[InstCombine] fix fmul reassociation to avoid creating an extra fdiv

This was supposed to be an NFC refactoring that will eventually allow
eliminating the isFast() predicate, but there's a rare possibility
that we would pessimize the code as shown in the test case because
we failed to check 'hasOneUse()' properly. This version also removes
an inefficiency of the old code; we would look for: 
(X * C) * C1 --> X * (C * C1)
...but that pattern is always handled by 
SimplifyAssociativeOrCommutative().

llvm-svn: 327404
This commit is contained in:
Sanjay Patel 2018-03-13 14:46:32 +00:00
parent 476ed8f26e
commit 204edeca56
2 changed files with 33 additions and 19 deletions

View File

@ -557,14 +557,28 @@ Instruction *InstCombiner::visitFMul(BinaryOperator &I) {
// Reassociate constant RHS with another constant to form constant expression.
if (I.isFast() && match(Op1, m_Constant(C)) && C->isFiniteNonZeroFP()) {
Constant *C1;
if (match(Op0, m_OneUse(m_FDiv(m_Constant(C1), m_Value(X))))) {
// (C1 / X) * C --> (C * C1) / X
Constant *CC1 = ConstantExpr::getFMul(C, C1);
if (CC1->isNormalFP())
return BinaryOperator::CreateFDivFMF(CC1, X, &I);
}
if (match(Op0, m_FDiv(m_Value(X), m_Constant(C1)))) {
// (X / C1) * C --> X * (C / C1)
Constant *CDivC1 = ConstantExpr::getFDiv(C, C1);
if (CDivC1->isNormalFP())
return BinaryOperator::CreateFMulFMF(X, CDivC1, &I);
// If the constant was a denormal, try reassociating differently.
// (X / C1) * C --> X / (C1 / C)
Constant *C1DivC = ConstantExpr::getFDiv(C1, C);
if (Op0->hasOneUse() && C1DivC->isNormalFP())
return BinaryOperator::CreateFDivFMF(X, C1DivC, &I);
}
// Let MDC denote an expression in one of these forms:
// X * C, C/X, X/C, where C is a constant.
//
// Try to simplify "MDC * Constant"
if (isFMulOrFDivWithConstant(Op0))
if (Value *V = foldFMulConst(cast<Instruction>(Op0), C, &I))
return replaceInstUsesWith(I, V);
// (MDC +/- C1) * C => (MDC * C) +/- (C1 * C)
Instruction *FAddSub = dyn_cast<Instruction>(Op0);
if (FAddSub &&

View File

@ -336,8 +336,8 @@ define float @log2half_commute(float %x1, float %y) {
define float @fdiv_constant_numerator_fmul(float %x) {
; CHECK-LABEL: @fdiv_constant_numerator_fmul(
; CHECK-NEXT: [[TMP1:%.*]] = fdiv fast float 1.200000e+07, [[X:%.*]]
; CHECK-NEXT: ret float [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fdiv fast float 1.200000e+07, [[X:%.*]]
; CHECK-NEXT: ret float [[T3]]
;
%t1 = fdiv float 2.0e+3, %x
%t3 = fmul fast float %t1, 6.0e+3
@ -365,8 +365,8 @@ define float @fdiv_constant_numerator_fmul_extra_use(float %x) {
define float @fdiv_constant_denominator_fmul(float %x) {
; CHECK-LABEL: @fdiv_constant_denominator_fmul(
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[X:%.*]], 3.000000e+00
; CHECK-NEXT: ret float [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fmul fast float [[X:%.*]], 3.000000e+00
; CHECK-NEXT: ret float [[T3]]
;
%t1 = fdiv float %x, 2.0e+3
%t3 = fmul fast float %t1, 6.0e+3
@ -375,8 +375,8 @@ define float @fdiv_constant_denominator_fmul(float %x) {
define <4 x float> @fdiv_constant_denominator_fmul_vec(<4 x float> %x) {
; CHECK-LABEL: @fdiv_constant_denominator_fmul_vec(
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <4 x float> [[X:%.*]], <float 3.000000e+00, float 2.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fmul fast <4 x float> [[X:%.*]], <float 3.000000e+00, float 2.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: ret <4 x float> [[T3]]
;
%t1 = fdiv <4 x float> %x, <float 2.0e+3, float 3.0e+3, float 2.0e+3, float 1.0e+3>
%t3 = fmul fast <4 x float> %t1, <float 6.0e+3, float 6.0e+3, float 2.0e+3, float 1.0e+3>
@ -387,8 +387,8 @@ define <4 x float> @fdiv_constant_denominator_fmul_vec(<4 x float> %x) {
define <4 x float> @fdiv_constant_denominator_fmul_vec_constexpr(<4 x float> %x) {
; CHECK-LABEL: @fdiv_constant_denominator_fmul_vec_constexpr(
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <4 x float> [[X:%.*]], <float 3.000000e+00, float 2.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fmul fast <4 x float> [[X:%.*]], <float 3.000000e+00, float 2.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: ret <4 x float> [[T3]]
;
%constExprMul = bitcast i128 trunc (i160 bitcast (<5 x float> <float 6.0e+3, float 6.0e+3, float 2.0e+3, float 1.0e+3, float undef> to i160) to i128) to <4 x float>
%t1 = fdiv <4 x float> %x, <float 2.0e+3, float 3.0e+3, float 2.0e+3, float 1.0e+3>
@ -416,21 +416,21 @@ define float @fdiv_constant_denominator_fmul_denorm(float %x) {
define float @fdiv_constant_denominator_fmul_denorm_try_harder(float %x) {
; CHECK-LABEL: @fdiv_constant_denominator_fmul_denorm_try_harder(
; CHECK-NEXT: [[TMP1:%.*]] = fdiv fast float [[X:%.*]], 0x47E8000000000000
; CHECK-NEXT: ret float [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fdiv fast float [[X:%.*]], 0x47E8000000000000
; CHECK-NEXT: ret float [[T3]]
;
%t1 = fdiv float %x, 3.0
%t3 = fmul fast float %t1, 0x3810000000000000
ret float %t3
}
; FIXME: We have 2 divisions instead of the 1 we started with.
; Negative test: we should not have 2 divisions instead of the 1 we started with.
define float @fdiv_constant_denominator_fmul_denorm_try_harder_extra_use(float %x) {
; CHECK-LABEL: @fdiv_constant_denominator_fmul_denorm_try_harder_extra_use(
; CHECK-NEXT: [[T1:%.*]] = fdiv float [[X:%.*]], 3.000000e+00
; CHECK-NEXT: [[TMP1:%.*]] = fdiv fast float [[X]], 0x47E8000000000000
; CHECK-NEXT: [[R:%.*]] = fadd float [[T1]], [[TMP1]]
; CHECK-NEXT: [[T3:%.*]] = fmul fast float [[T1]], 0x3810000000000000
; CHECK-NEXT: [[R:%.*]] = fadd float [[T1]], [[T3]]
; CHECK-NEXT: ret float [[R]]
;
%t1 = fdiv float %x, 3.0e+0