1; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -instcombine -S | FileCheck %s
2
3target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
4target triple = "x86_64-apple-macosx10.8.0"
5
6;CHECK-LABEL: @start_at_nonzero(
7;CHECK: mul nuw <4 x i32>
8;CHECK: ret i32
9define i32 @start_at_nonzero(i32* nocapture %a, i32 %start, i32 %end) nounwind uwtable ssp {
10entry:
11  %cmp3 = icmp slt i32 %start, %end
12  br i1 %cmp3, label %for.body.lr.ph, label %for.end
13
14for.body.lr.ph:                                   ; preds = %entry
15  %0 = sext i32 %start to i64
16  br label %for.body
17
18for.body:                                         ; preds = %for.body.lr.ph, %for.body
19  %indvars.iv = phi i64 [ %0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
20  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
21  %1 = load i32* %arrayidx, align 4
22  %mul = mul nuw i32 %1, 333
23  store i32 %mul, i32* %arrayidx, align 4
24  %indvars.iv.next = add i64 %indvars.iv, 1
25  %2 = trunc i64 %indvars.iv.next to i32
26  %cmp = icmp slt i32 %2, %end
27  br i1 %cmp, label %for.body, label %for.end
28
29for.end:                                          ; preds = %for.body, %entry
30  ret i32 4
31}
32