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
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -riscv-v-vector-bits-min=256 -passes='print<cost-model>' -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=256 -passes='print<cost-model>' -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
%V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
%V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
%V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
%V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
%V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
%V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
%V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
%V256 = call i1 @llvm.vector.reduce.and.v256i1(<256 x i1> undef)
%V512 = call i1 @llvm.vector.reduce.and.v512i1(<512 x i1> undef)
%V1024 = call i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1> undef)
ret i32 undef
}
define i32 @reduce_i8(i32 %arg) {
; CHECK-LABEL: 'reduce_i8'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.vector.reduce.and.v2i8(<2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i8 @llvm.vector.reduce.and.v32i8(<32 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i8 @llvm.vector.reduce.and.v64i8(<64 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i8 @llvm.vector.reduce.and.v128i8(<128 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef)
%V2 = call i8 @llvm.vector.reduce.and.v2i8(<2 x i8> undef)
%V4 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)
%V8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef)
%V16 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef)
%V32 = call i8 @llvm.vector.reduce.and.v32i8(<32 x i8> undef)
%V64 = call i8 @llvm.vector.reduce.and.v64i8(<64 x i8> undef)
%V128 = call i8 @llvm.vector.reduce.and.v128i8(<128 x i8> undef)
ret i32 undef
}
define i32 @reduce_i16(i32 %arg) {
; CHECK-LABEL: 'reduce_i16'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i16 @llvm.vector.reduce.and.v1i16(<1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.vector.reduce.and.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.vector.reduce.and.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i16 @llvm.vector.reduce.and.v32i16(<32 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i16 @llvm.vector.reduce.and.v64i16(<64 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i16 @llvm.vector.reduce.and.v128i16(<128 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i16 @llvm.vector.reduce.and.v1i16(<1 x i16> undef)
%V2 = call i16 @llvm.vector.reduce.and.v2i16(<2 x i16> undef)
%V4 = call i16 @llvm.vector.reduce.and.v4i16(<4 x i16> undef)
%V8 = call i16 @llvm.vector.reduce.and.v8i16(<8 x i16> undef)
%V16 = call i16 @llvm.vector.reduce.and.v16i16(<16 x i16> undef)
%V32 = call i16 @llvm.vector.reduce.and.v32i16(<32 x i16> undef)
%V64 = call i16 @llvm.vector.reduce.and.v64i16(<64 x i16> undef)
%V128 = call i16 @llvm.vector.reduce.and.v128i16(<128 x i16> undef)
ret i32 undef
}
define i32 @reduce_i32(i32 %arg) {
; CHECK-LABEL: 'reduce_i32'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i32 @llvm.vector.reduce.and.v1i32(<1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.vector.reduce.and.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i32 @llvm.vector.reduce.and.v16i32(<16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i32 @llvm.vector.reduce.and.v32i32(<32 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64 = call i32 @llvm.vector.reduce.and.v64i32(<64 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128 = call i32 @llvm.vector.reduce.and.v128i32(<128 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i32 @llvm.vector.reduce.and.v1i32(<1 x i32> undef)
%V2 = call i32 @llvm.vector.reduce.and.v2i32(<2 x i32> undef)
%V4 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> undef)
%V8 = call i32 @llvm.vector.reduce.and.v8i32(<8 x i32> undef)
%V16 = call i32 @llvm.vector.reduce.and.v16i32(<16 x i32> undef)
%V32 = call i32 @llvm.vector.reduce.and.v32i32(<32 x i32> undef)
%V64 = call i32 @llvm.vector.reduce.and.v64i32(<64 x i32> undef)
%V128 = call i32 @llvm.vector.reduce.and.v128i32(<128 x i32> undef)
ret i32 undef
}
define i32 @reduce_i64(i32 %arg) {
; CHECK-LABEL: 'reduce_i64'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i64 @llvm.vector.reduce.and.v1i64(<1 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16 = call i64 @llvm.vector.reduce.and.v16i64(<16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32 = call i64 @llvm.vector.reduce.and.v32i64(<32 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V64 = call i64 @llvm.vector.reduce.and.v64i64(<64 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V128 = call i64 @llvm.vector.reduce.and.v128i64(<128 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i64 @llvm.vector.reduce.and.v1i64(<1 x i64> undef)
%V2 = call i64 @llvm.vector.reduce.and.v2i64(<2 x i64> undef)
%V4 = call i64 @llvm.vector.reduce.and.v4i64(<4 x i64> undef)
%V8 = call i64 @llvm.vector.reduce.and.v8i64(<8 x i64> undef)
%V16 = call i64 @llvm.vector.reduce.and.v16i64(<16 x i64> undef)
%V32 = call i64 @llvm.vector.reduce.and.v32i64(<32 x i64> undef)
%V64 = call i64 @llvm.vector.reduce.and.v64i64(<64 x i64> undef)
%V128 = call i64 @llvm.vector.reduce.and.v128i64(<128 x i64> undef)
ret i32 undef
}
declare i1 @llvm.vector.reduce.and.v1i1(<1 x i1>)
declare i1 @llvm.vector.reduce.and.v2i1(<2 x i1>)
declare i1 @llvm.vector.reduce.and.v4i1(<4 x i1>)
declare i1 @llvm.vector.reduce.and.v8i1(<8 x i1>)
declare i1 @llvm.vector.reduce.and.v16i1(<16 x i1>)
declare i1 @llvm.vector.reduce.and.v32i1(<32 x i1>)
declare i1 @llvm.vector.reduce.and.v64i1(<64 x i1>)
declare i1 @llvm.vector.reduce.and.v128i1(<128 x i1>)
declare i1 @llvm.vector.reduce.and.v256i1(<256 x i1>)
declare i1 @llvm.vector.reduce.and.v512i1(<512 x i1>)
declare i1 @llvm.vector.reduce.and.v1024i1(<1024 x i1>)
declare i8 @llvm.vector.reduce.and.v1i8(<1 x i8>)
declare i8 @llvm.vector.reduce.and.v2i8(<2 x i8>)
declare i8 @llvm.vector.reduce.and.v4i8(<4 x i8>)
declare i8 @llvm.vector.reduce.and.v8i8(<8 x i8>)
declare i8 @llvm.vector.reduce.and.v16i8(<16 x i8>)
declare i8 @llvm.vector.reduce.and.v32i8(<32 x i8>)
declare i8 @llvm.vector.reduce.and.v64i8(<64 x i8>)
declare i8 @llvm.vector.reduce.and.v128i8(<128 x i8>)
declare i16 @llvm.vector.reduce.and.v1i16(<1 x i16>)
declare i16 @llvm.vector.reduce.and.v2i16(<2 x i16>)
declare i16 @llvm.vector.reduce.and.v4i16(<4 x i16>)
declare i16 @llvm.vector.reduce.and.v8i16(<8 x i16>)
declare i16 @llvm.vector.reduce.and.v16i16(<16 x i16>)
declare i16 @llvm.vector.reduce.and.v32i16(<32 x i16>)
declare i16 @llvm.vector.reduce.and.v64i16(<64 x i16>)
declare i16 @llvm.vector.reduce.and.v128i16(<128 x i16>)
declare i32 @llvm.vector.reduce.and.v1i32(<1 x i32>)
declare i32 @llvm.vector.reduce.and.v2i32(<2 x i32>)
declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.and.v8i32(<8 x i32>)
declare i32 @llvm.vector.reduce.and.v16i32(<16 x i32>)
declare i32 @llvm.vector.reduce.and.v32i32(<32 x i32>)
declare i32 @llvm.vector.reduce.and.v64i32(<64 x i32>)
declare i32 @llvm.vector.reduce.and.v128i32(<128 x i32>)
declare i64 @llvm.vector.reduce.and.v1i64(<1 x i64>)
declare i64 @llvm.vector.reduce.and.v2i64(<2 x i64>)
declare i64 @llvm.vector.reduce.and.v4i64(<4 x i64>)
declare i64 @llvm.vector.reduce.and.v8i64(<8 x i64>)
declare i64 @llvm.vector.reduce.and.v16i64(<16 x i64>)
declare i64 @llvm.vector.reduce.and.v32i64(<32 x i64>)
declare i64 @llvm.vector.reduce.and.v64i64(<64 x i64>)
declare i64 @llvm.vector.reduce.and.v128i64(<128 x i64>)
|
