Skip to content

[InstCombine] Fold fpto{s|u}i non-norm to zero #85569

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.

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 2 commits into from
Mar 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
19 changes: 19 additions & 0 deletions llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1923,17 +1923,36 @@ Instruction *InstCombinerImpl::foldItoFPtoI(CastInst &FI) {
return replaceInstUsesWith(FI, X);
}

static Instruction *foldFPtoI(Instruction &FI, InstCombiner &IC) {
// fpto{u/s}i non-norm --> 0
FPClassTest Mask =
FI.getOpcode() == Instruction::FPToUI ? fcPosNormal : fcNormal;
KnownFPClass FPClass =
computeKnownFPClass(FI.getOperand(0), Mask, /*Depth=*/0,
IC.getSimplifyQuery().getWithInstruction(&FI));
if (FPClass.isKnownNever(Mask))
return IC.replaceInstUsesWith(FI, ConstantInt::getNullValue(FI.getType()));

return nullptr;
}

Instruction *InstCombinerImpl::visitFPToUI(FPToUIInst &FI) {
if (Instruction *I = foldItoFPtoI(FI))
return I;

if (Instruction *I = foldFPtoI(FI, *this))
return I;

return commonCastTransforms(FI);
}

Instruction *InstCombinerImpl::visitFPToSI(FPToSIInst &FI) {
if (Instruction *I = foldItoFPtoI(FI))
return I;

if (Instruction *I = foldFPtoI(FI, *this))
return I;

return commonCastTransforms(FI);
}

Expand Down
88 changes: 88 additions & 0 deletions llvm/test/Transforms/InstCombine/fpcast.ll
Original file line number Diff line number Diff line change
Expand Up @@ -347,3 +347,91 @@ define double @masked_uint_to_fpext3(i32 %x) {
%r = fpext float %f to double
ret double %r
}

define i32 @fptosi_nonnorm(float nofpclass(norm) %x) {
; CHECK-LABEL: @fptosi_nonnorm(
; CHECK-NEXT: ret i32 0
;
%ret = fptosi float %x to i32
ret i32 %ret
}

define i32 @fptoui_nonnorm(float nofpclass(pnorm) %x) {
; CHECK-LABEL: @fptoui_nonnorm(
; CHECK-NEXT: ret i32 0
;
%ret = fptoui float %x to i32
ret i32 %ret
}

define i32 @fptosi_nonnnorm(float nofpclass(nnorm) %x) {
; CHECK-LABEL: @fptosi_nonnnorm(
; CHECK-NEXT: [[RET:%.*]] = fptosi float [[X:%.*]] to i32
; CHECK-NEXT: ret i32 [[RET]]
;
%ret = fptosi float %x to i32
ret i32 %ret
}

define i32 @fptoui_nonnnorm(float nofpclass(nnorm) %x) {
; CHECK-LABEL: @fptoui_nonnnorm(
; CHECK-NEXT: [[RET:%.*]] = fptoui float [[X:%.*]] to i32
; CHECK-NEXT: ret i32 [[RET]]
;
%ret = fptoui float %x to i32
ret i32 %ret
}

define i32 @fptosi_nonnorm_copysign(float %x) {
; CHECK-LABEL: @fptosi_nonnorm_copysign(
; CHECK-NEXT: ret i32 0
;
%val = call float @llvm.copysign.f32(float 0.0, float %x)
%ret = fptosi float %val to i32
ret i32 %ret
}

define <2 x i32> @fptosi_nonnorm_copysign_vec(<2 x float> %x) {
; CHECK-LABEL: @fptosi_nonnorm_copysign_vec(
; CHECK-NEXT: ret <2 x i32> zeroinitializer
;
%val = call <2 x float> @llvm.copysign.v2f32(<2 x float> zeroinitializer, <2 x float> %x)
%ret = fptosi <2 x float> %val to <2 x i32>
ret <2 x i32> %ret
}

define i32 @fptosi_nonnorm_fmul(float %x) {
; CHECK-LABEL: @fptosi_nonnorm_fmul(
; CHECK-NEXT: [[SEL:%.*]] = fmul float [[X:%.*]], 0.000000e+00
; CHECK-NEXT: [[RET:%.*]] = fptosi float [[SEL]] to i32
; CHECK-NEXT: ret i32 [[RET]]
;
%sel = fmul float %x, 0.000000e+00
%ret = fptosi float %sel to i32
ret i32 %ret
}

define i32 @fptosi_select(i1 %cond) {
; CHECK-LABEL: @fptosi_select(
; CHECK-NEXT: [[RET:%.*]] = select i1 [[COND:%.*]], i32 1, i32 -1
; CHECK-NEXT: ret i32 [[RET]]
;
%sel = select i1 %cond, float 1.0, float -1.0
%ret = fptosi float %sel to i32
ret i32 %ret
}

define i32 @mul_pos_zero_convert(i32 %a) {
; CHECK-LABEL: @mul_pos_zero_convert(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[FP:%.*]] = sitofp i32 [[A:%.*]] to float
; CHECK-NEXT: [[RET:%.*]] = fmul float [[FP]], 0.000000e+00
; CHECK-NEXT: [[CONV:%.*]] = fptosi float [[RET]] to i32
; CHECK-NEXT: ret i32 [[CONV]]
;
entry:
%fp = sitofp i32 %a to float
%ret = fmul float %fp, 0.000000e+00
%conv = fptosi float %ret to i32
ret i32 %conv
}