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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*%v. = load i32, ptr %in."
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512vl --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefix=AVX512
; REQUIRES: asserts
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i32] zeroinitializer, align 128
@B = global [1024 x i8] zeroinitializer, align 128
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 35 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 75 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; SSE2: LV: Found an estimated cost of 150 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
; SSE2: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 23 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 95 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX1: LV: Found an estimated cost of 190 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX1: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 17 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 17 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 17 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 17 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 17 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX2: LV: Found an estimated cost of 34 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX2: LV: Found an estimated cost of 34 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX2: LV: Found an estimated cost of 34 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX2: LV: Found an estimated cost of 34 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX2: LV: Found an estimated cost of 34 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 2 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 9 for VF 4 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 4 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 18 for VF 8 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 8 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 35 for VF 16 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 16 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 145 for VF 32 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 0 for VF 32 For instruction: %v4 = load i32, ptr %in4, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, ptr %in0, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v1 = load i32, ptr %in1, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v2 = load i32, ptr %in2, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v3 = load i32, ptr %in3, align 4
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v4 = load i32, ptr %in4, align 4
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%iv.0 = add nuw nsw i64 %iv, 0
%iv.1 = add nuw nsw i64 %iv, 1
%iv.2 = add nuw nsw i64 %iv, 2
%iv.3 = add nuw nsw i64 %iv, 3
%iv.4 = add nuw nsw i64 %iv, 4
%in0 = getelementptr inbounds [1024 x i32], ptr @A, i64 0, i64 %iv.0
%in1 = getelementptr inbounds [1024 x i32], ptr @A, i64 0, i64 %iv.1
%in2 = getelementptr inbounds [1024 x i32], ptr @A, i64 0, i64 %iv.2
%in3 = getelementptr inbounds [1024 x i32], ptr @A, i64 0, i64 %iv.3
%in4 = getelementptr inbounds [1024 x i32], ptr @A, i64 0, i64 %iv.4
%v0 = load i32, ptr %in0
%v1 = load i32, ptr %in1
%v2 = load i32, ptr %in2
%v3 = load i32, ptr %in3
%v4 = load i32, ptr %in4
%reduce.add.0 = add i32 %v0, %v1
%reduce.add.1 = add i32 %reduce.add.0, %v2
%reduce.add.2 = add i32 %reduce.add.1, %v3
%reduce.add.3 = add i32 %reduce.add.2, %v4
%reduce.add.3.narrow = trunc i32 %reduce.add.3 to i8
%out = getelementptr inbounds [1024 x i8], ptr @B, i64 0, i64 %iv.0
store i8 %reduce.add.3.narrow, ptr %out
%iv.next = add nuw nsw i64 %iv.0, 5
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
ret void
}
|
