From ea8327b80f357011a933e8a3f25df7fb556814cd Mon Sep 17 00:00:00 2001
From: Michael Zolotukhin <mzolotukhin@apple.com>
Date: Tue, 2 Dec 2014 22:59:06 +0000
Subject: [PATCH] PR21302. Vectorize only bottom-tested loops.

rdar://problem/18886083

llvm-svn: 223171
---
 llvm/lib/Transforms/Vectorize/LoopVectorize.cpp |  9 +++++++
 llvm/test/Transforms/LoopVectorize/loop-form.ll | 31 +++++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 llvm/test/Transforms/LoopVectorize/loop-form.ll

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 35b2ecf..a73c59b 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3537,6 +3537,15 @@ bool LoopVectorizationLegality::canVectorize() {
     return false;
   }
 
+  // We only handle bottom-tested loops, i.e. loop in which the condition is
+  // checked at the end of each iteration. With that we can assume that all
+  // instructions in the loop are executed the same number of times.
+  if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch()) {
+    emitAnalysis(
+        Report() << "loop control flow is not understood by vectorizer");
+    return false;
+  }
+
   // We need to have a loop header.
   DEBUG(dbgs() << "LV: Found a loop: " <<
         TheLoop->getHeader()->getName() << '\n');
diff --git a/llvm/test/Transforms/LoopVectorize/loop-form.ll b/llvm/test/Transforms/LoopVectorize/loop-form.ll
new file mode 100644
index 0000000..138df1d
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/loop-form.ll
@@ -0,0 +1,31 @@
+; RUN: opt -S -loop-vectorize < %s | FileCheck %s
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; Check that we vectorize only bottom-tested loops.
+; This is a reduced testcase from PR21302.
+;
+; rdar://problem/18886083
+
+%struct.X = type { i32, i16 }
+; CHECK-LABEL: @foo(
+; CHECK-NOT: vector.body
+
+define void @foo(i32 %n) {
+entry:
+  br label %for.cond
+
+for.cond:
+  %i = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %cmp = icmp slt i32 %i, %n
+  br i1 %cmp, label %for.body, label %if.end
+
+for.body:
+  %iprom = sext i32 %i to i64
+  %b = getelementptr inbounds %struct.X* undef, i64 %iprom, i32 1
+  store i16 0, i16* %b, align 4
+  %inc = add nsw i32 %i, 1
+  br label %for.cond
+
+if.end:
+  ret void
+}
-- 
2.7.4