[LV] Avoid vectorizing loops under opt for size that involve SCEV checks

Fix PR39417, PR39497

The loop vectorizer may generate runtime SCEV checks for overflow and stride==1
cases, leading to execution of original scalar loop. The latter is forbidden
when optimizing for size. An assert introduced in r344743 triggered the above
PR's showing it does happen. This patch fixes this behavior by preventing
vectorization in such cases.

Differential Revision: https://reviews.llvm.org/D53612

llvm-svn: 345959

1 files changed, 25 insertions, 1 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 23d4a6b2166..c9c70b5c536 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2557,7 +2557,8 @@ void InnerLoopVectorizer::emitSCEVChecks(Loop *L, BasicBlock *Bypass) {
     if (C->isZero())
       return;
 
-  assert(!Cost->foldTailByMasking() && "Cannot check stride when folding tail");
+  assert(!Cost->foldTailByMasking() &&
+         "Cannot SCEV check stride or overflow when folding tail");
   // Create a new block containing the stride check.
   BB->setName("vector.scevcheck");
   auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
@@ -4637,6 +4638,29 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
     return None;
   }
 
+  if (!PSE.getUnionPredicate().getPredicates().empty()) {
+    ORE->emit(createMissedAnalysis("CantVersionLoopWithOptForSize")
+              << "runtime SCEV checks needed. Enable vectorization of this "
+                 "loop with '#pragma clang loop vectorize(enable)' when "
+                 "compiling with -Os/-Oz");
+    LLVM_DEBUG(
+        dbgs()
+        << "LV: Aborting. Runtime SCEV check is required with -Os/-Oz.\n");
+    return None;
+  }
+
+  // FIXME: Avoid specializing for stride==1 instead of bailing out.
+  if (!Legal->getLAI()->getSymbolicStrides().empty()) {
+    ORE->emit(createMissedAnalysis("CantVersionLoopWithOptForSize")
+              << "runtime stride == 1 checks needed. Enable vectorization of "
+                 "this loop with '#pragma clang loop vectorize(enable)' when "
+                 "compiling with -Os/-Oz");
+    LLVM_DEBUG(
+        dbgs()
+        << "LV: Aborting. Runtime stride check is required with -Os/-Oz.\n");
+    return None;
+  }
+
   // If we optimize the program for size, avoid creating the tail loop.
   LLVM_DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');