huffyuvencdsp.asm

;******************************************************************************
;* SIMD-optimized HuffYUV encoding functions
;* Copyright (c) 2000, 2001 Fabrice Bellard
;* Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
;* MMX optimization by Nick Kurshev <nickols_k@mail.ru>
;* Ported to NASM syntax by Tiancheng "Timothy" Gu <timothygu99@gmail.com>
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* FFmpeg is distributed in the hope that it will be useful,
;* but WITHOUT ANY WARRANTY; without even the implied warranty of
;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;*

%include "libavutil/x86/x86util.asm"

SECTION .text

; void ff_sub_hfyu_median_pred_mmxext(uint8_t *dst, const uint8_t *src1,
;                                     const uint8_t *src2, int w,
;                                     int *left, int *left_top)
; TODO: sse2?
INIT_MMX mmxext
cglobal sub_hfyu_median_pred, 6,7,0, dst, src1, src2, w, left, left_top, i
; FIXME: move w to ptrdiff_t
    movsxdifnidn w, wd
    movu        m0, [src1]          ; LT
    LSHIFT      m0, 8
.loop:
    movu        m1, [src1 + i]      ; T
    movu        m2, [src2 + i - 1]  ; L
    movu        m3, [src2 + i]      ; X
    mova        m4, m2              ; L
    psubb       m2, m0              ; LT - L
    paddb       m2, m1              ; L + T - LT
    mova        m5, m4              ; L
    pmaxub      m4, m1              ; max(T, L)
    pminub      m1, m5              ; min(T, L)
    pminub      m4, m2              ; min(max(T, L), L + T - LT)
    pmaxub      m4, m1              ; pred = max(min(max(T, L), L + T - LT), min(T, L))
    psubb       m3, m4              ; dst - pred
    movu [dst + i], m3
    add          i, 8
    movu        m0, [src1 + i - 1]
    cmp          i, w
        jb      .loop
    movu