Index: llvm/trunk/lib/Transforms/Scalar/LoopStrengthReduce.cpp =================================================================== --- llvm/trunk/lib/Transforms/Scalar/LoopStrengthReduce.cpp +++ llvm/trunk/lib/Transforms/Scalar/LoopStrengthReduce.cpp @@ -325,7 +325,7 @@ // Look at addrec operands. if (const SCEVAddRecExpr *AR = dyn_cast(S)) - if (!AR->getStart()->isZero()) { + if (!AR->getStart()->isZero() && AR->isAffine()) { DoInitialMatch(AR->getStart(), L, Good, Bad, SE); DoInitialMatch(SE.getAddRecExpr(SE.getConstant(AR->getType(), 0), AR->getStepRecurrence(SE), @@ -568,7 +568,7 @@ // Distribute the sdiv over addrec operands, if the addrec doesn't overflow. if (const SCEVAddRecExpr *AR = dyn_cast(LHS)) { - if (IgnoreSignificantBits || isAddRecSExtable(AR, SE)) { + if ((IgnoreSignificantBits || isAddRecSExtable(AR, SE)) && AR->isAffine()) { const SCEV *Step = getExactSDiv(AR->getStepRecurrence(SE), RHS, SE, IgnoreSignificantBits); if (!Step) return nullptr; @@ -3196,7 +3196,7 @@ return nullptr; } else if (const SCEVAddRecExpr *AR = dyn_cast(S)) { // Split a non-zero base out of an addrec. - if (AR->getStart()->isZero()) + if (AR->getStart()->isZero() || !AR->isAffine()) return S; const SCEV *Remainder = CollectSubexprs(AR->getStart(), Index: llvm/trunk/test/Transforms/LoopStrengthReduce/ARM/addrec-is-loop-invariant.ll =================================================================== --- llvm/trunk/test/Transforms/LoopStrengthReduce/ARM/addrec-is-loop-invariant.ll +++ llvm/trunk/test/Transforms/LoopStrengthReduce/ARM/addrec-is-loop-invariant.ll @@ -0,0 +1,35 @@ +; RUN: llc -mtriple=armv8-eabi -verify-machineinstrs %s -o /dev/null + +; This test ensures that Loop Strength Reduction will +; not create an Add Reccurence Expression if not all +; its operands are loop invariants. + +define void @add_rec_expr() { +entry: + br label %loop0 + +loop0: + %c.0 = phi i32 [ 0, %entry ], [ %inc.0, %loop0 ] + %inc.0 = add nuw i32 %c.0, 1 + br i1 undef, label %loop0, label %bb1 + +bb1: + %mul.0 = mul i32 %c.0, %c.0 + %gelptr.0 = getelementptr inbounds i16, i16* undef, i32 %mul.0 + br label %loop1 + +loop1: + %inc.1 = phi i32 [ %inc.2, %bb4 ], [ 0, %bb1 ] + %mul.1 = mul i32 %inc.1, %c.0 + br label %bb3 + +bb3: + %add.0 = add i32 undef, %mul.1 + %gelptr.1 = getelementptr inbounds i16, i16* %gelptr.0, i32 %add.0 + store i16 undef, i16* %gelptr.1, align 2 + br label %bb4 + +bb4: + %inc.2 = add nuw i32 %inc.1, 1 + br label %loop1 +}