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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-unknown-linux -slp-threshold=-2 | FileCheck %s
define i32 @diamond_broadcast(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0
;
entry:
%ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld
store i32 %mul, i32* %B, align 4
%mul8 = mul i32 %ld, %ld
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %mul8, i32* %arrayidx9, align 4
%mul14 = mul i32 %ld, %ld
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %mul14, i32* %arrayidx15, align 4
%mul20 = mul i32 %ld, undef
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %mul20, i32* %arrayidx21, align 4
ret i32 0
}
define i32 @diamond_broadcast2(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0
;
entry:
%ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld
store i32 %mul, i32* %B, align 4
%mul8 = mul i32 %ld, %ld
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %mul8, i32* %arrayidx9, align 4
%mul14 = mul i32 %ld, %ld
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %mul14, i32* %arrayidx15, align 4
%mul20 = mul i32 undef, %ld
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %mul20, i32* %arrayidx21, align 4
ret i32 0
}
define i32 @diamond_broadcast3(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0
;
entry:
%ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld
store i32 %mul, i32* %B, align 4
%mul8 = mul i32 %ld, %ld
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %mul8, i32* %arrayidx9, align 4
%mul14 = mul i32 %ld, undef
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %mul14, i32* %arrayidx15, align 4
%mul20 = mul i32 undef, %ld
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %mul20, i32* %arrayidx21, align 4
ret i32 0
}
|
