From: Kyle Butt <kyle+llvm@iteratee.net>
Date: Fri, 8 Jan 2016 01:55:13 +0000 (+0000)
Subject: [Vectorization] Actually return from error case in isStridedPtr
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=505bc5070135483f0700cb04b33ff670efc84816;p=llvm

[Vectorization] Actually return from error case in isStridedPtr

The early return seems to be missed. This causes a radical and wrong loop
optimization on powerpc. It isn't reproducible on x86_64, because
"UseInterleaved" is false.

Patch by Tim Shen.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@257134 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Analysis/LoopAccessAnalysis.cpp b/lib/Analysis/LoopAccessAnalysis.cpp
index d7896ade354..8bcdcb86201 100644
--- a/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/lib/Analysis/LoopAccessAnalysis.cpp
@@ -845,6 +845,7 @@ int llvm::isStridedPtr(PredicatedScalarEvolution &PSE, Value *Ptr,
   if (Lp != AR->getLoop()) {
     DEBUG(dbgs() << "LAA: Bad stride - Not striding over innermost loop " <<
           *Ptr << " SCEV: " << *PtrScev << "\n");
+    return 0;
   }
 
   // The address calculation must not wrap. Otherwise, a dependence could be
diff --git a/test/Analysis/LoopAccessAnalysis/interleave-innermost.ll b/test/Analysis/LoopAccessAnalysis/interleave-innermost.ll
new file mode 100644
index 00000000000..6d8288e8ce3
--- /dev/null
+++ b/test/Analysis/LoopAccessAnalysis/interleave-innermost.ll
@@ -0,0 +1,29 @@
+; RUN: opt -loop-vectorize -force-vector-interleave=1 -S < %s | FileCheck %s
+; CHECK-LABEL: TestFoo
+; CHECK-NOT: %wide.vec
+
+target datalayout = "e-m:e-i64:64-n32:64"
+target triple = "powerpc64le-unknown-linux-gnu"
+
+define void @TestFoo(i1 %X, i1 %Y) {
+bb:
+  br label %.loopexit5.outer
+
+.loopexit5.outer:
+  br label %.lr.ph12
+
+.loopexit:
+  br i1 %X, label %.loopexit5.outer, label %.lr.ph12
+
+.lr.ph12:
+  %f.110 = phi i32* [ %tmp1, %.loopexit ], [ null, %.loopexit5.outer ]
+  %tmp1 = getelementptr inbounds i32, i32* %f.110, i64 -2
+  br i1 %Y, label %bb4, label %.loopexit
+
+bb4:
+  %j.27 = phi i32 [ 0, %.lr.ph12 ], [ %tmp7, %bb4 ]
+  %tmp5 = load i32, i32* %f.110, align 4
+  %tmp7 = add nsw i32 %j.27, 1
+  %exitcond = icmp eq i32 %tmp7, 0
+  br i1 %exitcond, label %.loopexit, label %bb4
+}