[llvm] [DirectX] Scalarize the dx.saturate intrinsic (PR #134381)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Apr 4 06:32:56 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-directx
Author: Justin Bogner (bogner)
<details>
<summary>Changes</summary>
The DXIL Saturate op only takes scalars.
Fixes #<!-- -->134378.
---
Full diff: https://github.com/llvm/llvm-project/pull/134381.diff
2 Files Affected:
- (modified) llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp (+1)
- (modified) llvm/test/CodeGen/DirectX/saturate.ll (+31-5)
``````````diff
diff --git a/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp b/llvm/lib/Target/DirectX/DirectXTargetTransformInfo.cpp
index 765e1977041b9..4cf3282b108f1 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 0bb1e55421046..1e4a235448a48 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) {{.*}}}
``````````
</details>
https://github.com/llvm/llvm-project/pull/134381
More information about the llvm-commits
mailing list