maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.r600.group.barrier.ll

32 lines
1023 B
LLVM
Raw Normal View History

AMDGPU/R600: Replace barrier intrinsics llvm-svn: 275870
2016-07-19 02:34:59 +08:00
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG %s
; EG-LABEL: {{^}}test_group_barrier:
; EG: GROUP_BARRIER
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_group_barrier(i32 addrspace(1)* %out) #0 {
AMDGPU/R600: Replace barrier intrinsics llvm-svn: 275870
2016-07-19 02:34:59 +08:00
entry:
%tmp = call i32 @llvm.r600.read.tidig.x()
%tmp1 = getelementptr i32, i32 addrspace(1)* %out, i32 %tmp
store i32 %tmp, i32 addrspace(1)* %tmp1
call void @llvm.r600.group.barrier()
%tmp2 = call i32 @llvm.r600.read.local.size.x()
%tmp3 = sub i32 %tmp2, 1
%tmp4 = sub i32 %tmp3, %tmp
%tmp5 = getelementptr i32, i32 addrspace(1)* %out, i32 %tmp4
%tmp6 = load i32, i32 addrspace(1)* %tmp5
store i32 %tmp6, i32 addrspace(1)* %tmp1
ret void
}
; Function Attrs: convergent nounwind
declare void @llvm.r600.group.barrier() #1
; Function Attrs: nounwind readnone
declare i32 @llvm.r600.read.tidig.x() #2
; Function Attrs: nounwind readnone
declare i32 @llvm.r600.read.local.size.x() #2
attributes #0 = { nounwind }
attributes #1 = { convergent nounwind }
attributes #2 = { nounwind readnone }