Skip to content

Instantly share code, notes, and snippets.

/-
Created Jan 12, 2017

Embed
What would you like to do?
Fatbin elf code:
================
arch = sm_35
code version = [1,7]
producer = cuda
host = linux
compile_size = 64bit
code for sm_35
Function : _Z3foofPf
.headerflags @"EF_CUDA_SM35 EF_CUDA_PTX_SM(EF_CUDA_SM35)"
/* 0x0800b0a010a01000 */
/*0008*/ MOV R1, c[0x0][0x44]; /* 0x64c03c00089c0006 */
/*0010*/ MOV32I R0, 0xf3000000; /* 0x74798000001fc002 */
/*0018*/ MOV R2, c[0x0][0x148]; /* 0x64c03c00291c000a */
/*0020*/ IADD R0, R0, c[0x0][0x140]; /* 0x60800000281c0002 */
/*0028*/ MOV R3, c[0x0][0x14c]; /* 0x64c03c00299c000e */
/*0030*/ ISETP.LE.U32.AND P0, PT, R0, c[0x2][0x0], PT; /* 0x5b301c40001c001e */
/*0038*/ @P0 BRA 0x60; /* 0x120000001000003c */
/* 0x08a010a0a0b8b800 */
/*0048*/ MOV R4, c[0x0][0x140]; /* 0x64c03c00281c0012 */
/*0050*/ CAL 0xb0; /* 0x130000002c000100 */
/*0058*/ BRA 0xa0; /* 0x12000000201c003c */
/*0060*/ MOV R0, c[0x0][0x140]; /* 0x64c03c00281c0002 */
/*0068*/ MUFU.RSQ R0, R0; /* 0x84000000029c0002 */
/*0070*/ FMUL.FTZ R4, R0, c[0x0][0x140]; /* 0x63408000281c0012 */
/*0078*/ FMUL.FTZ R7, R0, 0.5; /* 0xc34081f8001c001d */
/* 0x08b0a0b81000a0a0 */
/*0088*/ F2F.FTZ.F32.F32 R5, -R4; /* 0xe5418000021c2816 */
/*0090*/ FFMA R0, R5, R4, c[0x0][0x140]; /* 0x8c001000281c1402 */
/*0098*/ FFMA R4, R0, R7, R4; /* 0xcc001000039c0012 */
/*00a0*/ ST.E [R2], R4; /* 0xe4800000001c0810 */
/*00a8*/ EXIT; /* 0x18000000001c003c */
/*00b0*/ LOP32I.AND R0, R4, 0x7fffffff; /* 0x203fffffff9c1000 */
/*00b8*/ ISETP.NE.AND P0, PT, R0, RZ, PT; /* 0xdb581c007f9c001e */
/* 0x0800b0b81000b000 */
/*00c8*/ @!P0 BRA 0x170; /* 0x120000005020003c */
/*00d0*/ FSETP.LT.FTZ.AND P0, PT, R4, RZ, PT; /* 0xdd8c1c007f9c101e */
/*00d8*/ @!P0 BRA 0xf0; /* 0x120000000820003c */
/*00e0*/ MOV32I R4, 0x7fffffff; /* 0x743fffffff9fc012 */
/*00e8*/ BRA 0x170; /* 0x12000000401c003c */
/*00f0*/ FSETP.LE.FTZ.AND P0, PT, |R4|, +INF , PT; /* 0xb59c1ffc001c121d */
/*00f8*/ @P0 BRA 0x118; /* 0x120000000c00003c */
/* 0x08a0a0a000b0b810 */
/*0108*/ FADD.FTZ R4, R4, 1; /* 0xc2c081fc001c1011 */
/*0110*/ BRA 0x170; /* 0x120000002c1c003c */
/*0118*/ FSETP.EQ.FTZ.AND P0, PT, |R4|, +INF , PT; /* 0xb5941ffc001c121d */
/*0120*/ @P0 BRA.U 0x170; /* 0x120000002400023c */
/*0128*/ @!P0 FFMA R0, R4, 1.84467440737095516160e+19, RZ; /* 0x9403fefc00201001 */
/*0130*/ @!P0 MUFU.RSQ R4, R0; /* 0x8400000002a00012 */
/*0138*/ @!P0 FMUL.FTZ R5, R4, R0; /* 0xe340800000201016 */
/* 0x0800b800a0a0a010 */
/*0148*/ @!P0 FMUL.FTZ R4, R4, 0.5; /* 0xc34081f800201011 */
/*0150*/ @!P0 F2F.FTZ.F32.F32 R6, -R5; /* 0xe541800002a0281a */
/*0158*/ @!P0 FFMA R0, R6, R5, R0; /* 0xcc00000002a01802 */
/*0160*/ @!P0 FFMA R0, R0, R4, R5; /* 0xcc00140002200002 */
/*0168*/ @!P0 FMUL.FTZ R4, R0, 2.3283064365386962891e-10; /* 0xc340817c00200011 */
/*0170*/ RET; /* 0x19000000001c003c */
/*0178*/ BRA 0x178; /* 0x12007ffffc1c003c */
..........................
Fatbin ptx code:
================
arch = sm_35
code version = [5,0]
producer = cuda
host = linux
compile_size = 64bit
compressed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.