, cb, 0 ); | |
| - x264_cabac_ref_p( h, cb, 8 ); | |
| + cabac_ref_p( h, cb, 0 ); | |
| + cabac_ref_p( h, cb, 8 ); | |
| } | |
| - x264_cabac_mvd( h, cb, 0, 0, 4, 2 ); | |
| - x264_cabac_mvd( h, cb, 0, 8, 4, 2 ); | |
| + cabac_mvd( h, cb, 0, 0, 4, 2 ); | |
| + cabac_mvd( h, cb, 0, 8, 4, 2 ); | |
| } | |
| else //if( h->mb.i_partition == D_8x16 ) | |
| { | |
| @@ -463,11 +463,11 @@ | |
| x264_cabac_encode_decision_noup( cb, 17, 0 ); | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| { | |
| - x264_cabac_ref_p( h, cb, 0 ); | |
| - x264_cabac_ref_p( h, cb, 4 ); | |
| + cabac_ref_p( h, cb, 0 ); | |
| + cabac_ref_p( h, cb, 4 ); | |
| } | |
| - x264_cabac_mvd( h, cb, 0, 0, 2, 4 ); | |
| - x264_cabac_mvd( h, cb, 0, 4, 2, 4 ); | |
| + cabac_mvd( h, cb, 0, 0, 2, 4 ); | |
| + cabac_mvd( h, cb, 0, 4, 2, 4 ); | |
| } | |
| } | |
| else if( i_mb_type == P_8x8 ) | |
| @@ -478,25 +478,25 @@ | |
| /* sub mb type */ | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_cabac_subpartition_p( cb, h->mb.i_sub_partition[i] ); | |
| + cabac_subpartition_p( cb, h->mb.i_sub_partition[i] ); | |
| /* ref 0 */ | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| { | |
| - x264_cabac_ref_p( h, cb, 0 ); | |
| - x264_cabac_ref_p( h, cb, 4 ); | |
| - x264_cabac_ref_p( h, cb, 8 ); | |
| - x264_cabac_ref_p( h, cb, 12 ); | |
| + cabac_ref_p( h, cb, 0 ); | |
| + cabac_ref_p( h, cb, 4 ); | |
| + cabac_ref_p( h, cb, 8 ); | |
| + cabac_ref_p( h, cb, 12 ); | |
| } | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_cabac_8x8_mvd( h, cb, i ); | |
| + cabac_8x8_mvd( h, cb, i ); | |
| } | |
| else /* intra */ | |
| - x264_cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_P, chroma ); | |
| + cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_P, chroma ); | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_mb_header_b( x264_t *h, x264_cabac_t *cb, int i_mb_type, int chroma ) | |
| +static ALWAYS_INLINE void cabac_mb_header_b( x264_t *h, x264_cabac_t *cb, int i_mb_type, int chroma ) | |
| { | |
| int ctx = 0; | |
| if( (h->mb.i_neighbour & MB_LEFT) && h->mb.i_mb_type_left[0] != B_SKIP && h->mb.i_mb_type_left[0] != B_DIRECT ) | |
| @@ -521,26 +521,26 @@ | |
| /* sub mb type */ | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_cabac_subpartition_b( cb, h->mb.i_sub_partition[i] ); | |
| + cabac_subpartition_b( cb, h->mb.i_sub_partition[i] ); | |
| /* ref */ | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[0][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cabac_ref_b( h, cb, 0, 4*i ); | |
| + cabac_ref_b( h, cb, 0, 4*i ); | |
| if( h->mb.pic.i_fref[1] > 1 ) | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[1][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cabac_ref_b( h, cb, 1, 4*i ); | |
| + cabac_ref_b( h, cb, 1, 4*i ); | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[0][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cabac_mvd( h, cb, 0, 4*i, 2, 2 ); | |
| + cabac_mvd( h, cb, 0, 4*i, 2, 2 ); | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[1][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cabac_mvd( h, cb, 1, 4*i, 2, 2 ); | |
| + cabac_mvd( h, cb, 1, 4*i, 2, 2 ); | |
| } | |
| else if( i_mb_type >= B_L0_L0 && i_mb_type <= B_BI_BI ) | |
| { | |
| @@ -576,40 +576,40 @@ | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| { | |
| if( b_list[0][0] ) | |
| - x264_cabac_ref_b( h, cb, 0, 0 ); | |
| + cabac_ref_b( h, cb, 0, 0 ); | |
| if( b_list[0][1] && h->mb.i_partition != D_16x16 ) | |
| - x264_cabac_ref_b( h, cb, 0, 8 >> (h->mb.i_partition == D_8x16) ); | |
| + cabac_ref_b( h, cb, 0, 8 >> (h->mb.i_partition == D_8x16) ); | |
| } | |
| if( h->mb.pic.i_fref[1] > 1 ) | |
| { | |
| if( b_list[1][0] ) | |
| - x264_cabac_ref_b( h, cb, 1, 0 ); | |
| + cabac_ref_b( h, cb, 1, 0 ); | |
| if( b_list[1][1] && h->mb.i_partition != D_16x16 ) | |
| - x264_cabac_ref_b( h, cb, 1, 8 >> (h->mb.i_partition == D_8x16) ); | |
| + cabac_ref_b( h, cb, 1, 8 >> (h->mb.i_partition == D_8x16) ); | |
| } | |
| for( int i_list = 0; i_list < 2; i_list++ ) | |
| { | |
| if( h->mb.i_partition == D_16x16 ) | |
| { | |
| - if( b_list[i_list][0] ) x264_cabac_mvd( h, cb, i_list, 0, 4, 4 ); | |
| + if( b_list[i_list][0] ) cabac_mvd( h, cb, i_list, 0, 4, 4 ); | |
| } | |
| else if( h->mb.i_partition == D_16x8 ) | |
| { | |
| - if( b_list[i_list][0] ) x264_cabac_mvd( h, cb, i_list, 0, 4, 2 ); | |
| - if( b_list[i_list][1] ) x264_cabac_mvd( h, cb, i_list, 8, 4, 2 ); | |
| + if( b_list[i_list][0] ) cabac_mvd( h, cb, i_list, 0, 4, 2 ); | |
| + if( b_list[i_list][1] ) cabac_mvd( h, cb, i_list, 8, 4, 2 ); | |
| } | |
| else //if( h->mb.i_partition == D_8x16 ) | |
| { | |
| - if( b_list[i_list][0] ) x264_cabac_mvd( h, cb, i_list, 0, 2, 4 ); | |
| - if( b_list[i_list][1] ) x264_cabac_mvd( h, cb, i_list, 4, 2, 4 ); | |
| + if( b_list[i_list][0] ) cabac_mvd( h, cb, i_list, 0, 2, 4 ); | |
| + if( b_list[i_list][1] ) cabac_mvd( h, cb, i_list, 4, 2, 4 ); | |
| } | |
| } | |
| } | |
| else /* intra */ | |
| - x264_cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_B, chroma ); | |
| + cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_B, chroma ); | |
| } | |
| -static int ALWAYS_INLINE x264_cabac_cbf_ctxidxinc( x264_t *h, int i_cat, int i_idx, int b_intra, int b_dc ) | |
| +static ALWAYS_INLINE int cabac_cbf_ctxidxinc( x264_t *h, int i_cat, int i_idx, int b_intra, int b_dc ) | |
| { | |
| static const uint16_t base_ctx[14] = {85,89,93,97,101,1012,460,464,468,1016,472,476,480,1020}; | |
| @@ -644,53 +644,6 @@ | |
| } | |
| } | |
| -#if !RDO_SKIP_BS | |
| -extern const uint8_t x264_significant_coeff_flag_offset_8x8[2][64]; | |
| -extern const uint8_t x264_last_coeff_flag_offset_8x8[63]; | |
| -extern const uint8_t x264_coeff_flag_offset_chroma_422_dc[7]; | |
| -extern const uint16_t x264_significant_coeff_flag_offset[2][16]; | |
| -extern const uint16_t x264_last_coeff_flag_offset[2][16]; | |
| -extern const uint16_t x264_coeff_abs_level_m1_offset[16]; | |
| -extern const uint8_t x264_count_cat_m1[14]; | |
| -#else | |
| -/* Padded to [64] for easier addressing */ | |
| -const uint8_t x264_significant_coeff_flag_offset_8x8[2][64] = | |
| -{{ | |
| - 0, 1, 2, 3, 4, 5, 5, 4, 4, 3, 3, 4, 4, 4, 5, 5, | |
| - 4, 4, 4, 4, 3, 3, 6, 7, 7, 7, 8, 9,10, 9, 8, 7, | |
| - 7, 6,11,12,13,11, 6, 7, 8, 9,14,10, 9, 8, 6,11, | |
| - 12,13,11, 6, 9,14,10, 9,11,12,13,11,14,10,12 | |
| -},{ | |
| - 0, 1, 1, 2, 2, 3, 3, 4, 5, 6, 7, 7, 7, 8, 4, 5, | |
| - 6, 9,10,10, 8,11,12,11, 9, 9,10,10, 8,11,12,11, | |
| - 9, 9,10,10, 8,11,12,11, 9, 9,10,10, 8,13,13, 9, | |
| - 9,10,10, 8,13,13, 9, 9,10,10,14,14,14,14,14 | |
| -}}; | |
| -const uint8_t x264_last_coeff_flag_offset_8x8[63] = | |
| -{ | |
| - 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, | |
| - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, | |
| - 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, | |
| - 5, 5, 5, 5, 6, 6, 6, 6, 7, 7, 7, 7, 8, 8, 8 | |
| -}; | |
| -const uint8_t x264_coeff_flag_offset_chroma_422_dc[7] = { 0, 0, 1, 1, 2, 2, 2 }; /* MIN( i/2, 2 ) */ | |
| -const uint16_t x264_significant_coeff_flag_offset[2][16] = | |
| -{ | |
| - { 105+0, 105+15, 105+29, 105+44, 105+47, 402, 484+0, 484+15, 484+29, 660, 528+0, 528+15, 528+29, 718, 0, 0 }, | |
| - { 277+0, 277+15, 277+29, 277+44, 277+47, 436, 776+0, 776+15, 776+29, 675, 820+0, 820+15, 820+29, 733, 0, 0 } | |
| -}; | |
| -const uint16_t x264_last_coeff_flag_offset[2][16] = | |
| -{ | |
| - { 166+0, 166+15, 166+29, 166+44, 166+47, 417, 572+0, 572+15, 572+29, 690, 616+0, 616+15, 616+29, 748, 0, 0 }, | |
| - { 338+0, 338+15, 338+29, 338+44, 338+47, 451, 864+0, 864+15, 864+29, 699, 908+0, 908+15, 908+29, 757, 0, 0 } | |
| -}; | |
| -const uint16_t x264_coeff_abs_level_m1_offset[16] = | |
| -{ | |
| - 227+0, 227+10, 227+20, 227+30, 227+39, 426, 952+0, 952+10, 952+20, 708, 982+0, 982+10, 982+20, 766 | |
| -}; | |
| -const uint8_t x264_count_cat_m1[14] = {15, 14, 15, 3, 14, 63, 15, 14, 15, 63, 15, 14, 15, 63}; | |
| -#endif | |
| - | |
| // node ctx: 0..3: abslevel1 (with abslevelgt1 == 0). | |
| // 4..7: abslevelgt1 + 3 (and abslevel1 doesn't matter). | |
| /* map node ctx => cabac ctx for level=1 */ | |
| @@ -709,7 +662,7 @@ | |
| }; | |
| #if !RDO_SKIP_BS | |
| -static ALWAYS_INLINE void x264_cabac_block_residual_internal( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l, int chroma422dc ) | |
| +static ALWAYS_INLINE void cabac_block_residual_internal( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l, int chroma422dc ) | |
| { | |
| int ctx_sig = x264_significant_coeff_flag_offset[MB_INTERLACED][ctx_block_cat]; | |
| int ctx_last = x264_last_coeff_flag_offset[MB_INTERLACED][ctx_block_cat]; | |
| @@ -796,10 +749,10 @@ | |
| void x264_cabac_block_residual_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| - x264_cabac_block_residual_internal( h, cb, ctx_block_cat, l, 0 ); | |
| + cabac_block_residual_internal( h, cb, ctx_block_cat, l, 0 ); | |
| } | |
| -static void ALWAYS_INLINE x264_cabac_block_residual( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| +static ALWAYS_INLINE void cabac_block_residual( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| #if ARCH_X86_64 && HAVE_MMX && !defined( __MACH__ ) | |
| h->bsf.cabac_block_residual_internal( l, MB_INTERLACED, ctx_block_cat, cb ); | |
| @@ -807,19 +760,19 @@ | |
| x264_cabac_block_residual_c( h, cb, ctx_block_cat, l ); | |
| #endif | |
| } | |
| -static void x264_cabac_block_residual_422_dc( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| +static void cabac_block_residual_422_dc( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| /* Template a version specifically for chroma 4:2:2 DC in order to avoid | |
| * slowing down everything else due to the added complexity. */ | |
| - x264_cabac_block_residual_internal( h, cb, DCT_CHROMA_DC, l, 1 ); | |
| + cabac_block_residual_internal( h, cb, DCT_CHROMA_DC, l, 1 ); | |
| } | |
| -#define x264_cabac_block_residual_8x8( h, cb, cat, l ) x264_cabac_block_residual( h, cb, cat, l ) | |
| +#define cabac_block_residual_8x8( h, cb, cat, l ) cabac_block_residual( h, cb, cat, l ) | |
| #else | |
| /* Faster RDO by merging sigmap and level coding. Note that for 8x8dct and chroma 4:2:2 dc this is | |
| * slightly incorrect because the sigmap is not reversible (contexts are repeated). However, there | |
| * is nearly no quality penalty for this (~0.001db) and the speed boost (~30%) is worth it. */ | |
| -static void ALWAYS_INLINE x264_cabac_block_residual_internal( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l, int b_8x8, int chroma422dc ) | |
| +static ALWAYS_INLINE void cabac_block_residual_internal( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l, int b_8x8, int chroma422dc ) | |
| { | |
| const uint8_t *sig_offset = x264_significant_coeff_flag_offset_8x8[MB_INTERLACED]; | |
| int ctx_sig = x264_significant_coeff_flag_offset[MB_INTERLACED][ctx_block_cat]; | |
| @@ -906,14 +859,14 @@ | |
| void x264_cabac_block_residual_8x8_rd_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| - x264_cabac_block_residual_internal( h, cb, ctx_block_cat, l, 1, 0 ); | |
| + cabac_block_residual_internal( h, cb, ctx_block_cat, l, 1, 0 ); | |
| } | |
| void x264_cabac_block_residual_rd_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| - x264_cabac_block_residual_internal( h, cb, ctx_block_cat, l, 0, 0 ); | |
| + cabac_block_residual_internal( h, cb, ctx_block_cat, l, 0, 0 ); | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_block_residual_8x8( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| +static ALWAYS_INLINE void cabac_block_residual_8x8( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| #if ARCH_X86_64 && HAVE_MMX && !defined( __MACH__ ) | |
| h->bsf.cabac_block_residual_8x8_rd_internal( l, MB_INTERLACED, ctx_block_cat, cb ); | |
| @@ -921,7 +874,7 @@ | |
| x264_cabac_block_residual_8x8_rd_c( h, cb, ctx_block_cat, l ); | |
| #endif | |
| } | |
| -static ALWAYS_INLINE void x264_cabac_block_residual( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| +static ALWAYS_INLINE void cabac_block_residual( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| #if ARCH_X86_64 && HAVE_MMX && !defined( __MACH__ ) | |
| h->bsf.cabac_block_residual_rd_internal( l, MB_INTERLACED, ctx_block_cat, cb ); | |
| @@ -930,38 +883,38 @@ | |
| #endif | |
| } | |
| -static void x264_cabac_block_residual_422_dc( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| +static void cabac_block_residual_422_dc( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ) | |
| { | |
| - x264_cabac_block_residual_internal( h, cb, DCT_CHROMA_DC, l, 0, 1 ); | |
| + cabac_block_residual_internal( h, cb, DCT_CHROMA_DC, l, 0, 1 ); | |
| } | |
| #endif | |
| -#define x264_cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, b_dc, name )\ | |
| +#define cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, b_dc, name )\ | |
| do\ | |
| {\ | |
| - int ctxidxinc = x264_cabac_cbf_ctxidxinc( h, ctx_block_cat, i_idx, b_intra, b_dc );\ | |
| + int ctxidxinc = cabac_cbf_ctxidxinc( h, ctx_block_cat, i_idx, b_intra, b_dc );\ | |
| if( h->mb.cache.non_zero_count[x264_scan8[i_idx]] )\ | |
| {\ | |
| x264_cabac_encode_decision( cb, ctxidxinc, 1 );\ | |
| - x264_cabac_block_residual##name( h, cb, ctx_block_cat, l );\ | |
| + cabac_block_residual##name( h, cb, ctx_block_cat, l );\ | |
| }\ | |
| else\ | |
| x264_cabac_encode_decision( cb, ctxidxinc, 0 );\ | |
| } while( 0 ) | |
| -#define x264_cabac_block_residual_dc_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| - x264_cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 1, ) | |
| +#define cabac_block_residual_dc_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| + cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 1, ) | |
| -#define x264_cabac_block_residual_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| - x264_cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 0, ) | |
| +#define cabac_block_residual_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| + cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 0, ) | |
| -#define x264_cabac_block_residual_8x8_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| - x264_cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 0, _8x8 ) | |
| +#define cabac_block_residual_8x8_cbf( h, cb, ctx_block_cat, i_idx, l, b_intra )\ | |
| + cabac_block_residual_cbf_internal( h, cb, ctx_block_cat, i_idx, l, b_intra, 0, _8x8 ) | |
| -#define x264_cabac_block_residual_422_dc_cbf( h, cb, ch, b_intra )\ | |
| - x264_cabac_block_residual_cbf_internal( h, cb, DCT_CHROMA_DC, CHROMA_DC+(ch), h->dct.chroma_dc[ch], b_intra, 1, _422_dc ) | |
| +#define cabac_block_residual_422_dc_cbf( h, cb, ch, b_intra )\ | |
| + cabac_block_residual_cbf_internal( h, cb, DCT_CHROMA_DC, CHROMA_DC+(ch), h->dct.chroma_dc[ch], b_intra, 1, _422_dc ) | |
| -static ALWAYS_INLINE void x264_macroblock_write_cabac_internal( x264_t *h, x264_cabac_t *cb, int plane_count, int chroma ) | |
| +static ALWAYS_INLINE void macroblock_write_cabac_internal( x264_t *h, x264_cabac_t *cb, int plane_count, int chroma ) | |
| { | |
| const int i_mb_type = h->mb.i_type; | |
| @@ -972,16 +925,16 @@ | |
| if( SLICE_MBAFF && | |
| (!(h->mb.i_mb_y & 1) || IS_SKIP(h->mb.type[h->mb.i_mb_xy - h->mb.i_mb_stride])) ) | |
| { | |
| - x264_cabac_field_decoding_flag( h, cb ); | |
| + cabac_field_decoding_flag( h, cb ); | |
| } | |
| #endif | |
| if( h->sh.i_type == SLICE_TYPE_P ) | |
| - x264_cabac_mb_header_p( h, cb, i_mb_type, chroma ); | |
| + cabac_mb_header_p( h, cb, i_mb_type, chroma ); | |
| else if( h->sh.i_type == SLICE_TYPE_B ) | |
| - x264_cabac_mb_header_b( h, cb, i_mb_type, chroma ); | |
| + cabac_mb_header_b( h, cb, i_mb_type, chroma ); | |
| else //if( h->sh.i_type == SLICE_TYPE_I ) | |
| - x264_cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_I, chroma ); | |
| + cabac_mb_header_i( h, cb, i_mb_type, SLICE_TYPE_I, chroma ); | |
| #if !RDO_SKIP_BS | |
| i_mb_pos_tex = x264_cabac_pos( cb ); | |
| @@ -1012,20 +965,20 @@ | |
| if( i_mb_type != I_16x16 ) | |
| { | |
| - x264_cabac_cbp_luma( h, cb ); | |
| + cabac_cbp_luma( h, cb ); | |
| if( chroma ) | |
| - x264_cabac_cbp_chroma( h, cb ); | |
| + cabac_cbp_chroma( h, cb ); | |
| } | |
| if( x264_mb_transform_8x8_allowed( h ) && h->mb.i_cbp_luma ) | |
| { | |
| - x264_cabac_transform_size( h, cb ); | |
| + cabac_transform_size( h, cb ); | |
| } | |
| if( h->mb.i_cbp_luma || (chroma && h->mb.i_cbp_chroma) || i_mb_type == I_16x16 ) | |
| { | |
| const int b_intra = IS_INTRA( i_mb_type ); | |
| - x264_cabac_qp_delta( h, cb ); | |
| + cabac_qp_delta( h, cb ); | |
| /* write residual */ | |
| if( i_mb_type == I_16x16 ) | |
| @@ -1033,12 +986,12 @@ | |
| /* DC Luma */ | |
| for( int p = 0; p < plane_count; p++ ) | |
| { | |
| - x264_cabac_block_residual_dc_cbf( h, cb, ctx_cat_plane[DCT_LUMA_DC][p], LUMA_DC+p, h->dct.luma16x16_dc[p], 1 ); | |
| + cabac_block_residual_dc_cbf( h, cb, ctx_cat_plane[DCT_LUMA_DC][p], LUMA_DC+p, h->dct.luma16x16_dc[p], 1 ); | |
| /* AC Luma */ | |
| if( h->mb.i_cbp_luma ) | |
| for( int i = p*16; i < p*16+16; i++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_AC][p], i, h->dct.luma4x4[i]+1, 1 ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_AC][p], i, h->dct.luma4x4[i]+1, 1 ); | |
| } | |
| } | |
| else if( h->mb.b_transform_8x8 ) | |
| @@ -1086,14 +1039,14 @@ | |
| for( int p = 0; p < 3; p++ ) | |
| FOREACH_BIT( i, 0, h->mb.i_cbp_luma ) | |
| - x264_cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i*4+p*16, h->dct.luma8x8[i+p*4], b_intra ); | |
| + cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i*4+p*16, h->dct.luma8x8[i+p*4], b_intra ); | |
| MUNGE_8x8_NNZ( RESTORE ) | |
| } | |
| else | |
| { | |
| FOREACH_BIT( i, 0, h->mb.i_cbp_luma ) | |
| - x264_cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i] ); | |
| + cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i] ); | |
| } | |
| } | |
| else | |
| @@ -1101,20 +1054,20 @@ | |
| for( int p = 0; p < plane_count; p++ ) | |
| FOREACH_BIT( i8x8, 0, h->mb.i_cbp_luma ) | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i+i8x8*4+p*16, h->dct.luma4x4[i+i8x8*4+p*16], b_intra ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i+i8x8*4+p*16, h->dct.luma4x4[i+i8x8*4+p*16], b_intra ); | |
| } | |
| if( chroma && h->mb.i_cbp_chroma ) /* Chroma DC residual present */ | |
| { | |
| if( CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| - x264_cabac_block_residual_422_dc_cbf( h, cb, 0, b_intra ); | |
| - x264_cabac_block_residual_422_dc_cbf( h, cb, 1, b_intra ); | |
| + cabac_block_residual_422_dc_cbf( h, cb, 0, b_intra ); | |
| + cabac_block_residual_422_dc_cbf( h, cb, 1, b_intra ); | |
| } | |
| else | |
| { | |
| - x264_cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+0, h->dct.chroma_dc[0], b_intra ); | |
| - x264_cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+1, h->dct.chroma_dc[1], b_intra ); | |
| + cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+0, h->dct.chroma_dc[0], b_intra ); | |
| + cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+1, h->dct.chroma_dc[1], b_intra ); | |
| } | |
| if( h->mb.i_cbp_chroma == 2 ) /* Chroma AC residual present */ | |
| @@ -1122,7 +1075,7 @@ | |
| int step = 8 << CHROMA_V_SHIFT; | |
| for( int i = 16; i < 3*16; i += step ) | |
| for( int j = i; j < i+4; j++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, j, h->dct.luma4x4[j]+1, b_intra ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, j, h->dct.luma4x4[j]+1, b_intra ); | |
| } | |
| } | |
| } | |
| @@ -1135,9 +1088,11 @@ | |
| void x264_macroblock_write_cabac( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| if( CHROMA444 ) | |
| - x264_macroblock_write_cabac_internal( h, cb, 3, 0 ); | |
| + macroblock_write_cabac_internal( h, cb, 3, 0 ); | |
| + else if( CHROMA_FORMAT ) | |
| + macroblock_write_cabac_internal( h, cb, 1, 1 ); | |
| else | |
| - x264_macroblock_write_cabac_internal( h, cb, 1, 1 ); | |
| + macroblock_write_cabac_internal( h, cb, 1, 0 ); | |
| } | |
| #if RDO_SKIP_BS | |
| @@ -1148,7 +1103,7 @@ | |
| * only writes subpartition for p8x8, needed for sub-8x8 mode decision RDO | |
| * works on all partition sizes except 16x16 | |
| *****************************************************************************/ | |
| -static void x264_partition_size_cabac( x264_t *h, x264_cabac_t *cb, int i8, int i_pixel ) | |
| +static void partition_size_cabac( x264_t *h, x264_cabac_t *cb, int i8, int i_pixel ) | |
| { | |
| const int i_mb_type = h->mb.i_type; | |
| int b_8x16 = h->mb.i_partition == D_8x16; | |
| @@ -1156,22 +1111,22 @@ | |
| if( i_mb_type == P_8x8 ) | |
| { | |
| - x264_cabac_8x8_mvd( h, cb, i8 ); | |
| - x264_cabac_subpartition_p( cb, h->mb.i_sub_partition[i8] ); | |
| + cabac_8x8_mvd( h, cb, i8 ); | |
| + cabac_subpartition_p( cb, h->mb.i_sub_partition[i8] ); | |
| } | |
| else if( i_mb_type == P_L0 ) | |
| - x264_cabac_mvd( h, cb, 0, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| + cabac_mvd( h, cb, 0, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| else if( i_mb_type > B_DIRECT && i_mb_type < B_8x8 ) | |
| { | |
| - if( x264_mb_type_list_table[ i_mb_type ][0][!!i8] ) x264_cabac_mvd( h, cb, 0, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| - if( x264_mb_type_list_table[ i_mb_type ][1][!!i8] ) x264_cabac_mvd( h, cb, 1, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| + if( x264_mb_type_list_table[ i_mb_type ][0][!!i8] ) cabac_mvd( h, cb, 0, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| + if( x264_mb_type_list_table[ i_mb_type ][1][!!i8] ) cabac_mvd( h, cb, 1, 4*i8, 4>>b_8x16, 2<<b_8x16 ); | |
| } | |
| else //if( i_mb_type == B_8x8 ) | |
| { | |
| if( x264_mb_partition_listX_table[0][ h->mb.i_sub_partition[i8] ] ) | |
| - x264_cabac_mvd( h, cb, 0, 4*i8, 2, 2 ); | |
| + cabac_mvd( h, cb, 0, 4*i8, 2, 2 ); | |
| if( x264_mb_partition_listX_table[1][ h->mb.i_sub_partition[i8] ] ) | |
| - x264_cabac_mvd( h, cb, 1, 4*i8, 2, 2 ); | |
| + cabac_mvd( h, cb, 1, 4*i8, 2, 2 ); | |
| } | |
| for( int j = (i_pixel < PIXEL_8x8); j >= 0; j-- ) | |
| @@ -1182,14 +1137,14 @@ | |
| { | |
| if( CHROMA444 ) | |
| for( int p = 0; p < 3; p++ ) | |
| - x264_cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i8*4+p*16, h->dct.luma8x8[i8+p*4], 0 ); | |
| + cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i8*4+p*16, h->dct.luma8x8[i8+p*4], 0 ); | |
| else | |
| - x264_cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i8] ); | |
| + cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i8] ); | |
| } | |
| else | |
| for( int p = 0; p < plane_count; p++ ) | |
| for( int i4 = 0; i4 < 4; i4++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i4+i8*4+p*16, h->dct.luma4x4[i4+i8*4+p*16], 0 ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i4+i8*4+p*16, h->dct.luma4x4[i4+i8*4+p*16], 0 ); | |
| } | |
| if( h->mb.i_cbp_chroma ) | |
| @@ -1197,15 +1152,15 @@ | |
| if( CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| int offset = (5*i8) & 0x09; | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 16+offset, h->dct.luma4x4[16+offset]+1, 0 ); | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 18+offset, h->dct.luma4x4[18+offset]+1, 0 ); | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 32+offset, h->dct.luma4x4[32+offset]+1, 0 ); | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 34+offset, h->dct.luma4x4[34+offset]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 16+offset, h->dct.luma4x4[16+offset]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 18+offset, h->dct.luma4x4[18+offset]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 32+offset, h->dct.luma4x4[32+offset]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 34+offset, h->dct.luma4x4[34+offset]+1, 0 ); | |
| } | |
| else | |
| { | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 16+i8, h->dct.luma4x4[16+i8]+1, 0 ); | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 32+i8, h->dct.luma4x4[32+i8]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 16+i8, h->dct.luma4x4[16+i8]+1, 0 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, 32+i8, h->dct.luma4x4[32+i8]+1, 0 ); | |
| } | |
| } | |
| @@ -1213,63 +1168,63 @@ | |
| } | |
| } | |
| -static void x264_subpartition_size_cabac( x264_t *h, x264_cabac_t *cb, int i4, int i_pixel ) | |
| +static void subpartition_size_cabac( x264_t *h, x264_cabac_t *cb, int i4, int i_pixel ) | |
| { | |
| int b_8x4 = i_pixel == PIXEL_8x4; | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| if( i_pixel == PIXEL_4x4 ) | |
| - x264_cabac_mvd( h, cb, 0, i4, 1, 1 ); | |
| + cabac_mvd( h, cb, 0, i4, 1, 1 ); | |
| else | |
| - x264_cabac_mvd( h, cb, 0, i4, 1+b_8x4, 2-b_8x4 ); | |
| + cabac_mvd( h, cb, 0, i4, 1+b_8x4, 2-b_8x4 ); | |
| for( int p = 0; p < plane_count; p++ ) | |
| { | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], p*16+i4, h->dct.luma4x4[p*16+i4], 0 ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], p*16+i4, h->dct.luma4x4[p*16+i4], 0 ); | |
| if( i_pixel != PIXEL_4x4 ) | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], p*16+i4+2-b_8x4, h->dct.luma4x4[p*16+i4+2-b_8x4], 0 ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], p*16+i4+2-b_8x4, h->dct.luma4x4[p*16+i4+2-b_8x4], 0 ); | |
| } | |
| } | |
| -static void x264_partition_i8x8_size_cabac( x264_t *h, x264_cabac_t *cb, int i8, int i_mode ) | |
| +static void partition_i8x8_size_cabac( x264_t *h, x264_cabac_t *cb, int i8, int i_mode ) | |
| { | |
| const int i_pred = x264_mb_predict_intra4x4_mode( h, 4*i8 ); | |
| i_mode = x264_mb_pred_mode4x4_fix( i_mode ); | |
| - x264_cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| - x264_cabac_cbp_luma( h, cb ); | |
| + cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| + cabac_cbp_luma( h, cb ); | |
| if( h->mb.i_cbp_luma & (1 << i8) ) | |
| { | |
| if( CHROMA444 ) | |
| for( int p = 0; p < 3; p++ ) | |
| - x264_cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i8*4+p*16, h->dct.luma8x8[i8+p*4], 1 ); | |
| + cabac_block_residual_8x8_cbf( h, cb, ctx_cat_plane[DCT_LUMA_8x8][p], i8*4+p*16, h->dct.luma8x8[i8+p*4], 1 ); | |
| else | |
| - x264_cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i8] ); | |
| + cabac_block_residual_8x8( h, cb, DCT_LUMA_8x8, h->dct.luma8x8[i8] ); | |
| } | |
| } | |
| -static void x264_partition_i4x4_size_cabac( x264_t *h, x264_cabac_t *cb, int i4, int i_mode ) | |
| +static void partition_i4x4_size_cabac( x264_t *h, x264_cabac_t *cb, int i4, int i_mode ) | |
| { | |
| const int i_pred = x264_mb_predict_intra4x4_mode( h, i4 ); | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| i_mode = x264_mb_pred_mode4x4_fix( i_mode ); | |
| - x264_cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| + cabac_intra4x4_pred_mode( cb, i_pred, i_mode ); | |
| for( int p = 0; p < plane_count; p++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i4+p*16, h->dct.luma4x4[i4+p*16], 1 ); | |
| + cabac_block_residual_cbf( h, cb, ctx_cat_plane[DCT_LUMA_4x4][p], i4+p*16, h->dct.luma4x4[i4+p*16], 1 ); | |
| } | |
| -static void x264_chroma_size_cabac( x264_t *h, x264_cabac_t *cb ) | |
| +static void chroma_size_cabac( x264_t *h, x264_cabac_t *cb ) | |
| { | |
| - x264_cabac_intra_chroma_pred_mode( h, cb ); | |
| - x264_cabac_cbp_chroma( h, cb ); | |
| + cabac_intra_chroma_pred_mode( h, cb ); | |
| + cabac_cbp_chroma( h, cb ); | |
| if( h->mb.i_cbp_chroma ) | |
| { | |
| if( CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| - x264_cabac_block_residual_422_dc_cbf( h, cb, 0, 1 ); | |
| - x264_cabac_block_residual_422_dc_cbf( h, cb, 1, 1 ); | |
| + cabac_block_residual_422_dc_cbf( h, cb, 0, 1 ); | |
| + cabac_block_residual_422_dc_cbf( h, cb, 1, 1 ); | |
| } | |
| else | |
| { | |
| - x264_cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+0, h->dct.chroma_dc[0], 1 ); | |
| - x264_cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+1, h->dct.chroma_dc[1], 1 ); | |
| + cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+0, h->dct.chroma_dc[0], 1 ); | |
| + cabac_block_residual_dc_cbf( h, cb, DCT_CHROMA_DC, CHROMA_DC+1, h->dct.chroma_dc[1], 1 ); | |
| } | |
| if( h->mb.i_cbp_chroma == 2 ) | |
| @@ -1277,7 +1232,7 @@ | |
| int step = 8 << CHROMA_V_SHIFT; | |
| for( int i = 16; i < 3*16; i += step ) | |
| for( int j = i; j < i+4; j++ ) | |
| - x264_cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, j, h->dct.luma4x4[j]+1, 1 ); | |
| + cabac_block_residual_cbf( h, cb, DCT_CHROMA_AC, j, h->dct.luma4x4[j]+1, 1 ); | |
| } | |
| } | |
| } | |
| diff -ur x264-go/x264c/external/x264/encoder/cavlc.c x264-go.new/x264c/external/x264/encoder/cavlc.c | |
| --- x264-go/x264c/external/x264/encoder/cavlc.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/cavlc.c 2020-06-06 15:20:58.697039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * cavlc.c: cavlc bitstream writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -67,7 +67,7 @@ | |
| /**************************************************************************** | |
| * x264_cavlc_block_residual: | |
| ****************************************************************************/ | |
| -static inline int x264_cavlc_block_residual_escape( x264_t *h, int i_suffix_length, int level ) | |
| +static inline int cavlc_block_residual_escape( x264_t *h, int i_suffix_length, int level ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| static const uint16_t next_suffix[7] = { 0, 3, 6, 12, 24, 48, 0xffff }; | |
| @@ -118,7 +118,7 @@ | |
| return i_suffix_length; | |
| } | |
| -static int x264_cavlc_block_residual_internal( x264_t *h, int ctx_block_cat, dctcoef *l, int nC ) | |
| +static int cavlc_block_residual_internal( x264_t *h, int ctx_block_cat, dctcoef *l, int nC ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| static const uint8_t ctz_index[8] = {3,0,1,0,2,0,1,0}; | |
| @@ -163,7 +163,7 @@ | |
| i_suffix_length = x264_level_token[i_suffix_length][val_original].i_next; | |
| } | |
| else | |
| - i_suffix_length = x264_cavlc_block_residual_escape( h, i_suffix_length, val-LEVEL_TABLE_SIZE/2 ); | |
| + i_suffix_length = cavlc_block_residual_escape( h, i_suffix_length, val-LEVEL_TABLE_SIZE/2 ); | |
| for( int i = i_trailing+1; i < i_total; i++ ) | |
| { | |
| val = runlevel.level[i] + LEVEL_TABLE_SIZE/2; | |
| @@ -173,7 +173,7 @@ | |
| i_suffix_length = x264_level_token[i_suffix_length][val].i_next; | |
| } | |
| else | |
| - i_suffix_length = x264_cavlc_block_residual_escape( h, i_suffix_length, val-LEVEL_TABLE_SIZE/2 ); | |
| + i_suffix_length = cavlc_block_residual_escape( h, i_suffix_length, val-LEVEL_TABLE_SIZE/2 ); | |
| } | |
| } | |
| @@ -205,10 +205,10 @@ | |
| if( !*nnz )\ | |
| bs_write_vlc( &h->out.bs, x264_coeff0_token[nC] );\ | |
| else\ | |
| - *nnz = x264_cavlc_block_residual_internal(h,cat,l,nC);\ | |
| + *nnz = cavlc_block_residual_internal(h,cat,l,nC);\ | |
| } | |
| -static void x264_cavlc_qp_delta( x264_t *h ) | |
| +static void cavlc_qp_delta( x264_t *h ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| int i_dqp = h->mb.i_qp - h->mb.i_last_qp; | |
| @@ -238,7 +238,7 @@ | |
| bs_write_se( s, i_dqp ); | |
| } | |
| -static void x264_cavlc_mvd( x264_t *h, int i_list, int idx, int width ) | |
| +static void cavlc_mvd( x264_t *h, int i_list, int idx, int width ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| ALIGNED_4( int16_t mvp[2] ); | |
| @@ -247,31 +247,31 @@ | |
| bs_write_se( s, h->mb.cache.mv[i_list][x264_scan8[idx]][1] - mvp[1] ); | |
| } | |
| -static inline void x264_cavlc_8x8_mvd( x264_t *h, int i ) | |
| +static inline void cavlc_8x8_mvd( x264_t *h, int i ) | |
| { | |
| switch( h->mb.i_sub_partition[i] ) | |
| { | |
| case D_L0_8x8: | |
| - x264_cavlc_mvd( h, 0, 4*i, 2 ); | |
| + cavlc_mvd( h, 0, 4*i, 2 ); | |
| break; | |
| case D_L0_8x4: | |
| - x264_cavlc_mvd( h, 0, 4*i+0, 2 ); | |
| - x264_cavlc_mvd( h, 0, 4*i+2, 2 ); | |
| + cavlc_mvd( h, 0, 4*i+0, 2 ); | |
| + cavlc_mvd( h, 0, 4*i+2, 2 ); | |
| break; | |
| case D_L0_4x8: | |
| - x264_cavlc_mvd( h, 0, 4*i+0, 1 ); | |
| - x264_cavlc_mvd( h, 0, 4*i+1, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+0, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+1, 1 ); | |
| break; | |
| case D_L0_4x4: | |
| - x264_cavlc_mvd( h, 0, 4*i+0, 1 ); | |
| - x264_cavlc_mvd( h, 0, 4*i+1, 1 ); | |
| - x264_cavlc_mvd( h, 0, 4*i+2, 1 ); | |
| - x264_cavlc_mvd( h, 0, 4*i+3, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+0, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+1, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+2, 1 ); | |
| + cavlc_mvd( h, 0, 4*i+3, 1 ); | |
| break; | |
| } | |
| } | |
| -static ALWAYS_INLINE void x264_cavlc_macroblock_luma_residual( x264_t *h, int plane_count ) | |
| +static ALWAYS_INLINE void cavlc_macroblock_luma_residual( x264_t *h, int plane_count ) | |
| { | |
| if( h->mb.b_transform_8x8 ) | |
| { | |
| @@ -290,9 +290,9 @@ | |
| } | |
| #if RDO_SKIP_BS | |
| -static ALWAYS_INLINE void x264_cavlc_partition_luma_residual( x264_t *h, int i8, int p ) | |
| +static ALWAYS_INLINE void cavlc_partition_luma_residual( x264_t *h, int i8, int p ) | |
| { | |
| - if( h->mb.b_transform_8x8 && h->mb.cache.non_zero_count[x264_scan8[i8*4]] ) | |
| + if( h->mb.b_transform_8x8 && h->mb.cache.non_zero_count[x264_scan8[i8*4+p*16]] ) | |
| h->zigzagf.interleave_8x8_cavlc( h->dct.luma4x4[i8*4+p*16], h->dct.luma8x8[i8+p*4], | |
| &h->mb.cache.non_zero_count[x264_scan8[i8*4+p*16]] ); | |
| @@ -302,7 +302,7 @@ | |
| } | |
| #endif | |
| -static void x264_cavlc_mb_header_i( x264_t *h, int i_mb_type, int i_mb_i_offset, int chroma ) | |
| +static void cavlc_mb_header_i( x264_t *h, int i_mb_type, int i_mb_i_offset, int chroma ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| if( i_mb_type == I_16x16 ) | |
| @@ -334,7 +334,7 @@ | |
| bs_write_ue( s, x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode] ); | |
| } | |
| -static ALWAYS_INLINE void x264_cavlc_mb_header_p( x264_t *h, int i_mb_type, int chroma ) | |
| +static ALWAYS_INLINE void cavlc_mb_header_p( x264_t *h, int i_mb_type, int chroma ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| if( i_mb_type == P_L0 ) | |
| @@ -345,7 +345,7 @@ | |
| if( h->mb.pic.i_fref[0] > 1 ) | |
| bs_write_te( s, h->mb.pic.i_fref[0] - 1, h->mb.cache.ref[0][x264_scan8[0]] ); | |
| - x264_cavlc_mvd( h, 0, 0, 4 ); | |
| + cavlc_mvd( h, 0, 0, 4 ); | |
| } | |
| else if( h->mb.i_partition == D_16x8 ) | |
| { | |
| @@ -355,8 +355,8 @@ | |
| bs_write_te( s, h->mb.pic.i_fref[0] - 1, h->mb.cache.ref[0][x264_scan8[0]] ); | |
| bs_write_te( s, h->mb.pic.i_fref[0] - 1, h->mb.cache.ref[0][x264_scan8[8]] ); | |
| } | |
| - x264_cavlc_mvd( h, 0, 0, 4 ); | |
| - x264_cavlc_mvd( h, 0, 8, 4 ); | |
| + cavlc_mvd( h, 0, 0, 4 ); | |
| + cavlc_mvd( h, 0, 8, 4 ); | |
| } | |
| else if( h->mb.i_partition == D_8x16 ) | |
| { | |
| @@ -366,8 +366,8 @@ | |
| bs_write_te( s, h->mb.pic.i_fref[0] - 1, h->mb.cache.ref[0][x264_scan8[0]] ); | |
| bs_write_te( s, h->mb.pic.i_fref[0] - 1, h->mb.cache.ref[0][x264_scan8[4]] ); | |
| } | |
| - x264_cavlc_mvd( h, 0, 0, 2 ); | |
| - x264_cavlc_mvd( h, 0, 4, 2 ); | |
| + cavlc_mvd( h, 0, 0, 2 ); | |
| + cavlc_mvd( h, 0, 4, 2 ); | |
| } | |
| } | |
| else if( i_mb_type == P_8x8 ) | |
| @@ -402,13 +402,13 @@ | |
| } | |
| for( int i = 0; i < 4; i++ ) | |
| - x264_cavlc_8x8_mvd( h, i ); | |
| + cavlc_8x8_mvd( h, i ); | |
| } | |
| else //if( IS_INTRA( i_mb_type ) ) | |
| - x264_cavlc_mb_header_i( h, i_mb_type, 5, chroma ); | |
| + cavlc_mb_header_i( h, i_mb_type, 5, chroma ); | |
| } | |
| -static ALWAYS_INLINE void x264_cavlc_mb_header_b( x264_t *h, int i_mb_type, int chroma ) | |
| +static ALWAYS_INLINE void cavlc_mb_header_b( x264_t *h, int i_mb_type, int chroma ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| if( i_mb_type == B_8x8 ) | |
| @@ -432,10 +432,10 @@ | |
| /* mvd */ | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[0][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cavlc_mvd( h, 0, 4*i, 2 ); | |
| + cavlc_mvd( h, 0, 4*i, 2 ); | |
| for( int i = 0; i < 4; i++ ) | |
| if( x264_mb_partition_listX_table[1][ h->mb.i_sub_partition[i] ] ) | |
| - x264_cavlc_mvd( h, 1, 4*i, 2 ); | |
| + cavlc_mvd( h, 1, 4*i, 2 ); | |
| } | |
| else if( i_mb_type >= B_L0_L0 && i_mb_type <= B_BI_BI ) | |
| { | |
| @@ -450,8 +450,8 @@ | |
| { | |
| if( i_ref0_max && b_list[0][0] ) bs_write_te( s, i_ref0_max, h->mb.cache.ref[0][x264_scan8[0]] ); | |
| if( i_ref1_max && b_list[1][0] ) bs_write_te( s, i_ref1_max, h->mb.cache.ref[1][x264_scan8[0]] ); | |
| - if( b_list[0][0] ) x264_cavlc_mvd( h, 0, 0, 4 ); | |
| - if( b_list[1][0] ) x264_cavlc_mvd( h, 1, 0, 4 ); | |
| + if( b_list[0][0] ) cavlc_mvd( h, 0, 0, 4 ); | |
| + if( b_list[1][0] ) cavlc_mvd( h, 1, 0, 4 ); | |
| } | |
| else | |
| { | |
| @@ -461,24 +461,24 @@ | |
| if( i_ref1_max && b_list[1][1] ) bs_write_te( s, i_ref1_max, h->mb.cache.ref[1][x264_scan8[12]] ); | |
| if( h->mb.i_partition == D_16x8 ) | |
| { | |
| - if( b_list[0][0] ) x264_cavlc_mvd( h, 0, 0, 4 ); | |
| - if( b_list[0][1] ) x264_cavlc_mvd( h, 0, 8, 4 ); | |
| - if( b_list[1][0] ) x264_cavlc_mvd( h, 1, 0, 4 ); | |
| - if( b_list[1][1] ) x264_cavlc_mvd( h, 1, 8, 4 ); | |
| + if( b_list[0][0] ) cavlc_mvd( h, 0, 0, 4 ); | |
| + if( b_list[0][1] ) cavlc_mvd( h, 0, 8, 4 ); | |
| + if( b_list[1][0] ) cavlc_mvd( h, 1, 0, 4 ); | |
| + if( b_list[1][1] ) cavlc_mvd( h, 1, 8, 4 ); | |
| } | |
| else //if( h->mb.i_partition == D_8x16 ) | |
| { | |
| - if( b_list[0][0] ) x264_cavlc_mvd( h, 0, 0, 2 ); | |
| - if( b_list[0][1] ) x264_cavlc_mvd( h, 0, 4, 2 ); | |
| - if( b_list[1][0] ) x264_cavlc_mvd( h, 1, 0, 2 ); | |
| - if( b_list[1][1] ) x264_cavlc_mvd( h, 1, 4, 2 ); | |
| + if( b_list[0][0] ) cavlc_mvd( h, 0, 0, 2 ); | |
| + if( b_list[0][1] ) cavlc_mvd( h, 0, 4, 2 ); | |
| + if( b_list[1][0] ) cavlc_mvd( h, 1, 0, 2 ); | |
| + if( b_list[1][1] ) cavlc_mvd( h, 1, 4, 2 ); | |
| } | |
| } | |
| } | |
| else if( i_mb_type == B_DIRECT ) | |
| bs_write1( s, 1 ); | |
| else //if( IS_INTRA( i_mb_type ) ) | |
| - x264_cavlc_mb_header_i( h, i_mb_type, 23, chroma ); | |
| + cavlc_mb_header_i( h, i_mb_type, 23, chroma ); | |
| } | |
| /***************************************************************************** | |
| @@ -489,7 +489,7 @@ | |
| bs_t *s = &h->out.bs; | |
| const int i_mb_type = h->mb.i_type; | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| - int chroma = !CHROMA444; | |
| + int chroma = CHROMA_FORMAT == CHROMA_420 || CHROMA_FORMAT == CHROMA_422; | |
| #if RDO_SKIP_BS | |
| s->i_bits_encoded = 0; | |
| @@ -536,11 +536,11 @@ | |
| #endif | |
| if( h->sh.i_type == SLICE_TYPE_P ) | |
| - x264_cavlc_mb_header_p( h, i_mb_type, chroma ); | |
| + cavlc_mb_header_p( h, i_mb_type, chroma ); | |
| else if( h->sh.i_type == SLICE_TYPE_B ) | |
| - x264_cavlc_mb_header_b( h, i_mb_type, chroma ); | |
| + cavlc_mb_header_b( h, i_mb_type, chroma ); | |
| else //if( h->sh.i_type == SLICE_TYPE_I ) | |
| - x264_cavlc_mb_header_i( h, i_mb_type, 0, chroma ); | |
| + cavlc_mb_header_i( h, i_mb_type, 0, chroma ); | |
| #if !RDO_SKIP_BS | |
| i_mb_pos_tex = bs_pos( s ); | |
| @@ -557,7 +557,7 @@ | |
| if( i_mb_type == I_16x16 ) | |
| { | |
| - x264_cavlc_qp_delta( h ); | |
| + cavlc_qp_delta( h ); | |
| /* DC Luma */ | |
| for( int p = 0; p < plane_count; p++ ) | |
| @@ -572,8 +572,8 @@ | |
| } | |
| else if( h->mb.i_cbp_luma | h->mb.i_cbp_chroma ) | |
| { | |
| - x264_cavlc_qp_delta( h ); | |
| - x264_cavlc_macroblock_luma_residual( h, plane_count ); | |
| + cavlc_qp_delta( h ); | |
| + cavlc_macroblock_luma_residual( h, plane_count ); | |
| } | |
| if( h->mb.i_cbp_chroma ) | |
| { | |
| @@ -602,7 +602,7 @@ | |
| * only writes subpartition for p8x8, needed for sub-8x8 mode decision RDO | |
| * works on all partition sizes except 16x16 | |
| *****************************************************************************/ | |
| -static int x264_partition_size_cavlc( x264_t *h, int i8, int i_pixel ) | |
| +static int partition_size_cavlc( x264_t *h, int i8, int i_pixel ) | |
| { | |
| bs_t *s = &h->out.bs; | |
| const int i_mb_type = h->mb.i_type; | |
| @@ -614,28 +614,28 @@ | |
| if( i_mb_type == P_8x8 ) | |
| { | |
| - x264_cavlc_8x8_mvd( h, i8 ); | |
| + cavlc_8x8_mvd( h, i8 ); | |
| bs_write_ue( s, subpartition_p_to_golomb[ h->mb.i_sub_partition[i8] ] ); | |
| } | |
| else if( i_mb_type == P_L0 ) | |
| - x264_cavlc_mvd( h, 0, 4*i8, 4>>b_8x16 ); | |
| + cavlc_mvd( h, 0, 4*i8, 4>>b_8x16 ); | |
| else if( i_mb_type > B_DIRECT && i_mb_type < B_8x8 ) | |
| { | |
| - if( x264_mb_type_list_table[ i_mb_type ][0][!!i8] ) x264_cavlc_mvd( h, 0, 4*i8, 4>>b_8x16 ); | |
| - if( x264_mb_type_list_table[ i_mb_type ][1][!!i8] ) x264_cavlc_mvd( h, 1, 4*i8, 4>>b_8x16 ); | |
| + if( x264_mb_type_list_table[ i_mb_type ][0][!!i8] ) cavlc_mvd( h, 0, 4*i8, 4>>b_8x16 ); | |
| + if( x264_mb_type_list_table[ i_mb_type ][1][!!i8] ) cavlc_mvd( h, 1, 4*i8, 4>>b_8x16 ); | |
| } | |
| else //if( i_mb_type == B_8x8 ) | |
| { | |
| if( x264_mb_partition_listX_table[0][ h->mb.i_sub_partition[i8] ] ) | |
| - x264_cavlc_mvd( h, 0, 4*i8, 2 ); | |
| + cavlc_mvd( h, 0, 4*i8, 2 ); | |
| if( x264_mb_partition_listX_table[1][ h->mb.i_sub_partition[i8] ] ) | |
| - x264_cavlc_mvd( h, 1, 4*i8, 2 ); | |
| + cavlc_mvd( h, 1, 4*i8, 2 ); | |
| } | |
| for( j = (i_pixel < PIXEL_8x8); j >= 0; j-- ) | |
| { | |
| for( int p = 0; p < plane_count; p++ ) | |
| - x264_cavlc_partition_luma_residual( h, i8, p ); | |
| + cavlc_partition_luma_residual( h, i8, p ); | |
| if( h->mb.i_cbp_chroma ) | |
| { | |
| if( CHROMA_FORMAT == CHROMA_422 ) | |
| @@ -658,12 +658,12 @@ | |
| return h->out.bs.i_bits_encoded; | |
| } | |
| -static int x264_subpartition_size_cavlc( x264_t *h, int i4, int i_pixel ) | |
| +static int subpartition_size_cavlc( x264_t *h, int i4, int i_pixel ) | |
| { | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| int b_8x4 = i_pixel == PIXEL_8x4; | |
| h->out.bs.i_bits_encoded = 0; | |
| - x264_cavlc_mvd( h, 0, i4, 1+b_8x4 ); | |
| + cavlc_mvd( h, 0, i4, 1+b_8x4 ); | |
| for( int p = 0; p < plane_count; p++ ) | |
| { | |
| x264_cavlc_block_residual( h, DCT_LUMA_4x4, p*16+i4, h->dct.luma4x4[p*16+i4] ); | |
| @@ -674,7 +674,7 @@ | |
| return h->out.bs.i_bits_encoded; | |
| } | |
| -static int x264_cavlc_intra4x4_pred_size( x264_t *h, int i4, int i_mode ) | |
| +static int cavlc_intra4x4_pred_size( x264_t *h, int i4, int i_mode ) | |
| { | |
| if( x264_mb_predict_intra4x4_mode( h, i4 ) == x264_mb_pred_mode4x4_fix( i_mode ) ) | |
| return 1; | |
| @@ -682,26 +682,26 @@ | |
| return 4; | |
| } | |
| -static int x264_partition_i8x8_size_cavlc( x264_t *h, int i8, int i_mode ) | |
| +static int partition_i8x8_size_cavlc( x264_t *h, int i8, int i_mode ) | |
| { | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| - h->out.bs.i_bits_encoded = x264_cavlc_intra4x4_pred_size( h, 4*i8, i_mode ); | |
| + h->out.bs.i_bits_encoded = cavlc_intra4x4_pred_size( h, 4*i8, i_mode ); | |
| bs_write_ue( &h->out.bs, cbp_to_golomb[!CHROMA444][1][(h->mb.i_cbp_chroma << 4)|h->mb.i_cbp_luma] ); | |
| for( int p = 0; p < plane_count; p++ ) | |
| - x264_cavlc_partition_luma_residual( h, i8, p ); | |
| + cavlc_partition_luma_residual( h, i8, p ); | |
| return h->out.bs.i_bits_encoded; | |
| } | |
| -static int x264_partition_i4x4_size_cavlc( x264_t *h, int i4, int i_mode ) | |
| +static int partition_i4x4_size_cavlc( x264_t *h, int i4, int i_mode ) | |
| { | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| - h->out.bs.i_bits_encoded = x264_cavlc_intra4x4_pred_size( h, i4, i_mode ); | |
| + h->out.bs.i_bits_encoded = cavlc_intra4x4_pred_size( h, i4, i_mode ); | |
| for( int p = 0; p < plane_count; p++ ) | |
| x264_cavlc_block_residual( h, DCT_LUMA_4x4, p*16+i4, h->dct.luma4x4[p*16+i4] ); | |
| return h->out.bs.i_bits_encoded; | |
| } | |
| -static int x264_chroma_size_cavlc( x264_t *h ) | |
| +static int chroma_size_cavlc( x264_t *h ) | |
| { | |
| h->out.bs.i_bits_encoded = bs_size_ue( x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode] ); | |
| if( h->mb.i_cbp_chroma ) | |
| diff -ur x264-go/x264c/external/x264/encoder/encoder.c x264-go.new/x264c/external/x264/encoder/encoder.c | |
| --- x264-go/x264c/external/x264/encoder/encoder.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/encoder.c 2020-06-06 15:20:58.697039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * encoder.c: top-level encoder functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -40,16 +40,20 @@ | |
| #define bs_write_ue bs_write_ue_big | |
| -static int x264_encoder_frame_end( x264_t *h, x264_t *thread_current, | |
| - x264_nal_t **pp_nal, int *pi_nal, | |
| - x264_picture_t *pic_out ); | |
| +// forward declaration needed for template usage | |
| +void x264_nal_encode( x264_t *h, uint8_t *dst, x264_nal_t *nal ); | |
| +void x264_macroblock_cache_load_progressive( x264_t *h, int i_mb_x, int i_mb_y ); | |
| + | |
| +static int encoder_frame_end( x264_t *h, x264_t *thread_current, | |
| + x264_nal_t **pp_nal, int *pi_nal, | |
| + x264_picture_t *pic_out ); | |
| /**************************************************************************** | |
| * | |
| ******************************* x264 libs ********************************** | |
| * | |
| ****************************************************************************/ | |
| -static double x264_psnr( double sqe, double size ) | |
| +static double calc_psnr( double sqe, double size ) | |
| { | |
| double mse = sqe / (PIXEL_MAX*PIXEL_MAX * size); | |
| if( mse <= 0.0000000001 ) /* Max 100dB */ | |
| @@ -58,7 +62,7 @@ | |
| return -10.0 * log10( mse ); | |
| } | |
| -static double x264_ssim( double ssim ) | |
| +static double calc_ssim_db( double ssim ) | |
| { | |
| double inv_ssim = 1 - ssim; | |
| if( inv_ssim <= 0.0000000001 ) /* Max 100dB */ | |
| @@ -67,7 +71,7 @@ | |
| return -10.0 * log10( inv_ssim ); | |
| } | |
| -static int x264_threadpool_wait_all( x264_t *h ) | |
| +static int threadpool_wait_all( x264_t *h ) | |
| { | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| if( h->thread[i]->b_thread_active ) | |
| @@ -79,7 +83,7 @@ | |
| return 0; | |
| } | |
| -static void x264_frame_dump( x264_t *h ) | |
| +static void frame_dump( x264_t *h ) | |
| { | |
| FILE *f = x264_fopen( h->param.psz_dump_yuv, "r+b" ); | |
| if( !f ) | |
| @@ -87,26 +91,26 @@ | |
| /* Wait for the threads to finish deblocking */ | |
| if( h->param.b_sliced_threads ) | |
| - x264_threadpool_wait_all( h ); | |
| + threadpool_wait_all( h ); | |
| /* Write the frame in display order */ | |
| - int frame_size = FRAME_SIZE( h->param.i_height * h->param.i_width * sizeof(pixel) ); | |
| + int frame_size = FRAME_SIZE( h->param.i_height * h->param.i_width * SIZEOF_PIXEL ); | |
| if( !fseek( f, (int64_t)h->fdec->i_frame * frame_size, SEEK_SET ) ) | |
| { | |
| for( int p = 0; p < (CHROMA444 ? 3 : 1); p++ ) | |
| for( int y = 0; y < h->param.i_height; y++ ) | |
| - fwrite( &h->fdec->plane[p][y*h->fdec->i_stride[p]], sizeof(pixel), h->param.i_width, f ); | |
| - if( !CHROMA444 ) | |
| + fwrite( &h->fdec->plane[p][y*h->fdec->i_stride[p]], SIZEOF_PIXEL, h->param.i_width, f ); | |
| + if( CHROMA_FORMAT == CHROMA_420 || CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| int cw = h->param.i_width>>1; | |
| int ch = h->param.i_height>>CHROMA_V_SHIFT; | |
| - pixel *planeu = x264_malloc( 2 * (cw*ch*sizeof(pixel) + 32) ); | |
| + pixel *planeu = x264_malloc( 2 * (cw*ch*SIZEOF_PIXEL + 32) ); | |
| if( planeu ) | |
| { | |
| - pixel *planev = planeu + cw*ch + 32/sizeof(pixel); | |
| + pixel *planev = planeu + cw*ch + 32/SIZEOF_PIXEL; | |
| h->mc.plane_copy_deinterleave( planeu, cw, planev, cw, h->fdec->plane[1], h->fdec->i_stride[1], cw, ch ); | |
| - fwrite( planeu, 1, cw*ch*sizeof(pixel), f ); | |
| - fwrite( planev, 1, cw*ch*sizeof(pixel), f ); | |
| + fwrite( planeu, 1, cw*ch*SIZEOF_PIXEL, f ); | |
| + fwrite( planev, 1, cw*ch*SIZEOF_PIXEL, f ); | |
| x264_free( planeu ); | |
| } | |
| } | |
| @@ -115,9 +119,9 @@ | |
| } | |
| /* Fill "default" values */ | |
| -static void x264_slice_header_init( x264_t *h, x264_slice_header_t *sh, | |
| - x264_sps_t *sps, x264_pps_t *pps, | |
| - int i_idr_pic_id, int i_frame, int i_qp ) | |
| +static void slice_header_init( x264_t *h, x264_slice_header_t *sh, | |
| + x264_sps_t *sps, x264_pps_t *pps, | |
| + int i_idr_pic_id, int i_frame, int i_qp ) | |
| { | |
| x264_param_t *param = &h->param; | |
| @@ -206,7 +210,7 @@ | |
| sh->i_beta_offset = param->i_deblocking_filter_beta << 1; | |
| } | |
| -static void x264_slice_header_write( bs_t *s, x264_slice_header_t *sh, int i_nal_ref_idc ) | |
| +static void slice_header_write( bs_t *s, x264_slice_header_t *sh, int i_nal_ref_idc ) | |
| { | |
| if( sh->b_mbaff ) | |
| { | |
| @@ -289,25 +293,29 @@ | |
| { | |
| sh->b_weighted_pred = sh->weight[0][0].weightfn || sh->weight[0][1].weightfn || sh->weight[0][2].weightfn; | |
| /* pred_weight_table() */ | |
| - bs_write_ue( s, sh->weight[0][0].i_denom ); | |
| - bs_write_ue( s, sh->weight[0][1].i_denom ); | |
| + bs_write_ue( s, sh->weight[0][0].i_denom ); /* luma_log2_weight_denom */ | |
| + if( sh->sps->i_chroma_format_idc ) | |
| + bs_write_ue( s, sh->weight[0][1].i_denom ); /* chroma_log2_weight_denom */ | |
| for( int i = 0; i < sh->i_num_ref_idx_l0_active; i++ ) | |
| { | |
| int luma_weight_l0_flag = !!sh->weight[i][0].weightfn; | |
| - int chroma_weight_l0_flag = !!sh->weight[i][1].weightfn || !!sh->weight[i][2].weightfn; | |
| bs_write1( s, luma_weight_l0_flag ); | |
| if( luma_weight_l0_flag ) | |
| { | |
| bs_write_se( s, sh->weight[i][0].i_scale ); | |
| bs_write_se( s, sh->weight[i][0].i_offset ); | |
| } | |
| - bs_write1( s, chroma_weight_l0_flag ); | |
| - if( chroma_weight_l0_flag ) | |
| + if( sh->sps->i_chroma_format_idc ) | |
| { | |
| - for( int j = 1; j < 3; j++ ) | |
| + int chroma_weight_l0_flag = sh->weight[i][1].weightfn || sh->weight[i][2].weightfn; | |
| + bs_write1( s, chroma_weight_l0_flag ); | |
| + if( chroma_weight_l0_flag ) | |
| { | |
| - bs_write_se( s, sh->weight[i][j].i_scale ); | |
| - bs_write_se( s, sh->weight[i][j].i_offset ); | |
| + for( int j = 1; j < 3; j++ ) | |
| + { | |
| + bs_write_se( s, sh->weight[i][j].i_scale ); | |
| + bs_write_se( s, sh->weight[i][j].i_offset ); | |
| + } | |
| } | |
| } | |
| } | |
| @@ -357,11 +365,13 @@ | |
| /* If we are within a reasonable distance of the end of the memory allocated for the bitstream, */ | |
| /* reallocate, adding an arbitrary amount of space. */ | |
| -static int x264_bitstream_check_buffer_internal( x264_t *h, int size, int b_cabac, int i_nal ) | |
| +static int bitstream_check_buffer_internal( x264_t *h, int size, int b_cabac, int i_nal ) | |
| { | |
| if( (b_cabac && (h->cabac.p_end - h->cabac.p < size)) || | |
| (h->out.bs.p_end - h->out.bs.p < size) ) | |
| { | |
| + if( size > INT_MAX - h->out.i_bitstream ) | |
| + return -1; | |
| int buf_size = h->out.i_bitstream + size; | |
| uint8_t *buf = x264_malloc( buf_size ); | |
| if( !buf ) | |
| @@ -390,20 +400,20 @@ | |
| return 0; | |
| } | |
| -static int x264_bitstream_check_buffer( x264_t *h ) | |
| +static int bitstream_check_buffer( x264_t *h ) | |
| { | |
| int max_row_size = (2500 << SLICE_MBAFF) * h->mb.i_mb_width; | |
| - return x264_bitstream_check_buffer_internal( h, max_row_size, h->param.b_cabac, h->out.i_nal ); | |
| + return bitstream_check_buffer_internal( h, max_row_size, h->param.b_cabac, h->out.i_nal ); | |
| } | |
| -static int x264_bitstream_check_buffer_filler( x264_t *h, int filler ) | |
| +static int bitstream_check_buffer_filler( x264_t *h, int filler ) | |
| { | |
| filler += 32; // add padding for safety | |
| - return x264_bitstream_check_buffer_internal( h, filler, 0, -1 ); | |
| + return bitstream_check_buffer_internal( h, filler, 0, -1 ); | |
| } | |
| #if HAVE_THREAD | |
| -static void x264_encoder_thread_init( x264_t *h ) | |
| +static void encoder_thread_init( x264_t *h ) | |
| { | |
| if( h->param.i_sync_lookahead ) | |
| x264_lower_thread_priority( 10 ); | |
| @@ -418,18 +428,18 @@ | |
| * | |
| ****************************************************************************/ | |
| -static int x264_validate_parameters( x264_t *h, int b_open ) | |
| +static int validate_parameters( x264_t *h, int b_open ) | |
| { | |
| if( !h->param.pf_log ) | |
| { | |
| - x264_log( NULL, X264_LOG_ERROR, "pf_log not set! did you forget to call x264_param_default?\n" ); | |
| + x264_log_internal( X264_LOG_ERROR, "pf_log not set! did you forget to call x264_param_default?\n" ); | |
| return -1; | |
| } | |
| #if HAVE_MMX | |
| if( b_open ) | |
| { | |
| - int cpuflags = x264_cpu_detect(); | |
| + uint32_t cpuflags = x264_cpu_detect(); | |
| int fail = 0; | |
| #ifdef __SSE__ | |
| if( !(cpuflags & X264_CPU_SSE) ) | |
| @@ -462,7 +472,9 @@ | |
| } | |
| #endif | |
| - if( h->param.i_width <= 0 || h->param.i_height <= 0 ) | |
| +#define MAX_RESOLUTION 16384 | |
| + if( h->param.i_width <= 0 || h->param.i_height <= 0 || | |
| + h->param.i_width > MAX_RESOLUTION || h->param.i_height > MAX_RESOLUTION ) | |
| { | |
| x264_log( h, X264_LOG_ERROR, "invalid width x height (%dx%d)\n", | |
| h->param.i_width, h->param.i_height ); | |
| @@ -471,7 +483,12 @@ | |
| int i_csp = h->param.i_csp & X264_CSP_MASK; | |
| #if X264_CHROMA_FORMAT | |
| - if( CHROMA_FORMAT != CHROMA_420 && i_csp >= X264_CSP_I420 && i_csp < X264_CSP_I422 ) | |
| + if( CHROMA_FORMAT != CHROMA_400 && i_csp == X264_CSP_I400 ) | |
| + { | |
| + x264_log( h, X264_LOG_ERROR, "not compiled with 4:0:0 support\n" ); | |
| + return -1; | |
| + } | |
| + else if( CHROMA_FORMAT != CHROMA_420 && i_csp >= X264_CSP_I420 && i_csp < X264_CSP_I422 ) | |
| { | |
| x264_log( h, X264_LOG_ERROR, "not compiled with 4:2:0 support\n" ); | |
| return -1; | |
| @@ -489,13 +506,26 @@ | |
| #endif | |
| if( i_csp <= X264_CSP_NONE || i_csp >= X264_CSP_MAX ) | |
| { | |
| - x264_log( h, X264_LOG_ERROR, "invalid CSP (only I420/YV12/NV12/NV21/I422/YV16/NV16/YUYV/UYVY/" | |
| + x264_log( h, X264_LOG_ERROR, "invalid CSP (only I400/I420/YV12/NV12/NV21/I422/YV16/NV16/YUYV/UYVY/" | |
| "I444/YV24/BGR/BGRA/RGB supported)\n" ); | |
| return -1; | |
| } | |
| - int w_mod = i_csp < X264_CSP_I444 ? 2 : 1; | |
| - int h_mod = (i_csp < X264_CSP_I422 ? 2 : 1) << PARAM_INTERLACED; | |
| + int w_mod = 1; | |
| + int h_mod = 1 << (PARAM_INTERLACED || h->param.b_fake_interlaced); | |
| + if( i_csp == X264_CSP_I400 ) | |
| + { | |
| + h->param.analyse.i_chroma_qp_offset = 0; | |
| + h->param.analyse.b_chroma_me = 0; | |
| + h->param.vui.i_colmatrix = 2; /* undefined */ | |
| + } | |
| + else if( i_csp < X264_CSP_I444 ) | |
| + { | |
| + w_mod = 2; | |
| + if( i_csp < X264_CSP_I422 ) | |
| + h_mod *= 2; | |
| + } | |
| + | |
| if( h->param.i_width % w_mod ) | |
| { | |
| x264_log( h, X264_LOG_ERROR, "width not divisible by %d (%dx%d)\n", | |
| @@ -509,21 +539,21 @@ | |
| return -1; | |
| } | |
| - if( h->param.crop_rect.i_left >= h->param.i_width || | |
| - h->param.crop_rect.i_right >= h->param.i_width || | |
| - h->param.crop_rect.i_top >= h->param.i_height || | |
| - h->param.crop_rect.i_bottom >= h->param.i_height || | |
| + if( h->param.crop_rect.i_left < 0 || h->param.crop_rect.i_left >= h->param.i_width || | |
| + h->param.crop_rect.i_right < 0 || h->param.crop_rect.i_right >= h->param.i_width || | |
| + h->param.crop_rect.i_top < 0 || h->param.crop_rect.i_top >= h->param.i_height || | |
| + h->param.crop_rect.i_bottom < 0 || h->param.crop_rect.i_bottom >= h->param.i_height || | |
| h->param.crop_rect.i_left + h->param.crop_rect.i_right >= h->param.i_width || | |
| h->param.crop_rect.i_top + h->param.crop_rect.i_bottom >= h->param.i_height ) | |
| { | |
| - x264_log( h, X264_LOG_ERROR, "invalid crop-rect %u,%u,%u,%u\n", h->param.crop_rect.i_left, | |
| + x264_log( h, X264_LOG_ERROR, "invalid crop-rect %d,%d,%d,%d\n", h->param.crop_rect.i_left, | |
| h->param.crop_rect.i_top, h->param.crop_rect.i_right, h->param.crop_rect.i_bottom ); | |
| return -1; | |
| } | |
| if( h->param.crop_rect.i_left % w_mod || h->param.crop_rect.i_right % w_mod || | |
| h->param.crop_rect.i_top % h_mod || h->param.crop_rect.i_bottom % h_mod ) | |
| { | |
| - x264_log( h, X264_LOG_ERROR, "crop-rect %u,%u,%u,%u not divisible by %dx%d\n", h->param.crop_rect.i_left, | |
| + x264_log( h, X264_LOG_ERROR, "crop-rect %d,%d,%d,%d not divisible by %dx%d\n", h->param.crop_rect.i_left, | |
| h->param.crop_rect.i_top, h->param.crop_rect.i_right, h->param.crop_rect.i_bottom, w_mod, h_mod ); | |
| return -1; | |
| } | |
| @@ -791,21 +821,36 @@ | |
| memcpy( h->param.cqm_4ic, avcintra_lut[type][res][i].cqm_4ic, sizeof(h->param.cqm_4ic) ); | |
| memcpy( h->param.cqm_8iy, avcintra_lut[type][res][i].cqm_8iy, sizeof(h->param.cqm_8iy) ); | |
| - /* Need exactly 10 slices of equal MB count... why? $deity knows... */ | |
| - h->param.i_slice_max_mbs = ((h->param.i_width + 15) / 16) * ((h->param.i_height + 15) / 16) / 10; | |
| - h->param.i_slice_max_size = 0; | |
| - /* The slice structure only allows a maximum of 2 threads for 1080i/p | |
| - * and 1 or 5 threads for 720p */ | |
| - if( h->param.b_sliced_threads ) | |
| + /* Sony XAVC flavor much more simple */ | |
| + if( h->param.i_avcintra_flavor == X264_AVCINTRA_FLAVOR_SONY ) | |
| { | |
| - if( res ) | |
| - h->param.i_threads = X264_MIN( 2, h->param.i_threads ); | |
| - else | |
| + h->param.i_slice_count = 8; | |
| + if( h->param.b_sliced_threads ) | |
| + h->param.i_threads = h->param.i_slice_count; | |
| + /* Sony XAVC unlike AVC-Intra doesn't seem to have a QP floor */ | |
| + } | |
| + else | |
| + { | |
| + /* Need exactly 10 slices of equal MB count... why? $deity knows... */ | |
| + h->param.i_slice_max_mbs = ((h->param.i_width + 15) / 16) * ((h->param.i_height + 15) / 16) / 10; | |
| + h->param.i_slice_max_size = 0; | |
| + /* The slice structure only allows a maximum of 2 threads for 1080i/p | |
| + * and 1 or 5 threads for 720p */ | |
| + if( h->param.b_sliced_threads ) | |
| { | |
| - h->param.i_threads = X264_MIN( 5, h->param.i_threads ); | |
| - if( h->param.i_threads < 5 ) | |
| - h->param.i_threads = 1; | |
| + if( res ) | |
| + h->param.i_threads = X264_MIN( 2, h->param.i_threads ); | |
| + else | |
| + { | |
| + h->param.i_threads = X264_MIN( 5, h->param.i_threads ); | |
| + if( h->param.i_threads < 5 ) | |
| + h->param.i_threads = 1; | |
| + } | |
| } | |
| + | |
| + /* Official encoder doesn't appear to go under 13 | |
| + * and Avid cannot handle negative QPs */ | |
| + h->param.rc.i_qp_min = X264_MAX( h->param.rc.i_qp_min, QP_BD_OFFSET + 1 ); | |
| } | |
| if( type ) | |
| @@ -815,18 +860,14 @@ | |
| h->param.vui.i_sar_width = 4; | |
| h->param.vui.i_sar_height = 3; | |
| } | |
| - | |
| - /* Official encoder doesn't appear to go under 13 | |
| - * and Avid cannot handle negative QPs */ | |
| - h->param.rc.i_qp_min = X264_MAX( h->param.rc.i_qp_min, QP_BD_OFFSET + 1 ); | |
| } | |
| h->param.rc.f_rf_constant = x264_clip3f( h->param.rc.f_rf_constant, -QP_BD_OFFSET, 51 ); | |
| h->param.rc.f_rf_constant_max = x264_clip3f( h->param.rc.f_rf_constant_max, -QP_BD_OFFSET, 51 ); | |
| - h->param.rc.i_qp_constant = x264_clip3( h->param.rc.i_qp_constant, 0, QP_MAX ); | |
| + h->param.rc.i_qp_constant = x264_clip3( h->param.rc.i_qp_constant, -1, QP_MAX ); | |
| h->param.analyse.i_subpel_refine = x264_clip3( h->param.analyse.i_subpel_refine, 0, 11 ); | |
| - h->param.rc.f_ip_factor = X264_MAX( h->param.rc.f_ip_factor, 0.01f ); | |
| - h->param.rc.f_pb_factor = X264_MAX( h->param.rc.f_pb_factor, 0.01f ); | |
| + h->param.rc.f_ip_factor = x264_clip3f( h->param.rc.f_ip_factor, 0.01, 10.0 ); | |
| + h->param.rc.f_pb_factor = x264_clip3f( h->param.rc.f_pb_factor, 0.01, 10.0 ); | |
| if( h->param.rc.i_rc_method == X264_RC_CRF ) | |
| { | |
| h->param.rc.i_qp_constant = h->param.rc.f_rf_constant + QP_BD_OFFSET; | |
| @@ -852,19 +893,18 @@ | |
| /* 8x8dct is not useful without RD in CAVLC lossless */ | |
| if( !h->param.b_cabac && h->param.analyse.i_subpel_refine < 6 ) | |
| h->param.analyse.b_transform_8x8 = 0; | |
| - h->param.analyse.inter &= ~X264_ANALYSE_I8x8; | |
| - h->param.analyse.intra &= ~X264_ANALYSE_I8x8; | |
| - } | |
| - if( i_csp >= X264_CSP_I444 && h->param.b_cabac ) | |
| - { | |
| - /* Disable 8x8dct during 4:4:4+CABAC encoding for compatibility with libavcodec */ | |
| - h->param.analyse.b_transform_8x8 = 0; | |
| } | |
| if( h->param.rc.i_rc_method == X264_RC_CQP ) | |
| { | |
| float qp_p = h->param.rc.i_qp_constant; | |
| float qp_i = qp_p - 6*log2f( h->param.rc.f_ip_factor ); | |
| float qp_b = qp_p + 6*log2f( h->param.rc.f_pb_factor ); | |
| + if( qp_p < 0 ) | |
| + { | |
| + x264_log( h, X264_LOG_ERROR, "qp not specified\n" ); | |
| + return -1; | |
| + } | |
| + | |
| h->param.rc.i_qp_min = x264_clip3( (int)(X264_MIN3( qp_p, qp_i, qp_b )), 0, QP_MAX ); | |
| h->param.rc.i_qp_max = x264_clip3( (int)(X264_MAX3( qp_p, qp_i, qp_b ) + .999), 0, QP_MAX ); | |
| h->param.rc.i_aq_mode = 0; | |
| @@ -1338,6 +1378,9 @@ | |
| switch( CHROMA_FORMAT ) | |
| { | |
| + case CHROMA_400: | |
| + h->mc.prefetch_fenc = h->mc.prefetch_fenc_400; | |
| + break; | |
| case CHROMA_420: | |
| memcpy( h->predict_chroma, h->predict_8x8c, sizeof(h->predict_chroma) ); | |
| h->mc.prefetch_fenc = h->mc.prefetch_fenc_420; | |
| @@ -1368,7 +1411,7 @@ | |
| } | |
| } | |
| -static void x264_set_aspect_ratio( x264_t *h, x264_param_t *param, int initial ) | |
| +static void set_aspect_ratio( x264_t *h, x264_param_t *param, int initial ) | |
| { | |
| /* VUI */ | |
| if( param->vui.i_sar_width > 0 && param->vui.i_sar_height > 0 ) | |
| @@ -1431,7 +1474,7 @@ | |
| goto fail; | |
| } | |
| - if( x264_validate_parameters( h, 1 ) < 0 ) | |
| + if( validate_parameters( h, 1 ) < 0 ) | |
| goto fail; | |
| if( h->param.psz_cqm_file ) | |
| @@ -1461,9 +1504,10 @@ | |
| goto fail; | |
| } | |
| - x264_set_aspect_ratio( h, &h->param, 1 ); | |
| + set_aspect_ratio( h, &h->param, 1 ); | |
| x264_sps_init( h->sps, h->param.i_sps_id, &h->param ); | |
| + x264_sps_init_scaling_list( h->sps, &h->param ); | |
| x264_pps_init( h->pps, h->param.i_sps_id, &h->param, h->sps ); | |
| x264_validate_levels( h, 1 ); | |
| @@ -1517,6 +1561,7 @@ | |
| h->frames.i_largest_pts = h->frames.i_second_largest_pts = -1; | |
| h->frames.i_poc_last_open_gop = -1; | |
| + CHECKED_MALLOCZERO( h->cost_table, sizeof(*h->cost_table) ); | |
| CHECKED_MALLOCZERO( h->frames.unused[0], (h->frames.i_delay + 3) * sizeof(x264_frame_t *) ); | |
| /* Allocate room for max refs plus a few extra just in case. */ | |
| CHECKED_MALLOCZERO( h->frames.unused[1], (h->i_thread_frames + X264_REF_MAX + 4) * sizeof(x264_frame_t *) ); | |
| @@ -1553,7 +1598,7 @@ | |
| if( h->param.b_cabac ) | |
| x264_cabac_init( h ); | |
| else | |
| - x264_stack_align( x264_cavlc_init, h ); | |
| + x264_cavlc_init( h ); | |
| mbcmp_init( h ); | |
| chroma_dsp_init( h ); | |
| @@ -1606,9 +1651,13 @@ | |
| } | |
| h->out.i_nal = 0; | |
| - h->out.i_bitstream = X264_MAX( 1000000, h->param.i_width * h->param.i_height * 4 | |
| - * ( h->param.rc.i_rc_method == X264_RC_ABR ? pow( 0.95, h->param.rc.i_qp_min ) | |
| - : pow( 0.95, h->param.rc.i_qp_constant ) * X264_MAX( 1, h->param.rc.f_ip_factor ))); | |
| + h->out.i_bitstream = x264_clip3f( | |
| + h->param.i_width * h->param.i_height * 4 | |
| + * ( h->param.rc.i_rc_method == X264_RC_ABR | |
| + ? pow( 0.95, h->param.rc.i_qp_min ) | |
| + : pow( 0.95, h->param.rc.i_qp_constant ) * X264_MAX( 1, h->param.rc.f_ip_factor ) ), | |
| + 1000000, INT_MAX/3 | |
| + ); | |
| h->nal_buffer_size = h->out.i_bitstream * 3/2 + 4 + 64; /* +4 for startcode, +64 for nal_escape assembly padding */ | |
| CHECKED_MALLOC( h->nal_buffer, h->nal_buffer_size ); | |
| @@ -1616,7 +1665,7 @@ | |
| CHECKED_MALLOC( h->reconfig_h, sizeof(x264_t) ); | |
| if( h->param.i_threads > 1 && | |
| - x264_threadpool_init( &h->threadpool, h->param.i_threads, (void*)x264_encoder_thread_init, h ) ) | |
| + x264_threadpool_init( &h->threadpool, h->param.i_threads, (void*)encoder_thread_init, h ) ) | |
| goto fail; | |
| if( h->param.i_lookahead_threads > 1 && | |
| x264_threadpool_init( &h->lookaheadpool, h->param.i_lookahead_threads, NULL, NULL ) ) | |
| @@ -1717,26 +1766,20 @@ | |
| const char *profile = h->sps->i_profile_idc == PROFILE_BASELINE ? "Constrained Baseline" : | |
| h->sps->i_profile_idc == PROFILE_MAIN ? "Main" : | |
| h->sps->i_profile_idc == PROFILE_HIGH ? "High" : | |
| - h->sps->i_profile_idc == PROFILE_HIGH10 ? (h->sps->b_constraint_set3 == 1 ? "High 10 Intra" : "High 10") : | |
| - h->sps->i_profile_idc == PROFILE_HIGH422 ? (h->sps->b_constraint_set3 == 1 ? "High 4:2:2 Intra" : "High 4:2:2") : | |
| - h->sps->b_constraint_set3 == 1 ? "High 4:4:4 Intra" : "High 4:4:4 Predictive"; | |
| + h->sps->i_profile_idc == PROFILE_HIGH10 ? | |
| + (h->sps->b_constraint_set3 ? "High 10 Intra" : "High 10") : | |
| + h->sps->i_profile_idc == PROFILE_HIGH422 ? | |
| + (h->sps->b_constraint_set3 ? "High 4:2:2 Intra" : "High 4:2:2") : | |
| + h->sps->b_constraint_set3 ? "High 4:4:4 Intra" : "High 4:4:4 Predictive"; | |
| char level[4]; | |
| snprintf( level, sizeof(level), "%d.%d", h->sps->i_level_idc/10, h->sps->i_level_idc%10 ); | |
| if( h->sps->i_level_idc == 9 || ( h->sps->i_level_idc == 11 && h->sps->b_constraint_set3 && | |
| (h->sps->i_profile_idc == PROFILE_BASELINE || h->sps->i_profile_idc == PROFILE_MAIN) ) ) | |
| strcpy( level, "1b" ); | |
| - if( h->sps->i_profile_idc < PROFILE_HIGH10 ) | |
| - { | |
| - x264_log( h, X264_LOG_INFO, "profile %s, level %s\n", | |
| - profile, level ); | |
| - } | |
| - else | |
| - { | |
| - static const char * const subsampling[4] = { "4:0:0", "4:2:0", "4:2:2", "4:4:4" }; | |
| - x264_log( h, X264_LOG_INFO, "profile %s, level %s, %s %d-bit\n", | |
| - profile, level, subsampling[CHROMA_FORMAT], BIT_DEPTH ); | |
| - } | |
| + static const char * const subsampling[4] = { "4:0:0", "4:2:0", "4:2:2", "4:4:4" }; | |
| + x264_log( h, X264_LOG_INFO, "profile %s, level %s, %s, %d-bit\n", | |
| + profile, level, subsampling[CHROMA_FORMAT], BIT_DEPTH ); | |
| return h; | |
| fail: | |
| @@ -1745,10 +1788,10 @@ | |
| } | |
| /****************************************************************************/ | |
| -static int x264_encoder_try_reconfig( x264_t *h, x264_param_t *param, int *rc_reconfig ) | |
| +static int encoder_try_reconfig( x264_t *h, x264_param_t *param, int *rc_reconfig ) | |
| { | |
| *rc_reconfig = 0; | |
| - x264_set_aspect_ratio( h, param, 0 ); | |
| + set_aspect_ratio( h, param, 0 ); | |
| #define COPY(var) h->param.var = param->var | |
| COPY( i_frame_reference ); // but never uses more refs than initially specified | |
| COPY( i_bframe_bias ); | |
| @@ -1809,13 +1852,13 @@ | |
| COPY( rc.f_rf_constant_max ); | |
| #undef COPY | |
| - return x264_validate_parameters( h, 0 ); | |
| + return validate_parameters( h, 0 ); | |
| } | |
| int x264_encoder_reconfig_apply( x264_t *h, x264_param_t *param ) | |
| { | |
| int rc_reconfig; | |
| - int ret = x264_encoder_try_reconfig( h, param, &rc_reconfig ); | |
| + int ret = encoder_try_reconfig( h, param, &rc_reconfig ); | |
| mbcmp_init( h ); | |
| if( !ret ) | |
| @@ -1842,7 +1885,7 @@ | |
| h->reconfig_h->param = h->param; | |
| int rc_reconfig; | |
| - int ret = x264_encoder_try_reconfig( h->reconfig_h, param, &rc_reconfig ); | |
| + int ret = encoder_try_reconfig( h->reconfig_h, param, &rc_reconfig ); | |
| if( !ret ) | |
| h->reconfig = 1; | |
| else | |
| @@ -1860,7 +1903,7 @@ | |
| } | |
| /* internal usage */ | |
| -static void x264_nal_start( x264_t *h, int i_type, int i_ref_idc ) | |
| +static void nal_start( x264_t *h, int i_type, int i_ref_idc ) | |
| { | |
| x264_nal_t *nal = &h->out.nal[h->out.i_nal]; | |
| @@ -1874,7 +1917,7 @@ | |
| } | |
| /* if number of allocated nals is not enough, re-allocate a larger one. */ | |
| -static int x264_nal_check_buffer( x264_t *h ) | |
| +static int nal_check_buffer( x264_t *h ) | |
| { | |
| if( h->out.i_nal >= h->out.i_nals_allocated ) | |
| { | |
| @@ -1889,7 +1932,7 @@ | |
| return 0; | |
| } | |
| -static int x264_nal_end( x264_t *h ) | |
| +static int nal_end( x264_t *h ) | |
| { | |
| x264_nal_t *nal = &h->out.nal[h->out.i_nal]; | |
| uint8_t *end = &h->out.p_bitstream[bs_pos( &h->out.bs ) / 8]; | |
| @@ -1901,15 +1944,17 @@ | |
| h->param.nalu_process( h, nal, h->fenc->opaque ); | |
| h->out.i_nal++; | |
| - return x264_nal_check_buffer( h ); | |
| + return nal_check_buffer( h ); | |
| } | |
| -static int x264_check_encapsulated_buffer( x264_t *h, x264_t *h0, int start, | |
| - int previous_nal_size, int necessary_size ) | |
| +static int check_encapsulated_buffer( x264_t *h, x264_t *h0, int start, | |
| + int64_t previous_nal_size, int64_t necessary_size ) | |
| { | |
| if( h0->nal_buffer_size < necessary_size ) | |
| { | |
| necessary_size *= 2; | |
| + if( necessary_size > INT_MAX ) | |
| + return -1; | |
| uint8_t *buf = x264_malloc( necessary_size ); | |
| if( !buf ) | |
| return -1; | |
| @@ -1928,15 +1973,17 @@ | |
| return 0; | |
| } | |
| -static int x264_encoder_encapsulate_nals( x264_t *h, int start ) | |
| +static int encoder_encapsulate_nals( x264_t *h, int start ) | |
| { | |
| x264_t *h0 = h->thread[0]; | |
| - int nal_size = 0, previous_nal_size = 0; | |
| + int64_t nal_size = 0, previous_nal_size = 0; | |
| if( h->param.nalu_process ) | |
| { | |
| for( int i = start; i < h->out.i_nal; i++ ) | |
| nal_size += h->out.nal[i].i_payload; | |
| + if( nal_size > INT_MAX ) | |
| + return -1; | |
| return nal_size; | |
| } | |
| @@ -1947,10 +1994,10 @@ | |
| nal_size += h->out.nal[i].i_payload; | |
| /* Worst-case NAL unit escaping: reallocate the buffer if it's too small. */ | |
| - int necessary_size = previous_nal_size + nal_size * 3/2 + h->out.i_nal * 4 + 4 + 64; | |
| + int64_t necessary_size = previous_nal_size + nal_size * 3/2 + h->out.i_nal * 4 + 4 + 64; | |
| for( int i = start; i < h->out.i_nal; i++ ) | |
| necessary_size += h->out.nal[i].i_padding; | |
| - if( x264_check_encapsulated_buffer( h, h0, start, previous_nal_size, necessary_size ) ) | |
| + if( check_encapsulated_buffer( h, h0, start, previous_nal_size, necessary_size ) ) | |
| return -1; | |
| uint8_t *nal_buffer = h0->nal_buffer + previous_nal_size; | |
| @@ -1981,25 +2028,25 @@ | |
| /* Write SEI, SPS and PPS. */ | |
| /* generate sequence parameters */ | |
| - x264_nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST ); | |
| + nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST ); | |
| x264_sps_write( &h->out.bs, h->sps ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| /* generate picture parameters */ | |
| - x264_nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST ); | |
| + nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST ); | |
| x264_pps_write( &h->out.bs, h->sps, h->pps ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| /* identify ourselves */ | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| if( x264_sei_version_write( h, &h->out.bs ) ) | |
| return -1; | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| - frame_size = x264_encoder_encapsulate_nals( h, 0 ); | |
| + frame_size = encoder_encapsulate_nals( h, 0 ); | |
| if( frame_size < 0 ) | |
| return -1; | |
| @@ -2013,7 +2060,7 @@ | |
| /* Check to see whether we have chosen a reference list ordering different | |
| * from the standard's default. */ | |
| -static inline void x264_reference_check_reorder( x264_t *h ) | |
| +static inline void reference_check_reorder( x264_t *h ) | |
| { | |
| /* The reorder check doesn't check for missing frames, so just | |
| * force a reorder if one of the reference list is corrupt. */ | |
| @@ -2038,7 +2085,7 @@ | |
| } | |
| /* return -1 on failure, else return the index of the new reference frame */ | |
| -static int x264_weighted_reference_duplicate( x264_t *h, int i_ref, const x264_weight_t *w ) | |
| +static int weighted_reference_duplicate( x264_t *h, int i_ref, const x264_weight_t *w ) | |
| { | |
| int i = h->i_ref[0]; | |
| int j = 1; | |
| @@ -2077,7 +2124,7 @@ | |
| return j; | |
| } | |
| -static void x264_weighted_pred_init( x264_t *h ) | |
| +static void weighted_pred_init( x264_t *h ) | |
| { | |
| /* for now no analysis and set all weights to nothing */ | |
| for( int i_ref = 0; i_ref < h->i_ref[0]; i_ref++ ) | |
| @@ -2161,7 +2208,7 @@ | |
| h->sh.weight[0][2].i_denom = h->sh.weight[0][1].i_denom; | |
| } | |
| -static inline int x264_reference_distance( x264_t *h, x264_frame_t *frame ) | |
| +static inline int reference_distance( x264_t *h, x264_frame_t *frame ) | |
| { | |
| if( h->param.i_frame_packing == 5 ) | |
| return abs((h->fenc->i_frame&~1) - (frame->i_frame&~1)) + | |
| @@ -2170,7 +2217,7 @@ | |
| return abs(h->fenc->i_frame - frame->i_frame); | |
| } | |
| -static inline void x264_reference_build_list( x264_t *h, int i_poc ) | |
| +static inline void reference_build_list( x264_t *h, int i_poc ) | |
| { | |
| int b_ok; | |
| @@ -2227,7 +2274,7 @@ | |
| if( list ? h->fref[list][i+1]->i_poc < h->fref_nearest[list]->i_poc | |
| : h->fref[list][i+1]->i_poc > h->fref_nearest[list]->i_poc ) | |
| h->fref_nearest[list] = h->fref[list][i+1]; | |
| - if( x264_reference_distance( h, h->fref[list][i] ) > x264_reference_distance( h, h->fref[list][i+1] ) ) | |
| + if( reference_distance( h, h->fref[list][i] ) > reference_distance( h, h->fref[list][i+1] ) ) | |
| { | |
| XCHG( x264_frame_t*, h->fref[list][i], h->fref[list][i+1] ); | |
| b_ok = 0; | |
| @@ -2237,7 +2284,7 @@ | |
| } while( !b_ok ); | |
| } | |
| - x264_reference_check_reorder( h ); | |
| + reference_check_reorder( h ); | |
| h->i_ref[1] = X264_MIN( h->i_ref[1], h->frames.i_max_ref1 ); | |
| h->i_ref[0] = X264_MIN( h->i_ref[0], h->frames.i_max_ref0 ); | |
| @@ -2262,7 +2309,7 @@ | |
| { | |
| h->fenc->weight[0][0].i_denom = 0; | |
| SET_WEIGHT( w[0], 1, 1, 0, -1 ); | |
| - idx = x264_weighted_reference_duplicate( h, 0, w ); | |
| + idx = weighted_reference_duplicate( h, 0, w ); | |
| } | |
| else | |
| { | |
| @@ -2270,13 +2317,13 @@ | |
| { | |
| SET_WEIGHT( h->fenc->weight[0][0], 1, 1, 0, h->fenc->weight[0][0].i_offset ); | |
| } | |
| - x264_weighted_reference_duplicate( h, 0, x264_weight_none ); | |
| + weighted_reference_duplicate( h, 0, x264_weight_none ); | |
| if( h->fenc->weight[0][0].i_offset > -128 ) | |
| { | |
| w[0] = h->fenc->weight[0][0]; | |
| w[0].i_offset--; | |
| h->mc.weight_cache( h, &w[0] ); | |
| - idx = x264_weighted_reference_duplicate( h, 0, w ); | |
| + idx = weighted_reference_duplicate( h, 0, w ); | |
| } | |
| } | |
| } | |
| @@ -2288,7 +2335,7 @@ | |
| h->mb.pic.i_fref[1] = h->i_ref[1]; | |
| } | |
| -static void x264_fdec_filter_row( x264_t *h, int mb_y, int pass ) | |
| +static void fdec_filter_row( x264_t *h, int mb_y, int pass ) | |
| { | |
| /* mb_y is the mb to be encoded next, not the mb to be filtered here */ | |
| int b_hpel = h->fdec->b_kept_as_ref; | |
| @@ -2343,7 +2390,7 @@ | |
| for( int i = minpix_y>>(CHROMA_V_SHIFT && p); i < maxpix_y>>(CHROMA_V_SHIFT && p); i++ ) | |
| memcpy( h->fdec->plane_fld[p] + i*h->fdec->i_stride[p], | |
| h->fdec->plane[p] + i*h->fdec->i_stride[p], | |
| - h->mb.i_mb_width*16*sizeof(pixel) ); | |
| + h->mb.i_mb_width*16*SIZEOF_PIXEL ); | |
| if( h->fdec->b_kept_as_ref && (!h->param.b_sliced_threads || pass == 1) ) | |
| x264_frame_expand_border( h, h->fdec, min_y ); | |
| @@ -2408,7 +2455,7 @@ | |
| } | |
| } | |
| -static inline int x264_reference_update( x264_t *h ) | |
| +static inline int reference_update( x264_t *h ) | |
| { | |
| if( !h->fdec->b_kept_as_ref ) | |
| { | |
| @@ -2438,7 +2485,7 @@ | |
| return 0; | |
| } | |
| -static inline void x264_reference_reset( x264_t *h ) | |
| +static inline void reference_reset( x264_t *h ) | |
| { | |
| while( h->frames.reference[0] ) | |
| x264_frame_push_unused( h, x264_frame_pop( h->frames.reference ) ); | |
| @@ -2446,7 +2493,7 @@ | |
| h->fenc->i_poc = 0; | |
| } | |
| -static inline void x264_reference_hierarchy_reset( x264_t *h ) | |
| +static inline void reference_hierarchy_reset( x264_t *h ) | |
| { | |
| int ref; | |
| int b_hasdelayframe = 0; | |
| @@ -2483,12 +2530,12 @@ | |
| h->sh.i_mmco_remove_from_end = X264_MAX( ref + 2 - h->frames.i_max_dpb, 0 ); | |
| } | |
| -static inline void x264_slice_init( x264_t *h, int i_nal_type, int i_global_qp ) | |
| +static inline void slice_init( x264_t *h, int i_nal_type, int i_global_qp ) | |
| { | |
| /* ------------------------ Create slice header ----------------------- */ | |
| if( i_nal_type == NAL_SLICE_IDR ) | |
| { | |
| - x264_slice_header_init( h, &h->sh, h->sps, h->pps, h->i_idr_pic_id, h->i_frame_num, i_global_qp ); | |
| + slice_header_init( h, &h->sh, h->sps, h->pps, h->i_idr_pic_id, h->i_frame_num, i_global_qp ); | |
| /* alternate id */ | |
| if( h->param.i_avcintra_class ) | |
| @@ -2512,7 +2559,7 @@ | |
| } | |
| else | |
| { | |
| - x264_slice_header_init( h, &h->sh, h->sps, h->pps, -1, h->i_frame_num, i_global_qp ); | |
| + slice_header_init( h, &h->sh, h->sps, h->pps, -1, h->i_frame_num, i_global_qp ); | |
| h->sh.i_num_ref_idx_l0_active = h->i_ref[0] <= 0 ? 1 : h->i_ref[0]; | |
| h->sh.i_num_ref_idx_l1_active = h->i_ref[1] <= 0 ? 1 : h->i_ref[1]; | |
| @@ -2564,7 +2611,7 @@ | |
| int field_decoding_flag; | |
| } x264_bs_bak_t; | |
| -static ALWAYS_INLINE void x264_bitstream_backup( x264_t *h, x264_bs_bak_t *bak, int i_skip, int full ) | |
| +static ALWAYS_INLINE void bitstream_backup( x264_t *h, x264_bs_bak_t *bak, int i_skip, int full ) | |
| { | |
| if( full ) | |
| { | |
| @@ -2598,7 +2645,7 @@ | |
| } | |
| } | |
| -static ALWAYS_INLINE void x264_bitstream_restore( x264_t *h, x264_bs_bak_t *bak, int *skip, int full ) | |
| +static ALWAYS_INLINE void bitstream_restore( x264_t *h, x264_bs_bak_t *bak, int *skip, int full ) | |
| { | |
| if( full ) | |
| { | |
| @@ -2627,7 +2674,7 @@ | |
| } | |
| } | |
| -static intptr_t x264_slice_write( x264_t *h ) | |
| +static intptr_t slice_write( x264_t *h ) | |
| { | |
| int i_skip; | |
| int mb_xy, i_mb_x, i_mb_y; | |
| @@ -2654,7 +2701,7 @@ | |
| bs_realign( &h->out.bs ); | |
| /* Slice */ | |
| - x264_nal_start( h, h->i_nal_type, h->i_nal_ref_idc ); | |
| + nal_start( h, h->i_nal_type, h->i_nal_ref_idc ); | |
| h->out.nal[h->out.i_nal].i_first_mb = h->sh.i_first_mb; | |
| /* Slice header */ | |
| @@ -2666,7 +2713,7 @@ | |
| h->sh.i_qp = SPEC_QP( h->sh.i_qp ); | |
| h->sh.i_qp_delta = h->sh.i_qp - h->pps->i_pic_init_qp; | |
| - x264_slice_header_write( &h->out.bs, &h->sh, h->i_nal_ref_idc ); | |
| + slice_header_write( &h->out.bs, &h->sh, h->i_nal_ref_idc ); | |
| if( h->param.b_cabac ) | |
| { | |
| /* alignment needed */ | |
| @@ -2694,23 +2741,23 @@ | |
| if( i_mb_x == 0 ) | |
| { | |
| - if( x264_bitstream_check_buffer( h ) ) | |
| + if( bitstream_check_buffer( h ) ) | |
| return -1; | |
| if( !(i_mb_y & SLICE_MBAFF) && h->param.rc.i_vbv_buffer_size ) | |
| - x264_bitstream_backup( h, &bs_bak[BS_BAK_ROW_VBV], i_skip, 1 ); | |
| + bitstream_backup( h, &bs_bak[BS_BAK_ROW_VBV], i_skip, 1 ); | |
| if( !h->mb.b_reencode_mb ) | |
| - x264_fdec_filter_row( h, i_mb_y, 0 ); | |
| + fdec_filter_row( h, i_mb_y, 0 ); | |
| } | |
| if( back_up_bitstream ) | |
| { | |
| if( back_up_bitstream_cavlc ) | |
| - x264_bitstream_backup( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], i_skip, 0 ); | |
| + bitstream_backup( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], i_skip, 0 ); | |
| if( slice_max_size && !(i_mb_y & SLICE_MBAFF) ) | |
| { | |
| - x264_bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], i_skip, 0 ); | |
| + bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], i_skip, 0 ); | |
| if( (thread_last_mb+1-mb_xy) == h->param.i_slice_min_mbs ) | |
| - x264_bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], i_skip, 0 ); | |
| + bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], i_skip, 0 ); | |
| } | |
| } | |
| @@ -2775,7 +2822,7 @@ | |
| h->mb.i_skip_intra = 0; | |
| h->mb.b_skip_mc = 0; | |
| h->mb.b_overflow = 0; | |
| - x264_bitstream_restore( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], &i_skip, 0 ); | |
| + bitstream_restore( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], &i_skip, 0 ); | |
| goto reencode; | |
| } | |
| } | |
| @@ -2815,14 +2862,14 @@ | |
| slice_max_size = 0; | |
| goto cont; | |
| } | |
| - x264_bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], &i_skip, 0 ); | |
| + bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], &i_skip, 0 ); | |
| h->mb.b_reencode_mb = 1; | |
| h->sh.i_last_mb = thread_last_mb-h->param.i_slice_min_mbs; | |
| break; | |
| } | |
| if( mb_xy-SLICE_MBAFF*h->mb.i_mb_stride != h->sh.i_first_mb ) | |
| { | |
| - x264_bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], &i_skip, 0 ); | |
| + bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], &i_skip, 0 ); | |
| h->mb.b_reencode_mb = 1; | |
| if( SLICE_MBAFF ) | |
| { | |
| @@ -2851,7 +2898,7 @@ | |
| if( x264_ratecontrol_mb( h, mb_size ) < 0 ) | |
| { | |
| - x264_bitstream_restore( h, &bs_bak[BS_BAK_ROW_VBV], &i_skip, 1 ); | |
| + bitstream_restore( h, &bs_bak[BS_BAK_ROW_VBV], &i_skip, 1 ); | |
| h->mb.b_reencode_mb = 1; | |
| i_mb_x = 0; | |
| i_mb_y = i_mb_y - SLICE_MBAFF; | |
| @@ -2968,7 +3015,7 @@ | |
| bs_rbsp_trailing( &h->out.bs ); | |
| bs_flush( &h->out.bs ); | |
| } | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| if( h->sh.i_last_mb == (h->i_threadslice_end * h->mb.i_mb_width - 1) ) | |
| @@ -2977,7 +3024,7 @@ | |
| + (h->out.i_nal*NALU_OVERHEAD * 8) | |
| - h->stat.frame.i_tex_bits | |
| - h->stat.frame.i_mv_bits; | |
| - x264_fdec_filter_row( h, h->i_threadslice_end, 0 ); | |
| + fdec_filter_row( h, h->i_threadslice_end, 0 ); | |
| if( h->param.b_sliced_threads ) | |
| { | |
| @@ -2985,13 +3032,13 @@ | |
| x264_threadslice_cond_broadcast( h, 1 ); | |
| /* Do hpel now */ | |
| for( int mb_y = h->i_threadslice_start; mb_y <= h->i_threadslice_end; mb_y++ ) | |
| - x264_fdec_filter_row( h, mb_y, 1 ); | |
| + fdec_filter_row( h, mb_y, 1 ); | |
| x264_threadslice_cond_broadcast( h, 2 ); | |
| /* Do the first row of hpel, now that the previous slice is done */ | |
| if( h->i_thread_idx > 0 ) | |
| { | |
| x264_threadslice_cond_wait( h->thread[h->i_thread_idx-1], 2 ); | |
| - x264_fdec_filter_row( h, h->i_threadslice_start + (1 << SLICE_MBAFF), 2 ); | |
| + fdec_filter_row( h, h->i_threadslice_start + (1 << SLICE_MBAFF), 2 ); | |
| } | |
| } | |
| @@ -3007,7 +3054,7 @@ | |
| return 0; | |
| } | |
| -static void x264_thread_sync_context( x264_t *dst, x264_t *src ) | |
| +static void thread_sync_context( x264_t *dst, x264_t *src ) | |
| { | |
| if( dst == src ) | |
| return; | |
| @@ -3028,16 +3075,17 @@ | |
| dst->reconfig = src->reconfig; | |
| } | |
| -static void x264_thread_sync_stat( x264_t *dst, x264_t *src ) | |
| +static void thread_sync_stat( x264_t *dst, x264_t *src ) | |
| { | |
| if( dst != src ) | |
| memcpy( &dst->stat, &src->stat, offsetof(x264_t, stat.frame) - offsetof(x264_t, stat) ); | |
| } | |
| -static void *x264_slices_write( x264_t *h ) | |
| +static void *slices_write( x264_t *h ) | |
| { | |
| int i_slice_num = 0; | |
| int last_thread_mb = h->sh.i_last_mb; | |
| + int round_bias = h->param.i_avcintra_class ? 0 : h->param.i_slice_count/2; | |
| /* init stats */ | |
| memset( &h->stat.frame, 0, sizeof(h->stat.frame) ); | |
| @@ -3072,11 +3120,11 @@ | |
| int height = h->mb.i_mb_height >> PARAM_INTERLACED; | |
| int width = h->mb.i_mb_width << PARAM_INTERLACED; | |
| i_slice_num++; | |
| - h->sh.i_last_mb = (height * i_slice_num + h->param.i_slice_count/2) / h->param.i_slice_count * width - 1; | |
| + h->sh.i_last_mb = (height * i_slice_num + round_bias) / h->param.i_slice_count * width - 1; | |
| } | |
| } | |
| h->sh.i_last_mb = X264_MIN( h->sh.i_last_mb, last_thread_mb ); | |
| - if( x264_stack_align( x264_slice_write, h ) ) | |
| + if( slice_write( h ) ) | |
| goto fail; | |
| h->sh.i_first_mb = h->sh.i_last_mb + 1; | |
| // if i_first_mb is not the last mb in a row then go to the next mb in MBAFF order | |
| @@ -3093,8 +3141,10 @@ | |
| return (void *)-1; | |
| } | |
| -static int x264_threaded_slices_write( x264_t *h ) | |
| +static int threaded_slices_write( x264_t *h ) | |
| { | |
| + int round_bias = h->param.i_avcintra_class ? 0 : h->param.i_slice_count/2; | |
| + | |
| /* set first/last mb and sync contexts */ | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| { | |
| @@ -3105,13 +3155,13 @@ | |
| memcpy( &t->i_frame, &h->i_frame, offsetof(x264_t, rc) - offsetof(x264_t, i_frame) ); | |
| } | |
| int height = h->mb.i_mb_height >> PARAM_INTERLACED; | |
| - t->i_threadslice_start = ((height * i + h->param.i_slice_count/2) / h->param.i_threads) << PARAM_INTERLACED; | |
| - t->i_threadslice_end = ((height * (i+1) + h->param.i_slice_count/2) / h->param.i_threads) << PARAM_INTERLACED; | |
| + t->i_threadslice_start = ((height * i + round_bias) / h->param.i_threads) << PARAM_INTERLACED; | |
| + t->i_threadslice_end = ((height * (i+1) + round_bias) / h->param.i_threads) << PARAM_INTERLACED; | |
| t->sh.i_first_mb = t->i_threadslice_start * h->mb.i_mb_width; | |
| t->sh.i_last_mb = t->i_threadslice_end * h->mb.i_mb_width - 1; | |
| } | |
| - x264_stack_align( x264_analyse_weight_frame, h, h->mb.i_mb_height*16 + 16 ); | |
| + x264_analyse_weight_frame( h, h->mb.i_mb_height*16 + 16 ); | |
| x264_threads_distribute_ratecontrol( h ); | |
| @@ -3124,7 +3174,7 @@ | |
| } | |
| /* dispatch */ | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| - x264_threadpool_run( h->threadpool, (void*)x264_slices_write, h->thread[i] ); | |
| + x264_threadpool_run( h->threadpool, (void*)slices_write, h->thread[i] ); | |
| /* wait */ | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| x264_threadslice_cond_wait( h->thread[i], 1 ); | |
| @@ -3138,10 +3188,10 @@ | |
| { | |
| h->out.nal[h->out.i_nal] = t->out.nal[j]; | |
| h->out.i_nal++; | |
| - x264_nal_check_buffer( h ); | |
| + nal_check_buffer( h ); | |
| } | |
| /* All entries in stat.frame are ints except for ssd/ssim. */ | |
| - for( int j = 0; j < (offsetof(x264_t,stat.frame.i_ssd) - offsetof(x264_t,stat.frame.i_mv_bits)) / sizeof(int); j++ ) | |
| + for( size_t j = 0; j < (offsetof(x264_t,stat.frame.i_ssd) - offsetof(x264_t,stat.frame.i_mv_bits)) / sizeof(int); j++ ) | |
| ((int*)&h->stat.frame)[j] += ((int*)&t->stat.frame)[j]; | |
| for( int j = 0; j < 3; j++ ) | |
| h->stat.frame.i_ssd[j] += t->stat.frame.i_ssd[j]; | |
| @@ -3215,7 +3265,7 @@ | |
| h->i_thread_phase = (h->i_thread_phase + 1) % h->i_thread_frames; | |
| thread_current = h->thread[ h->i_thread_phase ]; | |
| thread_oldest = h->thread[ (h->i_thread_phase + 1) % h->i_thread_frames ]; | |
| - x264_thread_sync_context( thread_current, thread_prev ); | |
| + thread_sync_context( thread_current, thread_prev ); | |
| x264_thread_sync_ratecontrol( thread_current, thread_prev, thread_oldest ); | |
| h = thread_current; | |
| } | |
| @@ -3289,7 +3339,7 @@ | |
| return -1; | |
| } | |
| else | |
| - x264_stack_align( x264_adaptive_quant_frame, h, fenc, pic_in->prop.quant_offsets ); | |
| + x264_adaptive_quant_frame( h, fenc, pic_in->prop.quant_offsets ); | |
| if( pic_in->prop.quant_offsets_free ) | |
| pic_in->prop.quant_offsets_free( pic_in->prop.quant_offsets ); | |
| @@ -3322,7 +3372,7 @@ | |
| x264_lookahead_get_frames( h ); | |
| if( !h->frames.current[0] && x264_lookahead_is_empty( h ) ) | |
| - return x264_encoder_frame_end( thread_oldest, thread_current, pp_nal, pi_nal, pic_out ); | |
| + return encoder_frame_end( thread_oldest, thread_current, pp_nal, pi_nal, pic_out ); | |
| /* ------------------- Get frame to be encoded ------------------------- */ | |
| /* 4: get picture to encode */ | |
| @@ -3330,7 +3380,7 @@ | |
| /* If applicable, wait for previous frame reconstruction to finish */ | |
| if( h->param.b_sliced_threads ) | |
| - if( x264_threadpool_wait_all( h ) < 0 ) | |
| + if( threadpool_wait_all( h ) < 0 ) | |
| return -1; | |
| if( h->i_frame == 0 ) | |
| @@ -3352,7 +3402,7 @@ | |
| x264_ratecontrol_zone_init( h ); | |
| // ok to call this before encoding any frames, since the initial values of fdec have b_kept_as_ref=0 | |
| - if( x264_reference_update( h ) ) | |
| + if( reference_update( h ) ) | |
| return -1; | |
| h->fdec->i_lines_completed = -1; | |
| @@ -3394,7 +3444,7 @@ | |
| i_nal_type = NAL_SLICE_IDR; | |
| i_nal_ref_idc = NAL_PRIORITY_HIGHEST; | |
| h->sh.i_type = SLICE_TYPE_I; | |
| - x264_reference_reset( h ); | |
| + reference_reset( h ); | |
| h->frames.i_poc_last_open_gop = -1; | |
| } | |
| else if( h->fenc->i_type == X264_TYPE_I ) | |
| @@ -3402,7 +3452,7 @@ | |
| i_nal_type = NAL_SLICE; | |
| i_nal_ref_idc = NAL_PRIORITY_HIGH; /* Not completely true but for now it is (as all I/P are kept as ref)*/ | |
| h->sh.i_type = SLICE_TYPE_I; | |
| - x264_reference_hierarchy_reset( h ); | |
| + reference_hierarchy_reset( h ); | |
| if( h->param.b_open_gop ) | |
| h->frames.i_poc_last_open_gop = h->fenc->b_keyframe ? h->fenc->i_poc : -1; | |
| } | |
| @@ -3411,7 +3461,7 @@ | |
| i_nal_type = NAL_SLICE; | |
| i_nal_ref_idc = NAL_PRIORITY_HIGH; /* Not completely true but for now it is (as all I/P are kept as ref)*/ | |
| h->sh.i_type = SLICE_TYPE_P; | |
| - x264_reference_hierarchy_reset( h ); | |
| + reference_hierarchy_reset( h ); | |
| h->frames.i_poc_last_open_gop = -1; | |
| } | |
| else if( h->fenc->i_type == X264_TYPE_BREF ) | |
| @@ -3419,7 +3469,7 @@ | |
| i_nal_type = NAL_SLICE; | |
| i_nal_ref_idc = h->param.i_bframe_pyramid == X264_B_PYRAMID_STRICT ? NAL_PRIORITY_LOW : NAL_PRIORITY_HIGH; | |
| h->sh.i_type = SLICE_TYPE_B; | |
| - x264_reference_hierarchy_reset( h ); | |
| + reference_hierarchy_reset( h ); | |
| } | |
| else /* B frame */ | |
| { | |
| @@ -3454,7 +3504,7 @@ | |
| /* ------------------- Init ----------------------------- */ | |
| /* build ref list 0/1 */ | |
| - x264_reference_build_list( h, h->fdec->i_poc ); | |
| + reference_build_list( h, h->fdec->i_poc ); | |
| /* ---------------------- Write the bitstream -------------------------- */ | |
| /* Init bitstream context */ | |
| @@ -3485,10 +3535,11 @@ | |
| else | |
| pic_type = 7; | |
| - x264_nal_start( h, NAL_AUD, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_AUD, NAL_PRIORITY_DISPOSABLE ); | |
| bs_write( &h->out.bs, 3, pic_type ); | |
| bs_rbsp_trailing( &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + bs_flush( &h->out.bs ); | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + NALU_OVERHEAD; | |
| } | |
| @@ -3538,9 +3589,9 @@ | |
| if( h->param.b_repeat_headers ) | |
| { | |
| /* generate sequence parameters */ | |
| - x264_nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST ); | |
| + nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST ); | |
| x264_sps_write( &h->out.bs, h->sps ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| /* Pad AUD/SPS to 256 bytes like Panasonic */ | |
| if( h->param.i_avcintra_class ) | |
| @@ -3548,22 +3599,28 @@ | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + h->out.nal[h->out.i_nal-1].i_padding + NALU_OVERHEAD; | |
| /* generate picture parameters */ | |
| - x264_nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST ); | |
| + nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST ); | |
| x264_pps_write( &h->out.bs, h->sps, h->pps ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| if( h->param.i_avcintra_class ) | |
| - h->out.nal[h->out.i_nal-1].i_padding = 256 - h->out.nal[h->out.i_nal-1].i_payload - NALU_OVERHEAD; | |
| + { | |
| + int total_len = 256; | |
| + /* Sony XAVC uses an oversized PPS instead of SEI padding */ | |
| + if( h->param.i_avcintra_flavor == X264_AVCINTRA_FLAVOR_SONY ) | |
| + total_len += h->param.i_height == 1080 ? 18*512 : 10*512; | |
| + h->out.nal[h->out.i_nal-1].i_padding = total_len - h->out.nal[h->out.i_nal-1].i_payload - NALU_OVERHEAD; | |
| + } | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + h->out.nal[h->out.i_nal-1].i_padding + NALU_OVERHEAD; | |
| } | |
| - /* when frame threading is used, buffering period sei is written in x264_encoder_frame_end */ | |
| + /* when frame threading is used, buffering period sei is written in encoder_frame_end */ | |
| if( h->i_thread_frames == 1 && h->sps->vui.b_nal_hrd_parameters_present ) | |
| { | |
| x264_hrd_fullness( h ); | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_buffering_period_write( h, &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3572,10 +3629,10 @@ | |
| /* write extra sei */ | |
| for( int i = 0; i < h->fenc->extra_sei.num_payloads; i++ ) | |
| { | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_write( &h->out.bs, h->fenc->extra_sei.payloads[i].payload, h->fenc->extra_sei.payloads[i].payload_size, | |
| h->fenc->extra_sei.payloads[i].payload_type ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| if( h->fenc->extra_sei.sei_free ) | |
| @@ -3598,10 +3655,10 @@ | |
| if( h->param.b_repeat_headers && h->fenc->i_frame == 0 && !h->param.i_avcintra_class ) | |
| { | |
| /* identify ourself */ | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| if( x264_sei_version_write( h, &h->out.bs ) ) | |
| return -1; | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3609,9 +3666,9 @@ | |
| if( h->fenc->i_type != X264_TYPE_IDR ) | |
| { | |
| int time_to_recovery = h->param.b_open_gop ? 0 : X264_MIN( h->mb.i_mb_width - 1, h->param.i_keyint_max ) + h->param.i_bframe - 1; | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_recovery_point_write( h, &h->out.bs, time_to_recovery ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3619,9 +3676,18 @@ | |
| if( h->param.i_frame_packing >= 0 && (h->fenc->b_keyframe || h->param.i_frame_packing == 5) ) | |
| { | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_frame_packing_write( h, &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| + return -1; | |
| + overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| + } | |
| + | |
| + if( h->param.i_alternative_transfer != 2 ) | |
| + { | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + x264_sei_alternative_transfer_write( h, &h->out.bs ); | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3629,9 +3695,9 @@ | |
| /* generate sei pic timing */ | |
| if( h->sps->vui.b_pic_struct_present || h->sps->vui.b_nal_hrd_parameters_present ) | |
| { | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_pic_timing_write( h, &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3640,9 +3706,9 @@ | |
| if( !IS_X264_TYPE_B( h->fenc->i_type ) && h->b_sh_backup ) | |
| { | |
| h->b_sh_backup = 0; | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_dec_ref_pic_marking_write( h, &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| } | |
| @@ -3651,21 +3717,21 @@ | |
| h->i_cpb_delay_pir_offset_next = h->fenc->i_cpb_delay; | |
| /* Filler space: 10 or 18 SEIs' worth of space, depending on resolution */ | |
| - if( h->param.i_avcintra_class ) | |
| + if( h->param.i_avcintra_class && h->param.i_avcintra_flavor != X264_AVCINTRA_FLAVOR_SONY ) | |
| { | |
| /* Write an empty filler NAL to mimic the AUD in the P2 format*/ | |
| - x264_nal_start( h, NAL_FILLER, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_FILLER, NAL_PRIORITY_DISPOSABLE ); | |
| x264_filler_write( h, &h->out.bs, 0 ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + NALU_OVERHEAD; | |
| /* All lengths are magic lengths that decoders expect to see */ | |
| /* "UMID" SEI */ | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| if( x264_sei_avcintra_umid_write( h, &h->out.bs ) < 0 ) | |
| return -1; | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD; | |
| @@ -3682,10 +3748,10 @@ | |
| total_len = 9*512; | |
| } | |
| /* "VANC" SEI */ | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| if( x264_sei_avcintra_vanc_write( h, &h->out.bs, unpadded_len ) < 0 ) | |
| return -1; | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| h->out.nal[h->out.i_nal-1].i_padding = total_len - h->out.nal[h->out.i_nal-1].i_payload - SEI_OVERHEAD; | |
| @@ -3703,20 +3769,20 @@ | |
| if( h->param.rc.b_stat_read && h->sh.i_type != SLICE_TYPE_I ) | |
| { | |
| x264_reference_build_list_optimal( h ); | |
| - x264_reference_check_reorder( h ); | |
| + reference_check_reorder( h ); | |
| } | |
| if( h->i_ref[0] ) | |
| h->fdec->i_poc_l0ref0 = h->fref[0][0]->i_poc; | |
| /* ------------------------ Create slice header ----------------------- */ | |
| - x264_slice_init( h, i_nal_type, i_global_qp ); | |
| + slice_init( h, i_nal_type, i_global_qp ); | |
| /*------------------------- Weights -------------------------------------*/ | |
| if( h->sh.i_type == SLICE_TYPE_B ) | |
| x264_macroblock_bipred_init( h ); | |
| - x264_weighted_pred_init( h ); | |
| + weighted_pred_init( h ); | |
| if( i_nal_ref_idc != NAL_PRIORITY_DISPOSABLE ) | |
| h->i_frame_num++; | |
| @@ -3726,24 +3792,24 @@ | |
| h->i_threadslice_end = h->mb.i_mb_height; | |
| if( h->i_thread_frames > 1 ) | |
| { | |
| - x264_threadpool_run( h->threadpool, (void*)x264_slices_write, h ); | |
| + x264_threadpool_run( h->threadpool, (void*)slices_write, h ); | |
| h->b_thread_active = 1; | |
| } | |
| else if( h->param.b_sliced_threads ) | |
| { | |
| - if( x264_threaded_slices_write( h ) ) | |
| + if( threaded_slices_write( h ) ) | |
| return -1; | |
| } | |
| else | |
| - if( (intptr_t)x264_slices_write( h ) ) | |
| + if( (intptr_t)slices_write( h ) ) | |
| return -1; | |
| - return x264_encoder_frame_end( thread_oldest, thread_current, pp_nal, pi_nal, pic_out ); | |
| + return encoder_frame_end( thread_oldest, thread_current, pp_nal, pi_nal, pic_out ); | |
| } | |
| -static int x264_encoder_frame_end( x264_t *h, x264_t *thread_current, | |
| - x264_nal_t **pp_nal, int *pi_nal, | |
| - x264_picture_t *pic_out ) | |
| +static int encoder_frame_end( x264_t *h, x264_t *thread_current, | |
| + x264_nal_t **pp_nal, int *pi_nal, | |
| + x264_picture_t *pic_out ) | |
| { | |
| char psz_message[80]; | |
| @@ -3765,9 +3831,9 @@ | |
| if( h->i_thread_frames > 1 && h->fenc->b_keyframe && h->sps->vui.b_nal_hrd_parameters_present ) | |
| { | |
| x264_hrd_fullness( h ); | |
| - x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); | |
| x264_sei_buffering_period_write( h, &h->out.bs ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| /* buffering period sei must follow AUD, SPS and PPS and precede all other SEIs */ | |
| int idx = 0; | |
| @@ -3780,7 +3846,7 @@ | |
| h->out.nal[idx] = nal_tmp; | |
| } | |
| - int frame_size = x264_encoder_encapsulate_nals( h, 0 ); | |
| + int frame_size = encoder_encapsulate_nals( h, 0 ); | |
| if( frame_size < 0 ) | |
| return -1; | |
| @@ -3805,7 +3871,7 @@ | |
| pic_out->img.i_plane = h->fdec->i_plane; | |
| for( int i = 0; i < pic_out->img.i_plane; i++ ) | |
| { | |
| - pic_out->img.i_stride[i] = h->fdec->i_stride[i] * sizeof(pixel); | |
| + pic_out->img.i_stride[i] = h->fdec->i_stride[i] * SIZEOF_PIXEL; | |
| pic_out->img.plane[i] = (uint8_t*)h->fdec->plane[i]; | |
| } | |
| @@ -3825,7 +3891,7 @@ | |
| * We don't know the size of the last slice until encapsulation so we add filler to the encapsulated NAL */ | |
| if( h->param.i_avcintra_class ) | |
| { | |
| - if( x264_check_encapsulated_buffer( h, h->thread[0], h->out.i_nal, frame_size, frame_size + filler ) < 0 ) | |
| + if( check_encapsulated_buffer( h, h->thread[0], h->out.i_nal, frame_size, (int64_t)frame_size + filler ) < 0 ) | |
| return -1; | |
| x264_nal_t *nal = &h->out.nal[h->out.i_nal-1]; | |
| @@ -3860,13 +3926,13 @@ | |
| else | |
| f = X264_MAX( 0, filler - overhead ); | |
| - if( x264_bitstream_check_buffer_filler( h, f ) ) | |
| + if( bitstream_check_buffer_filler( h, f ) ) | |
| return -1; | |
| - x264_nal_start( h, NAL_FILLER, NAL_PRIORITY_DISPOSABLE ); | |
| + nal_start( h, NAL_FILLER, NAL_PRIORITY_DISPOSABLE ); | |
| x264_filler_write( h, &h->out.bs, f ); | |
| - if( x264_nal_end( h ) ) | |
| + if( nal_end( h ) ) | |
| return -1; | |
| - int total_size = x264_encoder_encapsulate_nals( h, h->out.i_nal-1 ); | |
| + int total_size = encoder_encapsulate_nals( h, h->out.i_nal-1 ); | |
| if( total_size < 0 ) | |
| return -1; | |
| frame_size += total_size; | |
| @@ -3883,7 +3949,7 @@ | |
| x264_noise_reduction_update( h ); | |
| /* ---------------------- Compute/Print statistics --------------------- */ | |
| - x264_thread_sync_stat( h, h->thread[0] ); | |
| + thread_sync_stat( h, h->thread[0] ); | |
| /* Slice stat */ | |
| h->stat.i_frame_count[h->sh.i_type]++; | |
| @@ -3892,8 +3958,6 @@ | |
| for( int i = 0; i < X264_MBTYPE_MAX; i++ ) | |
| h->stat.i_mb_count[h->sh.i_type][i] += h->stat.frame.i_mb_count[i]; | |
| - for( int i = 0; i < X264_PARTTYPE_MAX; i++ ) | |
| - h->stat.i_mb_partition[h->sh.i_type][i] += h->stat.frame.i_mb_partition[i]; | |
| for( int i = 0; i < 2; i++ ) | |
| h->stat.i_mb_count_8x8dct[i] += h->stat.frame.i_mb_count_8x8dct[i]; | |
| for( int i = 0; i < 6; i++ ) | |
| @@ -3902,9 +3966,13 @@ | |
| for( int j = 0; j < 13; j++ ) | |
| h->stat.i_mb_pred_mode[i][j] += h->stat.frame.i_mb_pred_mode[i][j]; | |
| if( h->sh.i_type != SLICE_TYPE_I ) | |
| + { | |
| + for( int i = 0; i < X264_PARTTYPE_MAX; i++ ) | |
| + h->stat.i_mb_partition[h->sh.i_type][i] += h->stat.frame.i_mb_partition[i]; | |
| for( int i_list = 0; i_list < 2; i_list++ ) | |
| for( int i = 0; i < X264_REF_MAX*2; i++ ) | |
| h->stat.i_mb_count_ref[h->sh.i_type][i_list][i] += h->stat.frame.i_mb_count_ref[i_list][i]; | |
| + } | |
| for( int i = 0; i < 3; i++ ) | |
| h->stat.i_mb_field[i] += h->stat.frame.i_mb_field[i]; | |
| if( h->sh.i_type == SLICE_TYPE_P && h->param.analyse.i_weighted_pred >= X264_WEIGHTP_SIMPLE ) | |
| @@ -3941,10 +4009,10 @@ | |
| }; | |
| int luma_size = h->param.i_width * h->param.i_height; | |
| int chroma_size = CHROMA_SIZE( luma_size ); | |
| - pic_out->prop.f_psnr[0] = x264_psnr( ssd[0], luma_size ); | |
| - pic_out->prop.f_psnr[1] = x264_psnr( ssd[1], chroma_size ); | |
| - pic_out->prop.f_psnr[2] = x264_psnr( ssd[2], chroma_size ); | |
| - pic_out->prop.f_psnr_avg = x264_psnr( ssd[0] + ssd[1] + ssd[2], luma_size + chroma_size*2 ); | |
| + pic_out->prop.f_psnr[0] = calc_psnr( ssd[0], luma_size ); | |
| + pic_out->prop.f_psnr[1] = calc_psnr( ssd[1], chroma_size ); | |
| + pic_out->prop.f_psnr[2] = calc_psnr( ssd[2], chroma_size ); | |
| + pic_out->prop.f_psnr_avg = calc_psnr( ssd[0] + ssd[1] + ssd[2], luma_size + chroma_size*2 ); | |
| h->stat.f_ssd_global[h->sh.i_type] += dur * (ssd[0] + ssd[1] + ssd[2]); | |
| h->stat.f_psnr_average[h->sh.i_type] += dur * pic_out->prop.f_psnr_avg; | |
| @@ -3980,9 +4048,9 @@ | |
| psz_message ); | |
| // keep stats all in one place | |
| - x264_thread_sync_stat( h->thread[0], h ); | |
| + thread_sync_stat( h->thread[0], h ); | |
| // for the use of the next frame | |
| - x264_thread_sync_stat( thread_current, h ); | |
| + thread_sync_stat( thread_current, h ); | |
| #ifdef DEBUG_MB_TYPE | |
| { | |
| @@ -4011,13 +4079,13 @@ | |
| } | |
| if( h->param.psz_dump_yuv ) | |
| - x264_frame_dump( h ); | |
| + frame_dump( h ); | |
| x264_emms(); | |
| return frame_size; | |
| } | |
| -static void x264_print_intra( int64_t *i_mb_count, double i_count, int b_print_pcm, char *intra ) | |
| +static void print_intra( int64_t *i_mb_count, double i_count, int b_print_pcm, char *intra ) | |
| { | |
| intra += sprintf( intra, "I16..4%s: %4.1f%% %4.1f%% %4.1f%%", | |
| b_print_pcm ? "..PCM" : "", | |
| @@ -4048,7 +4116,7 @@ | |
| #endif | |
| if( h->param.b_sliced_threads ) | |
| - x264_threadpool_wait_all( h ); | |
| + threadpool_wait_all( h ); | |
| if( h->param.i_threads > 1 ) | |
| x264_threadpool_delete( h->threadpool ); | |
| if( h->param.i_lookahead_threads > 1 ) | |
| @@ -4089,7 +4157,7 @@ | |
| (double)h->stat.i_frame_size[i_slice] / i_count, | |
| h->stat.f_psnr_mean_y[i_slice] / dur, h->stat.f_psnr_mean_u[i_slice] / dur, h->stat.f_psnr_mean_v[i_slice] / dur, | |
| h->stat.f_psnr_average[i_slice] / dur, | |
| - x264_psnr( h->stat.f_ssd_global[i_slice], dur * i_yuv_size ) ); | |
| + calc_psnr( h->stat.f_ssd_global[i_slice], dur * i_yuv_size ) ); | |
| } | |
| else | |
| { | |
| @@ -4126,7 +4194,7 @@ | |
| { | |
| int64_t *i_mb_count = h->stat.i_mb_count[SLICE_TYPE_I]; | |
| double i_count = (double)h->stat.i_frame_count[SLICE_TYPE_I] * h->mb.i_mb_count / 100.0; | |
| - x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| + print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| x264_log( h, X264_LOG_INFO, "mb I %s\n", buf ); | |
| } | |
| if( h->stat.i_frame_count[SLICE_TYPE_P] > 0 ) | |
| @@ -4134,7 +4202,7 @@ | |
| int64_t *i_mb_count = h->stat.i_mb_count[SLICE_TYPE_P]; | |
| double i_count = (double)h->stat.i_frame_count[SLICE_TYPE_P] * h->mb.i_mb_count / 100.0; | |
| int64_t *i_mb_size = i_mb_count_size[SLICE_TYPE_P]; | |
| - x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| + print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| x264_log( h, X264_LOG_INFO, | |
| "mb P %s P16..4: %4.1f%% %4.1f%% %4.1f%% %4.1f%% %4.1f%% skip:%4.1f%%\n", | |
| buf, | |
| @@ -4152,7 +4220,7 @@ | |
| double i_mb_list_count; | |
| int64_t *i_mb_size = i_mb_count_size[SLICE_TYPE_B]; | |
| int64_t list_count[3] = {0}; /* 0 == L0, 1 == L1, 2 == BI */ | |
| - x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| + print_intra( i_mb_count, i_count, b_print_pcm, buf ); | |
| for( int i = 0; i < X264_PARTTYPE_MAX; i++ ) | |
| for( int j = 0; j < 2; j++ ) | |
| { | |
| @@ -4232,17 +4300,27 @@ | |
| } | |
| buf[0] = 0; | |
| - int csize = CHROMA444 ? 4 : 1; | |
| - if( i_mb_count != i_all_intra ) | |
| - sprintf( buf, " inter: %.1f%% %.1f%% %.1f%%", | |
| - h->stat.i_mb_cbp[1] * 100.0 / ((i_mb_count - i_all_intra)*4), | |
| - h->stat.i_mb_cbp[3] * 100.0 / ((i_mb_count - i_all_intra)*csize), | |
| - h->stat.i_mb_cbp[5] * 100.0 / ((i_mb_count - i_all_intra)*csize) ); | |
| - x264_log( h, X264_LOG_INFO, "coded y,%s,%s intra: %.1f%% %.1f%% %.1f%%%s\n", | |
| - CHROMA444?"u":"uvDC", CHROMA444?"v":"uvAC", | |
| - h->stat.i_mb_cbp[0] * 100.0 / (i_all_intra*4), | |
| - h->stat.i_mb_cbp[2] * 100.0 / (i_all_intra*csize), | |
| - h->stat.i_mb_cbp[4] * 100.0 / (i_all_intra*csize), buf ); | |
| + if( CHROMA_FORMAT ) | |
| + { | |
| + int csize = CHROMA444 ? 4 : 1; | |
| + if( i_mb_count != i_all_intra ) | |
| + sprintf( buf, " inter: %.1f%% %.1f%% %.1f%%", | |
| + h->stat.i_mb_cbp[1] * 100.0 / ((i_mb_count - i_all_intra)*4), | |
| + h->stat.i_mb_cbp[3] * 100.0 / ((i_mb_count - i_all_intra)*csize), | |
| + h->stat.i_mb_cbp[5] * 100.0 / ((i_mb_count - i_all_intra)*csize) ); | |
| + x264_log( h, X264_LOG_INFO, "coded y,%s,%s intra: %.1f%% %.1f%% %.1f%%%s\n", | |
| + CHROMA444?"u":"uvDC", CHROMA444?"v":"uvAC", | |
| + h->stat.i_mb_cbp[0] * 100.0 / (i_all_intra*4), | |
| + h->stat.i_mb_cbp[2] * 100.0 / (i_all_intra*csize), | |
| + h->stat.i_mb_cbp[4] * 100.0 / (i_all_intra*csize), buf ); | |
| + } | |
| + else | |
| + { | |
| + if( i_mb_count != i_all_intra ) | |
| + sprintf( buf, " inter: %.1f%%", h->stat.i_mb_cbp[1] * 100.0 / ((i_mb_count - i_all_intra)*4) ); | |
| + x264_log( h, X264_LOG_INFO, "coded y intra: %.1f%%%s\n", | |
| + h->stat.i_mb_cbp[0] * 100.0 / (i_all_intra*4), buf ); | |
| + } | |
| int64_t fixed_pred_modes[4][9] = {{0}}; | |
| int64_t sum_pred_modes[4] = {0}; | |
| @@ -4289,9 +4367,13 @@ | |
| fixed_pred_modes[3][3] * 100.0 / sum_pred_modes[3] ); | |
| if( h->param.analyse.i_weighted_pred >= X264_WEIGHTP_SIMPLE && h->stat.i_frame_count[SLICE_TYPE_P] > 0 ) | |
| - x264_log( h, X264_LOG_INFO, "Weighted P-Frames: Y:%.1f%% UV:%.1f%%\n", | |
| - h->stat.i_wpred[0] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P], | |
| - h->stat.i_wpred[1] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P] ); | |
| + { | |
| + buf[0] = 0; | |
| + if( CHROMA_FORMAT ) | |
| + sprintf( buf, " UV:%.1f%%", h->stat.i_wpred[1] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P] ); | |
| + x264_log( h, X264_LOG_INFO, "Weighted P-Frames: Y:%.1f%%%s\n", | |
| + h->stat.i_wpred[0] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P], buf ); | |
| + } | |
| for( int i_list = 0; i_list < 2; i_list++ ) | |
| for( int i_slice = 0; i_slice < 2; i_slice++ ) | |
| @@ -4315,7 +4397,7 @@ | |
| if( h->param.analyse.b_ssim ) | |
| { | |
| float ssim = SUM3( h->stat.f_ssim_mean_y ) / duration; | |
| - x264_log( h, X264_LOG_INFO, "SSIM Mean Y:%.7f (%6.3fdb)\n", ssim, x264_ssim( ssim ) ); | |
| + x264_log( h, X264_LOG_INFO, "SSIM Mean Y:%.7f (%6.3fdb)\n", ssim, calc_ssim_db( ssim ) ); | |
| } | |
| if( h->param.analyse.b_psnr ) | |
| { | |
| @@ -4325,7 +4407,7 @@ | |
| SUM3( h->stat.f_psnr_mean_u ) / duration, | |
| SUM3( h->stat.f_psnr_mean_v ) / duration, | |
| SUM3( h->stat.f_psnr_average ) / duration, | |
| - x264_psnr( SUM3( h->stat.f_ssd_global ), duration * i_yuv_size ), | |
| + calc_psnr( SUM3( h->stat.f_ssd_global ), duration * i_yuv_size ), | |
| f_bitrate ); | |
| } | |
| else | |
| @@ -4345,6 +4427,7 @@ | |
| x264_free( h->nal_buffer ); | |
| x264_free( h->reconfig_h ); | |
| x264_analyse_free_costs( h ); | |
| + x264_free( h->cost_table ); | |
| if( h->i_thread_frames > 1 ) | |
| h = h->thread[h->i_thread_phase]; | |
| diff -ur x264-go/x264c/external/x264/encoder/lookahead.c x264-go.new/x264c/external/x264/encoder/lookahead.c | |
| --- x264-go/x264c/external/x264/encoder/lookahead.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/lookahead.c 2020-06-06 15:20:58.697039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * lookahead.c: high-level lookahead functions | |
| ***************************************************************************** | |
| - * Copyright (C) 2010-2017 Avail Media and x264 project | |
| + * Copyright (C) 2010-2020 Avail Media and x264 project | |
| * | |
| * Authors: Michael Kazmier <mkazmier@availmedia.com> | |
| * Alex Giladi <agiladi@availmedia.com> | |
| @@ -39,7 +39,7 @@ | |
| #include "common/common.h" | |
| #include "analyse.h" | |
| -static void x264_lookahead_shift( x264_sync_frame_list_t *dst, x264_sync_frame_list_t *src, int count ) | |
| +static void lookahead_shift( x264_sync_frame_list_t *dst, x264_sync_frame_list_t *src, int count ) | |
| { | |
| int i = count; | |
| while( i-- ) | |
| @@ -56,7 +56,7 @@ | |
| } | |
| } | |
| -static void x264_lookahead_update_last_nonb( x264_t *h, x264_frame_t *new_nonb ) | |
| +static void lookahead_update_last_nonb( x264_t *h, x264_frame_t *new_nonb ) | |
| { | |
| if( h->lookahead->last_nonb ) | |
| x264_frame_push_unused( h, h->lookahead->last_nonb ); | |
| @@ -65,11 +65,11 @@ | |
| } | |
| #if HAVE_THREAD | |
| -static void x264_lookahead_slicetype_decide( x264_t *h ) | |
| +static void lookahead_slicetype_decide( x264_t *h ) | |
| { | |
| - x264_stack_align( x264_slicetype_decide, h ); | |
| + x264_slicetype_decide( h ); | |
| - x264_lookahead_update_last_nonb( h, h->lookahead->next.list[0] ); | |
| + lookahead_update_last_nonb( h, h->lookahead->next.list[0] ); | |
| int shift_frames = h->lookahead->next.list[0]->i_bframes + 1; | |
| x264_pthread_mutex_lock( &h->lookahead->ofbuf.mutex ); | |
| @@ -77,24 +77,24 @@ | |
| x264_pthread_cond_wait( &h->lookahead->ofbuf.cv_empty, &h->lookahead->ofbuf.mutex ); | |
| x264_pthread_mutex_lock( &h->lookahead->next.mutex ); | |
| - x264_lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames ); | |
| + lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames ); | |
| x264_pthread_mutex_unlock( &h->lookahead->next.mutex ); | |
| /* For MB-tree and VBV lookahead, we have to perform propagation analysis on I-frames too. */ | |
| if( h->lookahead->b_analyse_keyframe && IS_X264_TYPE_I( h->lookahead->last_nonb->i_type ) ) | |
| - x264_stack_align( x264_slicetype_analyse, h, shift_frames ); | |
| + x264_slicetype_analyse( h, shift_frames ); | |
| x264_pthread_mutex_unlock( &h->lookahead->ofbuf.mutex ); | |
| } | |
| -static void *x264_lookahead_thread( x264_t *h ) | |
| +REALIGN_STACK static void *lookahead_thread( x264_t *h ) | |
| { | |
| while( !h->lookahead->b_exit_thread ) | |
| { | |
| x264_pthread_mutex_lock( &h->lookahead->ifbuf.mutex ); | |
| x264_pthread_mutex_lock( &h->lookahead->next.mutex ); | |
| int shift = X264_MIN( h->lookahead->next.i_max_size - h->lookahead->next.i_size, h->lookahead->ifbuf.i_size ); | |
| - x264_lookahead_shift( &h->lookahead->next, &h->lookahead->ifbuf, shift ); | |
| + lookahead_shift( &h->lookahead->next, &h->lookahead->ifbuf, shift ); | |
| x264_pthread_mutex_unlock( &h->lookahead->next.mutex ); | |
| if( h->lookahead->next.i_size <= h->lookahead->i_slicetype_length + h->param.b_vfr_input ) | |
| { | |
| @@ -105,22 +105,23 @@ | |
| else | |
| { | |
| x264_pthread_mutex_unlock( &h->lookahead->ifbuf.mutex ); | |
| - x264_lookahead_slicetype_decide( h ); | |
| + lookahead_slicetype_decide( h ); | |
| } | |
| } /* end of input frames */ | |
| x264_pthread_mutex_lock( &h->lookahead->ifbuf.mutex ); | |
| x264_pthread_mutex_lock( &h->lookahead->next.mutex ); | |
| - x264_lookahead_shift( &h->lookahead->next, &h->lookahead->ifbuf, h->lookahead->ifbuf.i_size ); | |
| + lookahead_shift( &h->lookahead->next, &h->lookahead->ifbuf, h->lookahead->ifbuf.i_size ); | |
| x264_pthread_mutex_unlock( &h->lookahead->next.mutex ); | |
| x264_pthread_mutex_unlock( &h->lookahead->ifbuf.mutex ); | |
| while( h->lookahead->next.i_size ) | |
| - x264_lookahead_slicetype_decide( h ); | |
| + lookahead_slicetype_decide( h ); | |
| x264_pthread_mutex_lock( &h->lookahead->ofbuf.mutex ); | |
| h->lookahead->b_thread_active = 0; | |
| x264_pthread_cond_broadcast( &h->lookahead->ofbuf.cv_fill ); | |
| x264_pthread_mutex_unlock( &h->lookahead->ofbuf.mutex ); | |
| return NULL; | |
| } | |
| + | |
| #endif | |
| int x264_lookahead_init( x264_t *h, int i_slicetype_length ) | |
| @@ -152,7 +153,7 @@ | |
| if( x264_macroblock_thread_allocate( look_h, 1 ) < 0 ) | |
| goto fail; | |
| - if( x264_pthread_create( &look->thread_handle, NULL, (void*)x264_lookahead_thread, look_h ) ) | |
| + if( x264_pthread_create( &look->thread_handle, NULL, (void*)lookahead_thread, look_h ) ) | |
| goto fail; | |
| look->b_thread_active = 1; | |
| @@ -201,7 +202,7 @@ | |
| return b_empty; | |
| } | |
| -static void x264_lookahead_encoder_shift( x264_t *h ) | |
| +static void lookahead_encoder_shift( x264_t *h ) | |
| { | |
| if( !h->lookahead->ofbuf.i_size ) | |
| return; | |
| @@ -221,7 +222,7 @@ | |
| x264_pthread_mutex_lock( &h->lookahead->ofbuf.mutex ); | |
| while( !h->lookahead->ofbuf.i_size && h->lookahead->b_thread_active ) | |
| x264_pthread_cond_wait( &h->lookahead->ofbuf.cv_fill, &h->lookahead->ofbuf.mutex ); | |
| - x264_lookahead_encoder_shift( h ); | |
| + lookahead_encoder_shift( h ); | |
| x264_pthread_mutex_unlock( &h->lookahead->ofbuf.mutex ); | |
| } | |
| else | |
| @@ -230,15 +231,15 @@ | |
| if( h->frames.current[0] || !h->lookahead->next.i_size ) | |
| return; | |
| - x264_stack_align( x264_slicetype_decide, h ); | |
| - x264_lookahead_update_last_nonb( h, h->lookahead->next.list[0] ); | |
| + x264_slicetype_decide( h ); | |
| + lookahead_update_last_nonb( h, h->lookahead->next.list[0] ); | |
| int shift_frames = h->lookahead->next.list[0]->i_bframes + 1; | |
| - x264_lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames ); | |
| + lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames ); | |
| /* For MB-tree and VBV lookahead, we have to perform propagation analysis on I-frames too. */ | |
| if( h->lookahead->b_analyse_keyframe && IS_X264_TYPE_I( h->lookahead->last_nonb->i_type ) ) | |
| - x264_stack_align( x264_slicetype_analyse, h, shift_frames ); | |
| + x264_slicetype_analyse( h, shift_frames ); | |
| - x264_lookahead_encoder_shift( h ); | |
| + lookahead_encoder_shift( h ); | |
| } | |
| } | |
| diff -ur x264-go/x264c/external/x264/encoder/macroblock.c x264-go.new/x264c/external/x264/encoder/macroblock.c | |
| --- x264-go/x264c/external/x264/encoder/macroblock.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/macroblock.c 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * macroblock.c: macroblock encoding | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -123,7 +123,7 @@ | |
| /* This means that decimation can be done merely by adjusting the CBP and NNZ | |
| * rather than memsetting the coefficients. */ | |
| -static void x264_mb_encode_i16x16( x264_t *h, int p, int i_qp ) | |
| +static void mb_encode_i16x16( x264_t *h, int p, int i_qp ) | |
| { | |
| pixel *p_src = h->mb.pic.p_fenc[p]; | |
| pixel *p_dst = h->mb.pic.p_fdec[p]; | |
| @@ -242,7 +242,7 @@ | |
| * Unlike luma blocks, this can't be done with a lookup table or | |
| * other shortcut technique because of the interdependencies | |
| * between the coefficients due to the chroma DC transform. */ | |
| -static ALWAYS_INLINE int x264_mb_optimize_chroma_dc( x264_t *h, dctcoef *dct_dc, int dequant_mf[6][16], int i_qp, int chroma422 ) | |
| +static ALWAYS_INLINE int mb_optimize_chroma_dc( x264_t *h, dctcoef *dct_dc, int dequant_mf[6][16], int i_qp, int chroma422 ) | |
| { | |
| int dmf = dequant_mf[i_qp%6][0] << i_qp/6; | |
| @@ -256,7 +256,7 @@ | |
| return h->quantf.optimize_chroma_2x2_dc( dct_dc, dmf ); | |
| } | |
| -static ALWAYS_INLINE void x264_mb_encode_chroma_internal( x264_t *h, int b_inter, int i_qp, int chroma422 ) | |
| +static ALWAYS_INLINE void mb_encode_chroma_internal( x264_t *h, int b_inter, int i_qp, int chroma422 ) | |
| { | |
| int nz, nz_dc; | |
| int b_decimate = b_inter && h->mb.b_dct_decimate; | |
| @@ -316,7 +316,7 @@ | |
| if( nz_dc ) | |
| { | |
| - if( !x264_mb_optimize_chroma_dc( h, dct_dc, dequant_mf, i_qp+3*chroma422, chroma422 ) ) | |
| + if( !mb_optimize_chroma_dc( h, dct_dc, dequant_mf, i_qp+3*chroma422, chroma422 ) ) | |
| continue; | |
| h->mb.cache.non_zero_count[x264_scan8[CHROMA_DC+ch]] = 1; | |
| if( chroma422 ) | |
| @@ -441,7 +441,7 @@ | |
| if( !nz_dc ) /* Whole block is empty */ | |
| continue; | |
| - if( !x264_mb_optimize_chroma_dc( h, dct_dc, dequant_mf, i_qp+3*chroma422, chroma422 ) ) | |
| + if( !mb_optimize_chroma_dc( h, dct_dc, dequant_mf, i_qp+3*chroma422, chroma422 ) ) | |
| { | |
| h->mb.cache.non_zero_count[x264_scan8[CHROMA_DC+ch]] = 0; | |
| continue; | |
| @@ -492,12 +492,12 @@ | |
| void x264_mb_encode_chroma( x264_t *h, int b_inter, int i_qp ) | |
| { | |
| if( CHROMA_FORMAT == CHROMA_420 ) | |
| - x264_mb_encode_chroma_internal( h, b_inter, i_qp, 0 ); | |
| + mb_encode_chroma_internal( h, b_inter, i_qp, 0 ); | |
| else | |
| - x264_mb_encode_chroma_internal( h, b_inter, i_qp, 1 ); | |
| + mb_encode_chroma_internal( h, b_inter, i_qp, 1 ); | |
| } | |
| -static void x264_macroblock_encode_skip( x264_t *h ) | |
| +static void macroblock_encode_skip( x264_t *h ) | |
| { | |
| M32( &h->mb.cache.non_zero_count[x264_scan8[ 0]] ) = 0; | |
| M32( &h->mb.cache.non_zero_count[x264_scan8[ 2]] ) = 0; | |
| @@ -530,8 +530,8 @@ | |
| { | |
| h->mc.copy[PIXEL_8x8]( h->mb.pic.p_fdec[1], FDEC_STRIDE, h->mb.pic.p_fenc[1]-FENC_STRIDE, FENC_STRIDE, height ); | |
| h->mc.copy[PIXEL_8x8]( h->mb.pic.p_fdec[2], FDEC_STRIDE, h->mb.pic.p_fenc[2]-FENC_STRIDE, FENC_STRIDE, height ); | |
| - memcpy( h->mb.pic.p_fdec[1], h->mb.pic.p_fdec[1]-FDEC_STRIDE, 8*sizeof(pixel) ); | |
| - memcpy( h->mb.pic.p_fdec[2], h->mb.pic.p_fdec[2]-FDEC_STRIDE, 8*sizeof(pixel) ); | |
| + memcpy( h->mb.pic.p_fdec[1], h->mb.pic.p_fdec[1]-FDEC_STRIDE, 8*SIZEOF_PIXEL ); | |
| + memcpy( h->mb.pic.p_fdec[2], h->mb.pic.p_fdec[2]-FDEC_STRIDE, 8*SIZEOF_PIXEL ); | |
| } | |
| else if( i_mode == I_PRED_CHROMA_H ) | |
| { | |
| @@ -560,7 +560,7 @@ | |
| if( i_mode == I_PRED_4x4_V ) | |
| { | |
| h->mc.copy[PIXEL_4x4]( p_dst, FDEC_STRIDE, p_src-stride, stride, 4 ); | |
| - memcpy( p_dst, p_dst-FDEC_STRIDE, 4*sizeof(pixel) ); | |
| + memcpy( p_dst, p_dst-FDEC_STRIDE, 4*SIZEOF_PIXEL ); | |
| } | |
| else if( i_mode == I_PRED_4x4_H ) | |
| { | |
| @@ -580,7 +580,7 @@ | |
| if( i_mode == I_PRED_8x8_V ) | |
| { | |
| h->mc.copy[PIXEL_8x8]( p_dst, FDEC_STRIDE, p_src-stride, stride, 8 ); | |
| - memcpy( p_dst, &edge[16], 8*sizeof(pixel) ); | |
| + memcpy( p_dst, &edge[16], 8*SIZEOF_PIXEL ); | |
| } | |
| else if( i_mode == I_PRED_8x8_H ) | |
| { | |
| @@ -600,7 +600,7 @@ | |
| if( i_mode == I_PRED_16x16_V ) | |
| { | |
| h->mc.copy[PIXEL_16x16]( p_dst, FDEC_STRIDE, h->mb.pic.p_fenc_plane[p]-stride, stride, 16 ); | |
| - memcpy( p_dst, p_dst-FDEC_STRIDE, 16*sizeof(pixel) ); | |
| + memcpy( p_dst, p_dst-FDEC_STRIDE, 16*SIZEOF_PIXEL ); | |
| } | |
| else if( i_mode == I_PRED_16x16_H ) | |
| { | |
| @@ -615,7 +615,7 @@ | |
| /***************************************************************************** | |
| * x264_macroblock_encode: | |
| *****************************************************************************/ | |
| -static ALWAYS_INLINE void x264_macroblock_encode_internal( x264_t *h, int plane_count, int chroma ) | |
| +static ALWAYS_INLINE void macroblock_encode_internal( x264_t *h, int plane_count, int chroma ) | |
| { | |
| int i_qp = h->mb.i_qp; | |
| int b_decimate = h->mb.b_dct_decimate; | |
| @@ -691,7 +691,7 @@ | |
| } | |
| } | |
| - x264_macroblock_encode_skip( h ); | |
| + macroblock_encode_skip( h ); | |
| return; | |
| } | |
| if( h->mb.i_type == B_SKIP ) | |
| @@ -699,7 +699,7 @@ | |
| /* don't do bskip motion compensation if it was already done in macroblock_analyse */ | |
| if( !h->mb.b_skip_mc ) | |
| x264_mb_mc( h ); | |
| - x264_macroblock_encode_skip( h ); | |
| + macroblock_encode_skip( h ); | |
| return; | |
| } | |
| @@ -708,7 +708,7 @@ | |
| h->mb.b_transform_8x8 = 0; | |
| for( int p = 0; p < plane_count; p++, i_qp = h->mb.i_chroma_qp ) | |
| - x264_mb_encode_i16x16( h, p, i_qp ); | |
| + mb_encode_i16x16( h, p, i_qp ); | |
| } | |
| else if( h->mb.i_type == I_8x8 ) | |
| { | |
| @@ -974,16 +974,18 @@ | |
| void x264_macroblock_encode( x264_t *h ) | |
| { | |
| if( CHROMA444 ) | |
| - x264_macroblock_encode_internal( h, 3, 0 ); | |
| + macroblock_encode_internal( h, 3, 0 ); | |
| + else if( CHROMA_FORMAT ) | |
| + macroblock_encode_internal( h, 1, 1 ); | |
| else | |
| - x264_macroblock_encode_internal( h, 1, 1 ); | |
| + macroblock_encode_internal( h, 1, 0 ); | |
| } | |
| /***************************************************************************** | |
| * x264_macroblock_probe_skip: | |
| * Check if the current MB could be encoded as a [PB]_SKIP | |
| *****************************************************************************/ | |
| -static ALWAYS_INLINE int x264_macroblock_probe_skip_internal( x264_t *h, int b_bidir, int plane_count, int chroma ) | |
| +static ALWAYS_INLINE int macroblock_probe_skip_internal( x264_t *h, int b_bidir, int plane_count, int chroma ) | |
| { | |
| ALIGNED_ARRAY_64( dctcoef, dct4x4,[8],[16] ); | |
| ALIGNED_ARRAY_64( dctcoef, dctscan,[16] ); | |
| @@ -1126,12 +1128,14 @@ | |
| int x264_macroblock_probe_skip( x264_t *h, int b_bidir ) | |
| { | |
| - if( CHROMA_FORMAT == CHROMA_444 ) | |
| - return x264_macroblock_probe_skip_internal( h, b_bidir, 3, CHROMA_444 ); | |
| + if( CHROMA_FORMAT == CHROMA_420 ) | |
| + return macroblock_probe_skip_internal( h, b_bidir, 1, CHROMA_420 ); | |
| else if( CHROMA_FORMAT == CHROMA_422 ) | |
| - return x264_macroblock_probe_skip_internal( h, b_bidir, 1, CHROMA_422 ); | |
| + return macroblock_probe_skip_internal( h, b_bidir, 1, CHROMA_422 ); | |
| + else if( CHROMA_FORMAT == CHROMA_444 ) | |
| + return macroblock_probe_skip_internal( h, b_bidir, 3, CHROMA_444 ); | |
| else | |
| - return x264_macroblock_probe_skip_internal( h, b_bidir, 1, CHROMA_420 ); | |
| + return macroblock_probe_skip_internal( h, b_bidir, 1, CHROMA_400 ); | |
| } | |
| /**************************************************************************** | |
| @@ -1172,7 +1176,7 @@ | |
| * RD only; 4 calls to this do not make up for one macroblock_encode. | |
| * doesn't transform chroma dc. | |
| *****************************************************************************/ | |
| -static ALWAYS_INLINE void x264_macroblock_encode_p8x8_internal( x264_t *h, int i8, int plane_count, int chroma ) | |
| +static ALWAYS_INLINE void macroblock_encode_p8x8_internal( x264_t *h, int i8, int plane_count, int chroma ) | |
| { | |
| int b_decimate = h->mb.b_dct_decimate; | |
| int i_qp = h->mb.i_qp; | |
| @@ -1365,18 +1369,20 @@ | |
| void x264_macroblock_encode_p8x8( x264_t *h, int i8 ) | |
| { | |
| - if( CHROMA444 ) | |
| - x264_macroblock_encode_p8x8_internal( h, i8, 3, CHROMA_444 ); | |
| + if( CHROMA_FORMAT == CHROMA_420 ) | |
| + macroblock_encode_p8x8_internal( h, i8, 1, CHROMA_420 ); | |
| else if( CHROMA_FORMAT == CHROMA_422 ) | |
| - x264_macroblock_encode_p8x8_internal( h, i8, 1, CHROMA_422 ); | |
| + macroblock_encode_p8x8_internal( h, i8, 1, CHROMA_422 ); | |
| + else if( CHROMA_FORMAT == CHROMA_444 ) | |
| + macroblock_encode_p8x8_internal( h, i8, 3, CHROMA_444 ); | |
| else | |
| - x264_macroblock_encode_p8x8_internal( h, i8, 1, CHROMA_420 ); | |
| + macroblock_encode_p8x8_internal( h, i8, 1, CHROMA_400 ); | |
| } | |
| /***************************************************************************** | |
| * RD only, luma only (for 4:2:0) | |
| *****************************************************************************/ | |
| -static ALWAYS_INLINE void x264_macroblock_encode_p4x4_internal( x264_t *h, int i4, int plane_count ) | |
| +static ALWAYS_INLINE void macroblock_encode_p4x4_internal( x264_t *h, int i4, int plane_count ) | |
| { | |
| int i_qp = h->mb.i_qp; | |
| @@ -1413,7 +1419,7 @@ | |
| void x264_macroblock_encode_p4x4( x264_t *h, int i8 ) | |
| { | |
| if( CHROMA444 ) | |
| - x264_macroblock_encode_p4x4_internal( h, i8, 3 ); | |
| + macroblock_encode_p4x4_internal( h, i8, 3 ); | |
| else | |
| - x264_macroblock_encode_p4x4_internal( h, i8, 1 ); | |
| + macroblock_encode_p4x4_internal( h, i8, 1 ); | |
| } | |
| diff -ur x264-go/x264c/external/x264/encoder/macroblock.h x264-go.new/x264c/external/x264/encoder/macroblock.h | |
| --- x264-go/x264c/external/x264/encoder/macroblock.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/macroblock.h 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * macroblock.h: macroblock encoding | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -29,11 +29,10 @@ | |
| #include "common/macroblock.h" | |
| -extern const int x264_lambda2_tab[QP_MAX_MAX+1]; | |
| -extern const uint16_t x264_lambda_tab[QP_MAX_MAX+1]; | |
| - | |
| +#define x264_rdo_init x264_template(rdo_init) | |
| void x264_rdo_init( void ); | |
| +#define x264_macroblock_probe_skip x264_template(macroblock_probe_skip) | |
| int x264_macroblock_probe_skip( x264_t *h, int b_bidir ); | |
| #define x264_macroblock_probe_pskip( h )\ | |
| @@ -41,32 +40,51 @@ | |
| #define x264_macroblock_probe_bskip( h )\ | |
| x264_macroblock_probe_skip( h, 1 ) | |
| +#define x264_predict_lossless_4x4 x264_template(predict_lossless_4x4) | |
| void x264_predict_lossless_4x4( x264_t *h, pixel *p_dst, int p, int idx, int i_mode ); | |
| +#define x264_predict_lossless_8x8 x264_template(predict_lossless_8x8) | |
| void x264_predict_lossless_8x8( x264_t *h, pixel *p_dst, int p, int idx, int i_mode, pixel edge[36] ); | |
| +#define x264_predict_lossless_16x16 x264_template(predict_lossless_16x16) | |
| void x264_predict_lossless_16x16( x264_t *h, int p, int i_mode ); | |
| +#define x264_predict_lossless_chroma x264_template(predict_lossless_chroma) | |
| void x264_predict_lossless_chroma( x264_t *h, int i_mode ); | |
| +#define x264_macroblock_encode x264_template(macroblock_encode) | |
| void x264_macroblock_encode ( x264_t *h ); | |
| +#define x264_macroblock_write_cabac x264_template(macroblock_write_cabac) | |
| void x264_macroblock_write_cabac ( x264_t *h, x264_cabac_t *cb ); | |
| +#define x264_macroblock_write_cavlc x264_template(macroblock_write_cavlc) | |
| void x264_macroblock_write_cavlc ( x264_t *h ); | |
| +#define x264_macroblock_encode_p8x8 x264_template(macroblock_encode_p8x8) | |
| void x264_macroblock_encode_p8x8( x264_t *h, int i8 ); | |
| +#define x264_macroblock_encode_p4x4 x264_template(macroblock_encode_p4x4) | |
| void x264_macroblock_encode_p4x4( x264_t *h, int i4 ); | |
| +#define x264_mb_encode_chroma x264_template(mb_encode_chroma) | |
| void x264_mb_encode_chroma( x264_t *h, int b_inter, int i_qp ); | |
| +#define x264_cabac_mb_skip x264_template(cabac_mb_skip) | |
| void x264_cabac_mb_skip( x264_t *h, int b_skip ); | |
| +#define x264_cabac_block_residual_c x264_template(cabac_block_residual_c) | |
| void x264_cabac_block_residual_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ); | |
| +#define x264_cabac_block_residual_8x8_rd_c x264_template(cabac_block_residual_8x8_rd_c) | |
| void x264_cabac_block_residual_8x8_rd_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ); | |
| +#define x264_cabac_block_residual_rd_c x264_template(cabac_block_residual_rd_c) | |
| void x264_cabac_block_residual_rd_c( x264_t *h, x264_cabac_t *cb, int ctx_block_cat, dctcoef *l ); | |
| +#define x264_quant_luma_dc_trellis x264_template(quant_luma_dc_trellis) | |
| int x264_quant_luma_dc_trellis( x264_t *h, dctcoef *dct, int i_quant_cat, int i_qp, | |
| int ctx_block_cat, int b_intra, int idx ); | |
| +#define x264_quant_chroma_dc_trellis x264_template(quant_chroma_dc_trellis) | |
| int x264_quant_chroma_dc_trellis( x264_t *h, dctcoef *dct, int i_qp, int b_intra, int idx ); | |
| +#define x264_quant_4x4_trellis x264_template(quant_4x4_trellis) | |
| int x264_quant_4x4_trellis( x264_t *h, dctcoef *dct, int i_quant_cat, | |
| int i_qp, int ctx_block_cat, int b_intra, int b_chroma, int idx ); | |
| +#define x264_quant_8x8_trellis x264_template(quant_8x8_trellis) | |
| int x264_quant_8x8_trellis( x264_t *h, dctcoef *dct, int i_quant_cat, | |
| int i_qp, int ctx_block_cat, int b_intra, int b_chroma, int idx ); | |
| +#define x264_noise_reduction_update x264_template(noise_reduction_update) | |
| void x264_noise_reduction_update( x264_t *h ); | |
| static ALWAYS_INLINE int x264_quant_4x4( x264_t *h, dctcoef dct[16], int i_qp, int ctx_block_cat, int b_intra, int p, int idx ) | |
| @@ -195,4 +213,3 @@ | |
| } | |
| #endif | |
| - | |
| diff -ur x264-go/x264c/external/x264/encoder/me.c x264-go.new/x264c/external/x264/encoder/me.c | |
| --- x264-go/x264c/external/x264/encoder/me.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/me.c 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * me.c: motion estimation | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -424,7 +424,7 @@ | |
| /* Uneven-cross Multi-Hexagon-grid Search | |
| * as in JM, except with different early termination */ | |
| - static const uint8_t x264_pixel_size_shift[7] = { 0, 1, 1, 2, 3, 3, 4 }; | |
| + static const uint8_t pixel_size_shift[7] = { 0, 1, 1, 2, 3, 3, 4 }; | |
| int ucost1, ucost2; | |
| int cross_start = 1; | |
| @@ -446,7 +446,7 @@ | |
| omx = bmx; omy = bmy; | |
| /* early termination */ | |
| -#define SAD_THRESH(v) ( bcost < ( v >> x264_pixel_size_shift[i_pixel] ) ) | |
| +#define SAD_THRESH(v) ( bcost < ( v >> pixel_size_shift[i_pixel] ) ) | |
| if( bcost == ucost2 && SAD_THRESH(2000) ) | |
| { | |
| COST_MV_X4( 0,-2, -1,-1, 1,-1, -2,0 ); | |
| @@ -633,7 +633,6 @@ | |
| /* successive elimination by comparing DC before a full SAD, | |
| * because sum(abs(diff)) >= abs(diff(sum)). */ | |
| uint16_t *sums_base = m->integral; | |
| - ALIGNED_16( static pixel zero[8*FENC_STRIDE] ) = {0}; | |
| ALIGNED_ARRAY_16( int, enc_dc,[4] ); | |
| int sad_size = i_pixel <= PIXEL_8x8 ? PIXEL_8x8 : PIXEL_4x4; | |
| int delta = x264_pixel_size[sad_size].w; | |
| @@ -641,7 +640,7 @@ | |
| int xn; | |
| uint16_t *cost_fpel_mvx = h->cost_mv_fpel[h->mb.i_qp][-m->mvp[0]&3] + (-m->mvp[0]>>2); | |
| - h->pixf.sad_x4[sad_size]( zero, p_fenc, p_fenc+delta, | |
| + h->pixf.sad_x4[sad_size]( (pixel*)x264_zero, p_fenc, p_fenc+delta, | |
| p_fenc+delta*FENC_STRIDE, p_fenc+delta+delta*FENC_STRIDE, | |
| FENC_STRIDE, enc_dc ); | |
| if( delta == 4 ) | |
| @@ -1012,7 +1011,7 @@ | |
| src[2][list][i] = h->mc.get_ref( pixv_buf[list][i], &stride[2][list][i], &m->p_fref[8],\ | |
| m->i_stride[2], mvx, mvy, bw, bh, x264_weight_none );\ | |
| }\ | |
| - else\ | |
| + else if( CHROMA_FORMAT )\ | |
| h->mc.mc_chroma( pixu_buf[list][i], pixv_buf[list][i], 8, m->p_fref[4], m->i_stride[1],\ | |
| mvx, 2*(mvy+mv##list##y_offset)>>chroma_v_shift, bw>>1, bh>>chroma_v_shift );\ | |
| }\ | |
| @@ -1022,9 +1021,10 @@ | |
| /* Don't unroll the BIME_CACHE loop. I couldn't find any way to force this | |
| * other than making its iteration count not a compile-time constant. */ | |
| +#define x264_iter_kludge x264_template(iter_kludge) | |
| int x264_iter_kludge = 0; | |
| -static void ALWAYS_INLINE x264_me_refine_bidir( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight, int i8, int i_lambda2, int rd ) | |
| +static ALWAYS_INLINE void me_refine_bidir( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight, int i8, int i_lambda2, int rd ) | |
| { | |
| int x = i8&1; | |
| int y = i8>>1; | |
| @@ -1043,8 +1043,8 @@ | |
| int chroma_x = (8 >> CHROMA_H_SHIFT) * x; | |
| int chroma_y = (8 >> chroma_v_shift) * y; | |
| pixel *pix = &h->mb.pic.p_fdec[0][8*x + 8*y*FDEC_STRIDE]; | |
| - pixel *pixu = &h->mb.pic.p_fdec[1][chroma_x + chroma_y*FDEC_STRIDE]; | |
| - pixel *pixv = &h->mb.pic.p_fdec[2][chroma_x + chroma_y*FDEC_STRIDE]; | |
| + pixel *pixu = CHROMA_FORMAT ? &h->mb.pic.p_fdec[1][chroma_x + chroma_y*FDEC_STRIDE] : NULL; | |
| + pixel *pixv = CHROMA_FORMAT ? &h->mb.pic.p_fdec[2][chroma_x + chroma_y*FDEC_STRIDE] : NULL; | |
| int ref0 = h->mb.cache.ref[0][s8]; | |
| int ref1 = h->mb.cache.ref[1][s8]; | |
| const int mv0y_offset = chroma_v_shift & MB_INTERLACED & ref0 ? (h->mb.i_mb_y & 1)*4 - 2 : 0; | |
| @@ -1134,7 +1134,7 @@ | |
| h->mc.avg[i_pixel]( pixu, FDEC_STRIDE, src[1][0][i0], stride[1][0][i0], src[1][1][i1], stride[1][1][i1], i_weight ); | |
| h->mc.avg[i_pixel]( pixv, FDEC_STRIDE, src[2][0][i0], stride[2][0][i0], src[2][1][i1], stride[2][1][i1], i_weight ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| h->mc.avg[chromapix]( pixu, FDEC_STRIDE, pixu_buf[0][i0], 8, pixu_buf[1][i1], 8, i_weight ); | |
| h->mc.avg[chromapix]( pixv, FDEC_STRIDE, pixv_buf[0][i0], 8, pixv_buf[1][i1], 8, i_weight ); | |
| @@ -1179,7 +1179,7 @@ | |
| void x264_me_refine_bidir_satd( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight ) | |
| { | |
| - x264_me_refine_bidir( h, m0, m1, i_weight, 0, 0, 0 ); | |
| + me_refine_bidir( h, m0, m1, i_weight, 0, 0, 0 ); | |
| } | |
| void x264_me_refine_bidir_rd( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight, int i8, int i_lambda2 ) | |
| @@ -1187,7 +1187,7 @@ | |
| /* Motion compensation is done as part of bidir_rd; don't repeat | |
| * it in encoding. */ | |
| h->mb.b_skip_mc = 1; | |
| - x264_me_refine_bidir( h, m0, m1, i_weight, i8, i_lambda2, 1 ); | |
| + me_refine_bidir( h, m0, m1, i_weight, i8, i_lambda2, 1 ); | |
| h->mb.b_skip_mc = 0; | |
| } | |
| @@ -1216,7 +1216,7 @@ | |
| h->mc.mc_luma( pixu, FDEC_STRIDE, &m->p_fref[4], m->i_stride[1], mx, my, bw, bh, &m->weight[1] ); \ | |
| h->mc.mc_luma( pixv, FDEC_STRIDE, &m->p_fref[8], m->i_stride[2], mx, my, bw, bh, &m->weight[2] ); \ | |
| } \ | |
| - else if( m->i_pixel <= PIXEL_8x8 ) \ | |
| + else if( CHROMA_FORMAT && m->i_pixel <= PIXEL_8x8 ) \ | |
| { \ | |
| h->mc.mc_chroma( pixu, pixv, FDEC_STRIDE, m->p_fref[4], m->i_stride[1], \ | |
| mx, 2*(my+mvy_offset)>>chroma_v_shift, bw>>1, bh>>chroma_v_shift ); \ | |
| @@ -1256,11 +1256,16 @@ | |
| pixu = &h->mb.pic.p_fdec[1][block_idx_xy_fdec[i4]]; | |
| pixv = &h->mb.pic.p_fdec[2][block_idx_xy_fdec[i4]]; | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| pixu = &h->mb.pic.p_fdec[1][(i8>>1)*(8*FDEC_STRIDE>>chroma_v_shift)+(i8&1)*4]; | |
| pixv = &h->mb.pic.p_fdec[2][(i8>>1)*(8*FDEC_STRIDE>>chroma_v_shift)+(i8&1)*4]; | |
| } | |
| + else | |
| + { | |
| + pixu = NULL; | |
| + pixv = NULL; | |
| + } | |
| h->mb.b_skip_mc = 1; | |
| diff -ur x264-go/x264c/external/x264/encoder/me.h x264-go.new/x264c/external/x264/encoder/me.h | |
| --- x264-go/x264c/external/x264/encoder/me.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/me.h 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * me.h: motion estimation | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -24,8 +24,8 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_ME_H | |
| -#define X264_ME_H | |
| +#ifndef X264_ENCODER_ME_H | |
| +#define X264_ENCODER_ME_H | |
| #define COST_MAX (1<<28) | |
| #define COST_MAX64 (1ULL<<60) | |
| @@ -52,18 +52,25 @@ | |
| /* output */ | |
| int cost_mv; /* lambda * nbits for the chosen mv */ | |
| int cost; /* satd + lambda * nbits */ | |
| - ALIGNED_4( int16_t mv[2] ); | |
| + ALIGNED_8( int16_t mv[2] ); | |
| } ALIGNED_64( x264_me_t ); | |
| +#define x264_me_search_ref x264_template(me_search_ref) | |
| void x264_me_search_ref( x264_t *h, x264_me_t *m, int16_t (*mvc)[2], int i_mvc, int *p_fullpel_thresh ); | |
| #define x264_me_search( h, m, mvc, i_mvc )\ | |
| x264_me_search_ref( h, m, mvc, i_mvc, NULL ) | |
| +#define x264_me_refine_qpel x264_template(me_refine_qpel) | |
| void x264_me_refine_qpel( x264_t *h, x264_me_t *m ); | |
| +#define x264_me_refine_qpel_refdupe x264_template(me_refine_qpel_refdupe) | |
| void x264_me_refine_qpel_refdupe( x264_t *h, x264_me_t *m, int *p_halfpel_thresh ); | |
| +#define x264_me_refine_qpel_rd x264_template(me_refine_qpel_rd) | |
| void x264_me_refine_qpel_rd( x264_t *h, x264_me_t *m, int i_lambda2, int i4, int i_list ); | |
| +#define x264_me_refine_bidir_rd x264_template(me_refine_bidir_rd) | |
| void x264_me_refine_bidir_rd( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight, int i8, int i_lambda2 ); | |
| +#define x264_me_refine_bidir_satd x264_template(me_refine_bidir_satd) | |
| void x264_me_refine_bidir_satd( x264_t *h, x264_me_t *m0, x264_me_t *m1, int i_weight ); | |
| +#define x264_rd_cost_part x264_template(rd_cost_part) | |
| uint64_t x264_rd_cost_part( x264_t *h, int i_lambda2, int i8, int i_pixel ); | |
| #define COPY1_IF_LT(x,y)\ | |
| diff -ur x264-go/x264c/external/x264/encoder/ratecontrol.c x264-go.new/x264c/external/x264/encoder/ratecontrol.c | |
| --- x264-go/x264c/external/x264/encoder/ratecontrol.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/ratecontrol.c 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * ratecontrol.c: ratecontrol | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Michael Niedermayer <michaelni@gmx.at> | |
| @@ -154,8 +154,8 @@ | |
| } mbtree; | |
| /* MBRC stuff */ | |
| - float frame_size_estimated; /* Access to this variable must be atomic: double is | |
| - * not atomic on all arches we care about */ | |
| + volatile float frame_size_estimated; /* Access to this variable must be atomic: double is | |
| + * not atomic on all arches we care about */ | |
| double frame_size_maximum; /* Maximum frame size due to MinCR */ | |
| double frame_size_planned; | |
| double slice_size_planned; | |
| @@ -243,7 +243,7 @@ | |
| stride <<= b_field; | |
| if( b_chroma ) | |
| { | |
| - ALIGNED_ARRAY_32( pixel, pix,[FENC_STRIDE*16] ); | |
| + ALIGNED_ARRAY_64( pixel, pix,[FENC_STRIDE*16] ); | |
| int chromapix = h->luma2chroma_pixel[PIXEL_16x16]; | |
| int shift = 7 - CHROMA_V_SHIFT; | |
| @@ -256,7 +256,7 @@ | |
| } | |
| // Find the total AC energy of the block in all planes. | |
| -static NOINLINE uint32_t x264_ac_energy_mb( x264_t *h, int mb_x, int mb_y, x264_frame_t *frame ) | |
| +static NOINLINE uint32_t ac_energy_mb( x264_t *h, int mb_x, int mb_y, x264_frame_t *frame ) | |
| { | |
| /* This function contains annoying hacks because GCC has a habit of reordering emms | |
| * and putting it after floating point ops. As a result, we put the emms at the end of the | |
| @@ -278,7 +278,7 @@ | |
| var_interlaced += ac_energy_plane( h, mb_x, mb_y, frame, 2, 0, 1, 1 ); | |
| var_progressive += ac_energy_plane( h, mb_x, mb_y, frame, 2, 0, 0, 0 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| { | |
| var_interlaced += ac_energy_plane( h, mb_x, mb_y, frame, 1, 1, 1, 1 ); | |
| var_progressive += ac_energy_plane( h, mb_x, mb_y, frame, 1, 1, 0, 0 ); | |
| @@ -293,7 +293,7 @@ | |
| var += ac_energy_plane( h, mb_x, mb_y, frame, 1, 0, PARAM_INTERLACED, 1 ); | |
| var += ac_energy_plane( h, mb_x, mb_y, frame, 2, 0, PARAM_INTERLACED, 1 ); | |
| } | |
| - else | |
| + else if( CHROMA_FORMAT ) | |
| var += ac_energy_plane( h, mb_x, mb_y, frame, 1, 1, PARAM_INTERLACED, 1 ); | |
| } | |
| x264_emms(); | |
| @@ -337,7 +337,7 @@ | |
| { | |
| for( int mb_y = 0; mb_y < h->mb.i_mb_height; mb_y++ ) | |
| for( int mb_x = 0; mb_x < h->mb.i_mb_width; mb_x++ ) | |
| - x264_ac_energy_mb( h, mb_x, mb_y, frame ); | |
| + ac_energy_mb( h, mb_x, mb_y, frame ); | |
| } | |
| else | |
| return; | |
| @@ -358,7 +358,7 @@ | |
| for( int mb_y = 0; mb_y < h->mb.i_mb_height; mb_y++ ) | |
| for( int mb_x = 0; mb_x < h->mb.i_mb_width; mb_x++ ) | |
| { | |
| - uint32_t energy = x264_ac_energy_mb( h, mb_x, mb_y, frame ); | |
| + uint32_t energy = ac_energy_mb( h, mb_x, mb_y, frame ); | |
| float qp_adj = powf( energy * bit_depth_correction + 1, 0.125f ); | |
| frame->f_qp_offset[mb_x + mb_y*h->mb.i_mb_stride] = qp_adj; | |
| avg_adj += qp_adj; | |
| @@ -390,7 +390,7 @@ | |
| } | |
| else | |
| { | |
| - uint32_t energy = x264_ac_energy_mb( h, mb_x, mb_y, frame ); | |
| + uint32_t energy = ac_energy_mb( h, mb_x, mb_y, frame ); | |
| qp_adj = strength * (x264_log2( X264_MAX(energy, 1) ) - (14.427f + 2*(BIT_DEPTH-8))); | |
| } | |
| if( quant_offsets ) | |
| @@ -413,7 +413,7 @@ | |
| } | |
| } | |
| -static int x264_macroblock_tree_rescale_init( x264_t *h, x264_ratecontrol_t *rc ) | |
| +static int macroblock_tree_rescale_init( x264_t *h, x264_ratecontrol_t *rc ) | |
| { | |
| /* Use fractional QP array dimensions to compensate for edge padding */ | |
| float srcdim[2] = {rc->mbtree.srcdim[0] / 16.f, rc->mbtree.srcdim[1] / 16.f}; | |
| @@ -486,7 +486,7 @@ | |
| return -1; | |
| } | |
| -static void x264_macroblock_tree_rescale_destroy( x264_ratecontrol_t *rc ) | |
| +static void macroblock_tree_rescale_destroy( x264_ratecontrol_t *rc ) | |
| { | |
| for( int i = 0; i < 2; i++ ) | |
| { | |
| @@ -505,7 +505,7 @@ | |
| return sum; | |
| } | |
| -static void x264_macroblock_tree_rescale( x264_t *h, x264_ratecontrol_t *rc, float *dst ) | |
| +static void macroblock_tree_rescale( x264_t *h, x264_ratecontrol_t *rc, float *dst ) | |
| { | |
| float *input, *output; | |
| int filtersize, stride, height; | |
| @@ -553,7 +553,7 @@ | |
| if( !fread( &i_type, 1, 1, rc->p_mbtree_stat_file_in ) ) | |
| goto fail; | |
| - if( fread( rc->mbtree.qp_buffer[rc->mbtree.qpbuf_pos], sizeof(uint16_t), rc->mbtree.src_mb_count, rc->p_mbtree_stat_file_in ) != rc->mbtree.src_mb_count ) | |
| + if( fread( rc->mbtree.qp_buffer[rc->mbtree.qpbuf_pos], sizeof(uint16_t), rc->mbtree.src_mb_count, rc->p_mbtree_stat_file_in ) != (unsigned)rc->mbtree.src_mb_count ) | |
| goto fail; | |
| if( i_type != i_type_actual && rc->mbtree.qpbuf_pos == 1 ) | |
| @@ -567,14 +567,14 @@ | |
| float *dst = rc->mbtree.rescale_enabled ? rc->mbtree.scale_buffer[0] : frame->f_qp_offset; | |
| h->mc.mbtree_fix8_unpack( dst, rc->mbtree.qp_buffer[rc->mbtree.qpbuf_pos], rc->mbtree.src_mb_count ); | |
| if( rc->mbtree.rescale_enabled ) | |
| - x264_macroblock_tree_rescale( h, rc, frame->f_qp_offset ); | |
| + macroblock_tree_rescale( h, rc, frame->f_qp_offset ); | |
| if( h->frames.b_have_lowres ) | |
| for( int i = 0; i < h->mb.i_mb_count; i++ ) | |
| frame->i_inv_qscale_factor[i] = x264_exp2fix8( frame->f_qp_offset[i] ); | |
| rc->mbtree.qpbuf_pos--; | |
| } | |
| else | |
| - x264_stack_align( x264_adaptive_quant_frame, h, frame, quant_offsets ); | |
| + x264_adaptive_quant_frame( h, frame, quant_offsets ); | |
| return 0; | |
| fail: | |
| x264_log( h, X264_LOG_ERROR, "Incomplete MB-tree stats file.\n" ); | |
| @@ -618,7 +618,7 @@ | |
| return 0; | |
| } | |
| -static char *x264_strcat_filename( char *input, char *suffix ) | |
| +static char *strcat_filename( char *input, char *suffix ) | |
| { | |
| char *output = x264_malloc( strlen( input ) + strlen( suffix ) + 1 ); | |
| if( !output ) | |
| @@ -713,8 +713,9 @@ | |
| rc->vbv_max_rate = vbv_max_bitrate; | |
| rc->buffer_size = vbv_buffer_size; | |
| rc->single_frame_vbv = rc->buffer_rate * 1.1 > rc->buffer_size; | |
| - rc->cbr_decay = 1.0 - rc->buffer_rate / rc->buffer_size | |
| - * 0.5 * X264_MAX(0, 1.5 - rc->buffer_rate * rc->fps / rc->bitrate); | |
| + if( rc->b_abr && h->param.rc.i_rc_method == X264_RC_ABR ) | |
| + rc->cbr_decay = 1.0 - rc->buffer_rate / rc->buffer_size | |
| + * 0.5 * X264_MAX(0, 1.5 - rc->buffer_rate * rc->fps / rc->bitrate); | |
| if( h->param.rc.i_rc_method == X264_RC_CRF && h->param.rc.f_rf_constant_max ) | |
| { | |
| rc->rate_factor_max_increment = h->param.rc.f_rf_constant_max - h->param.rc.f_rf_constant; | |
| @@ -771,9 +772,9 @@ | |
| rc->last_non_b_pict_type = -1; | |
| rc->cbr_decay = 1.0; | |
| - if( h->param.rc.i_rc_method == X264_RC_CRF && h->param.rc.b_stat_read ) | |
| + if( h->param.rc.i_rc_method != X264_RC_ABR && h->param.rc.b_stat_read ) | |
| { | |
| - x264_log( h, X264_LOG_ERROR, "constant rate-factor is incompatible with 2pass.\n" ); | |
| + x264_log( h, X264_LOG_ERROR, "CRF/CQP is incompatible with 2pass.\n" ); | |
| return -1; | |
| } | |
| @@ -878,7 +879,7 @@ | |
| } | |
| if( h->param.rc.b_mb_tree ) | |
| { | |
| - char *mbtree_stats_in = x264_strcat_filename( h->param.rc.psz_stat_in, ".mbtree" ); | |
| + char *mbtree_stats_in = strcat_filename( h->param.rc.psz_stat_in, ".mbtree" ); | |
| if( !mbtree_stats_in ) | |
| return -1; | |
| rc->p_mbtree_stat_file_in = x264_fopen( mbtree_stats_in, "rb" ); | |
| @@ -941,6 +942,7 @@ | |
| CMP_OPT_FIRST_PASS( "intra_refresh", h->param.b_intra_refresh ); | |
| CMP_OPT_FIRST_PASS( "open_gop", h->param.b_open_gop ); | |
| CMP_OPT_FIRST_PASS( "bluray_compat", h->param.b_bluray_compat ); | |
| + CMP_OPT_FIRST_PASS( "mbtree", h->param.rc.b_mb_tree ); | |
| if( (p = strstr( opts, "interlaced=" )) ) | |
| { | |
| @@ -1154,7 +1156,7 @@ | |
| if( h->param.rc.b_stat_write ) | |
| { | |
| char *p; | |
| - rc->psz_stat_file_tmpname = x264_strcat_filename( h->param.rc.psz_stat_out, ".temp" ); | |
| + rc->psz_stat_file_tmpname = strcat_filename( h->param.rc.psz_stat_out, ".temp" ); | |
| if( !rc->psz_stat_file_tmpname ) | |
| return -1; | |
| @@ -1171,8 +1173,8 @@ | |
| x264_free( p ); | |
| if( h->param.rc.b_mb_tree && !h->param.rc.b_stat_read ) | |
| { | |
| - rc->psz_mbtree_stat_file_tmpname = x264_strcat_filename( h->param.rc.psz_stat_out, ".mbtree.temp" ); | |
| - rc->psz_mbtree_stat_file_name = x264_strcat_filename( h->param.rc.psz_stat_out, ".mbtree" ); | |
| + rc->psz_mbtree_stat_file_tmpname = strcat_filename( h->param.rc.psz_stat_out, ".mbtree.temp" ); | |
| + rc->psz_mbtree_stat_file_name = strcat_filename( h->param.rc.psz_stat_out, ".mbtree" ); | |
| if( !rc->psz_mbtree_stat_file_tmpname || !rc->psz_mbtree_stat_file_name ) | |
| return -1; | |
| @@ -1192,7 +1194,7 @@ | |
| rc->mbtree.srcdim[0] = h->param.i_width; | |
| rc->mbtree.srcdim[1] = h->param.i_height; | |
| } | |
| - if( x264_macroblock_tree_rescale_init( h, rc ) < 0 ) | |
| + if( macroblock_tree_rescale_init( h, rc ) < 0 ) | |
| return -1; | |
| } | |
| @@ -1327,9 +1329,10 @@ | |
| static x264_zone_t *get_zone( x264_t *h, int frame_num ) | |
| { | |
| - for( int i = h->rc->i_zones - 1; i >= 0; i-- ) | |
| + x264_ratecontrol_t *rc = h->rc; | |
| + for( int i = rc->i_zones - 1; i >= 0; i-- ) | |
| { | |
| - x264_zone_t *z = &h->rc->zones[i]; | |
| + x264_zone_t *z = &rc->zones[i]; | |
| if( frame_num >= z->i_start && frame_num <= z->i_end ) | |
| return z; | |
| } | |
| @@ -1385,7 +1388,7 @@ | |
| x264_free( rc->pred_b_from_p ); | |
| x264_free( rc->entry ); | |
| x264_free( rc->entry_out ); | |
| - x264_macroblock_tree_rescale_destroy( rc ); | |
| + macroblock_tree_rescale_destroy( rc ); | |
| if( rc->zones ) | |
| { | |
| x264_free( rc->zones[0].param ); | |
| @@ -1432,7 +1435,7 @@ | |
| { | |
| int frame = h->fenc->i_frame; | |
| assert( frame >= 0 && frame < rc->num_entries ); | |
| - rce = h->rc->rce = &h->rc->entry[frame]; | |
| + rce = rc->rce = &rc->entry[frame]; | |
| if( h->sh.i_type == SLICE_TYPE_B | |
| && h->param.analyse.i_direct_mv_pred == X264_DIRECT_PRED_AUTO ) | |
| @@ -1693,7 +1696,7 @@ | |
| b1 = bits_so_far + predict_row_size_to_end( h, y, rc->qpm ) + size_of_other_slices; | |
| } | |
| - h->rc->frame_size_estimated = b1 - size_of_other_slices; | |
| + rc->frame_size_estimated = b1 - size_of_other_slices; | |
| /* If the current row was large enough to cause a large QP jump, try re-encoding it. */ | |
| if( rc->qpm > qp_max && prev_row_qp < qp_max && can_reencode_row ) | |
| @@ -1709,12 +1712,12 @@ | |
| } | |
| else | |
| { | |
| - h->rc->frame_size_estimated = bits_so_far; | |
| + rc->frame_size_estimated = bits_so_far; | |
| /* Last-ditch attempt: if the last row of the frame underflowed the VBV, | |
| * try again. */ | |
| if( rc->qpm < qp_max && can_reencode_row | |
| - && (h->rc->frame_size_estimated + size_of_other_slices > X264_MIN( rc->frame_size_maximum, rc->buffer_fill )) ) | |
| + && (bits_so_far + size_of_other_slices > X264_MIN( rc->frame_size_maximum, rc->buffer_fill )) ) | |
| { | |
| rc->qpm = qp_max; | |
| rc->qpa_rc = rc->qpa_rc_prev; | |
| @@ -1893,7 +1896,7 @@ | |
| h->mc.mbtree_fix8_pack( rc->mbtree.qp_buffer[0], h->fenc->f_qp_offset, h->mb.i_mb_count ); | |
| if( fwrite( &i_type, 1, 1, rc->p_mbtree_stat_file_out ) < 1 ) | |
| goto fail; | |
| - if( fwrite( rc->mbtree.qp_buffer[0], sizeof(uint16_t), h->mb.i_mb_count, rc->p_mbtree_stat_file_out ) < h->mb.i_mb_count ) | |
| + if( fwrite( rc->mbtree.qp_buffer[0], sizeof(uint16_t), h->mb.i_mb_count, rc->p_mbtree_stat_file_out ) < (unsigned)h->mb.i_mb_count ) | |
| goto fail; | |
| } | |
| } | |
| @@ -2211,7 +2214,7 @@ | |
| rcc->buffer_fill = h->thread[0]->rc->buffer_fill_final_min / h->sps->vui.i_time_scale; | |
| if( h->i_thread_frames > 1 ) | |
| { | |
| - int j = h->rc - h->thread[0]->rc; | |
| + int j = rcc - h->thread[0]->rc; | |
| for( int i = 1; i < h->i_thread_frames; i++ ) | |
| { | |
| x264_t *t = h->thread[ (j+i)%h->i_thread_frames ]; | |
| @@ -2445,7 +2448,7 @@ | |
| /* Limit planned size by MinCR */ | |
| if( rcc->b_vbv ) | |
| rcc->frame_size_planned = X264_MIN( rcc->frame_size_planned, rcc->frame_size_maximum ); | |
| - h->rc->frame_size_estimated = rcc->frame_size_planned; | |
| + rcc->frame_size_estimated = rcc->frame_size_planned; | |
| /* For row SATDs */ | |
| if( rcc->b_vbv ) | |
| @@ -2458,7 +2461,7 @@ | |
| double predicted_bits = total_bits; | |
| if( h->i_thread_frames > 1 ) | |
| { | |
| - int j = h->rc - h->thread[0]->rc; | |
| + int j = rcc - h->thread[0]->rc; | |
| for( int i = 1; i < h->i_thread_frames; i++ ) | |
| { | |
| x264_t *t = h->thread[(j+i) % h->i_thread_frames]; | |
| @@ -2627,12 +2630,12 @@ | |
| /* Limit planned size by MinCR */ | |
| if( rcc->b_vbv ) | |
| rcc->frame_size_planned = X264_MIN( rcc->frame_size_planned, rcc->frame_size_maximum ); | |
| - h->rc->frame_size_estimated = rcc->frame_size_planned; | |
| + rcc->frame_size_estimated = rcc->frame_size_planned; | |
| return q; | |
| } | |
| } | |
| -static void x264_threads_normalize_predictors( x264_t *h ) | |
| +static void threads_normalize_predictors( x264_t *h ) | |
| { | |
| double totalsize = 0; | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| @@ -2677,7 +2680,7 @@ | |
| } | |
| if( rc->b_vbv && rc->frame_size_planned ) | |
| { | |
| - x264_threads_normalize_predictors( h ); | |
| + threads_normalize_predictors( h ); | |
| if( rc->single_frame_vbv ) | |
| { | |
| @@ -2688,7 +2691,7 @@ | |
| float max_frame_error = x264_clip3f( 1.0 / (t->i_threadslice_end - t->i_threadslice_start), 0.05, 0.25 ); | |
| t->rc->slice_size_planned += 2 * max_frame_error * rc->frame_size_planned; | |
| } | |
| - x264_threads_normalize_predictors( h ); | |
| + threads_normalize_predictors( h ); | |
| } | |
| for( int i = 0; i < h->param.i_threads; i++ ) | |
| diff -ur x264-go/x264c/external/x264/encoder/ratecontrol.h x264-go.new/x264c/external/x264/encoder/ratecontrol.h | |
| --- x264-go/x264c/external/x264/encoder/ratecontrol.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/ratecontrol.h 2020-06-06 15:20:58.698039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * ratecontrol.h: ratecontrol | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Laurent Aimar <fenrir@via.ecp.fr> | |
| @@ -24,8 +24,8 @@ | |
| * For more information, contact us at licensing@x264.com. | |
| *****************************************************************************/ | |
| -#ifndef X264_RATECONTROL_H | |
| -#define X264_RATECONTROL_H | |
| +#ifndef X264_ENCODER_RATECONTROL_H | |
| +#define X264_ENCODER_RATECONTROL_H | |
| /* Completely arbitrary. Ratecontrol lowers relative quality at higher framerates | |
| * and the reverse at lower framerates; this serves as the center of the curve. | |
| @@ -39,28 +39,49 @@ | |
| #define CLIP_DURATION(f) x264_clip3f(f,MIN_FRAME_DURATION,MAX_FRAME_DURATION) | |
| +#define x264_ratecontrol_new x264_template(ratecontrol_new) | |
| int x264_ratecontrol_new ( x264_t * ); | |
| +#define x264_ratecontrol_delete x264_template(ratecontrol_delete) | |
| void x264_ratecontrol_delete( x264_t * ); | |
| +#define x264_ratecontrol_init_reconfigurable x264_template(ratecontrol_init_reconfigurable) | |
| void x264_ratecontrol_init_reconfigurable( x264_t *h, int b_init ); | |
| +#define x264_encoder_reconfig_apply x264_template(encoder_reconfig_apply) | |
| int x264_encoder_reconfig_apply( x264_t *h, x264_param_t *param ); | |
| +#define x264_adaptive_quant_frame x264_template(adaptive_quant_frame) | |
| void x264_adaptive_quant_frame( x264_t *h, x264_frame_t *frame, float *quant_offsets ); | |
| +#define x264_macroblock_tree_read x264_template(macroblock_tree_read) | |
| int x264_macroblock_tree_read( x264_t *h, x264_frame_t *frame, float *quant_offsets ); | |
| +#define x264_reference_build_list_optimal x264_template(reference_build_list_optimal) | |
| int x264_reference_build_list_optimal( x264_t *h ); | |
| +#define x264_thread_sync_ratecontrol x264_template(thread_sync_ratecontrol) | |
| void x264_thread_sync_ratecontrol( x264_t *cur, x264_t *prev, x264_t *next ); | |
| +#define x264_ratecontrol_zone_init x264_template(ratecontrol_zone_init) | |
| void x264_ratecontrol_zone_init( x264_t * ); | |
| +#define x264_ratecontrol_start x264_template(ratecontrol_start) | |
| void x264_ratecontrol_start( x264_t *, int i_force_qp, int overhead ); | |
| +#define x264_ratecontrol_slice_type x264_template(ratecontrol_slice_type) | |
| int x264_ratecontrol_slice_type( x264_t *, int i_frame ); | |
| +#define x264_ratecontrol_set_weights x264_template(ratecontrol_set_weights) | |
| void x264_ratecontrol_set_weights( x264_t *h, x264_frame_t *frm ); | |
| +#define x264_ratecontrol_mb x264_template(ratecontrol_mb) | |
| int x264_ratecontrol_mb( x264_t *, int bits ); | |
| +#define x264_ratecontrol_qp x264_template(ratecontrol_qp) | |
| int x264_ratecontrol_qp( x264_t * ); | |
| +#define x264_ratecontrol_mb_qp x264_template(ratecontrol_mb_qp) | |
| int x264_ratecontrol_mb_qp( x264_t *h ); | |
| +#define x264_ratecontrol_end x264_template(ratecontrol_end) | |
| int x264_ratecontrol_end( x264_t *, int bits, int *filler ); | |
| +#define x264_ratecontrol_summary x264_template(ratecontrol_summary) | |
| void x264_ratecontrol_summary( x264_t * ); | |
| +#define x264_rc_analyse_slice x264_template(rc_analyse_slice) | |
| int x264_rc_analyse_slice( x264_t *h ); | |
| +#define x264_threads_distribute_ratecontrol x264_template(threads_distribute_ratecontrol) | |
| void x264_threads_distribute_ratecontrol( x264_t *h ); | |
| +#define x264_threads_merge_ratecontrol x264_template(threads_merge_ratecontrol) | |
| void x264_threads_merge_ratecontrol( x264_t *h ); | |
| +#define x264_hrd_fullness x264_template(hrd_fullness) | |
| void x264_hrd_fullness( x264_t *h ); | |
| -#endif | |
| +#endif | |
| diff -ur x264-go/x264c/external/x264/encoder/rdo.c x264-go.new/x264c/external/x264/encoder/rdo.c | |
| --- x264-go/x264c/external/x264/encoder/rdo.c 2020-08-25 18:16:14.155874700 +0200 | |
| +++ x264-go.new/x264c/external/x264/encoder/rdo.c 2020-06-06 15:20:58.699039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * rdo.c: rate-distortion optimization | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Loren Merritt <lorenm@u.washington.edu> | |
| * Fiona Glaser <fiona@x264.com> | |
| @@ -32,7 +32,9 @@ | |
| /* Transition and size tables for abs<9 MVD and residual coding */ | |
| /* Consist of i_prefix-2 1s, one zero, and a bypass sign bit */ | |
| +#define x264_cabac_transition_unary x264_template(cabac_transition_unary) | |
| uint8_t x264_cabac_transition_unary[15][128]; | |
| +#define x264_cabac_size_unary x264_template(cabac_size_unary) | |
| uint16_t x264_cabac_size_unary[15][128]; | |
| /* Transition and size tables for abs>9 MVD */ | |
| /* Consist of 5 1s and a bypass sign bit */ | |
| @@ -46,7 +48,8 @@ | |
| #define bs_write_ue(s,v) ((s)->i_bits_encoded += bs_size_ue(v)) | |
| #define bs_write_se(s,v) ((s)->i_bits_encoded += bs_size_se(v)) | |
| #define bs_write_te(s,v,l) ((s)->i_bits_encoded += bs_size_te(v,l)) | |
| -#define x264_macroblock_write_cavlc static x264_macroblock_size_cavlc | |
| +#undef x264_macroblock_write_cavlc | |
| +#define x264_macroblock_write_cavlc static macroblock_size_cavlc | |
| #include "cavlc.c" | |
| /* CABAC: not exactly the same. x264_cabac_size_decision() keeps track of | |
| @@ -55,12 +58,14 @@ | |
| #undef x264_cabac_encode_decision_noup | |
| #undef x264_cabac_encode_bypass | |
| #undef x264_cabac_encode_terminal | |
| +#undef x264_cabac_encode_ue_bypass | |
| #define x264_cabac_encode_decision(c,x,v) x264_cabac_size_decision(c,x,v) | |
| #define x264_cabac_encode_decision_noup(c,x,v) x264_cabac_size_decision_noup(c,x,v) | |
| #define x264_cabac_encode_terminal(c) ((c)->f8_bits_encoded += 7) | |
| #define x264_cabac_encode_bypass(c,v) ((c)->f8_bits_encoded += 256) | |
| #define x264_cabac_encode_ue_bypass(c,e,v) ((c)->f8_bits_encoded += (bs_size_ue_big(v+(1<<e)-1)-e)<<8) | |
| -#define x264_macroblock_write_cabac static x264_macroblock_size_cabac | |
| +#undef x264_macroblock_write_cabac | |
| +#define x264_macroblock_write_cabac static macroblock_size_cabac | |
| #include "cabac.c" | |
| #define COPY_CABAC h->mc.memcpy_aligned( &cabac_tmp.f8_bits_encoded, &h->cabac.f8_bits_encoded, \ | |
| @@ -91,7 +96,6 @@ | |
| static const uint8_t satd_shift_x[3] = {3, 2, 2}; | |
| static const uint8_t satd_shift_y[3] = {2-1, 3-2, 2-2}; | |
| static const uint8_t satd_offset[3] = {0, 8, 16}; | |
| - ALIGNED_16( static pixel zero[16] ) = {0}; | |
| int cache_index = (x >> satd_shift_x[size - PIXEL_8x4]) + (y >> satd_shift_y[size - PIXEL_8x4]) | |
| + satd_offset[size - PIXEL_8x4]; | |
| int res = h->mb.pic.fenc_satd_cache[cache_index]; | |
| @@ -100,8 +104,8 @@ | |
| else | |
| { | |
| pixel *fenc = h->mb.pic.p_fenc[0] + x + y*FENC_STRIDE; | |
| - int dc = h->pixf.sad[size]( fenc, FENC_STRIDE, zero, 0 ) >> 1; | |
| - res = h->pixf.satd[size]( fenc, FENC_STRIDE, zero, 0 ) - dc; | |
| + int dc = h->pixf.sad[size]( fenc, FENC_STRIDE, (pixel*)x264_zero, 0 ) >> 1; | |
| + res = h->pixf.satd[size]( fenc, FENC_STRIDE, (pixel*)x264_zero, 0 ) - dc; | |
| h->mb.pic.fenc_satd_cache[cache_index] = res + 1; | |
| return res; | |
| } | |
| @@ -118,7 +122,6 @@ | |
| static inline int ssd_plane( x264_t *h, int size, int p, int x, int y ) | |
| { | |
| - ALIGNED_16( static pixel zero[16] ) = {0}; | |
| int satd = 0; | |
| pixel *fdec = h->mb.pic.p_fdec[p] + x + y*FDEC_STRIDE; | |
| pixel *fenc = h->mb.pic.p_fenc[p] + x + y*FENC_STRIDE; | |
| @@ -135,8 +138,8 @@ | |
| } | |
| else | |
| { | |
| - int dc = h->pixf.sad[size]( fdec, FDEC_STRIDE, zero, 0 ) >> 1; | |
| - satd = abs(h->pixf.satd[size]( fdec, FDEC_STRIDE, zero, 0 ) - dc - cached_satd( h, size, x, y )); | |
| + int dc = h->pixf.sad[size]( fdec, FDEC_STRIDE, (pixel*)x264_zero, 0 ) >> 1; | |
| + satd = abs(h->pixf.satd[size]( fdec, FDEC_STRIDE, (pixel*)x264_zero, 0 ) - dc - cached_satd( h, size, x, y )); | |
| } | |
| satd = (satd * h->mb.i_psy_rd * h->mb.i_psy_rd_lambda + 128) >> 8; | |
| } | |
| @@ -145,13 +148,17 @@ | |
| static inline int ssd_mb( x264_t *h ) | |
| { | |
| - int chroma_size = h->luma2chroma_pixel[PIXEL_16x16]; | |
| - int chroma_ssd = ssd_plane(h, chroma_size, 1, 0, 0) + ssd_plane(h, chroma_size, 2, 0, 0); | |
| - chroma_ssd = ((uint64_t)chroma_ssd * h->mb.i_chroma_lambda2_offset + 128) >> 8; | |
| - return ssd_plane(h, PIXEL_16x16, 0, 0, 0) + chroma_ssd; | |
| + int i_ssd = ssd_plane( h, PIXEL_16x16, 0, 0, 0 ); | |
| + if( CHROMA_FORMAT ) | |
| + { | |
| + int chroma_size = h->luma2chroma_pixel[PIXEL_16x16]; | |
| + int chroma_ssd = ssd_plane( h, chroma_size, 1, 0, 0 ) + ssd_plane( h, chroma_size, 2, 0, 0 ); | |
| + i_ssd += ((uint64_t)chroma_ssd * h->mb.i_chroma_lambda2_offset + 128) >> 8; | |
| + } | |
| + return i_ssd; | |
| } | |
| -static int x264_rd_cost_mb( x264_t *h, int i_lambda2 ) | |
| +static int rd_cost_mb( x264_t *h, int i_lambda2 ) | |
| { | |
| int b_transform_bak = h->mb.b_transform_8x8; | |
| int i_ssd; | |
| @@ -173,12 +180,12 @@ | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_macroblock_size_cabac( h, &cabac_tmp ); | |
| + macroblock_size_cabac( h, &cabac_tmp ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 32768 ) >> 16; | |
| } | |
| else | |
| { | |
| - x264_macroblock_size_cavlc( h ); | |
| + macroblock_size_cavlc( h ); | |
| i_bits = ( (uint64_t)h->out.bs.i_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| @@ -190,7 +197,7 @@ | |
| /* partition RD functions use 8 bits more precision to avoid large rounding errors at low QPs */ | |
| -static uint64_t x264_rd_cost_subpart( x264_t *h, int i_lambda2, int i4, int i_pixel ) | |
| +static uint64_t rd_cost_subpart( x264_t *h, int i_lambda2, int i4, int i_pixel ) | |
| { | |
| uint64_t i_ssd, i_bits; | |
| @@ -213,11 +220,11 @@ | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_subpartition_size_cabac( h, &cabac_tmp, i4, i_pixel ); | |
| + subpartition_size_cabac( h, &cabac_tmp, i4, i_pixel ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| else | |
| - i_bits = x264_subpartition_size_cavlc( h, i4, i_pixel ); | |
| + i_bits = subpartition_size_cavlc( h, i4, i_pixel ); | |
| return (i_ssd<<8) + i_bits; | |
| } | |
| @@ -229,12 +236,12 @@ | |
| if( i_pixel == PIXEL_16x16 ) | |
| { | |
| - int i_cost = x264_rd_cost_mb( h, i_lambda2 ); | |
| + int i_cost = rd_cost_mb( h, i_lambda2 ); | |
| return i_cost; | |
| } | |
| if( i_pixel > PIXEL_8x8 ) | |
| - return x264_rd_cost_subpart( h, i_lambda2, i4, i_pixel ); | |
| + return rd_cost_subpart( h, i_lambda2, i4, i_pixel ); | |
| h->mb.i_cbp_luma = 0; | |
| @@ -247,25 +254,28 @@ | |
| int ssd_x = 8*(i8&1); | |
| int ssd_y = 8*(i8>>1); | |
| i_ssd = ssd_plane( h, i_pixel, 0, ssd_x, ssd_y ); | |
| - int chromapix = h->luma2chroma_pixel[i_pixel]; | |
| - int chromassd = ssd_plane( h, chromapix, 1, ssd_x>>CHROMA_H_SHIFT, ssd_y>>CHROMA_V_SHIFT ) | |
| - + ssd_plane( h, chromapix, 2, ssd_x>>CHROMA_H_SHIFT, ssd_y>>CHROMA_V_SHIFT ); | |
| - i_ssd += ((uint64_t)chromassd * h->mb.i_chroma_lambda2_offset + 128) >> 8; | |
| + if( CHROMA_FORMAT ) | |
| + { | |
| + int chroma_size = h->luma2chroma_pixel[i_pixel]; | |
| + int chroma_ssd = ssd_plane( h, chroma_size, 1, ssd_x>>CHROMA_H_SHIFT, ssd_y>>CHROMA_V_SHIFT ) | |
| + + ssd_plane( h, chroma_size, 2, ssd_x>>CHROMA_H_SHIFT, ssd_y>>CHROMA_V_SHIFT ); | |
| + i_ssd += ((uint64_t)chroma_ssd * h->mb.i_chroma_lambda2_offset + 128) >> 8; | |
| + } | |
| if( h->param.b_cabac ) | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_partition_size_cabac( h, &cabac_tmp, i8, i_pixel ); | |
| + partition_size_cabac( h, &cabac_tmp, i8, i_pixel ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| else | |
| - i_bits = (uint64_t)x264_partition_size_cavlc( h, i8, i_pixel ) * i_lambda2; | |
| + i_bits = (uint64_t)partition_size_cavlc( h, i8, i_pixel ) * i_lambda2; | |
| return (i_ssd<<8) + i_bits; | |
| } | |
| -static uint64_t x264_rd_cost_i8x8( x264_t *h, int i_lambda2, int i8, int i_mode, pixel edge[4][32] ) | |
| +static uint64_t rd_cost_i8x8( x264_t *h, int i_lambda2, int i8, int i_mode, pixel edge[4][32] ) | |
| { | |
| uint64_t i_ssd, i_bits; | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| @@ -292,16 +302,16 @@ | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_partition_i8x8_size_cabac( h, &cabac_tmp, i8, i_mode ); | |
| + partition_i8x8_size_cabac( h, &cabac_tmp, i8, i_mode ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| else | |
| - i_bits = (uint64_t)x264_partition_i8x8_size_cavlc( h, i8, i_mode ) * i_lambda2; | |
| + i_bits = (uint64_t)partition_i8x8_size_cavlc( h, i8, i_mode ) * i_lambda2; | |
| return (i_ssd<<8) + i_bits; | |
| } | |
| -static uint64_t x264_rd_cost_i4x4( x264_t *h, int i_lambda2, int i4, int i_mode ) | |
| +static uint64_t rd_cost_i4x4( x264_t *h, int i_lambda2, int i4, int i_mode ) | |
| { | |
| uint64_t i_ssd, i_bits; | |
| int plane_count = CHROMA444 ? 3 : 1; | |
| @@ -326,16 +336,16 @@ | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_partition_i4x4_size_cabac( h, &cabac_tmp, i4, i_mode ); | |
| + partition_i4x4_size_cabac( h, &cabac_tmp, i4, i_mode ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| else | |
| - i_bits = (uint64_t)x264_partition_i4x4_size_cavlc( h, i4, i_mode ) * i_lambda2; | |
| + i_bits = (uint64_t)partition_i4x4_size_cavlc( h, i4, i_mode ) * i_lambda2; | |
| return (i_ssd<<8) + i_bits; | |
| } | |
| -static uint64_t x264_rd_cost_chroma( x264_t *h, int i_lambda2, int i_mode, int b_dct ) | |
| +static uint64_t rd_cost_chroma( x264_t *h, int i_lambda2, int i_mode, int b_dct ) | |
| { | |
| uint64_t i_ssd, i_bits; | |
| @@ -352,11 +362,11 @@ | |
| { | |
| x264_cabac_t cabac_tmp; | |
| COPY_CABAC; | |
| - x264_chroma_size_cabac( h, &cabac_tmp ); | |
| + chroma_size_cabac( h, &cabac_tmp ); | |
| i_bits = ( (uint64_t)cabac_tmp.f8_bits_encoded * i_lambda2 + 128 ) >> 8; | |
| } | |
| else | |
| - i_bits = (uint64_t)x264_chroma_size_cavlc( h ) * i_lambda2; | |
| + i_bits = (uint64_t)chroma_size_cavlc( h ) * i_lambda2; | |
| return (i_ssd<<8) + i_bits; | |
| } | |
| @@ -364,8 +374,8 @@ | |
| * Trellis RD quantization | |
| ****************************************************************************/ | |
| -#define TRELLIS_SCORE_MAX -1LL // negative marks the node as invalid | |
| -#define TRELLIS_SCORE_BIAS 1LL<<60; // bias so that all valid scores are positive, even after negative contributions from psy | |
| +#define TRELLIS_SCORE_MAX (~0ULL) // marks the node as invalid | |
| +#define TRELLIS_SCORE_BIAS (1ULL<<60) // bias so that all valid scores are positive, even after negative contributions from psy | |
| #define CABAC_SIZE_BITS 8 | |
| #define LAMBDA_BITS 4 | |
| @@ -695,8 +705,12 @@ | |
| } | |
| #if HAVE_MMX && ARCH_X86_64 && !defined( __MACH__ ) | |
| + uint64_t level_state0; | |
| + memcpy( &level_state0, cabac_state, sizeof(uint64_t) ); | |
| + uint16_t level_state1; | |
| + memcpy( &level_state1, cabac_state+8, sizeof(uint16_t) ); | |
| #define TRELLIS_ARGS unquant_mf, zigzag, lambda2, last_nnz, orig_coefs, quant_coefs, dct,\ | |
| - cabac_state_sig, cabac_state_last, M64(cabac_state), M16(cabac_state+8) | |
| + cabac_state_sig, cabac_state_last, level_state0, level_state1 | |
| if( num_coefs == 16 && !dc ) | |
| if( b_chroma || !h->mb.i_psy_trellis ) | |
| return h->quantf.trellis_cabac_4x4( TRELLIS_ARGS, b_ac ); | |
| @@ -907,8 +921,8 @@ | |
| const uint8_t *zigzag, int ctx_block_cat, int lambda2, int b_ac, | |
| int b_chroma, int dc, int num_coefs, int idx, int b_8x8 ) | |
| { | |
| - ALIGNED_16( dctcoef quant_coefs[2][16] ); | |
| - ALIGNED_16( dctcoef coefs[16] ) = {0}; | |
| + ALIGNED_ARRAY_16( dctcoef, quant_coefs,[2],[16] ); | |
| + ALIGNED_ARRAY_16( dctcoef, coefs,[16] ); | |
| const uint32_t *coef_weight1 = b_8x8 ? x264_dct8_weight_tab : x264_dct4_weight_tab; | |
| const uint32_t *coef_weight2 = b_8x8 ? x264_dct8_weight2_tab : x264_dct4_weight2_tab; | |
| int delta_distortion[16]; | |
| @@ -918,6 +932,9 @@ | |
| int nC = b_chroma && dc ? 3 + (num_coefs>>2) | |
| : ct_index[x264_mb_predict_non_zero_code( h, !b_chroma && dc ? (idx - LUMA_DC)*16 : idx )]; | |
| + for( i = 0; i < 16; i += 16/sizeof(*coefs) ) | |
| + M128( &coefs[i] ) = M128_ZERO; | |
| + | |
| /* Code for handling 8x8dct -> 4x4dct CAVLC munging. Input/output use a different | |
| * step/start/end than internal processing. */ | |
| int step = 1; | |
| @@ -997,7 +1014,7 @@ | |
| if( !coef_mask ) | |
| bs_write_vlc( &h->out.bs, x264_coeff0_token[nC] ); | |
| else | |
| - x264_cavlc_block_residual_internal( h, ctx_block_cat, coefs + b_ac, nC ); | |
| + cavlc_block_residual_internal( h, ctx_block_cat, coefs + b_ac, nC ); | |
| score = (int64_t)h->out.bs.i_bits_encoded * lambda2; | |
| /* QNS loop: pick the change that improves RD the most, apply it, repeat. | |
| @@ -1030,7 +1047,7 @@ | |
| if( !cur_mask ) | |
| bs_write_vlc( &h->out.bs, x264_coeff0_token[nC] ); | |
| else | |
| - x264_cavlc_block_residual_internal( h, ctx_block_cat, coefs + b_ac, nC ); | |
| + cavlc_block_residual_internal( h, ctx_block_cat, coefs + b_ac, nC ); | |
| cur_score += (int64_t)h->out.bs.i_bits_encoded * lambda2; | |
| coefs[i] = old_coef; | |
| @@ -1089,8 +1106,8 @@ | |
| DCT_LUMA_DC, h->mb.i_trellis_lambda2[0][b_intra], 0, 0, 1, 16, idx, 0 ); | |
| } | |
| -static const uint8_t x264_zigzag_scan2x2[4] = { 0, 1, 2, 3 }; | |
| -static const uint8_t x264_zigzag_scan2x4[8] = { 0, 2, 1, 4, 6, 3, 5, 7 }; | |
| +static const uint8_t zigzag_scan2x2[4] = { 0, 1, 2, 3 }; | |
| +static const uint8_t zigzag_scan2x4[8] = { 0, 2, 1, 4, 6, 3, 5, 7 }; | |
| int x264_quant_chroma_dc_trellis( x264_t *h, dctcoef *dct, int i_qp, int b_intra, int idx ) | |
| { | |
| @@ -1100,12 +1117,12 @@ | |
| if( CHROMA_FORMAT == CHROMA_422 ) | |
| { | |
| - zigzag = x264_zigzag_scan2x4; | |
| + zigzag = zigzag_scan2x4; | |
| num_coefs = 8; | |
| } | |
| else | |
| { | |
| - zigzag = x264_zigzag_scan2x2; | |
| + zigzag = zigzag_scan2x2; | |
| num_coefs = 4; | |
| } | |
| diff -ur x264-go/x264c/external/x264/encoder/set.c x264-go.new/x264c/external/x264/encoder/set.c | |
| --- x264-go/x264c/external/x264/encoder/set.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/set.c 2020-06-06 15:20:58.699039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * set: header writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -31,7 +31,7 @@ | |
| // Indexed by pic_struct values | |
| static const uint8_t num_clock_ts[10] = { 0, 1, 1, 1, 2, 2, 3, 3, 2, 3 }; | |
| -const static uint8_t avcintra_uuid[] = {0xF7, 0x49, 0x3E, 0xB3, 0xD4, 0x00, 0x47, 0x96, 0x86, 0x86, 0xC9, 0x70, 0x7B, 0x64, 0x37, 0x2A}; | |
| +static const uint8_t avcintra_uuid[] = {0xF7, 0x49, 0x3E, 0xB3, 0xD4, 0x00, 0x47, 0x96, 0x86, 0x86, 0xC9, 0x70, 0x7B, 0x64, 0x37, 0x2A}; | |
| static void transpose( uint8_t *buf, int w ) | |
| { | |
| @@ -40,15 +40,15 @@ | |
| XCHG( uint8_t, buf[w*i+j], buf[w*j+i] ); | |
| } | |
| -static void scaling_list_write( bs_t *s, x264_pps_t *pps, int idx ) | |
| +static void scaling_list_write( bs_t *s, x264_sps_t *sps, int idx ) | |
| { | |
| const int len = idx<4 ? 16 : 64; | |
| const uint8_t *zigzag = idx<4 ? x264_zigzag_scan4[0] : x264_zigzag_scan8[0]; | |
| - const uint8_t *list = pps->scaling_list[idx]; | |
| - const uint8_t *def_list = (idx==CQM_4IC) ? pps->scaling_list[CQM_4IY] | |
| - : (idx==CQM_4PC) ? pps->scaling_list[CQM_4PY] | |
| - : (idx==CQM_8IC+4) ? pps->scaling_list[CQM_8IY+4] | |
| - : (idx==CQM_8PC+4) ? pps->scaling_list[CQM_8PY+4] | |
| + const uint8_t *list = sps->scaling_list[idx]; | |
| + const uint8_t *def_list = (idx==CQM_4IC) ? sps->scaling_list[CQM_4IY] | |
| + : (idx==CQM_4PC) ? sps->scaling_list[CQM_4PY] | |
| + : (idx==CQM_8IC+4) ? sps->scaling_list[CQM_8IY+4] | |
| + : (idx==CQM_8PC+4) ? sps->scaling_list[CQM_8PY+4] | |
| : x264_cqm_jvt[idx]; | |
| if( !memcmp( list, def_list, len ) ) | |
| bs_write1( s, 0 ); // scaling_list_present_flag | |
| @@ -105,8 +105,12 @@ | |
| sps->i_id = i_id; | |
| sps->i_mb_width = ( param->i_width + 15 ) / 16; | |
| sps->i_mb_height= ( param->i_height + 15 ) / 16; | |
| + sps->b_frame_mbs_only = !(param->b_interlaced || param->b_fake_interlaced); | |
| + if( !sps->b_frame_mbs_only ) | |
| + sps->i_mb_height = ( sps->i_mb_height + 1 ) & ~1; | |
| sps->i_chroma_format_idc = csp >= X264_CSP_I444 ? CHROMA_444 : | |
| - csp >= X264_CSP_I422 ? CHROMA_422 : CHROMA_420; | |
| + csp >= X264_CSP_I422 ? CHROMA_422 : | |
| + csp >= X264_CSP_I420 ? CHROMA_420 : CHROMA_400; | |
| sps->b_qpprime_y_zero_transform_bypass = param->rc.i_rc_method == X264_RC_CQP && param->rc.i_qp_constant == 0; | |
| if( sps->b_qpprime_y_zero_transform_bypass || sps->i_chroma_format_idc == CHROMA_444 ) | |
| @@ -115,7 +119,7 @@ | |
| sps->i_profile_idc = PROFILE_HIGH422; | |
| else if( BIT_DEPTH > 8 ) | |
| sps->i_profile_idc = PROFILE_HIGH10; | |
| - else if( param->analyse.b_transform_8x8 || param->i_cqm_preset != X264_CQM_FLAT ) | |
| + else if( param->analyse.b_transform_8x8 || param->i_cqm_preset != X264_CQM_FLAT || sps->i_chroma_format_idc == CHROMA_400 ) | |
| sps->i_profile_idc = PROFILE_HIGH; | |
| else if( param->b_cabac || param->i_bframe > 0 || param->b_interlaced || param->b_fake_interlaced || param->analyse.i_weighted_pred > 0 ) | |
| sps->i_profile_idc = PROFILE_MAIN; | |
| @@ -178,9 +182,6 @@ | |
| sps->b_vui = 1; | |
| sps->b_gaps_in_frame_num_value_allowed = 0; | |
| - sps->b_frame_mbs_only = !(param->b_interlaced || param->b_fake_interlaced); | |
| - if( !sps->b_frame_mbs_only ) | |
| - sps->i_mb_height = ( sps->i_mb_height + 1 ) & ~1; | |
| sps->b_mb_adaptive_frame_field = param->b_interlaced; | |
| sps->b_direct8x8_inference = 1; | |
| @@ -197,22 +198,14 @@ | |
| sps->vui.b_color_description_present = 0; | |
| sps->vui.i_colorprim = ( param->vui.i_colorprim >= 0 && param->vui.i_colorprim <= 12 ? param->vui.i_colorprim : 2 ); | |
| - sps->vui.i_transfer = ( param->vui.i_transfer >= 0 && param->vui.i_transfer <= 17 ? param->vui.i_transfer : 2 ); | |
| - sps->vui.i_colmatrix = ( param->vui.i_colmatrix >= 0 && param->vui.i_colmatrix <= 11 ? param->vui.i_colmatrix : | |
| + sps->vui.i_transfer = ( param->vui.i_transfer >= 0 && param->vui.i_transfer <= 18 ? param->vui.i_transfer : 2 ); | |
| + sps->vui.i_colmatrix = ( param->vui.i_colmatrix >= 0 && param->vui.i_colmatrix <= 14 ? param->vui.i_colmatrix : | |
| ( csp >= X264_CSP_BGR ? 0 : 2 ) ); | |
| - if( sps->vui.i_colorprim != 2 || | |
| - sps->vui.i_transfer != 2 || | |
| - sps->vui.i_colmatrix != 2 ) | |
| - { | |
| + if( sps->vui.i_colorprim != 2 || sps->vui.i_transfer != 2 || sps->vui.i_colmatrix != 2 ) | |
| sps->vui.b_color_description_present = 1; | |
| - } | |
| - if( sps->vui.i_vidformat != 5 || | |
| - sps->vui.b_fullrange || | |
| - sps->vui.b_color_description_present ) | |
| - { | |
| + if( sps->vui.i_vidformat != 5 || sps->vui.b_fullrange || sps->vui.b_color_description_present ) | |
| sps->vui.b_signal_type_present = 1; | |
| - } | |
| /* FIXME: not sufficient for interlaced video */ | |
| sps->vui.b_chroma_loc_info_present = param->vui.i_chroma_loc > 0 && param->vui.i_chroma_loc <= 5 && | |
| @@ -247,6 +240,9 @@ | |
| sps->vui.i_log2_max_mv_length_horizontal = | |
| sps->vui.i_log2_max_mv_length_vertical = (int)log2f( X264_MAX( 1, param->analyse.i_mv_range*4-1 ) ) + 1; | |
| } | |
| + | |
| + sps->b_avcintra = !!param->i_avcintra_class; | |
| + sps->i_cqm_preset = param->i_cqm_preset; | |
| } | |
| void x264_sps_init_reconfigurable( x264_sps_t *sps, x264_param_t *param ) | |
| @@ -254,7 +250,7 @@ | |
| sps->crop.i_left = param->crop_rect.i_left; | |
| sps->crop.i_top = param->crop_rect.i_top; | |
| sps->crop.i_right = param->crop_rect.i_right + sps->i_mb_width*16 - param->i_width; | |
| - sps->crop.i_bottom = (param->crop_rect.i_bottom + sps->i_mb_height*16 - param->i_height) >> !sps->b_frame_mbs_only; | |
| + sps->crop.i_bottom = param->crop_rect.i_bottom + sps->i_mb_height*16 - param->i_height; | |
| sps->b_crop = sps->crop.i_left || sps->crop.i_top || | |
| sps->crop.i_right || sps->crop.i_bottom; | |
| @@ -267,6 +263,44 @@ | |
| } | |
| } | |
| +void x264_sps_init_scaling_list( x264_sps_t *sps, x264_param_t *param ) | |
| +{ | |
| + switch( sps->i_cqm_preset ) | |
| + { | |
| + case X264_CQM_FLAT: | |
| + for( int i = 0; i < 8; i++ ) | |
| + sps->scaling_list[i] = x264_cqm_flat16; | |
| + break; | |
| + case X264_CQM_JVT: | |
| + for( int i = 0; i < 8; i++ ) | |
| + sps->scaling_list[i] = x264_cqm_jvt[i]; | |
| + break; | |
| + case X264_CQM_CUSTOM: | |
| + /* match the transposed DCT & zigzag */ | |
| + transpose( param->cqm_4iy, 4 ); | |
| + transpose( param->cqm_4py, 4 ); | |
| + transpose( param->cqm_4ic, 4 ); | |
| + transpose( param->cqm_4pc, 4 ); | |
| + transpose( param->cqm_8iy, 8 ); | |
| + transpose( param->cqm_8py, 8 ); | |
| + transpose( param->cqm_8ic, 8 ); | |
| + transpose( param->cqm_8pc, 8 ); | |
| + sps->scaling_list[CQM_4IY] = param->cqm_4iy; | |
| + sps->scaling_list[CQM_4PY] = param->cqm_4py; | |
| + sps->scaling_list[CQM_4IC] = param->cqm_4ic; | |
| + sps->scaling_list[CQM_4PC] = param->cqm_4pc; | |
| + sps->scaling_list[CQM_8IY+4] = param->cqm_8iy; | |
| + sps->scaling_list[CQM_8PY+4] = param->cqm_8py; | |
| + sps->scaling_list[CQM_8IC+4] = param->cqm_8ic; | |
| + sps->scaling_list[CQM_8PC+4] = param->cqm_8pc; | |
| + for( int i = 0; i < 8; i++ ) | |
| + for( int j = 0; j < (i < 4 ? 16 : 64); j++ ) | |
| + if( sps->scaling_list[i][j] == 0 ) | |
| + sps->scaling_list[i] = x264_cqm_jvt[i]; | |
| + break; | |
| + } | |
| +} | |
| + | |
| void x264_sps_write( bs_t *s, x264_sps_t *sps ) | |
| { | |
| bs_realign( s ); | |
| @@ -290,7 +324,26 @@ | |
| bs_write_ue( s, BIT_DEPTH-8 ); // bit_depth_luma_minus8 | |
| bs_write_ue( s, BIT_DEPTH-8 ); // bit_depth_chroma_minus8 | |
| bs_write1( s, sps->b_qpprime_y_zero_transform_bypass ); | |
| - bs_write1( s, 0 ); // seq_scaling_matrix_present_flag | |
| + /* Exactly match the AVC-Intra bitstream */ | |
| + bs_write1( s, sps->b_avcintra ); // seq_scaling_matrix_present_flag | |
| + if( sps->b_avcintra ) | |
| + { | |
| + scaling_list_write( s, sps, CQM_4IY ); | |
| + scaling_list_write( s, sps, CQM_4IC ); | |
| + scaling_list_write( s, sps, CQM_4IC ); | |
| + bs_write1( s, 0 ); // no inter | |
| + bs_write1( s, 0 ); // no inter | |
| + bs_write1( s, 0 ); // no inter | |
| + scaling_list_write( s, sps, CQM_8IY+4 ); | |
| + bs_write1( s, 0 ); // no inter | |
| + if( sps->i_chroma_format_idc == CHROMA_444 ) | |
| + { | |
| + scaling_list_write( s, sps, CQM_8IC+4 ); | |
| + bs_write1( s, 0 ); // no inter | |
| + scaling_list_write( s, sps, CQM_8IC+4 ); | |
| + bs_write1( s, 0 ); // no inter | |
| + } | |
| + } | |
| } | |
| bs_write_ue( s, sps->i_log2_max_frame_num - 4 ); | |
| @@ -310,7 +363,7 @@ | |
| if( sps->b_crop ) | |
| { | |
| int h_shift = sps->i_chroma_format_idc == CHROMA_420 || sps->i_chroma_format_idc == CHROMA_422; | |
| - int v_shift = sps->i_chroma_format_idc == CHROMA_420; | |
| + int v_shift = (sps->i_chroma_format_idc == CHROMA_420) + !sps->b_frame_mbs_only; | |
| bs_write_ue( s, sps->crop.i_left >> h_shift ); | |
| bs_write_ue( s, sps->crop.i_right >> h_shift ); | |
| bs_write_ue( s, sps->crop.i_top >> v_shift ); | |
| @@ -446,43 +499,6 @@ | |
| pps->b_redundant_pic_cnt = 0; | |
| pps->b_transform_8x8_mode = param->analyse.b_transform_8x8 ? 1 : 0; | |
| - | |
| - pps->i_cqm_preset = param->i_cqm_preset; | |
| - | |
| - switch( pps->i_cqm_preset ) | |
| - { | |
| - case X264_CQM_FLAT: | |
| - for( int i = 0; i < 8; i++ ) | |
| - pps->scaling_list[i] = x264_cqm_flat16; | |
| - break; | |
| - case X264_CQM_JVT: | |
| - for( int i = 0; i < 8; i++ ) | |
| - pps->scaling_list[i] = x264_cqm_jvt[i]; | |
| - break; | |
| - case X264_CQM_CUSTOM: | |
| - /* match the transposed DCT & zigzag */ | |
| - transpose( param->cqm_4iy, 4 ); | |
| - transpose( param->cqm_4py, 4 ); | |
| - transpose( param->cqm_4ic, 4 ); | |
| - transpose( param->cqm_4pc, 4 ); | |
| - transpose( param->cqm_8iy, 8 ); | |
| - transpose( param->cqm_8py, 8 ); | |
| - transpose( param->cqm_8ic, 8 ); | |
| - transpose( param->cqm_8pc, 8 ); | |
| - pps->scaling_list[CQM_4IY] = param->cqm_4iy; | |
| - pps->scaling_list[CQM_4PY] = param->cqm_4py; | |
| - pps->scaling_list[CQM_4IC] = param->cqm_4ic; | |
| - pps->scaling_list[CQM_4PC] = param->cqm_4pc; | |
| - pps->scaling_list[CQM_8IY+4] = param->cqm_8iy; | |
| - pps->scaling_list[CQM_8PY+4] = param->cqm_8py; | |
| - pps->scaling_list[CQM_8IC+4] = param->cqm_8ic; | |
| - pps->scaling_list[CQM_8PC+4] = param->cqm_8pc; | |
| - for( int i = 0; i < 8; i++ ) | |
| - for( int j = 0; j < (i < 4 ? 16 : 64); j++ ) | |
| - if( pps->scaling_list[i][j] == 0 ) | |
| - pps->scaling_list[i] = x264_cqm_jvt[i]; | |
| - break; | |
| - } | |
| } | |
| void x264_pps_write( bs_t *s, x264_sps_t *sps, x264_pps_t *pps ) | |
| @@ -508,26 +524,27 @@ | |
| bs_write1( s, pps->b_constrained_intra_pred ); | |
| bs_write1( s, pps->b_redundant_pic_cnt ); | |
| - if( pps->b_transform_8x8_mode || pps->i_cqm_preset != X264_CQM_FLAT ) | |
| + int b_scaling_list = !sps->b_avcintra && sps->i_cqm_preset != X264_CQM_FLAT; | |
| + if( pps->b_transform_8x8_mode || b_scaling_list ) | |
| { | |
| bs_write1( s, pps->b_transform_8x8_mode ); | |
| - bs_write1( s, (pps->i_cqm_preset != X264_CQM_FLAT) ); | |
| - if( pps->i_cqm_preset != X264_CQM_FLAT ) | |
| + bs_write1( s, b_scaling_list ); | |
| + if( b_scaling_list ) | |
| { | |
| - scaling_list_write( s, pps, CQM_4IY ); | |
| - scaling_list_write( s, pps, CQM_4IC ); | |
| + scaling_list_write( s, sps, CQM_4IY ); | |
| + scaling_list_write( s, sps, CQM_4IC ); | |
| bs_write1( s, 0 ); // Cr = Cb | |
| - scaling_list_write( s, pps, CQM_4PY ); | |
| - scaling_list_write( s, pps, CQM_4PC ); | |
| + scaling_list_write( s, sps, CQM_4PY ); | |
| + scaling_list_write( s, sps, CQM_4PC ); | |
| bs_write1( s, 0 ); // Cr = Cb | |
| if( pps->b_transform_8x8_mode ) | |
| { | |
| - scaling_list_write( s, pps, CQM_8IY+4 ); | |
| - scaling_list_write( s, pps, CQM_8PY+4 ); | |
| + scaling_list_write( s, sps, CQM_8IY+4 ); | |
| + scaling_list_write( s, sps, CQM_8PY+4 ); | |
| if( sps->i_chroma_format_idc == CHROMA_444 ) | |
| { | |
| - scaling_list_write( s, pps, CQM_8IC+4 ); | |
| - scaling_list_write( s, pps, CQM_8PC+4 ); | |
| + scaling_list_write( s, sps, CQM_8IC+4 ); | |
| + scaling_list_write( s, sps, CQM_8PC+4 ); | |
| bs_write1( s, 0 ); // Cr = Cb | |
| bs_write1( s, 0 ); // Cr = Cb | |
| } | |
| @@ -555,7 +572,6 @@ | |
| bs_write( &q, 2, 0 ); //changing_slice_group 0 | |
| bs_align_10( &q ); | |
| - bs_flush( &q ); | |
| x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_RECOVERY_POINT ); | |
| } | |
| @@ -578,7 +594,7 @@ | |
| memcpy( payload, uuid, 16 ); | |
| sprintf( payload+16, "x264 - core %d%s - H.264/MPEG-4 AVC codec - " | |
| - "Copy%s 2003-2017 - http://www.videolan.org/x264.html - options: %s", | |
| + "Copy%s 2003-2020 - http://www.videolan.org/x264.html - options: %s", | |
| X264_BUILD, X264_VERSION, HAVE_GPL?"left":"right", opts ); | |
| length = strlen(payload)+1; | |
| @@ -610,7 +626,6 @@ | |
| } | |
| bs_align_10( &q ); | |
| - bs_flush( &q ); | |
| x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_BUFFERING_PERIOD ); | |
| } | |
| @@ -642,7 +657,6 @@ | |
| } | |
| bs_align_10( &q ); | |
| - bs_flush( &q ); | |
| x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_PIC_TIMING ); | |
| } | |
| @@ -685,11 +699,26 @@ | |
| bs_write1( &q, 0 ); // frame_packing_arrangement_extension_flag | |
| bs_align_10( &q ); | |
| - bs_flush( &q ); | |
| x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_FRAME_PACKING ); | |
| } | |
| +void x264_sei_alternative_transfer_write( x264_t *h, bs_t *s ) | |
| +{ | |
| + bs_t q; | |
| + ALIGNED_4( uint8_t tmp_buf[100] ); | |
| + M32( tmp_buf ) = 0; // shut up gcc | |
| + bs_init( &q, tmp_buf, 100 ); | |
| + | |
| + bs_realign( &q ); | |
| + | |
| + bs_write ( &q, 8, h->param.i_alternative_transfer ); // preferred_transfer_characteristics | |
| + | |
| + bs_align_10( &q ); | |
| + | |
| + x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_ALTERNATIVE_TRANSFER ); | |
| +} | |
| + | |
| void x264_filler_write( x264_t *h, bs_t *s, int filler ) | |
| { | |
| bs_realign( s ); | |
| @@ -729,7 +758,6 @@ | |
| } | |
| bs_align_10( &q ); | |
| - bs_flush( &q ); | |
| x264_sei_write( s, tmp_buf, bs_pos( &q ) / 8, SEI_DEC_REF_PIC_MARKING ); | |
| } | |
| @@ -766,7 +794,7 @@ | |
| { | |
| uint8_t data[6000]; | |
| const char *msg = "VANC"; | |
| - if( len > sizeof(data) ) | |
| + if( len < 0 || (unsigned)len > sizeof(data) ) | |
| { | |
| x264_log( h, X264_LOG_ERROR, "AVC-Intra SEI is too large (%d)\n", len ); | |
| return -1; | |
| @@ -781,31 +809,6 @@ | |
| return 0; | |
| } | |
| -const x264_level_t x264_levels[] = | |
| -{ | |
| - { 10, 1485, 99, 396, 64, 175, 64, 64, 0, 2, 0, 0, 1 }, | |
| - { 9, 1485, 99, 396, 128, 350, 64, 64, 0, 2, 0, 0, 1 }, /* "1b" */ | |
| - { 11, 3000, 396, 900, 192, 500, 128, 64, 0, 2, 0, 0, 1 }, | |
| - { 12, 6000, 396, 2376, 384, 1000, 128, 64, 0, 2, 0, 0, 1 }, | |
| - { 13, 11880, 396, 2376, 768, 2000, 128, 64, 0, 2, 0, 0, 1 }, | |
| - { 20, 11880, 396, 2376, 2000, 2000, 128, 64, 0, 2, 0, 0, 1 }, | |
| - { 21, 19800, 792, 4752, 4000, 4000, 256, 64, 0, 2, 0, 0, 0 }, | |
| - { 22, 20250, 1620, 8100, 4000, 4000, 256, 64, 0, 2, 0, 0, 0 }, | |
| - { 30, 40500, 1620, 8100, 10000, 10000, 256, 32, 22, 2, 0, 1, 0 }, | |
| - { 31, 108000, 3600, 18000, 14000, 14000, 512, 16, 60, 4, 1, 1, 0 }, | |
| - { 32, 216000, 5120, 20480, 20000, 20000, 512, 16, 60, 4, 1, 1, 0 }, | |
| - { 40, 245760, 8192, 32768, 20000, 25000, 512, 16, 60, 4, 1, 1, 0 }, | |
| - { 41, 245760, 8192, 32768, 50000, 62500, 512, 16, 24, 2, 1, 1, 0 }, | |
| - { 42, 522240, 8704, 34816, 50000, 62500, 512, 16, 24, 2, 1, 1, 1 }, | |
| - { 50, 589824, 22080, 110400, 135000, 135000, 512, 16, 24, 2, 1, 1, 1 }, | |
| - { 51, 983040, 36864, 184320, 240000, 240000, 512, 16, 24, 2, 1, 1, 1 }, | |
| - { 52, 2073600, 36864, 184320, 240000, 240000, 512, 16, 24, 2, 1, 1, 1 }, | |
| - { 60, 4177920, 139264, 696320, 240000, 240000, 8192, 16, 24, 2, 1, 1, 1 }, | |
| - { 61, 8355840, 139264, 696320, 480000, 480000, 8192, 16, 24, 2, 1, 1, 1 }, | |
| - { 62, 16711680, 139264, 696320, 800000, 800000, 8192, 16, 24, 2, 1, 1, 1 }, | |
| - { 0 } | |
| -}; | |
| - | |
| #define ERROR(...)\ | |
| {\ | |
| if( verbose )\ | |
| diff -ur x264-go/x264c/external/x264/encoder/set.h x264-go.new/x264c/external/x264/encoder/set.h | |
| --- x264-go/x264c/external/x264/encoder/set.h 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/set.h 2020-06-06 15:20:58.699039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * set.h: header writing | |
| ***************************************************************************** | |
| - * Copyright (C) 2003-2017 x264 project | |
| + * Copyright (C) 2003-2020 x264 project | |
| * | |
| * Authors: Laurent Aimar <fenrir@via.ecp.fr> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -27,21 +27,41 @@ | |
| #ifndef X264_ENCODER_SET_H | |
| #define X264_ENCODER_SET_H | |
| +#define x264_sps_init x264_template(sps_init) | |
| void x264_sps_init( x264_sps_t *sps, int i_id, x264_param_t *param ); | |
| +#define x264_sps_init_reconfigurable x264_template(sps_init_reconfigurable) | |
| void x264_sps_init_reconfigurable( x264_sps_t *sps, x264_param_t *param ); | |
| +#define x264_sps_init_scaling_list x264_template(sps_init_scaling_list) | |
| +void x264_sps_init_scaling_list( x264_sps_t *sps, x264_param_t *param ); | |
| +#define x264_sps_write x264_template(sps_write) | |
| void x264_sps_write( bs_t *s, x264_sps_t *sps ); | |
| +#define x264_pps_init x264_template(pps_init) | |
| void x264_pps_init( x264_pps_t *pps, int i_id, x264_param_t *param, x264_sps_t *sps ); | |
| +#define x264_pps_write x264_template(pps_write) | |
| void x264_pps_write( bs_t *s, x264_sps_t *sps, x264_pps_t *pps ); | |
| +#define x264_sei_recovery_point_write x264_template(sei_recovery_point_write) | |
| void x264_sei_recovery_point_write( x264_t *h, bs_t *s, int recovery_frame_cnt ); | |
| +#define x264_sei_version_write x264_template(sei_version_write) | |
| int x264_sei_version_write( x264_t *h, bs_t *s ); | |
| +#define x264_validate_levels x264_template(validate_levels) | |
| int x264_validate_levels( x264_t *h, int verbose ); | |
| +#define x264_sei_buffering_period_write x264_template(sei_buffering_period_write) | |
| void x264_sei_buffering_period_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_pic_timing_write x264_template(sei_pic_timing_write) | |
| void x264_sei_pic_timing_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_dec_ref_pic_marking_write x264_template(sei_dec_ref_pic_marking_write) | |
| void x264_sei_dec_ref_pic_marking_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_frame_packing_write x264_template(sei_frame_packing_write) | |
| void x264_sei_frame_packing_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_alternative_transfer_write x264_template(sei_alternative_transfer_write) | |
| +void x264_sei_alternative_transfer_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_avcintra_umid_write x264_template(sei_avcintra_umid_write) | |
| int x264_sei_avcintra_umid_write( x264_t *h, bs_t *s ); | |
| +#define x264_sei_avcintra_vanc_write x264_template(sei_avcintra_vanc_write) | |
| int x264_sei_avcintra_vanc_write( x264_t *h, bs_t *s, int len ); | |
| +#define x264_sei_write x264_template(sei_write) | |
| void x264_sei_write( bs_t *s, uint8_t *payload, int payload_size, int payload_type ); | |
| +#define x264_filler_write x264_template(filler_write) | |
| void x264_filler_write( x264_t *h, bs_t *s, int filler ); | |
| #endif | |
| diff -ur x264-go/x264c/external/x264/encoder/slicetype.c x264-go.new/x264c/external/x264/encoder/slicetype.c | |
| --- x264-go/x264c/external/x264/encoder/slicetype.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/slicetype.c 2020-06-06 15:20:58.699039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * slicetype.c: lookahead analysis | |
| ***************************************************************************** | |
| - * Copyright (C) 2005-2017 x264 project | |
| + * Copyright (C) 2005-2020 x264 project | |
| * | |
| * Authors: Fiona Glaser <fiona@x264.com> | |
| * Loren Merritt <lorenm@u.washington.edu> | |
| @@ -32,26 +32,21 @@ | |
| // Indexed by pic_struct values | |
| static const uint8_t delta_tfi_divisor[10] = { 0, 2, 1, 1, 2, 2, 3, 3, 4, 6 }; | |
| -static int x264_slicetype_frame_cost( x264_t *h, x264_mb_analysis_t *a, | |
| - x264_frame_t **frames, int p0, int p1, int b ); | |
| +static int slicetype_frame_cost( x264_t *h, x264_mb_analysis_t *a, | |
| + x264_frame_t **frames, int p0, int p1, int b ); | |
| +#define x264_weights_analyse x264_template(weights_analyse) | |
| void x264_weights_analyse( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, int b_lookahead ); | |
| #if HAVE_OPENCL | |
| -int x264_opencl_lowres_init( x264_t *h, x264_frame_t *fenc, int lambda ); | |
| -int x264_opencl_motionsearch( x264_t *h, x264_frame_t **frames, int b, int ref, int b_islist1, int lambda, const x264_weight_t *w ); | |
| -int x264_opencl_finalize_cost( x264_t *h, int lambda, x264_frame_t **frames, int p0, int p1, int b, int dist_scale_factor ); | |
| -int x264_opencl_precalculate_frame_cost( x264_t *h, x264_frame_t **frames, int lambda, int p0, int p1, int b ); | |
| -void x264_opencl_flush( x264_t *h ); | |
| -void x264_opencl_slicetype_prep( x264_t *h, x264_frame_t **frames, int num_frames, int lambda ); | |
| -void x264_opencl_slicetype_end( x264_t *h ); | |
| +#include "slicetype-cl.h" | |
| #endif | |
| -static void x264_lowres_context_init( x264_t *h, x264_mb_analysis_t *a ) | |
| +static void lowres_context_init( x264_t *h, x264_mb_analysis_t *a ) | |
| { | |
| a->i_qp = X264_LOOKAHEAD_QP; | |
| a->i_lambda = x264_lambda_tab[ a->i_qp ]; | |
| - x264_mb_analyse_load_costs( h, a ); | |
| + mb_analyse_load_costs( h, a ); | |
| if( h->param.analyse.i_subpel_refine > 1 ) | |
| { | |
| h->mb.i_me_method = X264_MIN( X264_ME_HEX, h->param.analyse.i_me_method ); | |
| @@ -66,7 +61,7 @@ | |
| } | |
| /* makes a non-h264 weight (i.e. fix7), into an h264 weight */ | |
| -static void x264_weight_get_h264( int weight_nonh264, int offset, x264_weight_t *w ) | |
| +static void weight_get_h264( int weight_nonh264, int offset, x264_weight_t *w ) | |
| { | |
| w->i_offset = offset; | |
| w->i_denom = 7; | |
| @@ -79,7 +74,7 @@ | |
| w->i_scale = X264_MIN( w->i_scale, 127 ); | |
| } | |
| -static NOINLINE pixel *x264_weight_cost_init_luma( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dest ) | |
| +static NOINLINE pixel *weight_cost_init_luma( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dest ) | |
| { | |
| int ref0_distance = fenc->i_frame - ref->i_frame - 1; | |
| /* Note: this will never run during lookahead as weights_analyse is only called if no | |
| @@ -113,7 +108,7 @@ | |
| * fenc = ref + offset | |
| * v = u + stride * chroma height */ | |
| -static NOINLINE void x264_weight_cost_init_chroma( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dstu, pixel *dstv ) | |
| +static NOINLINE void weight_cost_init_chroma( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dstu, pixel *dstv ) | |
| { | |
| int ref0_distance = fenc->i_frame - ref->i_frame - 1; | |
| int i_stride = fenc->i_stride[1]; | |
| @@ -145,7 +140,7 @@ | |
| x264_emms(); | |
| } | |
| -static NOINLINE pixel *x264_weight_cost_init_chroma444( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dst, int p ) | |
| +static NOINLINE pixel *weight_cost_init_chroma444( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, pixel *dst, int p ) | |
| { | |
| int ref0_distance = fenc->i_frame - ref->i_frame - 1; | |
| int i_stride = fenc->i_stride[p]; | |
| @@ -173,7 +168,7 @@ | |
| return ref->plane[p]; | |
| } | |
| -static int x264_weight_slice_header_cost( x264_t *h, x264_weight_t *w, int b_chroma ) | |
| +static int weight_slice_header_cost( x264_t *h, x264_weight_t *w, int b_chroma ) | |
| { | |
| /* Add cost of weights in the slice header. */ | |
| int lambda = x264_lambda_tab[X264_LOOKAHEAD_QP]; | |
| @@ -194,7 +189,7 @@ | |
| return lambda * numslices * ( 10 + denom_cost + 2 * (bs_size_se( w[0].i_scale ) + bs_size_se( w[0].i_offset )) ); | |
| } | |
| -static NOINLINE unsigned int x264_weight_cost_luma( x264_t *h, x264_frame_t *fenc, pixel *src, x264_weight_t *w ) | |
| +static NOINLINE unsigned int weight_cost_luma( x264_t *h, x264_frame_t *fenc, pixel *src, x264_weight_t *w ) | |
| { | |
| unsigned int cost = 0; | |
| int i_stride = fenc->i_stride_lowres; | |
| @@ -214,7 +209,7 @@ | |
| int cmp = h->pixf.mbcmp[PIXEL_8x8]( buf, 8, &fenc_plane[pixoff], i_stride ); | |
| cost += X264_MIN( cmp, fenc->i_intra_cost[i_mb] ); | |
| } | |
| - cost += x264_weight_slice_header_cost( h, w, 0 ); | |
| + cost += weight_slice_header_cost( h, w, 0 ); | |
| } | |
| else | |
| for( int y = 0; y < i_lines; y += 8, pixoff = y*i_stride ) | |
| @@ -227,7 +222,7 @@ | |
| return cost; | |
| } | |
| -static NOINLINE unsigned int x264_weight_cost_chroma( x264_t *h, x264_frame_t *fenc, pixel *ref, x264_weight_t *w ) | |
| +static NOINLINE unsigned int weight_cost_chroma( x264_t *h, x264_frame_t *fenc, pixel *ref, x264_weight_t *w ) | |
| { | |
| unsigned int cost = 0; | |
| int i_stride = fenc->i_stride[1]; | |
| @@ -250,7 +245,7 @@ | |
| * pixels. */ | |
| cost += h->pixf.asd8( buf, 8, &src[pixoff], i_stride, height ); | |
| } | |
| - cost += x264_weight_slice_header_cost( h, w, 1 ); | |
| + cost += weight_slice_header_cost( h, w, 1 ); | |
| } | |
| else | |
| for( int y = 0; y < i_lines; y += height, pixoff = y*i_stride ) | |
| @@ -260,7 +255,7 @@ | |
| return cost; | |
| } | |
| -static NOINLINE unsigned int x264_weight_cost_chroma444( x264_t *h, x264_frame_t *fenc, pixel *ref, x264_weight_t *w, int p ) | |
| +static NOINLINE unsigned int weight_cost_chroma444( x264_t *h, x264_frame_t *fenc, pixel *ref, x264_weight_t *w, int p ) | |
| { | |
| unsigned int cost = 0; | |
| int i_stride = fenc->i_stride[p]; | |
| @@ -277,7 +272,7 @@ | |
| w->weightfn[16>>2]( buf, 16, &ref[pixoff], i_stride, w, 16 ); | |
| cost += h->pixf.mbcmp[PIXEL_16x16]( buf, 16, &src[pixoff], i_stride ); | |
| } | |
| - cost += x264_weight_slice_header_cost( h, w, 1 ); | |
| + cost += weight_slice_header_cost( h, w, 1 ); | |
| } | |
| else | |
| for( int y = 0; y < i_lines; y += 16, pixoff = y*i_stride ) | |
| @@ -302,11 +297,21 @@ | |
| float ref_mean[3]; | |
| for( int plane = 0; plane <= 2*!b_lookahead; plane++ ) | |
| { | |
| - float fenc_var = fenc->i_pixel_ssd[plane] + !ref->i_pixel_ssd[plane]; | |
| - float ref_var = ref->i_pixel_ssd[plane] + !ref->i_pixel_ssd[plane]; | |
| - guess_scale[plane] = sqrtf( fenc_var / ref_var ); | |
| - fenc_mean[plane] = (float)fenc->i_pixel_sum[plane] / (fenc->i_lines[!!plane] * fenc->i_width[!!plane]) / (1 << (BIT_DEPTH - 8)); | |
| - ref_mean[plane] = (float) ref->i_pixel_sum[plane] / (fenc->i_lines[!!plane] * fenc->i_width[!!plane]) / (1 << (BIT_DEPTH - 8)); | |
| + if( !plane || CHROMA_FORMAT ) | |
| + { | |
| + int zero_bias = !ref->i_pixel_ssd[plane]; | |
| + float fenc_var = fenc->i_pixel_ssd[plane] + zero_bias; | |
| + float ref_var = ref->i_pixel_ssd[plane] + zero_bias; | |
| + guess_scale[plane] = sqrtf( fenc_var / ref_var ); | |
| + fenc_mean[plane] = (float)(fenc->i_pixel_sum[plane] + zero_bias) / (fenc->i_lines[!!plane] * fenc->i_width[!!plane]) / (1 << (BIT_DEPTH - 8)); | |
| + ref_mean[plane] = (float)( ref->i_pixel_sum[plane] + zero_bias) / (fenc->i_lines[!!plane] * fenc->i_width[!!plane]) / (1 << (BIT_DEPTH - 8)); | |
| + } | |
| + else | |
| + { | |
| + guess_scale[plane] = 1; | |
| + fenc_mean[plane] = 0; | |
| + ref_mean[plane] = 0; | |
| + } | |
| } | |
| int chroma_denom = 7; | |
| @@ -323,7 +328,7 @@ | |
| } | |
| /* Don't check chroma in lookahead, or if there wasn't a luma weight. */ | |
| - for( int plane = 0; plane <= 2 && !( plane && ( !weights[0].weightfn || b_lookahead ) ); plane++ ) | |
| + for( int plane = 0; plane < (CHROMA_FORMAT ? 3 : 1) && !( plane && ( !weights[0].weightfn || b_lookahead ) ); plane++ ) | |
| { | |
| int minoff, minscale, mindenom; | |
| unsigned int minscore, origscore; | |
| @@ -347,7 +352,7 @@ | |
| } | |
| } | |
| else | |
| - x264_weight_get_h264( round( guess_scale[plane] * 128 ), 0, &weights[plane] ); | |
| + weight_get_h264( round( guess_scale[plane] * 128 ), 0, &weights[plane] ); | |
| found = 0; | |
| mindenom = weights[plane].i_denom; | |
| @@ -360,27 +365,27 @@ | |
| if( !fenc->b_intra_calculated ) | |
| { | |
| x264_mb_analysis_t a; | |
| - x264_lowres_context_init( h, &a ); | |
| - x264_slicetype_frame_cost( h, &a, &fenc, 0, 0, 0 ); | |
| + lowres_context_init( h, &a ); | |
| + slicetype_frame_cost( h, &a, &fenc, 0, 0, 0 ); | |
| } | |
| - mcbuf = x264_weight_cost_init_luma( h, fenc, ref, h->mb.p_weight_buf[0] ); | |
| - origscore = minscore = x264_weight_cost_luma( h, fenc, mcbuf, NULL ); | |
| + mcbuf = weight_cost_init_luma( h, fenc, ref, h->mb.p_weight_buf[0] ); | |
| + origscore = minscore = weight_cost_luma( h, fenc, mcbuf, NULL ); | |
| } | |
| else | |
| { | |
| if( CHROMA444 ) | |
| { | |
| - mcbuf = x264_weight_cost_init_chroma444( h, fenc, ref, h->mb.p_weight_buf[0], plane ); | |
| - origscore = minscore = x264_weight_cost_chroma444( h, fenc, mcbuf, NULL, plane ); | |
| + mcbuf = weight_cost_init_chroma444( h, fenc, ref, h->mb.p_weight_buf[0], plane ); | |
| + origscore = minscore = weight_cost_chroma444( h, fenc, mcbuf, NULL, plane ); | |
| } | |
| else | |
| { | |
| pixel *dstu = h->mb.p_weight_buf[0]; | |
| pixel *dstv = h->mb.p_weight_buf[0]+fenc->i_stride[1]*fenc->i_lines[1]; | |
| if( !chroma_initted++ ) | |
| - x264_weight_cost_init_chroma( h, fenc, ref, dstu, dstv ); | |
| + weight_cost_init_chroma( h, fenc, ref, dstu, dstv ); | |
| mcbuf = plane == 1 ? dstu : dstv; | |
| - origscore = minscore = x264_weight_cost_chroma( h, fenc, mcbuf, NULL ); | |
| + origscore = minscore = weight_cost_chroma( h, fenc, mcbuf, NULL ); | |
| } | |
| } | |
| @@ -409,8 +414,7 @@ | |
| * because scale has a much wider range than offset (because of denom), so | |
| * it should almost never need to be clamped. */ | |
| cur_offset = x264_clip3( cur_offset, -128, 127 ); | |
| - cur_scale = (1 << mindenom) * (fenc_mean[plane] - cur_offset) / ref_mean[plane] + 0.5f; | |
| - cur_scale = x264_clip3( cur_scale, 0, 127 ); | |
| + cur_scale = x264_clip3f( (1 << mindenom) * (fenc_mean[plane] - cur_offset) / ref_mean[plane] + 0.5f, 0, 127 ); | |
| } | |
| int start_offset = x264_clip3( cur_offset - offset_dist, -128, 127 ); | |
| int end_offset = x264_clip3( cur_offset + offset_dist, -128, 127 ); | |
| @@ -421,12 +425,12 @@ | |
| if( plane ) | |
| { | |
| if( CHROMA444 ) | |
| - s = x264_weight_cost_chroma444( h, fenc, mcbuf, &weights[plane], plane ); | |
| + s = weight_cost_chroma444( h, fenc, mcbuf, &weights[plane], plane ); | |
| else | |
| - s = x264_weight_cost_chroma( h, fenc, mcbuf, &weights[plane] ); | |
| + s = weight_cost_chroma( h, fenc, mcbuf, &weights[plane] ); | |
| } | |
| else | |
| - s = x264_weight_cost_luma( h, fenc, mcbuf, &weights[plane] ); | |
| + s = weight_cost_luma( h, fenc, mcbuf, &weights[plane] ); | |
| COPY4_IF_LT( minscore, s, minscale, cur_scale, minoff, i_off, found, 1 ); | |
| // Don't check any more offsets if the previous one had a lower cost than the current one | |
| @@ -487,7 +491,7 @@ | |
| if( weights[0].weightfn && b_lookahead ) | |
| { | |
| //scale lowres in lookahead for slicetype_frame_cost | |
| - pixel *src = ref->buffer_lowres[0]; | |
| + pixel *src = ref->buffer_lowres; | |
| pixel *dst = h->mb.p_weight_buf[0]; | |
| int width = ref->i_width_lowres + PADH*2; | |
| int height = ref->i_lines_lowres + PADV*2; | |
| @@ -508,10 +512,10 @@ | |
| #define NUM_ROWS 3 | |
| #define ROW_SATD (NUM_INTS + (h->mb.i_mb_y - h->i_threadslice_start)) | |
| -static void x264_slicetype_mb_cost( x264_t *h, x264_mb_analysis_t *a, | |
| - x264_frame_t **frames, int p0, int p1, int b, | |
| - int dist_scale_factor, int do_search[2], const x264_weight_t *w, | |
| - int *output_inter, int *output_intra ) | |
| +static void slicetype_mb_cost( x264_t *h, x264_mb_analysis_t *a, | |
| + x264_frame_t **frames, int p0, int p1, int b, | |
| + int dist_scale_factor, int do_search[2], const x264_weight_t *w, | |
| + int *output_inter, int *output_intra ) | |
| { | |
| x264_frame_t *fref0 = frames[p0]; | |
| x264_frame_t *fref1 = frames[p1]; | |
| @@ -524,8 +528,8 @@ | |
| const int i_stride = fenc->i_stride_lowres; | |
| const int i_pel_offset = 8 * (i_mb_x + i_mb_y * i_stride); | |
| const int i_bipred_weight = h->param.analyse.b_weighted_bipred ? 64 - (dist_scale_factor>>2) : 32; | |
| - int16_t (*fenc_mvs[2])[2] = { &fenc->lowres_mvs[0][b-p0-1][i_mb_xy], &fenc->lowres_mvs[1][p1-b-1][i_mb_xy] }; | |
| - int (*fenc_costs[2]) = { &fenc->lowres_mv_costs[0][b-p0-1][i_mb_xy], &fenc->lowres_mv_costs[1][p1-b-1][i_mb_xy] }; | |
| + int16_t (*fenc_mvs[2])[2] = { b != p0 ? &fenc->lowres_mvs[0][b-p0-1][i_mb_xy] : NULL, b != p1 ? &fenc->lowres_mvs[1][p1-b-1][i_mb_xy] : NULL }; | |
| + int (*fenc_costs[2]) = { b != p0 ? &fenc->lowres_mv_costs[0][b-p0-1][i_mb_xy] : NULL, b != p1 ? &fenc->lowres_mv_costs[1][p1-b-1][i_mb_xy] : NULL }; | |
| int b_frame_score_mb = (i_mb_x > 0 && i_mb_x < h->mb.i_mb_width - 1 && | |
| i_mb_y > 0 && i_mb_y < h->mb.i_mb_height - 1) || | |
| h->mb.i_mb_width <= 2 || h->mb.i_mb_height <= 2; | |
| @@ -654,7 +658,7 @@ | |
| { | |
| int i_mvc = 0; | |
| int16_t (*fenc_mv)[2] = fenc_mvs[l]; | |
| - ALIGNED_4( int16_t mvc[4][2] ); | |
| + ALIGNED_ARRAY_8( int16_t, mvc,[4],[2] ); | |
| /* Reverse-order MV prediction. */ | |
| M32( mvc[0] ) = 0; | |
| @@ -716,10 +720,10 @@ | |
| pixel *src = &fenc->lowres[0][i_pel_offset]; | |
| const int intra_penalty = 5 * a->i_lambda; | |
| int satds[3]; | |
| - int pixoff = 4 / sizeof(pixel); | |
| + int pixoff = 4 / SIZEOF_PIXEL; | |
| /* Avoid store forwarding stalls by writing larger chunks */ | |
| - memcpy( pix-FDEC_STRIDE, src-i_stride, 16 * sizeof(pixel) ); | |
| + memcpy( pix-FDEC_STRIDE, src-i_stride, 16 * SIZEOF_PIXEL ); | |
| for( int i = -1; i < 8; i++ ) | |
| M32( &pix[i*FDEC_STRIDE-pixoff] ) = M32( &src[i*i_stride-pixoff] ); | |
| @@ -808,7 +812,7 @@ | |
| int *output_intra; | |
| } x264_slicetype_slice_t; | |
| -static void x264_slicetype_slice_cost( x264_slicetype_slice_t *s ) | |
| +static void slicetype_slice_cost( x264_slicetype_slice_t *s ) | |
| { | |
| x264_t *h = s->h; | |
| @@ -826,12 +830,12 @@ | |
| for( h->mb.i_mb_y = start_y; h->mb.i_mb_y >= end_y; h->mb.i_mb_y-- ) | |
| for( h->mb.i_mb_x = start_x; h->mb.i_mb_x >= end_x; h->mb.i_mb_x-- ) | |
| - x264_slicetype_mb_cost( h, s->a, s->frames, s->p0, s->p1, s->b, s->dist_scale_factor, | |
| - s->do_search, s->w, s->output_inter, s->output_intra ); | |
| + slicetype_mb_cost( h, s->a, s->frames, s->p0, s->p1, s->b, s->dist_scale_factor, | |
| + s->do_search, s->w, s->output_inter, s->output_intra ); | |
| } | |
| -static int x264_slicetype_frame_cost( x264_t *h, x264_mb_analysis_t *a, | |
| - x264_frame_t **frames, int p0, int p1, int b ) | |
| +static int slicetype_frame_cost( x264_t *h, x264_mb_analysis_t *a, | |
| + x264_frame_t **frames, int p0, int p1, int b ) | |
| { | |
| int i_score = 0; | |
| int do_search[2]; | |
| @@ -923,7 +927,7 @@ | |
| output_inter[i+1] = output_inter[i] + thread_output_size + PAD_SIZE; | |
| output_intra[i+1] = output_intra[i] + thread_output_size + PAD_SIZE; | |
| - x264_threadpool_run( h->lookaheadpool, (void*)x264_slicetype_slice_cost, &s[i] ); | |
| + x264_threadpool_run( h->lookaheadpool, (void*)slicetype_slice_cost, &s[i] ); | |
| } | |
| for( int i = 0; i < h->param.i_lookahead_threads; i++ ) | |
| x264_threadpool_wait( h->lookaheadpool, &s[i] ); | |
| @@ -937,7 +941,7 @@ | |
| output_inter[0][NUM_ROWS] = output_intra[0][NUM_ROWS] = h->mb.i_mb_height; | |
| x264_slicetype_slice_t s = (x264_slicetype_slice_t){ h, a, frames, p0, p1, b, dist_scale_factor, do_search, w, | |
| output_inter[0], output_intra[0] }; | |
| - x264_slicetype_slice_cost( &s ); | |
| + slicetype_slice_cost( &s ); | |
| } | |
| /* Sum up accumulators */ | |
| @@ -993,7 +997,7 @@ | |
| /* If MB-tree changes the quantizers, we need to recalculate the frame cost without | |
| * re-running lookahead. */ | |
| -static int x264_slicetype_frame_cost_recalculate( x264_t *h, x264_frame_t **frames, int p0, int p1, int b ) | |
| +static int slicetype_frame_cost_recalculate( x264_t *h, x264_frame_t **frames, int p0, int p1, int b ) | |
| { | |
| int i_score = 0; | |
| int *row_satd = frames[b]->i_row_satds[b-p0][p1-b]; | |
| @@ -1023,7 +1027,7 @@ | |
| /* Trade off precision in mbtree for increased range */ | |
| #define MBTREE_PRECISION 0.5f | |
| -static void x264_macroblock_tree_finish( x264_t *h, x264_frame_t *frame, float average_duration, int ref0_distance ) | |
| +static void macroblock_tree_finish( x264_t *h, x264_frame_t *frame, float average_duration, int ref0_distance ) | |
| { | |
| int fps_factor = round( CLIP_DURATION(average_duration) / CLIP_DURATION(frame->f_duration) * 256 / MBTREE_PRECISION ); | |
| float weightdelta = 0.0; | |
| @@ -1045,12 +1049,12 @@ | |
| } | |
| } | |
| -static void x264_macroblock_tree_propagate( x264_t *h, x264_frame_t **frames, float average_duration, int p0, int p1, int b, int referenced ) | |
| +static void macroblock_tree_propagate( x264_t *h, x264_frame_t **frames, float average_duration, int p0, int p1, int b, int referenced ) | |
| { | |
| uint16_t *ref_costs[2] = {frames[p0]->i_propagate_cost,frames[p1]->i_propagate_cost}; | |
| int dist_scale_factor = ( ((b-p0) << 8) + ((p1-p0) >> 1) ) / (p1-p0); | |
| int i_bipred_weight = h->param.analyse.b_weighted_bipred ? 64 - (dist_scale_factor>>2) : 32; | |
| - int16_t (*mvs[2])[2] = { frames[b]->lowres_mvs[0][b-p0-1], frames[b]->lowres_mvs[1][p1-b-1] }; | |
| + int16_t (*mvs[2])[2] = { b != p0 ? frames[b]->lowres_mvs[0][b-p0-1] : NULL, b != p1 ? frames[b]->lowres_mvs[1][p1-b-1] : NULL }; | |
| int bipred_weights[2] = {i_bipred_weight, 64 - i_bipred_weight}; | |
| int16_t *buf = h->scratch_buffer; | |
| uint16_t *propagate_cost = frames[b]->i_propagate_cost; | |
| @@ -1082,10 +1086,10 @@ | |
| } | |
| if( h->param.rc.i_vbv_buffer_size && h->param.rc.i_lookahead && referenced ) | |
| - x264_macroblock_tree_finish( h, frames[b], average_duration, b == p1 ? b - p0 : 0 ); | |
| + macroblock_tree_finish( h, frames[b], average_duration, b == p1 ? b - p0 : 0 ); | |
| } | |
| -static void x264_macroblock_tree( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int num_frames, int b_intra ) | |
| +static void macroblock_tree( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int num_frames, int b_intra ) | |
| { | |
| int idx = !b_intra; | |
| int last_nonb, cur_nonb = 1; | |
| @@ -1100,7 +1104,7 @@ | |
| int i = num_frames; | |
| if( b_intra ) | |
| - x264_slicetype_frame_cost( h, a, frames, 0, 0, 0 ); | |
| + slicetype_frame_cost( h, a, frames, 0, 0, 0 ); | |
| while( i > 0 && IS_X264_TYPE_B( frames[i]->i_type ) ) | |
| i--; | |
| @@ -1134,13 +1138,13 @@ | |
| cur_nonb--; | |
| if( cur_nonb < idx ) | |
| break; | |
| - x264_slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, last_nonb ); | |
| + slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, last_nonb ); | |
| memset( frames[cur_nonb]->i_propagate_cost, 0, h->mb.i_mb_count * sizeof(uint16_t) ); | |
| bframes = last_nonb - cur_nonb - 1; | |
| if( h->param.i_bframe_pyramid && bframes > 1 ) | |
| { | |
| int middle = (bframes + 1)/2 + cur_nonb; | |
| - x264_slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, middle ); | |
| + slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, middle ); | |
| memset( frames[middle]->i_propagate_cost, 0, h->mb.i_mb_count * sizeof(uint16_t) ); | |
| while( i > cur_nonb ) | |
| { | |
| @@ -1148,52 +1152,52 @@ | |
| int p1 = i < middle ? middle : last_nonb; | |
| if( i != middle ) | |
| { | |
| - x264_slicetype_frame_cost( h, a, frames, p0, p1, i ); | |
| - x264_macroblock_tree_propagate( h, frames, average_duration, p0, p1, i, 0 ); | |
| + slicetype_frame_cost( h, a, frames, p0, p1, i ); | |
| + macroblock_tree_propagate( h, frames, average_duration, p0, p1, i, 0 ); | |
| } | |
| i--; | |
| } | |
| - x264_macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, middle, 1 ); | |
| + macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, middle, 1 ); | |
| } | |
| else | |
| { | |
| while( i > cur_nonb ) | |
| { | |
| - x264_slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, i ); | |
| - x264_macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, i, 0 ); | |
| + slicetype_frame_cost( h, a, frames, cur_nonb, last_nonb, i ); | |
| + macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, i, 0 ); | |
| i--; | |
| } | |
| } | |
| - x264_macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, last_nonb, 1 ); | |
| + macroblock_tree_propagate( h, frames, average_duration, cur_nonb, last_nonb, last_nonb, 1 ); | |
| last_nonb = cur_nonb; | |
| } | |
| if( !h->param.rc.i_lookahead ) | |
| { | |
| - x264_slicetype_frame_cost( h, a, frames, 0, last_nonb, last_nonb ); | |
| - x264_macroblock_tree_propagate( h, frames, average_duration, 0, last_nonb, last_nonb, 1 ); | |
| + slicetype_frame_cost( h, a, frames, 0, last_nonb, last_nonb ); | |
| + macroblock_tree_propagate( h, frames, average_duration, 0, last_nonb, last_nonb, 1 ); | |
| XCHG( uint16_t*, frames[last_nonb]->i_propagate_cost, frames[0]->i_propagate_cost ); | |
| } | |
| - x264_macroblock_tree_finish( h, frames[last_nonb], average_duration, last_nonb ); | |
| + macroblock_tree_finish( h, frames[last_nonb], average_duration, last_nonb ); | |
| if( h->param.i_bframe_pyramid && bframes > 1 && !h->param.rc.i_vbv_buffer_size ) | |
| - x264_macroblock_tree_finish( h, frames[last_nonb+(bframes+1)/2], average_duration, 0 ); | |
| + macroblock_tree_finish( h, frames[last_nonb+(bframes+1)/2], average_duration, 0 ); | |
| } | |
| -static int x264_vbv_frame_cost( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int p0, int p1, int b ) | |
| +static int vbv_frame_cost( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int p0, int p1, int b ) | |
| { | |
| - int cost = x264_slicetype_frame_cost( h, a, frames, p0, p1, b ); | |
| + int cost = slicetype_frame_cost( h, a, frames, p0, p1, b ); | |
| if( h->param.rc.i_aq_mode ) | |
| { | |
| if( h->param.rc.b_mb_tree ) | |
| - return x264_slicetype_frame_cost_recalculate( h, frames, p0, p1, b ); | |
| + return slicetype_frame_cost_recalculate( h, frames, p0, p1, b ); | |
| else | |
| return frames[b]->i_cost_est_aq[b-p0][p1-b]; | |
| } | |
| return cost; | |
| } | |
| -static void x264_calculate_durations( x264_t *h, x264_frame_t *cur_frame, x264_frame_t *prev_frame, int64_t *i_cpb_delay, int64_t *i_coded_fields ) | |
| +static void calculate_durations( x264_t *h, x264_frame_t *cur_frame, x264_frame_t *prev_frame, int64_t *i_cpb_delay, int64_t *i_coded_fields ) | |
| { | |
| cur_frame->i_cpb_delay = *i_cpb_delay; | |
| cur_frame->i_dpb_output_delay = cur_frame->i_field_cnt - *i_coded_fields; | |
| @@ -1219,7 +1223,7 @@ | |
| cur_frame->i_cpb_duration = cur_frame->i_duration; | |
| } | |
| -static void x264_vbv_lookahead( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int num_frames, int keyframe ) | |
| +static void vbv_lookahead( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int num_frames, int keyframe ) | |
| { | |
| int last_nonb = 0, cur_nonb = 1, idx = 0; | |
| x264_frame_t *prev_frame = NULL; | |
| @@ -1240,11 +1244,11 @@ | |
| if( next_nonb != cur_nonb ) | |
| { | |
| int p0 = IS_X264_TYPE_I( frames[cur_nonb]->i_type ) ? cur_nonb : last_nonb; | |
| - frames[next_nonb]->i_planned_satd[idx] = x264_vbv_frame_cost( h, a, frames, p0, cur_nonb, cur_nonb ); | |
| + frames[next_nonb]->i_planned_satd[idx] = vbv_frame_cost( h, a, frames, p0, cur_nonb, cur_nonb ); | |
| frames[next_nonb]->i_planned_type[idx] = frames[cur_nonb]->i_type; | |
| frames[cur_nonb]->i_coded_fields_lookahead = h->i_coded_fields_lookahead; | |
| frames[cur_nonb]->i_cpb_delay_lookahead = h->i_cpb_delay_lookahead; | |
| - x264_calculate_durations( h, frames[cur_nonb], prev_frame, &h->i_cpb_delay_lookahead, &h->i_coded_fields_lookahead ); | |
| + calculate_durations( h, frames[cur_nonb], prev_frame, &h->i_cpb_delay_lookahead, &h->i_coded_fields_lookahead ); | |
| if( prev_frame ) | |
| { | |
| frames[next_nonb]->f_planned_cpb_duration[prev_frame_idx] = (double)prev_frame->i_cpb_duration * | |
| @@ -1259,11 +1263,11 @@ | |
| /* Handle the B-frames: coded order */ | |
| for( int i = last_nonb+1; i < cur_nonb; i++, idx++ ) | |
| { | |
| - frames[next_nonb]->i_planned_satd[idx] = x264_vbv_frame_cost( h, a, frames, last_nonb, cur_nonb, i ); | |
| + frames[next_nonb]->i_planned_satd[idx] = vbv_frame_cost( h, a, frames, last_nonb, cur_nonb, i ); | |
| frames[next_nonb]->i_planned_type[idx] = X264_TYPE_B; | |
| frames[i]->i_coded_fields_lookahead = h->i_coded_fields_lookahead; | |
| frames[i]->i_cpb_delay_lookahead = h->i_cpb_delay_lookahead; | |
| - x264_calculate_durations( h, frames[i], prev_frame, &h->i_cpb_delay_lookahead, &h->i_coded_fields_lookahead ); | |
| + calculate_durations( h, frames[i], prev_frame, &h->i_cpb_delay_lookahead, &h->i_coded_fields_lookahead ); | |
| if( prev_frame ) | |
| { | |
| frames[next_nonb]->f_planned_cpb_duration[prev_frame_idx] = (double)prev_frame->i_cpb_duration * | |
| @@ -1282,10 +1286,10 @@ | |
| frames[next_nonb]->i_planned_type[idx] = X264_TYPE_AUTO; | |
| } | |
| -static int x264_slicetype_path_cost( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, char *path, int threshold ) | |
| +static uint64_t slicetype_path_cost( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, char *path, uint64_t threshold ) | |
| { | |
| + uint64_t cost = 0; | |
| int loc = 1; | |
| - int cost = 0; | |
| int cur_nonb = 0; | |
| path--; /* Since the 1st path element is really the second frame */ | |
| while( path[loc] ) | |
| @@ -1297,9 +1301,9 @@ | |
| /* Add the cost of the non-B-frame found above */ | |
| if( path[next_nonb] == 'P' ) | |
| - cost += x264_slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, next_nonb ); | |
| + cost += slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, next_nonb ); | |
| else /* I-frame */ | |
| - cost += x264_slicetype_frame_cost( h, a, frames, next_nonb, next_nonb, next_nonb ); | |
| + cost += slicetype_frame_cost( h, a, frames, next_nonb, next_nonb, next_nonb ); | |
| /* Early terminate if the cost we have found is larger than the best path cost so far */ | |
| if( cost > threshold ) | |
| break; | |
| @@ -1307,15 +1311,15 @@ | |
| if( h->param.i_bframe_pyramid && next_nonb - cur_nonb > 2 ) | |
| { | |
| int middle = cur_nonb + (next_nonb - cur_nonb)/2; | |
| - cost += x264_slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, middle ); | |
| + cost += slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, middle ); | |
| for( int next_b = loc; next_b < middle && cost < threshold; next_b++ ) | |
| - cost += x264_slicetype_frame_cost( h, a, frames, cur_nonb, middle, next_b ); | |
| + cost += slicetype_frame_cost( h, a, frames, cur_nonb, middle, next_b ); | |
| for( int next_b = middle+1; next_b < next_nonb && cost < threshold; next_b++ ) | |
| - cost += x264_slicetype_frame_cost( h, a, frames, middle, next_nonb, next_b ); | |
| + cost += slicetype_frame_cost( h, a, frames, middle, next_nonb, next_b ); | |
| } | |
| else | |
| for( int next_b = loc; next_b < next_nonb && cost < threshold; next_b++ ) | |
| - cost += x264_slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, next_b ); | |
| + cost += slicetype_frame_cost( h, a, frames, cur_nonb, next_nonb, next_b ); | |
| loc = next_nonb + 1; | |
| cur_nonb = next_nonb; | |
| @@ -1327,11 +1331,11 @@ | |
| /* Uses strings due to the fact that the speed of the control functions is | |
| negligible compared to the cost of running slicetype_frame_cost, and because | |
| it makes debugging easier. */ | |
| -static void x264_slicetype_path( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int length, char (*best_paths)[X264_LOOKAHEAD_MAX+1] ) | |
| +static void slicetype_path( x264_t *h, x264_mb_analysis_t *a, x264_frame_t **frames, int length, char (*best_paths)[X264_LOOKAHEAD_MAX+1] ) | |
| { | |
| char paths[2][X264_LOOKAHEAD_MAX+1]; | |
| int num_paths = X264_MIN( h->param.i_bframe+1, length ); | |
| - int best_cost = COST_MAX; | |
| + uint64_t best_cost = COST_MAX64; | |
| int best_possible = 0; | |
| int idx = 0; | |
| @@ -1362,9 +1366,9 @@ | |
| if( possible || !best_possible ) | |
| { | |
| if( possible && !best_possible ) | |
| - best_cost = COST_MAX; | |
| + best_cost = COST_MAX64; | |
| /* Calculate the actual cost of the current path */ | |
| - int cost = x264_slicetype_path_cost( h, a, frames, paths[idx], best_cost ); | |
| + uint64_t cost = slicetype_path_cost( h, a, frames, paths[idx], best_cost ); | |
| if( cost < best_cost ) | |
| { | |
| best_cost = cost; | |
| @@ -1386,7 +1390,7 @@ | |
| if( real_scenecut && h->param.i_frame_packing == 5 && (frame->i_frame&1) ) | |
| return 0; | |
| - x264_slicetype_frame_cost( h, a, frames, p0, p1, p1 ); | |
| + slicetype_frame_cost( h, a, frames, p0, p1, p1 ); | |
| int icost = frame->i_cost_est[0][0]; | |
| int pcost = frame->i_cost_est[p1-p0][0]; | |
| @@ -1473,7 +1477,7 @@ | |
| x264_frame_t *frames[X264_LOOKAHEAD_MAX+3] = { NULL, }; | |
| int num_frames, orig_num_frames, keyint_limit, framecnt; | |
| int i_max_search = X264_MIN( h->lookahead->next.i_size, X264_LOOKAHEAD_MAX ); | |
| - int vbv_lookahead = h->param.rc.i_vbv_buffer_size && h->param.rc.i_lookahead; | |
| + int b_vbv_lookahead = h->param.rc.i_vbv_buffer_size && h->param.rc.i_lookahead; | |
| /* For determinism we should limit the search to the number of frames lookahead has for sure | |
| * in h->lookahead->next.list buffer, except at the end of stream. | |
| * For normal calls with (intra_minigop == 0) that is h->lookahead->i_slicetype_length + 1 frames. | |
| @@ -1490,12 +1494,12 @@ | |
| for( framecnt = 0; framecnt < i_max_search; framecnt++ ) | |
| frames[framecnt+1] = h->lookahead->next.list[framecnt]; | |
| - x264_lowres_context_init( h, &a ); | |
| + lowres_context_init( h, &a ); | |
| if( !framecnt ) | |
| { | |
| if( h->param.rc.b_mb_tree ) | |
| - x264_macroblock_tree( h, &a, frames, 0, keyframe ); | |
| + macroblock_tree( h, &a, frames, 0, keyframe ); | |
| return; | |
| } | |
| @@ -1506,7 +1510,7 @@ | |
| * there will be significant visual artifacts if the frames just before | |
| * go down in quality due to being referenced less, despite it being | |
| * more RD-optimal. */ | |
| - if( (h->param.analyse.b_psy && h->param.rc.b_mb_tree) || vbv_lookahead ) | |
| + if( (h->param.analyse.b_psy && h->param.rc.b_mb_tree) || b_vbv_lookahead ) | |
| num_frames = framecnt; | |
| else if( h->param.b_open_gop && num_frames < framecnt ) | |
| num_frames++; | |
| @@ -1556,7 +1560,7 @@ | |
| /* Perform the frametype analysis. */ | |
| for( int j = 2; j <= num_frames; j++ ) | |
| - x264_slicetype_path( h, &a, frames, j, best_paths ); | |
| + slicetype_path( h, &a, frames, j, best_paths ); | |
| /* Load the results of the analysis into the frame types. */ | |
| for( int j = 1; j < num_frames; j++ ) | |
| @@ -1607,9 +1611,9 @@ | |
| int bframes = j - last_nonb - 1; | |
| memset( path, 'B', bframes ); | |
| strcpy( path+bframes, "PP" ); | |
| - int cost_p = x264_slicetype_path_cost( h, &a, frames+last_nonb, path, COST_MAX ); | |
| + uint64_t cost_p = slicetype_path_cost( h, &a, frames+last_nonb, path, COST_MAX64 ); | |
| strcpy( path+bframes, "BP" ); | |
| - int cost_b = x264_slicetype_path_cost( h, &a, frames+last_nonb, path, cost_p ); | |
| + uint64_t cost_b = slicetype_path_cost( h, &a, frames+last_nonb, path, cost_p ); | |
| if( cost_b < cost_p ) | |
| frames[j]->i_type = X264_TYPE_B; | |
| @@ -1672,7 +1676,7 @@ | |
| /* Perform the actual macroblock tree analysis. | |
| * Don't go farther than the maximum keyframe interval; this helps in short GOPs. */ | |
| if( h->param.rc.b_mb_tree ) | |
| - x264_macroblock_tree( h, &a, frames, X264_MIN(num_frames, h->param.i_keyint_max), keyframe ); | |
| + macroblock_tree( h, &a, frames, X264_MIN(num_frames, h->param.i_keyint_max), keyframe ); | |
| /* Enforce keyframe limit. */ | |
| if( !h->param.b_intra_refresh ) | |
| @@ -1727,8 +1731,8 @@ | |
| } | |
| } | |
| - if( vbv_lookahead ) | |
| - x264_vbv_lookahead( h, &a, frames, num_frames, keyframe ); | |
| + if( b_vbv_lookahead ) | |
| + vbv_lookahead( h, &a, frames, num_frames, keyframe ); | |
| /* Restore frametypes for all frames that haven't actually been decided yet. */ | |
| for( int j = reset_start; j <= num_frames; j++ ) | |
| @@ -1899,7 +1903,7 @@ | |
| int p0, p1, b; | |
| p1 = b = bframes + 1; | |
| - x264_lowres_context_init( h, &a ); | |
| + lowres_context_init( h, &a ); | |
| frames[0] = h->lookahead->last_nonb; | |
| memcpy( &frames[1], h->lookahead->next.list, (bframes+1) * sizeof(x264_frame_t*) ); | |
| @@ -1908,12 +1912,12 @@ | |
| else // P | |
| p0 = 0; | |
| - x264_slicetype_frame_cost( h, &a, frames, p0, p1, b ); | |
| + slicetype_frame_cost( h, &a, frames, p0, p1, b ); | |
| if( (p0 != p1 || bframes) && h->param.rc.i_vbv_buffer_size ) | |
| { | |
| /* We need the intra costs for row SATDs. */ | |
| - x264_slicetype_frame_cost( h, &a, frames, b, b, b ); | |
| + slicetype_frame_cost( h, &a, frames, b, b, b ); | |
| /* We need B-frame costs for row SATDs. */ | |
| p0 = 0; | |
| @@ -1924,7 +1928,7 @@ | |
| p1++; | |
| else | |
| p1 = bframes + 1; | |
| - x264_slicetype_frame_cost( h, &a, frames, p0, p1, b ); | |
| + slicetype_frame_cost( h, &a, frames, p0, p1, b ); | |
| if( frames[b]->i_type == X264_TYPE_BREF ) | |
| p0 = b; | |
| } | |
| @@ -1961,12 +1965,12 @@ | |
| h->lookahead->next.list[i]->i_coded = i_coded++; | |
| if( i ) | |
| { | |
| - x264_calculate_durations( h, h->lookahead->next.list[i], h->lookahead->next.list[i-1], &h->i_cpb_delay, &h->i_coded_fields ); | |
| + calculate_durations( h, h->lookahead->next.list[i], h->lookahead->next.list[i-1], &h->i_cpb_delay, &h->i_coded_fields ); | |
| h->lookahead->next.list[0]->f_planned_cpb_duration[i-1] = (double)h->lookahead->next.list[i]->i_cpb_duration * | |
| h->sps->vui.i_num_units_in_tick / h->sps->vui.i_time_scale; | |
| } | |
| else | |
| - x264_calculate_durations( h, h->lookahead->next.list[i], NULL, &h->i_cpb_delay, &h->i_coded_fields ); | |
| + calculate_durations( h, h->lookahead->next.list[i], NULL, &h->i_cpb_delay, &h->i_coded_fields ); | |
| } | |
| } | |
| @@ -1994,9 +1998,9 @@ | |
| if( h->param.rc.b_mb_tree && !h->param.rc.b_stat_read ) | |
| { | |
| - cost = x264_slicetype_frame_cost_recalculate( h, frames, p0, p1, b ); | |
| + cost = slicetype_frame_cost_recalculate( h, frames, p0, p1, b ); | |
| if( b && h->param.rc.i_vbv_buffer_size ) | |
| - x264_slicetype_frame_cost_recalculate( h, frames, b, b, b ); | |
| + slicetype_frame_cost_recalculate( h, frames, b, b, b ); | |
| } | |
| /* In AQ, use the weighted score instead. */ | |
| else if( h->param.rc.i_aq_mode ) | |
| diff -ur x264-go/x264c/external/x264/encoder/slicetype-cl.c x264-go.new/x264c/external/x264/encoder/slicetype-cl.c | |
| --- x264-go/x264c/external/x264/encoder/slicetype-cl.c 2018-02-14 22:45:04.000000000 +0100 | |
| +++ x264-go.new/x264c/external/x264/encoder/slicetype-cl.c 2020-06-06 15:20:58.699039438 +0200 | |
| @@ -1,7 +1,7 @@ | |
| /***************************************************************************** | |
| * slicetype-cl.c: OpenCL slicetype decision code (lowres lookahead) | |
| ***************************************************************************** | |
| - * Copyright (C) 2012-2017 x264 project | |
| + * Copyright (C) 2012-2020 x264 project | |
| * | |
| * Authors: Steve Borho <sborho@multicorewareinc.com> | |
| * | |
| @@ -26,12 +26,14 @@ | |
| #include "common/common.h" | |
| #include "macroblock.h" | |
| #include "me.h" | |
| +#include "slicetype-cl.h" | |
| #if HAVE_OPENCL | |
| #ifdef _WIN32 | |
| #include <windows.h> | |
| #endif | |
| +#define x264_weights_analyse x264_template(weights_analyse) | |
| void x264_weights_analyse( x264_t *h, x264_frame_t *fenc, x264_frame_t *ref, int b_lookahead ); | |
| /* We define CL_QUEUE_THREAD_HANDLE_AMD here because it is not defined | |
| @@ -67,7 +69,7 @@ | |
| h->opencl.pl_occupancy = 0; | |
| } | |
| -static void *x264_opencl_alloc_locked( x264_t *h, int bytes ) | |
| +static void *opencl_alloc_locked( x264_t *h, int bytes ) | |
| { | |
| if( h->opencl.pl_occupancy + bytes >= |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment