Index: lib/Transforms/Vectorize/SLPVectorizer.cpp =================================================================== --- lib/Transforms/Vectorize/SLPVectorizer.cpp +++ lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -1625,6 +1625,15 @@ return true; } +/// Checks that \p I is used in the single instruction. +static bool hasOneUse(Instruction *I) { + if (I->hasOneUse()) + return true; + User *U0 = *I->user_begin(); + return std::all_of(I->user_begin(), I->user_end(), + [U0](User *U) -> bool { return U0 == U; }); +} + int BoUpSLP::getEntryCost(TreeEntry *E) { ArrayRef VL = E->Scalars; @@ -1660,7 +1669,7 @@ int DeadCost = 0; for (unsigned i = 0, e = VL.size(); i < e; ++i) { Instruction *E = cast(VL[i]); - if (E->hasOneUse()) + if (hasOneUse(E)) // Take credit for instruction that will become dead. DeadCost += TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, i); Index: test/Transforms/SLPVectorizer/X86/extractelement.ll =================================================================== --- test/Transforms/SLPVectorizer/X86/extractelement.ll +++ test/Transforms/SLPVectorizer/X86/extractelement.ll @@ -3,11 +3,10 @@ define float @f(<2 x float> %x) { ; CHECK-LABEL: @f( -; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x float> [[X:%.*]], i32 0 -; CHECK-NEXT: [[X1:%.*]] = extractelement <2 x float> [[X]], i32 1 -; CHECK-NEXT: [[X0X0:%.*]] = fmul float [[X0]], [[X0]] -; CHECK-NEXT: [[X1X1:%.*]] = fmul float [[X1]], [[X1]] -; CHECK-NEXT: [[ADD:%.*]] = fadd float [[X0X0]], [[X1X1]] +; CHECK-NEXT: [[TMP1:%.*]] = fmul <2 x float> [[X:%.*]], [[X]] +; CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x float> [[TMP1]], i32 0 +; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP1]], i32 1 +; CHECK-NEXT: [[ADD:%.*]] = fadd float [[TMP2]], [[TMP3]] ; CHECK-NEXT: ret float [[ADD]] ; %x0 = extractelement <2 x float> %x, i32 0