[InstCombine] Fix regression introduced at r227197.
This patch fixes a problem I accidentally introduced in an instruction combine
on select instructions added at r227197. That revision taught the instruction
combiner how to fold a cttz/ctlz followed by a icmp plus select into a single
cttz/ctlz with flag 'is_zero_undef' cleared.
However, the new rule added at r227197 would have produced wrong results in the
case where a cttz/ctlz with flag 'is_zero_undef' cleared was follwed by a
zero-extend or truncate. In that case, the folded instruction would have
been inserted in a wrong location thus leaving the CFG in an inconsistent
state.
This patch fixes the problem and add two reproducible test cases to
existing test 'InstCombine/select-cmp-cttz-ctlz.ll'.
llvm-svn: 229124
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
index 0debe63..b92d90d 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -482,16 +482,12 @@
match(Count, m_Intrinsic<Intrinsic::ctlz>(m_Specific(CmpLHS)))) {
IntrinsicInst *II = cast<IntrinsicInst>(Count);
IRBuilder<> Builder(II);
- if (cast<ConstantInt>(II->getArgOperand(1))->isOne()) {
- // Explicitly clear the 'undef_on_zero' flag.
- IntrinsicInst *NewI = cast<IntrinsicInst>(II->clone());
- Type *Ty = NewI->getArgOperand(1)->getType();
- NewI->setArgOperand(1, Constant::getNullValue(Ty));
- Builder.Insert(NewI);
- Count = NewI;
- }
-
- return Builder.CreateZExtOrTrunc(Count, ValueOnZero->getType());
+ // Explicitly clear the 'undef_on_zero' flag.
+ IntrinsicInst *NewI = cast<IntrinsicInst>(II->clone());
+ Type *Ty = NewI->getArgOperand(1)->getType();
+ NewI->setArgOperand(1, Constant::getNullValue(Ty));
+ Builder.Insert(NewI);
+ return Builder.CreateZExtOrTrunc(NewI, ValueOnZero->getType());
}
return nullptr;