Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- //
- // Generated by NVIDIA NVVM Compiler
- // Compiler built on Wed Sep 26 00:26:26 2012 (1348590386)
- // Cuda compilation tools, release 5.0, V0.2.1221
- //
- .version 3.1
- .target sm_20, debug
- .address_size 64
- .file 1 "C:\\Users\\Mansoor\\Documents\\Visual Studio 2010\\Projects\\Testing_PTX\\x64/Debug/TestingPTX.compute_20.cpp3.i"
- .file 2 "C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v5.0/nvvm/ci_include.h"
- .file 3 "C:/Users/Mansoor/Documents/Visual Studio 2010/Projects/Testing_PTX/TestingPTX.cu"
- .visible .entry _Z5helloPfS_(
- .param .u64 _Z5helloPfS__param_0,
- .param .u64 _Z5helloPfS__param_1
- )
- {
- .reg .s32 %r<4>;
- .reg .f32 %f<2>;
- .reg .s64 %rd<9>;
- .loc 3 13 1
- func_begin0:
- .loc 3 13 0
- .loc 3 13 1
- ld.param.u64 %rd1, [_Z5helloPfS__param_0];
- ld.param.u64 %rd2, [_Z5helloPfS__param_1];
- func_exec_begin0:
- .loc 3 15 1
- tmp0:
- mov.u32 %r1, %ctaid.x;
- tmp1:
- .loc 3 16 1
- cvt.s64.s32 %rd3, %r1;
- shl.b64 %rd4, %rd3, 2;
- add.s64 %rd5, %rd2, %rd4;
- ld.f32 %f1, [%rd5];
- cvt.s64.s32 %rd6, %r1;
- shl.b64 %rd7, %rd6, 2;
- add.s64 %rd8, %rd1, %rd7;
- st.f32 [%rd8], %f1;
- tmp2:
- .loc 3 20 2
- ret;
- tmp3:
- func_end0:
- }
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement