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
|
// RUN: mlir-opt %s -split-input-file -allow-unregistered-dialect -pass-pipeline="builtin.module(func.func(linalg-detensorize))" | FileCheck %s
#map0 = affine_map<() -> ()>
#attrs = {
indexing_maps = [#map0, #map0, #map0],
iterator_types = []
}
func.func @main() -> (tensor<i32>) attributes {} {
%c0 = arith.constant 0 : i32
%0 = tensor.from_elements %c0 : tensor<i32>
%c10 = arith.constant 10 : i32
%1 = tensor.from_elements %c10 : tensor<i32>
cf.br ^bb1(%0 : tensor<i32>)
^bb1(%2: tensor<i32>): // 2 preds: ^bb0, ^bb2
%3 = tensor.empty() : tensor<i1>
%4 = linalg.generic #attrs
ins(%2, %1 : tensor<i32>, tensor<i32>)
outs(%3 : tensor<i1>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i1):
%8 = arith.cmpi slt, %arg0, %arg1 : i32
linalg.yield %8 : i1
} -> tensor<i1>
%5 = tensor.extract %4[] : tensor<i1>
cf.cond_br %5, ^bb2(%2 : tensor<i32>), ^bb3(%2 : tensor<i32>)
^bb2(%6: tensor<i32>): // pred: ^bb1
%7 = tensor.empty() : tensor<i32>
%8 = linalg.generic #attrs
ins(%6, %6 : tensor<i32>, tensor<i32>)
outs(%7 : tensor<i32>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i32):
%9 = arith.addi %arg0, %arg1 : i32
linalg.yield %9 : i32
} -> tensor<i32>
cf.br ^bb3(%8 : tensor<i32>)
^bb3(%10: tensor<i32>): // pred: ^bb1
return %10 : tensor<i32>
}
// CHECK-LABEL: func @main()
// CHECK-DAG: arith.constant 0
// CHECK-DAG: arith.constant 10
// CHECK: cf.br ^[[bb1:.*]](%{{.*}}: i32)
// CHECK-NEXT: ^[[bb1]](%{{.*}}: i32):
// CHECK-NEXT: arith.cmpi slt, %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.cond_br %{{.*}}, ^[[bb2:.*]](%{{.*}} : i32), ^bb3(%{{.*}} : i32)
// CHECK-NEXT: ^[[bb2]](%{{.*}}: i32)
// CHECK-NEXT: arith.addi %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.br ^[[bb3:.*]](%{{.*}} : i32)
// CHECK-NEXT: ^[[bb3]](%{{.*}}: i32)
// CHECK-NEXT: tensor.from_elements %{{.*}} : tensor<i32>
// CHECK-NEXT: return %{{.*}}
// CHECK-NEXT: }
// -----
// Similar to the above test with one change: one of the block after the
// if-condition passes/forwards its tensor argument to another block.
#map0 = affine_map<() -> ()>
#attrs = {
indexing_maps = [#map0, #map0, #map0],
iterator_types = []
}
func.func @main() -> (tensor<i32>) attributes {} {
%c0 = arith.constant 0 : i32
%0 = tensor.from_elements %c0 : tensor<i32>
%c10 = arith.constant 10 : i32
%1 = tensor.from_elements %c10 : tensor<i32>
cf.br ^bb1(%0 : tensor<i32>)
^bb1(%2: tensor<i32>): // 2 preds: ^bb0, ^bb2
%3 = tensor.empty() : tensor<i1>
%4 = linalg.generic #attrs
ins(%2, %1 : tensor<i32>, tensor<i32>)
outs(%3 : tensor<i1>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i1):
%8 = arith.cmpi slt, %arg0, %arg1 : i32
linalg.yield %8 : i1
} -> tensor<i1>
%5 = tensor.extract %4[] : tensor<i1>
cf.cond_br %5, ^bb2(%2 : tensor<i32>), ^bb3(%2 : tensor<i32>)
^bb2(%6: tensor<i32>): // pred: ^bb1
%7 = tensor.empty() : tensor<i32>
%8 = linalg.generic #attrs
ins(%6, %6 : tensor<i32>, tensor<i32>)
outs(%7 : tensor<i32>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i32):
%9 = arith.addi %arg0, %arg1 : i32
linalg.yield %9 : i32
} -> tensor<i32>
cf.br ^bb3(%8 : tensor<i32>)
^bb3(%10: tensor<i32>): // pred: ^bb1
cf.br ^bb4(%10 : tensor<i32>)
^bb4(%11: tensor<i32>): // pred: ^bb1
return %11 : tensor<i32>
}
// CHECK-LABEL: func @main()
// CHECK-DAG: arith.constant 0
// CHECK-DAG: arith.constant 10
// CHECK: cf.br ^[[bb1:.*]](%{{.*}}: i32)
// CHECK-NEXT: ^[[bb1]](%{{.*}}: i32):
// CHECK-NEXT: arith.cmpi slt, %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.cond_br %{{.*}}, ^[[bb2:.*]](%{{.*}} : i32), ^bb3(%{{.*}} : i32)
// CHECK-NEXT: ^[[bb2]](%{{.*}}: i32)
// CHECK-NEXT: arith.addi %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.br ^[[bb3:.*]](%{{.*}} : i32)
// CHECK-NEXT: ^[[bb3]](%{{.*}}: i32)
// CHECK-NEXT: cf.br ^[[bb4:.*]](%{{.*}} : i32)
// CHECK-NEXT: ^[[bb4]](%{{.*}}: i32)
// CHECK-NEXT: tensor.from_elements %{{.*}} : tensor<i32>
// CHECK-NEXT: return %{{.*}}
// CHECK-NEXT: }
// -----
#map0 = affine_map<() -> ()>
#attrs = {
indexing_maps = [#map0, #map0, #map0],
iterator_types = []
}
func.func @main() -> (tensor<i32>) attributes {} {
%c0 = arith.constant 0 : i32
%0 = tensor.from_elements %c0 : tensor<i32>
%c10 = arith.constant 10 : i32
%1 = tensor.from_elements %c10 : tensor<i32>
cf.br ^bb1(%0 : tensor<i32>)
^bb1(%2: tensor<i32>): // 2 preds: ^bb0, ^bb2
%3 = tensor.empty() : tensor<i1>
%4 = linalg.generic #attrs
ins(%2, %1 : tensor<i32>, tensor<i32>)
outs(%3 : tensor<i1>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i1):
%8 = arith.cmpi slt, %arg0, %arg1 : i32
linalg.yield %8 : i1
} -> tensor<i1>
%5 = tensor.extract %4[] : tensor<i1>
// This cf.cond_br intentionally has bb2 as it's target for both branches. This
// is to make sure that the "forward phase" of the cost-model correctly adds
// the users of a block argument (in this case bb2's argument) to the work
// list.
cf.cond_br %5, ^bb2(%2 : tensor<i32>), ^bb2(%2 : tensor<i32>)
^bb2(%6: tensor<i32>): // pred: ^bb1
%12 = tensor.from_elements %c10 : tensor<i32>
%7 = tensor.empty() : tensor<i32>
%8 = linalg.generic #attrs
ins(%6, %12 : tensor<i32>, tensor<i32>)
outs(%7 : tensor<i32>) {
^bb0(%arg0: i32, %arg1: i32, %arg2: i32):
%9 = arith.addi %arg0, %arg1 : i32
linalg.yield %9 : i32
} -> tensor<i32>
cf.br ^bb3(%8 : tensor<i32>)
^bb3(%10: tensor<i32>): // pred: ^bb1
return %10 : tensor<i32>
}
// CHECK-LABEL: func @main()
// CHECK-DAG: arith.constant 0
// CHECK-DAG: arith.constant 10
// CHECK: cf.br ^[[bb1:.*]](%{{.*}}: i32)
// CHECK-NEXT: ^[[bb1]](%{{.*}}: i32):
// CHECK-NEXT: arith.cmpi slt, %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.cond_br %{{.*}}, ^[[bb2:.*]](%{{.*}} : i32), ^bb2(%{{.*}} : i32)
// CHECK-NEXT: ^[[bb2]](%{{.*}}: i32)
// CHECK-NEXT: arith.addi %{{.*}}, %{{.*}}
// CHECK-NEXT: cf.br ^[[bb3:.*]](%{{.*}} : i32)
// CHECK-NEXT: ^[[bb3]](%{{.*}}: i32)
// CHECK-NEXT: tensor.from_elements %{{.*}} : tensor<i32>
// CHECK-NEXT: return %{{.*}}
// CHECK-NEXT: }
|
