blob: 3c13718874e7889d6282663dabddbda118d752f2 (
plain)
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
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=armv8a-linux-gnueabihf -mattr=+fp64 -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s --check-prefix=CHECK-V8
; RUN: opt < %s -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s --check-prefix=CHECK-MVEI
define void @and() {
; CHECK-V8-LABEL: 'and'
; CHECK-V8-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.and.v1i64(<1 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 2 for: %v2i64 = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v4i64 = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.and.v2i32(<2 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 4 for: %v4i32 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 5 for: %v8i32 = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.and.v2i16(<2 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i16 = call i16 @llvm.vector.reduce.and.v4i16(<4 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 8 for: %v8i16 = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 9 for: %v16i16 = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.and.v2i8(<2 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 15 for: %v8i8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 16 for: %v16i8 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 17 for: %v32i8 = call i8 @llvm.vector.reduce.and.v32i8(<32 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-MVEI-LABEL: 'and'
; CHECK-MVEI-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.and.v1i64(<1 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 4 for: %v2i64 = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %v4i64 = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.and.v2i32(<2 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i32 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:9 CodeSize:8 Lat:9 SizeLat:9 for: %v8i32 = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.and.v2i16(<2 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:7 CodeSize:5 Lat:7 SizeLat:7 for: %v4i16 = call i16 @llvm.vector.reduce.and.v4i16(<4 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 15 for: %v8i16 = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:17 CodeSize:16 Lat:17 SizeLat:17 for: %v16i16 = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.and.v2i8(<2 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:11 CodeSize:9 Lat:11 SizeLat:11 for: %v8i8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 31 for: %v16i8 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:33 CodeSize:32 Lat:33 SizeLat:33 for: %v32i8 = call i8 @llvm.vector.reduce.and.v32i8(<32 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
entry:
%v1i64 = call i64 @llvm.vector.reduce.and.v1i64(<1 x i64> undef)
%v2i64 = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> undef)
%v4i64 = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> undef)
%v2i32 = call i32 @llvm.vector.reduce.and.v2i32(<2 x i32> undef)
%v4i32 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> undef)
%v8i32 = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> undef)
%v2i16 = call i16 @llvm.vector.reduce.and.v2i16(<2 x i16> undef)
%v4i16 = call i16 @llvm.vector.reduce.and.v4i16(<4 x i16> undef)
%v8i16 = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> undef)
%v16i16 = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> undef)
%v2i8 = call i8 @llvm.vector.reduce.and.v2i8(<2 x i8> undef)
%v4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
%v8i8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
%v16i8 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
%v32i8 = call i8 @llvm.vector.reduce.and.v32i8(<32 x i8> undef)
ret void
}
define void @or() {
; CHECK-V8-LABEL: 'or'
; CHECK-V8-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.or.v1i64(<1 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 2 for: %v2i64 = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v4i64 = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.or.v2i32(<2 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 4 for: %v4i32 = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 5 for: %v8i32 = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.or.v2i16(<2 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i16 = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 8 for: %v8i16 = call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 9 for: %v16i16 = call i16 @llvm.vector.reduce.or.v16i16(<16 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.or.v2i8(<2 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 15 for: %v8i8 = call i8 @llvm.vector.reduce.or.v8i8(<8 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 16 for: %v16i8 = call i8 @llvm.vector.reduce.or.v16i8(<16 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 17 for: %v32i8 = call i8 @llvm.vector.reduce.or.v32i8(<32 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-MVEI-LABEL: 'or'
; CHECK-MVEI-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.or.v1i64(<1 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 4 for: %v2i64 = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %v4i64 = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.or.v2i32(<2 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i32 = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:9 CodeSize:8 Lat:9 SizeLat:9 for: %v8i32 = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.or.v2i16(<2 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:7 CodeSize:5 Lat:7 SizeLat:7 for: %v4i16 = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 15 for: %v8i16 = call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:17 CodeSize:16 Lat:17 SizeLat:17 for: %v16i16 = call i16 @llvm.vector.reduce.or.v16i16(<16 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.or.v2i8(<2 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:11 CodeSize:9 Lat:11 SizeLat:11 for: %v8i8 = call i8 @llvm.vector.reduce.or.v8i8(<8 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 31 for: %v16i8 = call i8 @llvm.vector.reduce.or.v16i8(<16 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:33 CodeSize:32 Lat:33 SizeLat:33 for: %v32i8 = call i8 @llvm.vector.reduce.or.v32i8(<32 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
entry:
%v1i64 = call i64 @llvm.vector.reduce.or.v1i64(<1 x i64> undef)
%v2i64 = call i64 @llvm.vector.reduce.or.v2i64(<2 x i64> undef)
%v4i64 = call i64 @llvm.vector.reduce.or.v4i64(<4 x i64> undef)
%v2i32 = call i32 @llvm.vector.reduce.or.v2i32(<2 x i32> undef)
%v4i32 = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> undef)
%v8i32 = call i32 @llvm.vector.reduce.or.v8i32(<8 x i32> undef)
%v2i16 = call i16 @llvm.vector.reduce.or.v2i16(<2 x i16> undef)
%v4i16 = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> undef)
%v8i16 = call i16 @llvm.vector.reduce.or.v8i16(<8 x i16> undef)
%v16i16 = call i16 @llvm.vector.reduce.or.v16i16(<16 x i16> undef)
%v2i8 = call i8 @llvm.vector.reduce.or.v2i8(<2 x i8> undef)
%v4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef)
%v8i8 = call i8 @llvm.vector.reduce.or.v8i8(<8 x i8> undef)
%v16i8 = call i8 @llvm.vector.reduce.or.v16i8(<16 x i8> undef)
%v32i8 = call i8 @llvm.vector.reduce.or.v32i8(<32 x i8> undef)
ret void
}
define void @xor() {
; CHECK-V8-LABEL: 'xor'
; CHECK-V8-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.xor.v1i64(<1 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 2 for: %v2i64 = call i64 @llvm.vector.reduce.xor.v2i64(<2 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v4i64 = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.xor.v2i32(<2 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 4 for: %v4i32 = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 5 for: %v8i32 = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.xor.v2i16(<2 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i16 = call i16 @llvm.vector.reduce.xor.v4i16(<4 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 8 for: %v8i16 = call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 9 for: %v16i16 = call i16 @llvm.vector.reduce.xor.v16i16(<16 x i16> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.xor.v2i8(<2 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 15 for: %v8i8 = call i8 @llvm.vector.reduce.xor.v8i8(<8 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 16 for: %v16i8 = call i8 @llvm.vector.reduce.xor.v16i8(<16 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of 17 for: %v32i8 = call i8 @llvm.vector.reduce.xor.v32i8(<32 x i8> undef)
; CHECK-V8-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-MVEI-LABEL: 'xor'
; CHECK-MVEI-NEXT: Cost Model: Found costs of 1 for: %v1i64 = call i64 @llvm.vector.reduce.xor.v1i64(<1 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 4 for: %v2i64 = call i64 @llvm.vector.reduce.xor.v2i64(<2 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:6 CodeSize:5 Lat:6 SizeLat:6 for: %v4i64 = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i32 = call i32 @llvm.vector.reduce.xor.v2i32(<2 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i32 = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:9 CodeSize:8 Lat:9 SizeLat:9 for: %v8i32 = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i16 = call i16 @llvm.vector.reduce.xor.v2i16(<2 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:7 CodeSize:5 Lat:7 SizeLat:7 for: %v4i16 = call i16 @llvm.vector.reduce.xor.v4i16(<4 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 15 for: %v8i16 = call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:17 CodeSize:16 Lat:17 SizeLat:17 for: %v16i16 = call i16 @llvm.vector.reduce.xor.v16i16(<16 x i16> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 3 for: %v2i8 = call i8 @llvm.vector.reduce.xor.v2i8(<2 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 7 for: %v4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:11 CodeSize:9 Lat:11 SizeLat:11 for: %v8i8 = call i8 @llvm.vector.reduce.xor.v8i8(<8 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of 31 for: %v16i8 = call i8 @llvm.vector.reduce.xor.v16i8(<16 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:33 CodeSize:32 Lat:33 SizeLat:33 for: %v32i8 = call i8 @llvm.vector.reduce.xor.v32i8(<32 x i8> undef)
; CHECK-MVEI-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
entry:
%v1i64 = call i64 @llvm.vector.reduce.xor.v1i64(<1 x i64> undef)
%v2i64 = call i64 @llvm.vector.reduce.xor.v2i64(<2 x i64> undef)
%v4i64 = call i64 @llvm.vector.reduce.xor.v4i64(<4 x i64> undef)
%v2i32 = call i32 @llvm.vector.reduce.xor.v2i32(<2 x i32> undef)
%v4i32 = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> undef)
%v8i32 = call i32 @llvm.vector.reduce.xor.v8i32(<8 x i32> undef)
%v2i16 = call i16 @llvm.vector.reduce.xor.v2i16(<2 x i16> undef)
%v4i16 = call i16 @llvm.vector.reduce.xor.v4i16(<4 x i16> undef)
%v8i16 = call i16 @llvm.vector.reduce.xor.v8i16(<8 x i16> undef)
%v16i16 = call i16 @llvm.vector.reduce.xor.v16i16(<16 x i16> undef)
%v2i8 = call i8 @llvm.vector.reduce.xor.v2i8(<2 x i8> undef)
%v4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef)
%v8i8 = call i8 @llvm.vector.reduce.xor.v8i8(<8 x i8> undef)
%v16i8 = call i8 @llvm.vector.reduce.xor.v16i8(<16 x i8> undef)
%v32i8 = call i8 @llvm.vector.reduce.xor.v32i8(<32 x i8> undef)
ret void
}
|
