From 41591e7e3004e7ad02a3fdf237866b871288442b Mon Sep 17 00:00:00 2001
From: Michael Zolotukhin <mzolotukhin@apple.com>
Date: Wed, 16 Sep 2015 03:25:09 +0000
Subject: [PATCH 1/1] [Unroll] Fix a bug in UnrolledInstAnalyzer::visitLoad.

We only checked that a global is initialized with constants, which is
incorrect. We should be checking that GlobalVariable *is* a constant,
not just initialized with it.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@247769 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Transforms/Scalar/LoopUnrollPass.cpp      |  2 +-
 .../LoopUnroll/full-unroll-heuristics-2.ll    | 29 +++++++++++++++++++
 2 files changed, 30 insertions(+), 1 deletion(-)
 create mode 100644 test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index 6c510a5f9d9..0e4462618aa 100644
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -415,7 +415,7 @@ private:
     auto *GV = dyn_cast<GlobalVariable>(AddressIt->second.Base);
     // We're only interested in loads that can be completely folded to a
     // constant.
-    if (!GV || !GV->hasInitializer())
+    if (!GV || !GV->hasInitializer() || !GV->isConstant())
       return false;
 
     ConstantDataSequential *CDS =
diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
new file mode 100644
index 00000000000..cd687834fdf
--- /dev/null
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
@@ -0,0 +1,29 @@
+; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=50 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; Though @unknown_global is initialized with constant values, we can't consider
+; it as a constant, so we shouldn't unroll the loop.
+; CHECK: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @unknown_global, i64 0, i64 %iv
+@unknown_global = internal unnamed_addr global [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
+
+define i32 @foo(i32* noalias nocapture readonly %src) {
+entry:
+  br label %loop
+
+loop:                                                ; preds = %loop, %entry
+  %iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
+  %r  = phi i32 [ 0, %entry ], [ %add, %loop ]
+  %arrayidx = getelementptr inbounds i32, i32* %src, i64 %iv
+  %src_element = load i32, i32* %arrayidx, align 4
+  %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @unknown_global, i64 0, i64 %iv
+  %const_array_element = load i32, i32* %array_const_idx, align 4
+  %mul = mul nsw i32 %src_element, %const_array_element
+  %add = add nsw i32 %mul, %r
+  %inc = add nuw nsw i64 %iv, 1
+  %exitcond86.i = icmp eq i64 %inc, 9
+  br i1 %exitcond86.i, label %loop.end, label %loop
+
+loop.end:                                            ; preds = %loop
+  %r.lcssa = phi i32 [ %r, %loop ]
+  ret i32 %r.lcssa
+}
-- 
2.34.1