From b0573547f68078ac72d0c0cd639d53fa98f91264 Mon Sep 17 00:00:00 2001
From: Geoff Berry <gberry@codeaurora.org>
Date: Wed, 28 Jun 2017 17:01:15 +0000
Subject: [PATCH] [LoopUnroll] Fix bug in computeUnrollCount causing it to not
 honor MaxCount

Reviewers: sanjoy, anna, reames, apilipenko, igor-laevsky, mkuper

Subscribers: mcrosier, llvm-commits, mzolotukhin

Differential Revision: https://reviews.llvm.org/D34532

llvm-svn: 306564
---
 llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp |  2 ++
 .../Transforms/LoopUnroll/unroll-maxcount.ll  | 31 +++++++++++++++++++
 2 files changed, 33 insertions(+)
 create mode 100644 llvm/test/Transforms/LoopUnroll/unroll-maxcount.ll

diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
index 8bdbb3ff01f0..530a68424d5c 100644
--- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -836,6 +836,8 @@ static bool computeUnrollCount(
     } else {
       UP.Count = TripCount;
     }
+    if (UP.Count > UP.MaxCount)
+      UP.Count = UP.MaxCount;
     if ((PragmaFullUnroll || PragmaEnableUnroll) && TripCount &&
         UP.Count != TripCount)
       ORE->emit(
diff --git a/llvm/test/Transforms/LoopUnroll/unroll-maxcount.ll b/llvm/test/Transforms/LoopUnroll/unroll-maxcount.ll
new file mode 100644
index 000000000000..4cbd757aec22
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/unroll-maxcount.ll
@@ -0,0 +1,31 @@
+; RUN: opt < %s -S -loop-unroll -unroll-allow-partial -unroll-max-count=1 | FileCheck %s
+; Checks that unroll MaxCount is honored.
+;
+; CHECK-LABEL: @foo(
+; CHECK-LABEL: for.body:
+; CHECK-NEXT: phi
+; CHECK-NEXT: getelementptr
+; CHECK-NEXT: load
+; CHECK-NEXT: add
+; CHECK-NEXT: store
+; CHECK-NEXT: add
+; CHECK-NEXT: icmp
+; CHECK-NEXT: br
+define void @foo(i32* nocapture %a) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %inc = add nsw i32 %0, 1
+  store i32 %inc, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+