diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp --- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp @@ -599,9 +599,10 @@ // Check that this PHI type is allowed. if (!PhiTy->isIntegerTy() && !PhiTy->isFloatingPointTy() && !PhiTy->isPointerTy()) { + LLVM_DEBUG(dbgs() + << "LV: Not vectorizing: Found a non-int non-pointer PHI.\n"); ORE->emit(createMissedAnalysis("CFGNotUnderstood", Phi) << "loop control flow is not understood by vectorizer"); - LLVM_DEBUG(dbgs() << "LV: Found an non-int non-pointer PHI.\n"); return false; } @@ -967,7 +968,8 @@ // We must have a loop in canonical form. Loops with indirectbr in them cannot // be canonicalized. if (!Lp->getLoopPreheader()) { - LLVM_DEBUG(dbgs() << "LV: Loop doesn't have a legal pre-header.\n"); + LLVM_DEBUG(dbgs() + << "LV: Not vectorizing: Loop doesn't have a legal pre-header.\n"); ORE->emit(createMissedAnalysis("CFGNotUnderstood") << "loop control flow is not understood by vectorizer"); if (DoExtraAnalysis) @@ -978,6 +980,8 @@ // We must have a single backedge. if (Lp->getNumBackEdges() != 1) { + LLVM_DEBUG(dbgs() + << "LV: Not vectorizing: The loop must have a single backedge.\n"); ORE->emit(createMissedAnalysis("CFGNotUnderstood") << "loop control flow is not understood by vectorizer"); if (DoExtraAnalysis) @@ -988,6 +992,8 @@ // We must have a single exiting block. if (!Lp->getExitingBlock()) { + LLVM_DEBUG(dbgs() + << "LV: Not vectorizing: The loop must have an exiting block.\n"); ORE->emit(createMissedAnalysis("CFGNotUnderstood") << "loop control flow is not understood by vectorizer"); if (DoExtraAnalysis) @@ -1000,6 +1006,8 @@ // checked at the end of each iteration. With that we can assume that all // instructions in the loop are executed the same number of times. if (Lp->getExitingBlock() != Lp->getLoopLatch()) { + LLVM_DEBUG(dbgs() + << "LV: Not vectorizing: The exiting block is not the loop latch.\n"); ORE->emit(createMissedAnalysis("CFGNotUnderstood") << "loop control flow is not understood by vectorizer"); if (DoExtraAnalysis) diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -1432,6 +1432,9 @@ RPOT.perform(LI); if (!containsIrreducibleCFG(RPOT, *LI)) { V.push_back(&L); + LLVM_DEBUG(dbgs() << "LV: The loop '" + << L.getName() + << "' is eligible as supported.\n"); // TODO: Collect inner loops inside marked outer loops in case // vectorization fails for the outer loop. Do not invoke // 'containsIrreducibleCFG' again for inner loops when the outer loop is @@ -7579,16 +7582,22 @@ // legality and profitability checks. This means running the loop vectorizer // will simplify all loops, regardless of whether anything end up being // vectorized. - for (auto &L : *LI) - Changed |= + for (auto &L : *LI) { + bool Simplified = simplifyLoop(L, DT, LI, SE, AC, nullptr, false /* PreserveLCSSA */); + LLVM_DEBUG( + if (Simplified) + dbgs() << "LV: The loop '" << L->getName() << "' has been simplified.\n"; + ); + Changed |= Simplified; + } // Build up a worklist of inner-loops to vectorize. This is necessary as // the act of vectorizing or partially unrolling a loop creates new loops // and can invalidate iterators across the loops. SmallVector Worklist; - for (Loop *L : *LI) + for (auto &L : *LI) collectSupportedLoops(*L, LI, ORE, Worklist); LoopsAnalyzed += Worklist.size();