[llvm] d18ab0e - [InstCombine] Fold fabs over selects (#86390)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Apr 22 00:37:45 PDT 2024
Author: Yingwei Zheng
Date: 2024-04-22T15:37:42+08:00
New Revision: d18ab0e1bd5032d213acb94ef70564d221f63fa7
URL: https://github.com/llvm/llvm-project/commit/d18ab0e1bd5032d213acb94ef70564d221f63fa7
DIFF: https://github.com/llvm/llvm-project/commit/d18ab0e1bd5032d213acb94ef70564d221f63fa7.diff
LOG: [InstCombine] Fold fabs over selects (#86390)
This patch folds fabs over select if it is beneficial. I also tried
other interger/fp intrinsics. Only handling fabs shows benefit to some
real-world applications.
Added:
Modified:
llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
llvm/test/Transforms/InstCombine/fabs.ll
llvm/test/Transforms/InstCombine/intrinsic-select.ll
llvm/test/Transforms/InstCombine/simplify-demanded-fpclass.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index e7a2f54f86809f..a37a4cde96f899 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -2501,10 +2501,16 @@ Instruction *InstCombinerImpl::visitCallInst(CallInst &CI) {
if (match(II->getArgOperand(0),
m_Select(m_Value(Cond), m_Value(TVal), m_Value(FVal)))) {
// fabs (select Cond, TrueC, FalseC) --> select Cond, AbsT, AbsF
- if (isa<Constant>(TVal) && isa<Constant>(FVal)) {
+ if (isa<Constant>(TVal) || isa<Constant>(FVal)) {
CallInst *AbsT = Builder.CreateCall(II->getCalledFunction(), {TVal});
CallInst *AbsF = Builder.CreateCall(II->getCalledFunction(), {FVal});
- return SelectInst::Create(Cond, AbsT, AbsF);
+ SelectInst *SI = SelectInst::Create(Cond, AbsT, AbsF);
+ FastMathFlags FMF1 = II->getFastMathFlags();
+ FastMathFlags FMF2 =
+ cast<SelectInst>(II->getArgOperand(0))->getFastMathFlags();
+ FMF2.setNoSignedZeros(false);
+ SI->setFastMathFlags(FMF1 | FMF2);
+ return SI;
}
// fabs (select Cond, -FVal, FVal) --> fabs FVal
if (match(TVal, m_FNeg(m_Specific(FVal))))
diff --git a/llvm/test/Transforms/InstCombine/fabs.ll b/llvm/test/Transforms/InstCombine/fabs.ll
index 5ec65784e7a348..cccf0f4457b6ab 100644
--- a/llvm/test/Transforms/InstCombine/fabs.ll
+++ b/llvm/test/Transforms/InstCombine/fabs.ll
@@ -179,9 +179,9 @@ define float @fabs_select_constant_neg0(i32 %c) {
define float @fabs_select_var_constant_negative(i32 %c, float %x) {
; CHECK-LABEL: @fabs_select_var_constant_negative(
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[C:%.*]], 0
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[CMP]], float [[X:%.*]], float -1.000000e+00
-; CHECK-NEXT: [[FABS:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
-; CHECK-NEXT: ret float [[FABS]]
+; CHECK-NEXT: [[FABS:%.*]] = call float @llvm.fabs.f32(float [[SELECT:%.*]])
+; CHECK-NEXT: [[FABS1:%.*]] = select i1 [[CMP]], float [[FABS]], float 1.000000e+00
+; CHECK-NEXT: ret float [[FABS1]]
;
%cmp = icmp eq i32 %c, 0
%select = select i1 %cmp, float %x, float -1.0
diff --git a/llvm/test/Transforms/InstCombine/intrinsic-select.ll b/llvm/test/Transforms/InstCombine/intrinsic-select.ll
index f37226bbd5b09c..1727d8f2758b01 100644
--- a/llvm/test/Transforms/InstCombine/intrinsic-select.ll
+++ b/llvm/test/Transforms/InstCombine/intrinsic-select.ll
@@ -280,3 +280,67 @@ entry:
%ret = icmp eq i64 %masked, 0
ret i1 %ret
}
+
+define double @test_fabs_select1(double %a) {
+; CHECK-LABEL: @test_fabs_select1(
+; CHECK-NEXT: [[COND:%.*]] = fcmp uno double [[A:%.*]], 0.000000e+00
+; CHECK-NEXT: [[SEL1:%.*]] = select i1 [[COND]], double 0x7FF8000000000000, double [[A]]
+; CHECK-NEXT: ret double [[SEL1]]
+;
+ %cond = fcmp uno double %a, 0.000000e+00
+ %sel1 = select i1 %cond, double 0x7FF8000000000000, double %a
+ %fabs = call double @llvm.fabs.f64(double %sel1)
+ %sel2 = select i1 %cond, double %fabs, double %a
+ ret double %sel2
+}
+
+define <2 x double> @test_fabs_select1_vec(<2 x double> %a) {
+; CHECK-LABEL: @test_fabs_select1_vec(
+; CHECK-NEXT: [[COND:%.*]] = fcmp uno <2 x double> [[A:%.*]], zeroinitializer
+; CHECK-NEXT: [[SEL2:%.*]] = select <2 x i1> [[COND]], <2 x double> <double 0x7FF8000000000000, double 0x7FF8000000000000>, <2 x double> [[A]]
+; CHECK-NEXT: ret <2 x double> [[SEL2]]
+;
+ %cond = fcmp uno <2 x double> %a, zeroinitializer
+ %sel1 = select <2 x i1> %cond, <2 x double> splat(double 0x7FF8000000000000), <2 x double> %a
+ %fabs = call <2 x double> @llvm.fabs.v2f64(<2 x double> %sel1)
+ %sel2 = select <2 x i1> %cond, <2 x double> %fabs, <2 x double> %a
+ ret <2 x double> %sel2
+}
+
+define double @test_fabs_select2(double %a) {
+; CHECK-LABEL: @test_fabs_select2(
+; CHECK-NEXT: [[ABS1:%.*]] = call double @llvm.fabs.f64(double [[A:%.*]])
+; CHECK-NEXT: [[CMP:%.*]] = fcmp oeq double [[ABS1]], 0x7FF0000000000000
+; CHECK-NEXT: [[ABS2:%.*]] = select i1 [[CMP]], double 0.000000e+00, double [[ABS1]]
+; CHECK-NEXT: ret double [[ABS2]]
+;
+ %abs1 = call double @llvm.fabs.f64(double %a)
+ %cmp = fcmp oeq double %abs1, 0x7FF0000000000000
+ %sel = select i1 %cmp, double -0.000000e+00, double %abs1
+ %abs2 = call double @llvm.fabs.f64(double %sel)
+ ret double %abs2
+}
+
+; nsz flag should be dropped.
+
+define double @test_fabs_select_fmf1(i1 %cond, double %a) {
+; CHECK-LABEL: @test_fabs_select_fmf1(
+; CHECK-NEXT: [[A:%.*]] = call double @llvm.fabs.f64(double [[A1:%.*]])
+; CHECK-NEXT: [[FABS:%.*]] = select nnan ninf i1 [[COND:%.*]], double 0.000000e+00, double [[A]]
+; CHECK-NEXT: ret double [[FABS]]
+;
+ %sel1 = select nnan ninf nsz i1 %cond, double 0.0, double %a
+ %fabs = call double @llvm.fabs.f64(double %sel1)
+ ret double %fabs
+}
+
+define double @test_fabs_select_fmf2(i1 %cond, double %a) {
+; CHECK-LABEL: @test_fabs_select_fmf2(
+; CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[A:%.*]])
+; CHECK-NEXT: [[SEL1:%.*]] = select nnan ninf nsz i1 [[COND:%.*]], double 0.000000e+00, double [[TMP1]]
+; CHECK-NEXT: ret double [[SEL1]]
+;
+ %sel1 = select i1 %cond, double 0.0, double %a
+ %fabs = call nnan ninf nsz double @llvm.fabs.f64(double %sel1)
+ ret double %fabs
+}
diff --git a/llvm/test/Transforms/InstCombine/simplify-demanded-fpclass.ll b/llvm/test/Transforms/InstCombine/simplify-demanded-fpclass.ll
index 5dfeb0734fbbed..a7d01b4f824db0 100644
--- a/llvm/test/Transforms/InstCombine/simplify-demanded-fpclass.ll
+++ b/llvm/test/Transforms/InstCombine/simplify-demanded-fpclass.ll
@@ -387,8 +387,8 @@ define nofpclass(inf) float @ret_nofpclass_inf__fabs_select_pinf_rhs(i1 %cond, f
define nofpclass(ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives__fabs_select_pinf_rhs(i1 %cond, float %x) {
; CHECK-LABEL: define nofpclass(ninf nzero nsub nnorm) float @ret_nofpclass_no_negatives__fabs_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[FABS:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[FABS:%.*]] = select i1 [[COND]], float [[TMP1]], float 0x7FF0000000000000
; CHECK-NEXT: ret float [[FABS]]
;
%select = select i1 %cond, float %x, float 0x7FF0000000000000
@@ -411,8 +411,8 @@ define nofpclass(pinf pnorm psub pzero) float @ret_nofpclass_no_positives__fabs_
define nofpclass(nan ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives_nan__fabs_select_pinf_rhs(i1 %cond, float %x) {
; CHECK-LABEL: define nofpclass(nan ninf nzero nsub nnorm) float @ret_nofpclass_no_negatives_nan__fabs_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[FABS:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[FABS:%.*]] = select i1 [[COND]], float [[TMP1]], float 0x7FF0000000000000
; CHECK-NEXT: ret float [[FABS]]
;
%select = select i1 %cond, float %x, float 0x7FF0000000000000
@@ -665,8 +665,8 @@ define nofpclass(inf pnorm psub pzero) float @ret_nofpclass_no_positives_noinf__
define nofpclass(ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives__copysign_unknown_select_pinf_rhs(i1 %cond, float %x, float %unknown.sign) {
; CHECK-LABEL: define nofpclass(ninf nzero nsub nnorm) float @ret_nofpclass_no_negatives__copysign_unknown_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]], float [[UNKNOWN_SIGN:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[COPYSIGN:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[COPYSIGN:%.*]] = select i1 [[COND]], float [[TMP1]], float 0x7FF0000000000000
; CHECK-NEXT: ret float [[COPYSIGN]]
;
%select = select i1 %cond, float %x, float 0x7FF0000000000000
@@ -678,8 +678,8 @@ define nofpclass(ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives__copys
define nofpclass(pinf pnorm psub pzero) float @ret_nofpclass_no_positives__copysign_unknown_select_pinf_rhs(i1 %cond, float %x, float %unknown.sign) {
; CHECK-LABEL: define nofpclass(pinf pzero psub pnorm) float @ret_nofpclass_no_positives__copysign_unknown_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]], float [[UNKNOWN_SIGN:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[TMP1:%.*]] = select i1 [[COND]], float [[TMP2]], float 0x7FF0000000000000
; CHECK-NEXT: [[COPYSIGN:%.*]] = fneg float [[TMP1]]
; CHECK-NEXT: ret float [[COPYSIGN]]
;
@@ -692,8 +692,8 @@ define nofpclass(pinf pnorm psub pzero) float @ret_nofpclass_no_positives__copys
define nofpclass(nan ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives_nonan__copysign_unknown_select_pinf_rhs(i1 %cond, float %x, float %unknown.sign) {
; CHECK-LABEL: define nofpclass(nan ninf nzero nsub nnorm) float @ret_nofpclass_no_negatives_nonan__copysign_unknown_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]], float [[UNKNOWN_SIGN:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[COPYSIGN:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[COPYSIGN:%.*]] = select i1 [[COND]], float [[TMP1]], float 0x7FF0000000000000
; CHECK-NEXT: ret float [[COPYSIGN]]
;
%select = select i1 %cond, float %x, float 0x7FF0000000000000
@@ -705,8 +705,8 @@ define nofpclass(nan ninf nnorm nsub nzero) float @ret_nofpclass_no_negatives_no
define nofpclass(nan pinf pnorm psub pzero) float @ret_nofpclass_no_positives_nonan__copysign_unknown_select_pinf_rhs(i1 %cond, float %x, float %unknown.sign) {
; CHECK-LABEL: define nofpclass(nan pinf pzero psub pnorm) float @ret_nofpclass_no_positives_nonan__copysign_unknown_select_pinf_rhs
; CHECK-SAME: (i1 [[COND:%.*]], float [[X:%.*]], float [[UNKNOWN_SIGN:%.*]]) {
-; CHECK-NEXT: [[SELECT:%.*]] = select i1 [[COND]], float [[X]], float 0x7FF0000000000000
-; CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[SELECT]])
+; CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.fabs.f32(float [[X]])
+; CHECK-NEXT: [[TMP1:%.*]] = select i1 [[COND]], float [[TMP2]], float 0x7FF0000000000000
; CHECK-NEXT: [[COPYSIGN:%.*]] = fneg float [[TMP1]]
; CHECK-NEXT: ret float [[COPYSIGN]]
;
More information about the llvm-commits
mailing list