8cae08c2d7
Change-Id: Id88abb3698a224177fd0531e3e16013dde6dd95e
[ROCm/hip commit: 7ae453f349]
39 rivejä
712 B
Plaintext
39 rivejä
712 B
Plaintext
//
|
|
// Generated by NVIDIA NVVM Compiler
|
|
//
|
|
// Compiler Build ID: CL-19856038
|
|
// Cuda compilation tools, release 7.5, V7.5.17
|
|
// Based on LLVM 3.4svn
|
|
//
|
|
|
|
.version 4.3
|
|
.target sm_20
|
|
.address_size 64
|
|
|
|
// .globl hello_world
|
|
|
|
.visible .entry hello_world(
|
|
.param .u64 hello_world_param_0,
|
|
.param .u64 hello_world_param_1
|
|
)
|
|
{
|
|
.reg .f32 %f<2>;
|
|
.reg .b32 %r<2>;
|
|
.reg .b64 %rd<8>;
|
|
|
|
|
|
ld.param.u64 %rd1, [hello_world_param_0];
|
|
ld.param.u64 %rd2, [hello_world_param_1];
|
|
cvta.to.global.u64 %rd3, %rd2;
|
|
cvta.to.global.u64 %rd4, %rd1;
|
|
mov.u32 %r1, %tid.x;
|
|
mul.wide.s32 %rd5, %r1, 4;
|
|
add.s64 %rd6, %rd4, %rd5;
|
|
ld.global.f32 %f1, [%rd6];
|
|
add.s64 %rd7, %rd3, %rd5;
|
|
st.global.f32 [%rd7], %f1;
|
|
ret;
|
|
}
|
|
|
|
|