1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=aarch64-unknown-linux-gnu -mcpu=cortex-a57 | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c) {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 2
; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[C]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = add nsw <4 x i32> [[TMP3]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = sdiv <4 x i32> [[TMP4]], <i32 2, i32 2, i32 2, i32 2>
; CHECK-NEXT: [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: ret void
;
entry:
%0 = load i32, i32* %b, align 4
%1 = load i32, i32* %c, align 4
%add = add nsw i32 %1, %0
%div = sdiv i32 %add, 2
store i32 %div, i32* %a, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 1
%2 = load i32, i32* %arrayidx3, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %c, i64 1
%3 = load i32, i32* %arrayidx4, align 4
%add5 = add nsw i32 %3, %2
%div6 = sdiv i32 %add5, 2
%arrayidx7 = getelementptr inbounds i32, i32* %a, i64 1
store i32 %div6, i32* %arrayidx7, align 4
%arrayidx8 = getelementptr inbounds i32, i32* %b, i64 2
%4 = load i32, i32* %arrayidx8, align 4
%arrayidx9 = getelementptr inbounds i32, i32* %c, i64 2
%5 = load i32, i32* %arrayidx9, align 4
%add10 = add nsw i32 %5, %4
%div11 = sdiv i32 %add10, 2
%arrayidx12 = getelementptr inbounds i32, i32* %a, i64 2
store i32 %div11, i32* %arrayidx12, align 4
%arrayidx13 = getelementptr inbounds i32, i32* %b, i64 3
%6 = load i32, i32* %arrayidx13, align 4
%arrayidx14 = getelementptr inbounds i32, i32* %c, i64 3
%7 = load i32, i32* %arrayidx14, align 4
%add15 = add nsw i32 %7, %6
%div16 = sdiv i32 %add15, 2
%arrayidx17 = getelementptr inbounds i32, i32* %a, i64 3
store i32 %div16, i32* %arrayidx17, align 4
ret void
}
|