[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

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');
 

llvm/test/Transforms/LoopVectorize/X86/optsize.ll

@@ -3,6 +3,7 @@
 ; will produce a tail loop with the optimize for size or the minimize size
 ; attributes. This is a target-dependent version of the test.
 ; RUN: opt < %s -loop-vectorize -force-vector-width=64 -S -mtriple=x86_64-unknown-linux -mcpu=skx | FileCheck %s
+; RUN: opt < %s -loop-vectorize -S -mtriple=x86_64-unknown-linux -mcpu=skx | FileCheck %s --check-prefix AUTOVF
 
 target datalayout = "E-m:e-p:32:32-i64:32-f64:32:64-a:0:32-n32-S128"
 
@@ -136,3 +137,62 @@ for.end:                                          ; preds = %for.body
 
 attributes #1 = { minsize }
 
+
+; We can't vectorize this one because we version for stride==1; even having TC
+; a multiple of VF.
+; CHECK-LABEL: @scev4stride1
+; CHECK-NOT: vector.scevcheck
+; CHECK-NOT: vector.body:
+; CHECK-LABEL: for.body:
+; AUTOVF-LABEL: @scev4stride1
+; AUTOVF-NOT: vector.scevcheck
+; AUTOVF-NOT: vector.body:
+; AUTOVF-LABEL: for.body:
+define void @scev4stride1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %k) #2 {
+for.body.preheader:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %mul = mul nsw i32 %i.07, %k
+  %arrayidx = getelementptr inbounds i32, i32* %b, i32 %mul
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %a, i32 %i.07
+  store i32 %0, i32* %arrayidx1, align 4
+  %inc = add nuw nsw i32 %i.07, 1
+  %exitcond = icmp eq i32 %inc, 256
+  br i1 %exitcond, label %for.end.loopexit, label %for.body
+
+for.end.loopexit:                                 ; preds = %for.body
+  ret void
+}
+
+attributes #2 = { optsize }
+
+
+; PR39497
+; We can't vectorize this one because we version for overflow check and tiny
+; trip count leads to opt-for-size (which otherwise could fold the tail by
+; masking).
+; CHECK-LABEL: @main
+; CHECK-NOT: vector.scevcheck
+; CHECK-NOT: vector.body:
+; CHECK-LABEL: for.cond:
+; AUTOVF-LABEL: @main
+; AUTOVF-NOT: vector.scevcheck
+; AUTOVF-NOT: vector.body:
+; AUTOVF-LABEL: for.cond:
+define i32 @main() local_unnamed_addr {
+while.cond:
+  br label %for.cond
+
+for.cond:
+  %d.0 = phi i32 [ 0, %while.cond ], [ %add, %for.cond ]
+  %conv = and i32 %d.0, 65535
+  %cmp = icmp ult i32 %conv, 4
+  %add = add nuw nsw i32 %conv, 1
+  br i1 %cmp, label %for.cond, label %while.cond.loopexit
+
+while.cond.loopexit:
+  ret i32 0
+}

llvm/test/Transforms/LoopVectorize/pr39417-optsize-scevchecks.ll

@@ -0,0 +1,54 @@
+; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+; PR39417
+; Check that the need for overflow check prevents vectorizing a loop with tiny
+; trip count (which implies opt for size).
+; CHECK-LABEL: @func_34
+; CHECK-NOT: vector.scevcheck
+; CHECK-NOT: vector.body:
+; CHECK-LABEL: bb67:
+define void @func_34() {
+bb1:
+  br label %bb67
+
+bb67:
+  %storemerge2 = phi i32 [ 0, %bb1 ], [ %_tmp2300, %bb67 ]
+  %sext = shl i32 %storemerge2, 16
+  %_tmp2299 = ashr exact i32 %sext, 16
+  %_tmp2300 = add nsw i32 %_tmp2299, 1
+  %_tmp2310 = trunc i32 %_tmp2300 to i16
+  %_tmp2312 = icmp slt i16 %_tmp2310, 3
+  br i1 %_tmp2312, label %bb67, label %bb68
+
+bb68:
+  ret void
+}
+
+; Check that the need for stride==1 check prevents vectorizing a loop under opt
+; for size.
+; CHECK-LABEL: @scev4stride1
+; CHECK-NOT: vector.scevcheck
+; CHECK-NOT: vector.body:
+; CHECK-LABEL: for.body:
+define void @scev4stride1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %k) #0 {
+for.body.preheader:
+  br label %for.body
+
+for.body:
+  %i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %mul = mul nsw i32 %i.07, %k
+  %arrayidx = getelementptr inbounds i32, i32* %b, i32 %mul
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %a, i32 %i.07
+  store i32 %0, i32* %arrayidx1, align 4
+  %inc = add nuw nsw i32 %i.07, 1
+  %exitcond = icmp eq i32 %inc, 1024
+  br i1 %exitcond, label %for.end.loopexit, label %for.body
+
+for.end.loopexit:
+  ret void
+}
+
+attributes #0 = { optsize }