diff options
| author | Justin Bogner <mail@justinbogner.com> | 2025-04-08 08:54:10 +0900 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-04-08 08:54:10 +0900 |
| commit | 0afa872a0db41cba313df473aa3fea52a35c8e70 (patch) | |
| tree | 19465730ad885b939c5ef8410b2b390881c4a649 | |
| parent | 65813e0e94c0403dad61e8365b39d76d7b3bfc14 (diff) | |
| download | llvm-0afa872a0db41cba313df473aa3fea52a35c8e70.zip llvm-0afa872a0db41cba313df473aa3fea52a35c8e70.tar.gz llvm-0afa872a0db41cba313df473aa3fea52a35c8e70.tar.bz2 | |
[DirectX] Scalarize the dx.saturate intrinsic (#134381)
The DXIL Saturate op only takes scalars.
Fixes #134378.
| -rw-r--r-- | llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp | 1 | ||||
| -rw-r--r-- | llvm/test/CodeGen/DirectX/saturate.ll | 36 |
2 files changed, 32 insertions, 5 deletions
diff --git a/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp b/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp index 765e197..4cf3282b 100644 --- a/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp +++ b/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp @@ -44,6 +44,7 @@ bool DirectXTTIImpl::isTargetIntrinsicTriviallyScalarizable( case Intrinsic::dx_firstbituhigh: case Intrinsic::dx_frac: case Intrinsic::dx_rsqrt: + case Intrinsic::dx_saturate: case Intrinsic::dx_splitdouble: case Intrinsic::dx_wave_readlane: case Intrinsic::dx_wave_reduce_max: diff --git a/llvm/test/CodeGen/DirectX/saturate.ll b/llvm/test/CodeGen/DirectX/saturate.ll index 0bb1e55..1e4a235 100644 --- a/llvm/test/CodeGen/DirectX/saturate.ll +++ b/llvm/test/CodeGen/DirectX/saturate.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s +; RUN: opt -S -scalarizer -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-library %s | FileCheck %s ; Make sure the intrinsic dx.saturate is to appropriate DXIL op for half/float/double data types. ; CHECK-LABEL: test_saturate_half @@ -28,9 +28,35 @@ entry: ret double %hlsl.saturate } -; CHECK: attributes #[[#ATTR]] = {{{.*}} memory(none) {{.*}}} +; CHECK-LABEL: test_saturate_half4 +define noundef <4 x half> @test_saturate_half4(<4 x half> noundef %p0) { +entry: + ; CHECK: call half @dx.op.unary.f16(i32 7, half + ; CHECK: call half @dx.op.unary.f16(i32 7, half + ; CHECK: call half @dx.op.unary.f16(i32 7, half + ; CHECK: call half @dx.op.unary.f16(i32 7, half + %hlsl.saturate = call <4 x half> @llvm.dx.saturate.v4f16(<4 x half> %p0) + ret <4 x half> %hlsl.saturate +} + +; CHECK-LABEL: test_saturate_float3 +define noundef <3 x float> @test_saturate_float3(<3 x float> noundef %p0) { +entry: + ; CHECK: call float @dx.op.unary.f32(i32 7, float + ; CHECK: call float @dx.op.unary.f32(i32 7, float + ; CHECK: call float @dx.op.unary.f32(i32 7, float + %hlsl.saturate = call <3 x float> @llvm.dx.saturate.v3f32(<3 x float> %p0) + ret <3 x float> %hlsl.saturate +} -declare half @llvm.dx.saturate.f16(half) -declare float @llvm.dx.saturate.f32(float) -declare double @llvm.dx.saturate.f64(double) +; CHECK-LABEL: test_saturate_double2 +define noundef <2 x double> @test_saturate_double2(<2 x double> noundef %p0) { +entry: + ; CHECK: call double @dx.op.unary.f64(i32 7, double + ; CHECK: call double @dx.op.unary.f64(i32 7, double + %hlsl.saturate = call <2 x double> @llvm.dx.saturate.v4f64(<2 x double> %p0) + ret <2 x double> %hlsl.saturate +} + +; CHECK: attributes #[[#ATTR]] = {{{.*}} memory(none) {{.*}}} |