diff options
| author | Tom Stellard <thomas.stellard@amd.com> | 2013-10-23 02:53:47 +0000 |
|---|---|---|
| committer | Tom Stellard <thomas.stellard@amd.com> | 2013-10-23 02:53:47 +0000 |
| commit | 96b5670cf454a586bee6d364fa91398c2e085852 (patch) | |
| tree | 9fe34e5905e94884ab47d23ba7fba5fe386d2fc2 /test/CodeGen/R600 | |
| parent | f95b1621887e3409ceec2db47e1b44271d934735 (diff) | |
| download | external_llvm-96b5670cf454a586bee6d364fa91398c2e085852.zip external_llvm-96b5670cf454a586bee6d364fa91398c2e085852.tar.gz external_llvm-96b5670cf454a586bee6d364fa91398c2e085852.tar.bz2 | |
R600/SI: fix MIMG writemask adjustement
This fixes piglit:
- shaders/glsl-fs-texture2d-masked
- shaders/glsl-fs-texture2d-masked-4
Patch by: Marek Olšák
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193222 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/R600')
| -rw-r--r-- | test/CodeGen/R600/llvm.SI.sample-masked.ll | 93 |
1 files changed, 93 insertions, 0 deletions
diff --git a/test/CodeGen/R600/llvm.SI.sample-masked.ll b/test/CodeGen/R600/llvm.SI.sample-masked.ll new file mode 100644 index 0000000..454e48b --- /dev/null +++ b/test/CodeGen/R600/llvm.SI.sample-masked.ll @@ -0,0 +1,93 @@ +;RUN: llc < %s -march=r600 -mcpu=verde | FileCheck %s + +; CHECK-LABEL: @v1 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}_VGPR{{[0-9]}}, 13 +define void @v1(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 0 + %3 = extractelement <4 x float> %1, i32 2 + %4 = extractelement <4 x float> %1, i32 3 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %4, float %4) + ret void +} + +; CHECK-LABEL: @v2 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}_VGPR{{[0-9]}}, 11 +define void @v2(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 0 + %3 = extractelement <4 x float> %1, i32 1 + %4 = extractelement <4 x float> %1, i32 3 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %4, float %4) + ret void +} + +; CHECK-LABEL: @v3 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}_VGPR{{[0-9]}}, 14 +define void @v3(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 1 + %3 = extractelement <4 x float> %1, i32 2 + %4 = extractelement <4 x float> %1, i32 3 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %4, float %4) + ret void +} + +; CHECK-LABEL: @v4 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}_VGPR{{[0-9]}}, 7 +define void @v4(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 0 + %3 = extractelement <4 x float> %1, i32 1 + %4 = extractelement <4 x float> %1, i32 2 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %4, float %4) + ret void +} + +; CHECK-LABEL: @v5 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}, 10 +define void @v5(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 1 + %3 = extractelement <4 x float> %1, i32 3 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %3, float %3) + ret void +} + +; CHECK-LABEL: @v6 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}, 6 +define void @v6(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 1 + %3 = extractelement <4 x float> %1, i32 2 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %3, float %3) + ret void +} + +; CHECK-LABEL: @v7 +; CHECK: IMAGE_SAMPLE VGPR{{[[0-9]}}_VGPR{{[0-9]}}, 9 +define void @v7(i32 %a1) { +entry: + %0 = insertelement <1 x i32> undef, i32 %a1, i32 0 + %1 = call <4 x float> @llvm.SI.sample.v1i32(<1 x i32> %0, <32 x i8> undef, <16 x i8> undef, i32 0) + %2 = extractelement <4 x float> %1, i32 0 + %3 = extractelement <4 x float> %1, i32 3 + call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %2, float %3, float %3, float %3) + ret void +} + +declare <4 x float> @llvm.SI.sample.v1i32(<1 x i32>, <32 x i8>, <16 x i8>, i32) readnone + +declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float) |