maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[InstCombine] Allow undef vectors when foldSelectToCopysign 

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D125671
This commit is contained in:
Chenbing Zheng 2022-05-19 10:57:49 +08:00
parent d699e54ca2
commit 51df77f36d
2 changed files with 9 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
View File

@ -2276,7 +2276,8 @@ static Instruction *foldSelectToCopysign(SelectInst &Sel,
// Match select ?, TC, FC where the constants are equal but negated.
// TODO: Generalize to handle a negated variable operand?
const APFloat *TC, *FC;
if (!match(TVal, m_APFloat(TC)) || !match(FVal, m_APFloat(FC)) ||
if (!match(TVal, m_APFloatAllowUndef(TC)) ||
!match(FVal, m_APFloatAllowUndef(FC)) ||
!abs(*TC).bitwiseIsEqual(abs(*FC)))
return nullptr;
@ -2302,7 +2303,7 @@ static Instruction *foldSelectToCopysign(SelectInst &Sel,
// Canonicalize the magnitude argument as the positive constant since we do
// not care about its sign.
Value *MagArg = TC->isNegative() ? FVal : TVal;
Value *MagArg = ConstantFP::get(SelType, abs(*TC));
Function *F = Intrinsic::getDeclaration(Sel.getModule(), Intrinsic::copysign,
Sel.getType());
return CallInst::Create(F, { MagArg, X });

19
llvm/test/Transforms/InstCombine/select.ll
View File

@ -1689,13 +1689,10 @@ define float @copysign3(float %x) {
ret float %r
}
; TODO: Allow undefs when matching vectors.
define <2 x float> @copysign_vec_undef(<2 x float> %x) {
; CHECK-LABEL: @copysign_vec_undef(
; CHECK-NEXT: [[I:%.*]] = bitcast <2 x float> [[X:%.*]] to <2 x i32>
; CHECK-NEXT: [[ISNEG:%.*]] = icmp slt <2 x i32> [[I]], zeroinitializer
; CHECK-NEXT: [[R:%.*]] = select nnan arcp <2 x i1> [[ISNEG]], <2 x float> <float 4.200000e+01, float undef>, <2 x float> <float -4.200000e+01, float -4.200000e+01>
; CHECK-NEXT: [[TMP1:%.*]] = fneg <2 x float> [[X:%.*]]
; CHECK-NEXT: [[R:%.*]] = call <2 x float> @llvm.copysign.v2f32(<2 x float> <float 4.200000e+01, float 4.200000e+01>, <2 x float> [[TMP1]])
; CHECK-NEXT: ret <2 x float> [[R]]
;
%i = bitcast <2 x float> %x to <2 x i32>
@ -1706,27 +1703,23 @@ define <2 x float> @copysign_vec_undef(<2 x float> %x) {
define <2 x float> @copysign_vec_undef1(<2 x float> %x) {
; CHECK-LABEL: @copysign_vec_undef1(
; CHECK-NEXT: [[I:%.*]] = bitcast <2 x float> [[X:%.*]] to <2 x i32>
; CHECK-NEXT: [[ISNEG:%.*]] = icmp slt <2 x i32> [[I]], zeroinitializer
; CHECK-NEXT: [[R:%.*]] = select nnan arcp <2 x i1> [[ISNEG]], <2 x float> <float 4.200000e+01, float 4.200000e+01>, <2 x float> <float undef, float -4.200000e+01>
; CHECK-NEXT: [[R:%.*]] = call <2 x float> @llvm.copysign.v2f32(<2 x float> <float 4.200000e+01, float 4.200000e+01>, <2 x float> [[X:%.*]])
; CHECK-NEXT: ret <2 x float> [[R]]
;
%i = bitcast <2 x float> %x to <2 x i32>
%isneg = icmp ugt <2 x i32> %i, <i32 2147483647, i32 2147483647>
%isneg = icmp ult <2 x i32> %i, <i32 2147483648, i32 2147483648>
%r = select arcp nnan <2 x i1> %isneg, <2 x float> <float 42.0, float 42.0>, <2 x float> <float undef, float -42.0>
ret <2 x float> %r
}
define <2 x float> @copysign_vec_undef3(<2 x float> %x) {
; CHECK-LABEL: @copysign_vec_undef3(
; CHECK-NEXT: [[I:%.*]] = bitcast <2 x float> [[X:%.*]] to <2 x i32>
; CHECK-NEXT: [[ISNEG:%.*]] = icmp slt <2 x i32> [[I]], zeroinitializer
; CHECK-NEXT: [[R:%.*]] = select nnan arcp <2 x i1> [[ISNEG]], <2 x float> <float 4.200000e+01, float undef>, <2 x float> <float -4.200000e+01, float undef>
; CHECK-NEXT: [[R:%.*]] = call <2 x float> @llvm.copysign.v2f32(<2 x float> <float 4.200000e+01, float 4.200000e+01>, <2 x float> [[X:%.*]])
; CHECK-NEXT: ret <2 x float> [[R]]
;
%i = bitcast <2 x float> %x to <2 x i32>
%isneg = icmp ugt <2 x i32> %i, <i32 2147483647, i32 2147483647>
%r = select arcp nnan <2 x i1> %isneg, <2 x float> <float 42.0, float undef>, <2 x float> <float -42.0, float undef>
%r = select arcp nnan <2 x i1> %isneg, <2 x float> <float -42.0, float undef>, <2 x float> <float +42.0, float undef>
ret <2 x float> %r
}