https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/131060
>From 4b8aef2f108aeb71dc1ffb29392cbb1a4548a576 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <matthew.arsena...@amd.com>
Date: Thu, 13 Mar 2025 10:37:11 +0700
Subject: [PATCH] AMDGPU: Make fmed3 intrinsic propagate poison
---
.../AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 5 ++++
.../InstCombine/AMDGPU/amdgcn-intrinsics.ll | 24 +++++++++++++++++++
2 files changed, 29 insertions(+)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index e1ab33c399b0b..02977a61efb55 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -827,6 +827,11 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC,
IntrinsicInst &II) const {
Value *Src1 = II.getArgOperand(1);
Value *Src2 = II.getArgOperand(2);
+ for (Value *Src : {Src0, Src1, Src2}) {
+ if (isa<PoisonValue>(Src))
+ return IC.replaceInstUsesWith(II, Src);
+ }
+
// Checking for NaN before canonicalization provides better fidelity when
// mapping other operations onto fmed3 since the order of operands is
// unchanged.
diff --git a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
index 2f64e4d15f357..af5c66165e67e 100644
--- a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
+++ b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
@@ -2121,6 +2121,30 @@ define float @fmed3_0_1_undef_f32() {
ret float %med
}
+define float @fmed3_poison_x_y_f32(float %x, float %y) {
+; CHECK-LABEL: @fmed3_poison_x_y_f32(
+; CHECK-NEXT: ret float poison
+;
+ %med3 = call float @llvm.amdgcn.fmed3.f32(float poison, float %x, float %y)
+ ret float %med3
+}
+
+define float @fmed3_x_poison_y_f32(float %x, float %y) {
+; CHECK-LABEL: @fmed3_x_poison_y_f32(
+; CHECK-NEXT: ret float poison
+;
+ %med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float poison, float %y)
+ ret float %med3
+}
+
+define float @fmed3_x_y_poison_f32(float %x, float %y) {
+; CHECK-LABEL: @fmed3_x_y_poison_f32(
+; CHECK-NEXT: ret float poison
+;
+ %med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float poison)
+ ret float %med3
+}
+
; --------------------------------------------------------------------
; llvm.amdgcn.icmp
; --------------------------------------------------------------------
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
