2 files changed, 74 insertions, 2 deletions
diff --git a/test/Transforms/LoopUnroll/X86/partial.ll b/test/Transforms/LoopUnroll/X86/partial.ll
index 15867cb..a2b04c7 100644
--- a/test/Transforms/LoopUnroll/X86/partial.ll
+++ b/test/Transforms/LoopUnroll/X86/partial.ll
@@ -1,5 +1,5 @@
-; RUN: opt < %s -S -loop-unroll -mcpu=nehalem -x86-use-partial-unrolling=1 | FileCheck %s
-; RUN: opt < %s -S -loop-unroll -mcpu=core -x86-use-partial-unrolling=1 | FileCheck -check-prefix=CHECK-NOUNRL %s
+; RUN: opt < %s -S -loop-unroll -mcpu=nehalem | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -mcpu=core -unroll-runtime=0 | FileCheck -check-prefix=CHECK-NOUNRL %s
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
@@ -76,5 +76,52 @@ for.end:                                          ; preds = %vector.body
   ret void
 }
 
+define zeroext i16 @test1(i16* nocapture readonly %arr, i32 %n) #0 {
+entry:
+  %cmp25 = icmp eq i32 %n, 0
+  br i1 %cmp25, label %for.end, label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %reduction.026 = phi i16 [ %add14, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i16* %arr, i64 %indvars.iv
+  %0 = load i16* %arrayidx, align 2
+  %add = add i16 %0, %reduction.026
+  %sext = mul i64 %indvars.iv, 12884901888
+  %idxprom3 = ashr exact i64 %sext, 32
+  %arrayidx4 = getelementptr inbounds i16* %arr, i64 %idxprom3
+  %1 = load i16* %arrayidx4, align 2
+  %add7 = add i16 %add, %1
+  %sext28 = mul i64 %indvars.iv, 21474836480
+  %idxprom10 = ashr exact i64 %sext28, 32
+  %arrayidx11 = getelementptr inbounds i16* %arr, i64 %idxprom10
+  %2 = load i16* %arrayidx11, align 2
+  %add14 = add i16 %add7, %2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  %reduction.0.lcssa = phi i16 [ 0, %entry ], [ %add14, %for.body ]
+  ret i16 %reduction.0.lcssa
+
+; This loop is too large to be partially unrolled (size=16)
+
+; CHECK-LABEL: @test1
+; CHECK: br
+; CHECK: br
+; CHECK: br
+; CHECK: br
+; CHECK-NOT: br
+
+; CHECK-NOUNRL-LABEL: @test1
+; CHECK-NOUNRL: br
+; CHECK-NOUNRL: br
+; CHECK-NOUNRL: br
+; CHECK-NOUNRL: br
+; CHECK-NOUNRL-NOT: br
+}
+
 attributes #0 = { nounwind uwtable }
 
diff --git a/test/Transforms/LoopUnroll/loop-remarks.ll b/test/Transforms/LoopUnroll/loop-remarks.ll
new file mode 100644
index 0000000..ff3ac17
--- /dev/null
+++ b/test/Transforms/LoopUnroll/loop-remarks.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s -S -loop-unroll -pass-remarks=loop-unroll -unroll-count=16 2>&1 | FileCheck -check-prefix=COMPLETE-UNROLL %s
+; RUN: opt < %s -S -loop-unroll -pass-remarks=loop-unroll -unroll-count=4 2>&1 | FileCheck -check-prefix=PARTIAL-UNROLL %s
+
+; COMPLETE-UNROLL: remark: {{.*}}: completely unrolled loop with 16 iterations
+; PARTIAL-UNROLL: remark: {{.*}}: unrolled loop by a factor of 4
+
+define i32 @sum() {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %s.06 = phi i32 [ 0, %entry ], [ %add1, %for.body ]
+  %i.05 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %add = add nsw i32 %i.05, 4
+  %call = tail call i32 @baz(i32 %add) #2
+  %add1 = add nsw i32 %call, %s.06
+  %inc = add nsw i32 %i.05, 1
+  %exitcond = icmp eq i32 %inc, 16
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret i32 %add1
+}
+
+declare i32 @baz(i32)