n@n:~/desktop$ nvcc stack_overflow.cu
n@n:~/desktop$ cuobjdump -sass a.out
Fatbin elf code:
================
arch = sm_20
code version = [1,7]
producer = <unknown>
host = linux
compile_size = 64bit
code for sm_20
Fatbin elf code:
================
arch = sm_20
code version = [1,7]
producer = cuda
host = linux
compile_size = 64bit
code for sm_20
Function : _Z11test_kernelPmPjii
.headerflags @"EF_CUDA_SM20 EF_CUDA_PTX_SM(EF_CUDA_SM20)"
/*0000*/ MOV R1, c[0x1][0x100]; /* 0x2800440400005de4 */
/*0008*/ ISUB R1, R1, 0x8; /* 0x4800c00020105d03 */
/*0010*/ S2R R0, SR_CTAID.X; /* 0x2c00000094001c04 */
/*0018*/ S2R R2, SR_TID.X; /* 0x2c00000084009c04 */
/*0020*/ LOP.OR R6, R1, c[0x0][0x4]; /* 0x6800400010119c43 */
/*0028*/ MOV R4, c[0xe][0x10]; /* 0x2800780040011de4 */
/*0030*/ IMAD R31, R0, c[0x0][0x8], R2; /* 0x200440002007dca3 */
n@n:~/desktop$ cuobjdump -sass a.out
Fatbin elf code:
================
arch = sm_20
code version = [1,7]
producer = <unknown>
host = linux
compile_size = 64bit
code for sm_20
Fatbin elf code:
================
arch = sm_20
code version = [1,7]
producer = cuda
host = linux
compile_size = 64bit
code for sm_20
Function : _Z11test_kernelPmPjii
.headerflags @"EF_CUDA_SM20 EF_CUDA_PTX_SM(EF_CUDA_SM20)"
/*0000*/ MOV R1, c[0x1][0x100]; /* 0x2800440400005de4 */
/*0008*/ ISUB R1, R1, 0x8; /* 0x4800c00020105d03 */
/*0010*/ S2R R0, SR_CTAID.X; /* 0x2c00000094001c04 */
/*0018*/ S2R R2, SR_TID.X; /* 0x2c00000084009c04 */
/*0020*/ LOP.OR R6, R1, c[0x0][0x4]; /* 0x6800400010119c43 */
/*0028*/ MOV R4, c[0xe][0x10]; /* 0x2800780040011de4 */
/*0030*/ IMAD R31, R0, c[0x0][0x8], R2; /* 0x200440002007dca3 */