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

[InstCombine] change canonicalization to fabs() to use FMF on fsub 

Similar to rL362909:
This isn't the ideal fix (use FMF on the select), but it's still an
improvement until we have better FMF propagation to selects and other
FP math operators.

I don't think there's much risk of regression from this change by
not including the FMF on the fcmp any more. The nsz/nnan FMF
should be the same on the fcmp and the fsub because they have the
same operand.

llvm-svn: 362943
This commit is contained in:
Sanjay Patel 2019-06-10 14:46:36 +00:00
parent b87669f166
commit 8b6d9f60ed
2 changed files with 29 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
View File

@ -1866,27 +1866,29 @@ Instruction *InstCombiner::visitSelectInst(SelectInst &SI) {
// NOTE: if we wanted to, this is where to detect MIN/MAX
}
// Canonicalize select with fcmp to fabs(). -0.0 makes this tricky. We need
// fast-math-flags (nsz) or fsub with +0.0 (not fneg) for this to work. We
// also require nnan because we do not want to unintentionally change the
// sign of a NaN value.
Value *X = FCI->getOperand(0);
FCmpInst::Predicate Pred = FCI->getPredicate();
if (match(FCI->getOperand(1), m_AnyZeroFP()) && FCI->hasNoNaNs()) {
// (X <= +/-0.0) ? (0.0 - X) : X --> fabs(X)
// (X > +/-0.0) ? X : (0.0 - X) --> fabs(X)
if ((X == FalseVal && Pred == FCmpInst::FCMP_OLE &&
match(TrueVal, m_FSub(m_PosZeroFP(), m_Specific(X)))) ||
(X == TrueVal && Pred == FCmpInst::FCMP_OGT &&
match(FalseVal, m_FSub(m_PosZeroFP(), m_Specific(X))))) {
Value *Fabs = Builder.CreateUnaryIntrinsic(Intrinsic::fabs, X, FCI);
return replaceInstUsesWith(SI, Fabs);
}
}
}
// FIXME: These folds should test/propagate FMF from the select, not the fneg.
// Canonicalize select with fcmp to fabs(). -0.0 makes this tricky. We need
// fast-math-flags (nsz) or fsub with +0.0 (not fneg) for this to work. We
// also require nnan because we do not want to unintentionally change the
// sign of a NaN value.
// FIXME: These folds should test/propagate FMF from the select, not the
// fsub or fneg.
// (X <= +/-0.0) ? (0.0 - X) : X --> fabs(X)
Instruction *FSub;
if (match(CondVal, m_FCmp(Pred, m_Specific(FalseVal), m_AnyZeroFP())) &&
match(TrueVal, m_FSub(m_PosZeroFP(), m_Specific(FalseVal))) &&
match(TrueVal, m_Instruction(FSub)) && FSub->hasNoNaNs()) {
Value *Fabs = Builder.CreateUnaryIntrinsic(Intrinsic::fabs, FalseVal, FSub);
return replaceInstUsesWith(SI, Fabs);
}
// (X > +/-0.0) ? X : (0.0 - X) --> fabs(X)
if (match(CondVal, m_FCmp(Pred, m_Specific(TrueVal), m_AnyZeroFP())) &&
match(FalseVal, m_FSub(m_PosZeroFP(), m_Specific(TrueVal))) &&
match(FalseVal, m_Instruction(FSub)) && FSub->hasNoNaNs()) {
Value *Fabs = Builder.CreateUnaryIntrinsic(Intrinsic::fabs, TrueVal, FSub);
return replaceInstUsesWith(SI, Fabs);
}
// With nnan and nsz:
// (X < +/-0.0) ? -X : X --> fabs(X)
// (X <= +/-0.0) ? -X : X --> fabs(X)

16
llvm/test/Transforms/InstCombine/fabs.ll
View File

@ -269,8 +269,8 @@ define double @select_fcmp_nnan_ole_zero(double %x) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan double @llvm.fabs.f64(double [[X:%.*]])
; CHECK-NEXT: ret double [[TMP1]]
;
%lezero = fcmp nnan ole double %x, 0.0
%negx = fsub double 0.0, %x
%lezero = fcmp ole double %x, 0.0
%negx = fsub nnan double 0.0, %x
%fabs = select i1 %lezero, double %negx, double %x
ret double %fabs
}
@ -282,8 +282,8 @@ define <2 x float> @select_fcmp_nnan_ole_negzero(<2 x float> %x) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan <2 x float> @llvm.fabs.v2f32(<2 x float> [[X:%.*]])
; CHECK-NEXT: ret <2 x float> [[TMP1]]
;
%lezero = fcmp nnan ole <2 x float> %x, <float -0.0, float -0.0>
%negx = fsub <2 x float> <float 0.0, float undef>, %x
%lezero = fcmp ole <2 x float> %x, <float -0.0, float -0.0>
%negx = fsub nnan <2 x float> <float 0.0, float undef>, %x
%fabs = select <2 x i1> %lezero, <2 x float> %negx, <2 x float> %x
ret <2 x float> %fabs
}
@ -295,8 +295,8 @@ define fp128 @select_fcmp_nnan_ogt_zero(fp128 %x) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan fp128 @llvm.fabs.f128(fp128 [[X:%.*]])
; CHECK-NEXT: ret fp128 [[TMP1]]
;
%gtzero = fcmp nnan ogt fp128 %x, zeroinitializer
%negx = fsub fp128 zeroinitializer, %x
%gtzero = fcmp ogt fp128 %x, zeroinitializer
%negx = fsub nnan fp128 zeroinitializer, %x
%fabs = select i1 %gtzero, fp128 %x, fp128 %negx
ret fp128 %fabs
}
@ -308,8 +308,8 @@ define half @select_fcmp_nnan_ogt_negzero(half %x) {
; CHECK-NEXT: [[TMP1:%.*]] = call nnan half @llvm.fabs.f16(half [[X:%.*]])
; CHECK-NEXT: ret half [[TMP1]]
;
%gtzero = fcmp nnan ogt half %x, -0.0
%negx = fsub half 0.0, %x
%gtzero = fcmp ogt half %x, -0.0
%negx = fsub nnan half 0.0, %x
%fabs = select i1 %gtzero, half %x, half %negx
ret half %fabs
}