Skip to content

AMDGPU: Use minnum instead of maxnum for fmed3 src2-nan fold #139531

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 12, 2025
Merged

AMDGPU: Use minnum instead of maxnum for fmed3 src2-nan fold #139531

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -867,7 +867,7 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
} else if (match(Src1, PatternMatch::m_NaN()) || isa<UndefValue>(Src1)) {
V = IC.Builder.CreateMinNum(Src0, Src2);
} else if (match(Src2, PatternMatch::m_NaN()) || isa<UndefValue>(Src2)) {
V = IC.Builder.CreateMaxNum(Src0, Src1);
V = IC.Builder.CreateMinNum(Src0, Src1);
}

if (V) {
Expand Down
16 changes: 8 additions & 8 deletions llvm/test/Transforms/InstCombine/AMDGPU/fmed3.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ define float @fmed3_x_undef_y_f32(float %x, float %y) #1 {
define float @fmed3_x_y_undef_f32(float %x, float %y) #1 {
; CHECK-LABEL: define float @fmed3_x_y_undef_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float undef)
Expand Down Expand Up @@ -147,7 +147,7 @@ define float @fmed3_x_qnan0_y_f32(float %x, float %y) #1 {
define float @fmed3_x_y_qnan0_f32(float %x, float %y) #1 {
; CHECK-LABEL: define float @fmed3_x_y_qnan0_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float 0x7FF8000000000000)
Expand Down Expand Up @@ -276,7 +276,7 @@ define float @fmed3_0_nan_1_f32() #1 {
define float @fmed3_0_1_nan_f32() #1 {
; CHECK-LABEL: define float @fmed3_0_1_nan_f32(
; CHECK-SAME: ) #[[ATTR1]] {
; CHECK-NEXT: ret float 1.000000e+00
; CHECK-NEXT: ret float 0.000000e+00
;
%med = call float @llvm.amdgcn.fmed3.f32(float 0.0, float 1.0, float 0x7FF8001000000000)
ret float %med
Expand All @@ -303,7 +303,7 @@ define float @fmed3_0_undef_1_f32() #1 {
define float @fmed3_0_1_undef_f32() #1 {
; CHECK-LABEL: define float @fmed3_0_1_undef_f32(
; CHECK-SAME: ) #[[ATTR1]] {
; CHECK-NEXT: ret float 1.000000e+00
; CHECK-NEXT: ret float 0.000000e+00
;
%med = call float @llvm.amdgcn.fmed3.f32(float 0.0, float 1.0, float undef)
ret float %med
Expand Down Expand Up @@ -359,7 +359,7 @@ define float @fmed3_x_snan1_y_f32(float %x, float %y) #1 {
define float @fmed3_x_y_snan1_f32(float %x, float %y) #1 {
; CHECK-LABEL: define float @fmed3_x_y_snan1_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float 0x7FF4000000000000)
Expand Down Expand Up @@ -414,7 +414,7 @@ define float @fmed3_snan1_neg1_2_f32(float %x, float %y) #1 {
define float @fmed3_neg2_3_snan1_f32(float %x, float %y) #1 {
; CHECK-LABEL: define float @fmed3_neg2_3_snan1_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: ret float 3.000000e+00
; CHECK-NEXT: ret float -2.000000e+00
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float -2.0, float 3.0, float 0x7FF4000000000000)
ret float %med3
Expand Down Expand Up @@ -447,7 +447,7 @@ define amdgpu_ps float @amdgpu_ps_default_fmed3_x_snan1_y_f32(float %x, float %y
define amdgpu_ps float @amdgpu_ps_default_fmed3_x_y_snan1_f32(float %x, float %y) {
; CHECK-LABEL: define amdgpu_ps float @amdgpu_ps_default_fmed3_x_y_snan1_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR2]] {
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float 0x7FF4000000000000)
Expand Down Expand Up @@ -480,7 +480,7 @@ define amdgpu_ps float @amdgpu_ps_attr_fmed3_x_snan1_y_f32(float %x, float %y) #
define amdgpu_ps float @amdgpu_ps_attr_fmed3_x_y_snan1_f32(float %x, float %y) #1 {
; CHECK-LABEL: define amdgpu_ps float @amdgpu_ps_attr_fmed3_x_y_snan1_f32(
; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) #[[ATTR1]] {
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.maxnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: [[MED3:%.*]] = call float @llvm.minnum.f32(float [[X]], float [[Y]])
; CHECK-NEXT: ret float [[MED3]]
;
%med3 = call float @llvm.amdgcn.fmed3.f32(float %x, float %y, float 0x7FF4000000000000)
Expand Down
Loading