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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target 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"
target triple = "x86_64-apple-macosx10.8.0"
; int foo(int * restrict B, int * restrict A, int n, int m) {
; B[0] = n * A[0] + m * A[0];
; B[1] = n * A[1] + m * A[1];
; B[2] = n * A[2] + m * A[2];
; B[3] = n * A[3] + m * A[3];
; return 0;
; }
define i32 @foo(i32* noalias nocapture %B, i32* noalias nocapture %A, i32 %n, i32 %m) #0 {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[MUL238:%.*]] = add i32 [[M:%.*]], [[N:%.*]]
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[MUL238]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i32> [[TMP1]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* [[TMP4]], align 4
; CHECK-NEXT: ret i32 0
;
entry:
%0 = load i32, i32* %A, align 4
%mul238 = add i32 %m, %n
%add = mul i32 %0, %mul238
store i32 %add, i32* %B, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %A, i64 1
%1 = load i32, i32* %arrayidx4, align 4
%add8 = mul i32 %1, %mul238
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %add8, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %A, i64 2
%2 = load i32, i32* %arrayidx10, align 4
%add14 = mul i32 %2, %mul238
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %add14, i32* %arrayidx15, align 4
%arrayidx16 = getelementptr inbounds i32, i32* %A, i64 3
%3 = load i32, i32* %arrayidx16, align 4
%add20 = mul i32 %3, %mul238
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %add20, i32* %arrayidx21, align 4
ret i32 0
}
; int extr_user(int * restrict B, int * restrict A, int n, int m) {
; B[0] = n * A[0] + m * A[0];
; B[1] = n * A[1] + m * A[1];
; B[2] = n * A[2] + m * A[2];
; B[3] = n * A[3] + m * A[3];
; return A[0];
; }
define i32 @extr_user(i32* noalias nocapture %B, i32* noalias nocapture %A, i32 %n, i32 %m) {
; CHECK-LABEL: @extr_user(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[MUL238:%.*]] = add i32 [[M:%.*]], [[N:%.*]]
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[MUL238]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i32> [[TMP1]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* [[TMP4]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[TMP1]], i32 0
; CHECK-NEXT: ret i32 [[TMP5]]
;
entry:
%0 = load i32, i32* %A, align 4
%mul238 = add i32 %m, %n
%add = mul i32 %0, %mul238
store i32 %add, i32* %B, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %A, i64 1
%1 = load i32, i32* %arrayidx4, align 4
%add8 = mul i32 %1, %mul238
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %add8, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %A, i64 2
%2 = load i32, i32* %arrayidx10, align 4
%add14 = mul i32 %2, %mul238
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %add14, i32* %arrayidx15, align 4
%arrayidx16 = getelementptr inbounds i32, i32* %A, i64 3
%3 = load i32, i32* %arrayidx16, align 4
%add20 = mul i32 %3, %mul238
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %add20, i32* %arrayidx21, align 4
ret i32 %0 ;<--------- This value has multiple users
}
; In this example we have an external user that is not the first element in the vector.
define i32 @extr_user1(i32* noalias nocapture %B, i32* noalias nocapture %A, i32 %n, i32 %m) {
; CHECK-LABEL: @extr_user1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[MUL238:%.*]] = add i32 [[M:%.*]], [[N:%.*]]
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[A]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[MUL238]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i32> [[TMP1]], [[SHUFFLE]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP3]], <4 x i32>* [[TMP4]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[TMP1]], i32 1
; CHECK-NEXT: ret i32 [[TMP5]]
;
entry:
%0 = load i32, i32* %A, align 4
%mul238 = add i32 %m, %n
%add = mul i32 %0, %mul238
store i32 %add, i32* %B, align 4
%arrayidx4 = getelementptr inbounds i32, i32* %A, i64 1
%1 = load i32, i32* %arrayidx4, align 4
%add8 = mul i32 %1, %mul238
%arrayidx9 = getelementptr inbounds i32, i32* %B, i64 1
store i32 %add8, i32* %arrayidx9, align 4
%arrayidx10 = getelementptr inbounds i32, i32* %A, i64 2
%2 = load i32, i32* %arrayidx10, align 4
%add14 = mul i32 %2, %mul238
%arrayidx15 = getelementptr inbounds i32, i32* %B, i64 2
store i32 %add14, i32* %arrayidx15, align 4
%arrayidx16 = getelementptr inbounds i32, i32* %A, i64 3
%3 = load i32, i32* %arrayidx16, align 4
%add20 = mul i32 %3, %mul238
%arrayidx21 = getelementptr inbounds i32, i32* %B, i64 3
store i32 %add20, i32* %arrayidx21, align 4
ret i32 %1 ;<--------- This value has multiple users
}
|
