forked from OSchip/llvm-project
[GlobalISel] Change widenScalar of G_FCONSTANT to mutate into G_CONSTANT.
Widening a G_FCONSTANT by extending and then generating G_FPTRUNC doesn't produce the same result all the time. Instead, we can just transform it to a G_CONSTANT of the same bit pattern and truncate using a plain G_TRUNC instead. Fixes https://github.com/llvm/llvm-project/issues/56454 Differential Revision: https://reviews.llvm.org/D129743
This commit is contained in:
parent
0a92e0728c
commit
d4f84df0a0
|
@ -2393,30 +2393,14 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
|
|||
return Legalized;
|
||||
}
|
||||
case TargetOpcode::G_FCONSTANT: {
|
||||
// To avoid changing the bits of the constant due to extension to a larger
|
||||
// type and then using G_FPTRUNC, we simply convert to a G_CONSTANT.
|
||||
MachineOperand &SrcMO = MI.getOperand(1);
|
||||
LLVMContext &Ctx = MIRBuilder.getMF().getFunction().getContext();
|
||||
APFloat Val = SrcMO.getFPImm()->getValueAPF();
|
||||
bool LosesInfo;
|
||||
switch (WideTy.getSizeInBits()) {
|
||||
case 32:
|
||||
Val.convert(APFloat::IEEEsingle(), APFloat::rmNearestTiesToEven,
|
||||
&LosesInfo);
|
||||
break;
|
||||
case 64:
|
||||
Val.convert(APFloat::IEEEdouble(), APFloat::rmNearestTiesToEven,
|
||||
&LosesInfo);
|
||||
break;
|
||||
default:
|
||||
return UnableToLegalize;
|
||||
}
|
||||
|
||||
assert(!LosesInfo && "extend should always be lossless");
|
||||
|
||||
Observer.changingInstr(MI);
|
||||
SrcMO.setFPImm(ConstantFP::get(Ctx, Val));
|
||||
|
||||
widenScalarDst(MI, WideTy, 0, TargetOpcode::G_FPTRUNC);
|
||||
Observer.changedInstr(MI);
|
||||
APInt Val = SrcMO.getFPImm()->getValueAPF().bitcastToAPInt();
|
||||
MIRBuilder.setInstrAndDebugLoc(MI);
|
||||
auto IntCst = MIRBuilder.buildConstant(MI.getOperand(0).getReg(), Val);
|
||||
widenScalarDst(*IntCst, WideTy, 0, TargetOpcode::G_TRUNC);
|
||||
MI.eraseFromParent();
|
||||
return Legalized;
|
||||
}
|
||||
case TargetOpcode::G_IMPLICIT_DEF: {
|
||||
|
|
|
@ -48,10 +48,8 @@ body: |
|
|||
; CHECK-NEXT: $w0 = COPY [[C]](s32)
|
||||
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 2.000000e+00
|
||||
; CHECK-NEXT: $x0 = COPY [[C1]](s64)
|
||||
; CHECK-NEXT: [[C2:%[0-9]+]]:_(s32) = G_FCONSTANT float 0.000000e+00
|
||||
; CHECK-NEXT: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[C2]](s32)
|
||||
; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC]](s16)
|
||||
; CHECK-NEXT: $w0 = COPY [[ANYEXT]](s32)
|
||||
; CHECK-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
|
||||
; CHECK-NEXT: $w0 = COPY [[C2]](s32)
|
||||
%0:_(s32) = G_FCONSTANT float 1.0
|
||||
$w0 = COPY %0
|
||||
%1:_(s64) = G_FCONSTANT double 2.0
|
||||
|
|
|
@ -8,8 +8,7 @@ tracksRegLiveness: true
|
|||
body: |
|
||||
bb.0:
|
||||
; NO-FP16-LABEL: name: fp16
|
||||
; NO-FP16: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 0.000000e+00
|
||||
; NO-FP16-NEXT: %cst:_(s16) = G_FPTRUNC [[C]](s32)
|
||||
; NO-FP16: %cst:_(s16) = G_CONSTANT i16 0
|
||||
; NO-FP16-NEXT: $h0 = COPY %cst(s16)
|
||||
; NO-FP16-NEXT: RET_ReallyLR implicit $h0
|
||||
; FP16-LABEL: name: fp16
|
||||
|
@ -19,4 +18,42 @@ body: |
|
|||
%cst:_(s16) = G_FCONSTANT half 0.0
|
||||
$h0 = COPY %cst
|
||||
RET_ReallyLR implicit $h0
|
||||
...
|
||||
---
|
||||
name: fp16_non_zero
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
; NO-FP16-LABEL: name: fp16_non_zero
|
||||
; NO-FP16: %cst:_(s16) = G_CONSTANT i16 16384
|
||||
; NO-FP16-NEXT: $h0 = COPY %cst(s16)
|
||||
; NO-FP16-NEXT: RET_ReallyLR implicit $h0
|
||||
; FP16-LABEL: name: fp16_non_zero
|
||||
; FP16: %cst:_(s16) = G_FCONSTANT half 0xH4000
|
||||
; FP16-NEXT: $h0 = COPY %cst(s16)
|
||||
; FP16-NEXT: RET_ReallyLR implicit $h0
|
||||
%cst:_(s16) = G_FCONSTANT half 2.0
|
||||
$h0 = COPY %cst
|
||||
RET_ReallyLR implicit $h0
|
||||
...
|
||||
---
|
||||
name: nan
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.1.entry:
|
||||
; NO-FP16-LABEL: name: nan
|
||||
; NO-FP16: %cst:_(s16) = G_CONSTANT i16 31745
|
||||
; NO-FP16-NEXT: %ext:_(s32) = G_FPEXT %cst(s16)
|
||||
; NO-FP16-NEXT: $w0 = COPY %ext(s32)
|
||||
; NO-FP16-NEXT: RET_ReallyLR implicit $w0
|
||||
; FP16-LABEL: name: nan
|
||||
; FP16: %cst:_(s16) = G_FCONSTANT half 0xH7C01
|
||||
; FP16-NEXT: %ext:_(s32) = G_FPEXT %cst(s16)
|
||||
; FP16-NEXT: $w0 = COPY %ext(s32)
|
||||
; FP16-NEXT: RET_ReallyLR implicit $w0
|
||||
%cst:_(s16) = G_FCONSTANT half 0xH7C01
|
||||
%ext:_(s32) = G_FPEXT %cst(s16)
|
||||
$w0 = COPY %ext(s32)
|
||||
RET_ReallyLR implicit $w0
|
||||
|
||||
...
|
||||
|
|
Loading…
Reference in New Issue