diff options
| author | Alexander Timofeev <Alexander.Timofeev@amd.com> | 2017-07-03 14:54:11 +0000 |
|---|---|---|
| committer | Alexander Timofeev <Alexander.Timofeev@amd.com> | 2017-07-03 14:54:11 +0000 |
| commit | ea7f08bee53c696f75adfc099b6c8e7b58b1ebe3 (patch) | |
| tree | e6d6b05455101b83b74a58899c469db57b308ddf /llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll | |
| parent | 53d69e329b3b195b22afb565645031145966a2d8 (diff) | |
| download | bcm5719-llvm-ea7f08bee53c696f75adfc099b6c8e7b58b1ebe3.tar.gz bcm5719-llvm-ea7f08bee53c696f75adfc099b6c8e7b58b1ebe3.zip | |
[AMDGPU] Switch scalarize global loads ON by default
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307026
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll | 9 |
1 files changed, 7 insertions, 2 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll b/llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll index 6eb1fc1d0cc..4e52a5f80d8 100644 --- a/llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll +++ b/llvm/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll @@ -2,6 +2,8 @@ ; RUN: llc -march=amdgcn -enable-no-signed-zeros-fp-math=1 < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-UNSAFE %s ; RUN: llc -march=amdgcn -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-UNSAFE %s +declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone + ; Test that the -enable-no-signed-zeros-fp-math flag works ; GCN-LABEL: {{^}}fneg_fsub_f32: @@ -10,8 +12,11 @@ ; GCN-UNSAFE-NOT: xor define amdgpu_kernel void @fneg_fsub_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 { - %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1 - %a = load float, float addrspace(1)* %in, align 4 + %tid = call i32 @llvm.amdgcn.workitem.id.x() + %add = add i32 %tid, 1 + %gep = getelementptr float, float addrspace(1)* %in, i32 %tid + %b_ptr = getelementptr float, float addrspace(1)* %in, i32 %add + %a = load float, float addrspace(1)* %gep, align 4 %b = load float, float addrspace(1)* %b_ptr, align 4 %result = fsub float %a, %b %neg.result = fsub float -0.0, %result |
