[llvm-branch-commits] [llvm] AMDGPU: Make sqrt and rsq intrinsics propagate poison (PR #130914)

[via llvm-branch-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/130914.diff


2 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp (+2) 
- (modified) llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll (+24) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index 6f6556365ebf6..5314738b2b8ac 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -548,6 +548,8 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
   case Intrinsic::amdgcn_sqrt:
   case Intrinsic::amdgcn_rsq: {
     Value *Src = II.getArgOperand(0);
+    if (isa<PoisonValue>(Src))
+      return IC.replaceInstUsesWith(II, Src);
 
     // TODO: Move to ConstantFolding/InstSimplify?
     if (isa<UndefValue>(Src)) {
diff --git a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
index 42ddc71dab848..fca3860240294 100644
--- a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
+++ b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
@@ -89,6 +89,14 @@ declare half @llvm.amdgcn.sqrt.f16(half) nounwind readnone
 declare float @llvm.amdgcn.sqrt.f32(float) nounwind readnone
 declare double @llvm.amdgcn.sqrt.f64(double) nounwind readnone
 
+define half @test_constant_fold_sqrt_f16_poison() nounwind {
+; CHECK-LABEL: @test_constant_fold_sqrt_f16_poison(
+; CHECK-NEXT:    ret half poison
+;
+  %val = call half @llvm.amdgcn.sqrt.f16(half poison) nounwind readnone
+  ret half %val
+}
+
 define half @test_constant_fold_sqrt_f16_undef() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f16_undef(
 ; CHECK-NEXT:    ret half 0xH7E00
@@ -97,6 +105,14 @@ define half @test_constant_fold_sqrt_f16_undef() nounwind {
   ret half %val
 }
 
+define float @test_constant_fold_sqrt_f32_poison() nounwind {
+; CHECK-LABEL: @test_constant_fold_sqrt_f32_poison(
+; CHECK-NEXT:    ret float poison
+;
+  %val = call float @llvm.amdgcn.sqrt.f32(float poison) nounwind readnone
+  ret float %val
+}
+
 define float @test_constant_fold_sqrt_f32_undef() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f32_undef(
 ; CHECK-NEXT:    ret float 0x7FF8000000000000
@@ -234,6 +250,14 @@ define double @test_amdgcn_sqrt_f64(double %arg) {
 
 declare float @llvm.amdgcn.rsq.f32(float) nounwind readnone
 
+define float @test_constant_fold_rsq_f32_poison() nounwind {
+; CHECK-LABEL: @test_constant_fold_rsq_f32_poison(
+; CHECK-NEXT:    ret float poison
+;
+  %val = call float @llvm.amdgcn.rsq.f32(float poison) nounwind readnone
+  ret float %val
+}
+
 define float @test_constant_fold_rsq_f32_undef() nounwind {
 ; CHECK-LABEL: @test_constant_fold_rsq_f32_undef(
 ; CHECK-NEXT:    ret float 0x7FF8000000000000

``````````

</details>


https://github.com/llvm/llvm-project/pull/130914