1 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
2 ; RUN: opt -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -S < %s | FileCheck %s
4 @bar = external global [4 x [4 x i32]], align 4
5 @dct_luma = external global [4 x [4 x i32]], align 4
7 define void @foo() local_unnamed_addr {
10 ; CHECK-NEXT: [[ADD277:%.*]] = add nsw i32 undef, undef
11 ; CHECK-NEXT: store i32 [[ADD277]], i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4
12 ; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4
13 ; CHECK-NEXT: [[ARRAYIDX372:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 0
14 ; CHECK-NEXT: [[ARRAYIDX372_1:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 1
15 ; CHECK-NEXT: [[ARRAYIDX372_2:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 2
16 ; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* bitcast (i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 2) to <2 x i32>*), align 4
17 ; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i32 0
18 ; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[ADD277]], i32 1
19 ; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
20 ; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
21 ; CHECK-NEXT: [[TMP6:%.*]] = add nsw <4 x i32> poison, [[TMP5]]
22 ; CHECK-NEXT: [[TMP7:%.*]] = ashr <4 x i32> [[TMP6]], <i32 6, i32 6, i32 6, i32 6>
23 ; CHECK-NEXT: [[ARRAYIDX372_3:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3
24 ; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[ARRAYIDX372]] to <4 x i32>*
25 ; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4
26 ; CHECK-NEXT: unreachable
29 %add277 = add nsw i32 undef, undef
30 store i32 %add277, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4
31 %0 = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4
32 %sub355 = add nsw i32 undef, %0
33 %shr.i = ashr i32 %sub355, 6
34 %arrayidx372 = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 0
35 store i32 %shr.i, i32* %arrayidx372, align 4
36 %sub355.1 = add nsw i32 undef, %add277
37 %shr.i.1 = ashr i32 %sub355.1, 6
38 %arrayidx372.1 = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 1
39 store i32 %shr.i.1, i32* %arrayidx372.1, align 4
40 %1 = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 2), align 4
41 %sub355.2 = add nsw i32 undef, %1
42 %shr.i.2 = ashr i32 %sub355.2, 6
43 %arrayidx372.2 = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 2
44 store i32 %shr.i.2, i32* %arrayidx372.2, align 4
45 %2 = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 3), align 4
46 %sub355.3 = add nsw i32 undef, %2
47 %shr.i.3 = ashr i32 %sub355.3, 6
48 %arrayidx372.3 = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3
49 store i32 %shr.i.3, i32* %arrayidx372.3, align 4