|
- //
- // Generated by NVIDIA NVVM Compiler
- //
- // Compiler Build ID: CL-26907403
- // Cuda compilation tools, release 10.1, V10.1.243
- // Based on LLVM 3.4svn
- //
-
- .version 6.4
- .target sm_60
- .address_size 64
-
- // .globl Fused_Add_Add_split_10353490691581225422_kernel0
-
- .visible .entry Fused_Add_Add_split_10353490691581225422_kernel0(
- .param .u64 Fused_Add_Add_split_10353490691581225422_kernel0_param_0,
- .param .u64 Fused_Add_Add_split_10353490691581225422_kernel0_param_1,
- .param .u64 Fused_Add_Add_split_10353490691581225422_kernel0_param_2,
- .param .u64 Fused_Add_Add_split_10353490691581225422_kernel0_param_3
- )
- {
- .reg .f32 %f<6>;
- .reg .b32 %r<5>;
- .reg .b64 %rd<14>;
-
-
- ld.param.u64 %rd1, [Fused_Add_Add_split_10353490691581225422_kernel0_param_0];
- ld.param.u64 %rd2, [Fused_Add_Add_split_10353490691581225422_kernel0_param_1];
- ld.param.u64 %rd3, [Fused_Add_Add_split_10353490691581225422_kernel0_param_2];
- ld.param.u64 %rd4, [Fused_Add_Add_split_10353490691581225422_kernel0_param_3];
- cvta.to.global.u64 %rd5, %rd4;
- cvta.to.global.u64 %rd6, %rd3;
- cvta.to.global.u64 %rd7, %rd2;
- cvta.to.global.u64 %rd8, %rd1;
- mov.u32 %r1, %ctaid.x;
- shl.b32 %r2, %r1, 5;
- mov.u32 %r3, %tid.x;
- add.s32 %r4, %r2, %r3;
- mul.wide.s32 %rd9, %r4, 4;
- add.s64 %rd10, %rd8, %rd9;
- ld.global.nc.f32 %f1, [%rd10];
- add.s64 %rd11, %rd7, %rd9;
- ld.global.nc.f32 %f2, [%rd11];
- add.f32 %f3, %f1, %f2;
- add.s64 %rd12, %rd6, %rd9;
- ld.global.nc.f32 %f4, [%rd12];
- add.f32 %f5, %f3, %f4;
- add.s64 %rd13, %rd5, %rd9;
- st.global.f32 [%rd13], %f5;
- ret;
- }
-
|