1; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -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"
4
5@array = common global [1024 x i32] zeroinitializer, align 16
6
7define void @array_at_plus_one(i32 %n) {
8; CHECK-LABEL: @array_at_plus_one(
9; CHECK: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
10; CHECK: [[VEC_IV_TRUNC:%.+]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %vector.ph ], [ [[VEC_IV_TRUNC_NEXT:%.+]], %vector.body ]
11; CHECK: [[T1:%.+]] = add i64 %index, 0
12; CHECK: [[T2:%.+]] = add nsw i64 [[T1]], 12
13; CHECK-NEXT: [[GEP:%.+]] = getelementptr inbounds [1024 x i32], [1024 x i32]* @array, i64 0, i64 [[T2]]
14; CHECK-NEXT: [[GEP0:%.+]] = getelementptr inbounds i32, i32* [[GEP]], i32 0
15; CHECK-NEXT: [[BC:%.+]] = bitcast i32* [[GEP0]] to <4 x i32>*
16; CHECK-NEXT: store <4 x i32> [[VEC_IV_TRUNC]], <4 x i32>* [[BC]]
17; CHECK: [[VEC_IV_TRUNC_NEXT]] = add <4 x i32> [[VEC_IV_TRUNC]], <i32 4, i32 4, i32 4, i32 4>
18; CHECK: ret void
19;
20entry:
21  br label %loop
22
23loop:
24  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
25  %iv.plus.12 = add nsw i64 %iv, 12
26  %gep = getelementptr inbounds [1024 x i32], [1024 x i32]* @array, i64 0, i64 %iv.plus.12
27  %iv.trunc = trunc i64 %iv to i32
28  store i32 %iv.trunc, i32* %gep, align 4
29  %iv.next = add i64 %iv, 1
30  %lftr.wideiv = trunc i64 %iv.next to i32
31  %exitcond = icmp eq i32 %lftr.wideiv, %n
32  br i1 %exitcond, label %exit, label %loop
33
34exit:
35  ret void
36}
37