https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/139530
None
>From 012d451378314c9633c3a38891fca23c027e54b5 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <matthew.arsena...@amd.com>
Date: Mon, 12 May 2025 10:42:16 +0200
Subject: [PATCH] AMDGPU: Disable most fmed3 folds for strictfp
---
.../lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp | 3 +++
llvm/test/Transforms/InstCombine/AMDGPU/fmed3.ll | 12 ++++++------
2 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index e76396f6ffbb0..1494428cb2bf5 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -855,6 +855,9 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC,
IntrinsicInst &II) const {
return IC.replaceInstUsesWith(II, Src);
}
+ if (II.isStrictFP())
+ break;
+
// 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/fmed3.ll
b/llvm/test/Transforms/InstCombine/AMDGPU/fmed3.ll
index 5274ac1093a26..bf94637b36a34 100644
--- a/llvm/test/Transforms/InstCombine/AMDGPU/fmed3.ll
+++ b/llvm/test/Transforms/InstCombine/AMDGPU/fmed3.ll
@@ -494,7 +494,7 @@ define amdgpu_ps float
@amdgpu_ps_attr_fmed3_x_y_snan1_f32(float %x, float %y) #
define float @fmed3_qnan0_x_y_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_qnan0_x_y_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3:[0-9]+]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float
0x7FF8000000000000, float [[X]], float [[Y]]) #[[ATTR5:[0-9]+]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float 0x7FF8000000000000, float
%x, float %y) strictfp
@@ -504,7 +504,7 @@ define float @fmed3_qnan0_x_y_f32_strictfp(float %x, float
%y) #2 {
define float @fmed3_x_qnan0_y_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_x_qnan0_y_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float [[X]],
float 0x7FF8000000000000, float [[Y]]) #[[ATTR5]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float
0x7FF8000000000000, float %y) strictfp
@@ -514,7 +514,7 @@ define float @fmed3_x_qnan0_y_f32_strictfp(float %x, float
%y) #2 {
define float @fmed3_x_y_qnan0_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_x_y_qnan0_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float [[X]],
float [[Y]], float 0x7FF8000000000000) #[[ATTR5]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float
0x7FF8000000000000) strictfp
@@ -524,7 +524,7 @@ define float @fmed3_x_y_qnan0_f32_strictfp(float %x, float
%y) #2 {
define float @fmed3_snan1_x_y_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_snan1_x_y_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float
0x7FF4000000000000, float [[X]], float [[Y]]) #[[ATTR5]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float 0x7FF4000000000000, float
%x, float %y) strictfp
@@ -534,7 +534,7 @@ define float @fmed3_snan1_x_y_f32_strictfp(float %x, float
%y) #2 {
define float @fmed3_x_snan1_y_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_x_snan1_y_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float [[X]],
float 0x7FF4000000000000, float [[Y]]) #[[ATTR5]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float
0x7FF4000000000000, float %y) strictfp
@@ -544,7 +544,7 @@ define float @fmed3_x_snan1_y_f32_strictfp(float %x, float
%y) #2 {
define float @fmed3_x_y_snan1_f32_strictfp(float %x, float %y) #2 {
; CHECK-LABEL: define float @fmed3_x_y_snan1_f32_strictfp(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR3]] {
-; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float
[[Y]])
+; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.amdgcn.fmed3.f32(float [[X]],
float [[Y]], float 0x7FF4000000000000) #[[ATTR5]]
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float
0x7FF4000000000000) strictfp
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
