LoopVectorizer: Fix a bug in the vectorization of BinaryOperators. The BinaryOperator can be folded to an Undef, and we don't want to set NSW flags to undef vals.

PR14878

llvm-svn: 172079

2 files changed, 29 insertions, 4 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index cde4bb889e2..4803a9d038c 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1682,13 +1682,13 @@ InnerLoopVectorizer::vectorizeBlockInLoop(LoopVectorizationLegality *Legal,
       for (unsigned Part = 0; Part < UF; ++Part) {
         Value *V = Builder.CreateBinOp(BinOp->getOpcode(), A[Part], B[Part]);
 
-        // Update the NSW, NUW and Exact flags.
-        BinaryOperator *VecOp = cast<BinaryOperator>(V);
-        if (isa<OverflowingBinaryOperator>(BinOp)) {
+        // Update the NSW, NUW and Exact flags. Notice: V can be an Undef.
+        BinaryOperator *VecOp = dyn_cast<BinaryOperator>(V);
+        if (VecOp && isa<OverflowingBinaryOperator>(BinOp)) {
           VecOp->setHasNoSignedWrap(BinOp->hasNoSignedWrap());
           VecOp->setHasNoUnsignedWrap(BinOp->hasNoUnsignedWrap());
         }
-        if (isa<PossiblyExactOperator>(VecOp))
+        if (VecOp && isa<PossiblyExactOperator>(VecOp))
           VecOp->setIsExact(BinOp->isExact());
 
         Entry[Part] = V;
diff --git a/llvm/test/Transforms/LoopVectorize/nsw-crash.ll b/llvm/test/Transforms/LoopVectorize/nsw-crash.ll
new file mode 100644
index 00000000000..e5fad14d0dd
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/nsw-crash.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4
+
+target datalayout =
+"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.7.0"
+
+define void @test() {
+entry:
+  br i1 undef, label %while.end, label %while.body.lr.ph
+
+while.body.lr.ph:
+  br label %while.body
+
+while.body:
+  %it.sroa.0.091 = phi i32* [ undef, %while.body.lr.ph ], [ %incdec.ptr.i, %while.body ]
+  %incdec.ptr.i = getelementptr inbounds i32* %it.sroa.0.091, i64 1
+  %inc32 = add i32 undef, 1                                        ; <------------- Make sure we don't set NSW flags to the undef.
+  %cmp.i11 = icmp eq i32* %incdec.ptr.i, undef
+  br i1 %cmp.i11, label %while.end, label %while.body
+
+while.end:
+  ret void
+}
+
+