From 0c23f4cf6c8f94d3a678e1cb8683b1a85064ed70 Mon Sep 17 00:00:00 2001
From: Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net>
Date: Fri, 13 Feb 2015 16:33:34 +0000
Subject: [PATCH] [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
---
 .../InstCombine/InstCombineSelect.cpp         | 16 +++++------
 .../InstCombine/select-cmp-cttz-ctlz.ll       | 27 +++++++++++++++++++
 2 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/lib/Transforms/InstCombine/InstCombineSelect.cpp b/lib/Transforms/InstCombine/InstCombineSelect.cpp
index 0debe63faf4..b92d90d0789 100644
--- a/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -482,16 +482,12 @@ static Value *foldSelectCttzCtlz(ICmpInst *ICI, Value *TrueVal, Value *FalseVal,
       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;
diff --git a/test/Transforms/InstCombine/select-cmp-cttz-ctlz.ll b/test/Transforms/InstCombine/select-cmp-cttz-ctlz.ll
index 390e6bc51f8..894bf6db0a4 100644
--- a/test/Transforms/InstCombine/select-cmp-cttz-ctlz.ll
+++ b/test/Transforms/InstCombine/select-cmp-cttz-ctlz.ll
@@ -292,6 +292,33 @@ entry:
   ret i16 %cond
 }
 
+define i64 @select_bug1(i32 %x) {
+; CHECK-LABEL: @select_bug1(
+; CHECK: [[VAR1:%[a-zA-Z0-9]+]] = tail call i32 @llvm.cttz.i32(i32 %x, i1 false)
+; CHECK-NEXT: [[VAR2:%[a-zA-Z0-9]+]] = zext i32 [[VAR1]] to i64
+; CHECK-NEXT: ret i64 [[VAR2]]
+entry:
+  %0 = tail call i32 @llvm.cttz.i32(i32 %x, i1 false)
+  %conv = zext i32 %0 to i64
+  %tobool = icmp ne i32 %x, 0
+  %cond = select i1 %tobool, i64 %conv, i64 32
+  ret i64 %cond
+}
+
+define i16 @select_bug2(i32 %x) {
+; CHECK-LABEL: @select_bug2(
+; CHECK: [[VAR1:%[a-zA-Z0-9]+]] = tail call i32 @llvm.cttz.i32(i32 %x, i1 false)
+; CHECK-NEXT: [[VAR2:%[a-zA-Z0-9]+]] = trunc i32 [[VAR1]] to i16
+; CHECK-NEXT: ret i16 [[VAR2]]
+entry:
+  %0 = tail call i32 @llvm.cttz.i32(i32 %x, i1 false)
+  %conv = trunc i32 %0 to i16
+  %tobool = icmp ne i32 %x, 0
+  %cond = select i1 %tobool, i16 %conv, i16 32
+  ret i16 %cond
+}
+
+
 declare i16 @llvm.ctlz.i16(i16, i1)
 declare i32 @llvm.ctlz.i32(i32, i1)
 declare i64 @llvm.ctlz.i64(i64, i1)