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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
|
// RUN: mlir-opt %s -test-transform-dialect-interpreter -split-input-file -canonicalize -cse -verify-diagnostics | FileCheck %s
func.func @reduction_tile(%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%1 = arith.mulf %arg7, %arg7 : f32
%2 = arith.addf %1, %arg9 : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_scf %0
by tile_sizes = [0, 5] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// CHECK-DAG: #[[MAP0:.*]] = affine_map<(d0, d1) -> (d0, d1)>
// CHECK-DAG: #[[MAP1:.*]] = affine_map<(d0, d1) -> (d0)>
// CHECK-DAG: #[[MAP2:.*]] = affine_map<(d0)[s0] -> (-d0 + s0, 5)>
// CHECK: func @reduction_tile(%[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?xf32>
// CHECK-DAG: %[[I:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-DAG: %[[C5:.*]] = arith.constant 5 : index
// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
// CHECK-DAG: %[[D0:.*]] = tensor.dim %[[ARG0]], %[[C0]] : tensor<?x?xf32>
// CHECK-DAG: %[[D1:.*]] = tensor.dim %[[ARG0]], %[[C1]] : tensor<?x?xf32>
// CHECK-DAG: %[[D2:.*]] = tensor.dim %[[ARG1]], %[[C0]] : tensor<?xf32>
// CHECK: %[[E:.*]] = tensor.empty(%[[D2]]) : tensor<?x5xf32>
// CHECK: %[[F:.*]] = linalg.fill ins(%[[I]] : f32) outs(%[[E]] : tensor<?x5xf32>) -> tensor<?x5xf32>
// CHECK: %[[L:.*]] = scf.for %[[K:.*]] = %[[C0]] to %[[D1]] step %[[C5]] iter_args(%[[ARG3:.*]] = %[[F]]) -> (tensor<?x5xf32>) {
// CHECK: %[[PS:.*]] = affine.min #[[MAP2]](%[[K]])[%[[D1]]]
// CHECK: %[[EXT2:.*]] = tensor.extract_slice %[[ARG0]][0, %[[K:.*]]] [%[[D0]], %[[PS]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[EXT:.*]] = tensor.extract_slice %[[ARG3]][0, 0] [%[[D0]], %[[PS]]] [1, 1] : tensor<?x5xf32> to tensor<?x?xf32>
// CHECK: %[[PR:.*]] = linalg.generic {indexing_maps = [#[[MAP0]], #[[MAP0]]], iterator_types = ["parallel", "parallel"]} ins(%[[EXT2]] : tensor<?x?xf32>) outs(%[[EXT]] : tensor<?x?xf32>) {
// CHECK: arith.mulf
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?x?xf32>
// CHECK: %[[D3:.*]] = tensor.dim %[[PR]], %[[C0]] : tensor<?x?xf32>
// CHECK: %[[D4:.*]] = tensor.dim %[[PR]], %[[C1]] : tensor<?x?xf32>
// CHECK: %[[INS:.*]] = tensor.insert_slice %[[PR]] into %[[ARG3]][0, 0] [%[[D3]], %[[D4]]] [1, 1] : tensor<?x?xf32> into tensor<?x5xf32>
// CHECK: scf.yield %[[INS]] : tensor<?x5xf32>
// CHECK: }
// CHECK: %[[R:.*]] = linalg.generic {indexing_maps = [#[[MAP0]], #[[MAP1]]], iterator_types = ["parallel", "reduction"]} ins(%[[L]] : tensor<?x5xf32>) outs(%[[ARG1]] : tensor<?xf32>) {
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?xf32>
// CHECK: return %[[R]] : tensor<?xf32>
// -----
func.func @reduction_tile_transpose(%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d1)>],
iterator_types = ["reduction", "parallel"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%42 = arith.addf %arg7, %arg9 : f32
linalg.yield %42 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_scf %0
by tile_sizes = [5, 0] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// CHECK: func @reduction_tile_transpose
// CHECK: tensor.empty(%{{.*}}) : tensor<5x?xf32>
// CHECK: linalg.fill {{.*}} : tensor<5x?xf32>) -> tensor<5x?xf32>
// CHECK: scf.for
// CHECK: linalg.generic
// CHECK: %[[D3:.*]] = tensor.dim %{{.*}}, %[[C0]] : tensor<?x?xf32>
// CHECK: %[[D4:.*]] = tensor.dim %{{.*}}, %[[C1]] : tensor<?x?xf32>
// CHECK: %[[INS:.*]] = tensor.insert_slice %[[PR]] into %[[ARG3]][0, 0] [%[[D3]], %[[D4]]] [1, 1] : tensor<?x?xf32> into tensor<5x?xf32>
// CHECK: scf.yield {{.*}} : tensor<5x?xf32>
// CHECK: }
// CHECK: linalg.generic
// CHECK: return
// -----
func.func @reduction_tile_parallel(
%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%1 = arith.mulf %arg7, %arg7 : f32
%2 = arith.addf %1, %arg9 : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_forall %0
by num_threads = [0, 5], tile_sizes = [] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// CHECK-DAG: #[[MAP0:.*]] = affine_map<(d0)[s0] -> (-(d0 * (s0 ceildiv 5)) + s0, s0 ceildiv 5)>
// CHECK-DAG: #[[MAP1:.*]] = affine_map<(d0) -> (0, d0)>
// CHECK-DAG: #[[MAP2:.*]] = affine_map<(d0)[s0] -> (d0 * (s0 ceildiv 5))>
// CHECK-DAG: #[[MAP3:.*]] = affine_map<(d0, d1) -> (d0, d1)>
// CHECK-DAG: #[[MAP4:.*]] = affine_map<(d0, d1) -> (d0)>
// CHECK: func @reduction_tile_parallel(%[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?xf32>
// CHECK-DAG: %[[I:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
// CHECK-DAG: %[[D0:.*]] = tensor.dim %[[ARG0]], %[[C0]] : tensor<?x?xf32>
// CHECK-DAG: %[[D1:.*]] = tensor.dim %[[ARG0]], %[[C1]] : tensor<?x?xf32>
// CHECK-DAG: %[[D2:.*]] = tensor.dim %[[ARG1]], %[[C0]] : tensor<?xf32>
// CHECK: %[[E:.*]] = tensor.empty(%[[D2]]) : tensor<?x5xf32>
// CHECK: %[[F:.*]] = linalg.fill ins(%[[I]] : f32) outs(%[[E]] : tensor<?x5xf32>) -> tensor<?x5xf32>
// CHECK: %[[L:.*]] = scf.forall (%[[IV:.+]]) in (5) shared_outs(%[[ARG3:.+]] = %[[F]]) -> (tensor<?x5xf32>) {
// CHECK-DAG: %[[TS0:.+]] = affine.min #[[MAP0]](%[[IV]])[%[[D1]]]
// CHECK-DAG: %[[TS1:.+]] = affine.max #[[MAP1]](%[[TS0]])
// CHECK-DAG: %[[ET:.+]] = tensor.extract_slice %[[ARG3:.+]][0, %[[IV]]] [%[[D0]], 1] [1, 1] : tensor<?x5xf32> to tensor<?xf32>
// CHECK: %[[TINDEX:.+]] = affine.apply #[[MAP2]](%[[IV]])[%[[D1]]]
// CHECK: %[[INCHUNK:.+]] = tensor.extract_slice %[[ARG0]][0, %[[TINDEX]]] [%[[D0]], %[[TS1]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[TEMPEXT:.+]] = tensor.extract_slice %[[ET]][0] [%[[D0]]] [1] : tensor<?xf32> to tensor<?xf32>
// CHECK: %[[PARTIAL:.+]] = linalg.generic {indexing_maps = [#[[MAP3]], #[[MAP4]]], iterator_types = ["parallel", "reduction"]} ins(%[[INCHUNK]] : tensor<?x?xf32>) outs(%[[TEMPEXT]] : tensor<?xf32>) {
// CHECK: arith.mulf
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?xf32>
// CHECK: scf.forall.in_parallel {
// CHECK: tensor.parallel_insert_slice %[[PARTIAL]] into %[[ARG3]][0, %[[IV]]] [%[[D0]], 1] [1, 1] : tensor<?xf32> into tensor<?x5xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[R:.*]] = linalg.generic {indexing_maps = [#[[MAP3]], #[[MAP4]]], iterator_types = ["parallel", "reduction"]} ins(%[[L]] : tensor<?x5xf32>) outs(%[[ARG1]] : tensor<?xf32>) {
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?xf32>
// CHECK: return %[[R]] : tensor<?xf32>
// -----
func.func @matmul_tile_parallel(
%A: tensor<?x?xf32>, %B: tensor<?x?xf32>, %out: tensor<?x?xf32>) -> tensor<?x?xf32> {
%matmul = linalg.matmul ins(%A, %B: tensor<?x?xf32>, tensor<?x?xf32>)
outs(%out: tensor<?x?xf32>) -> tensor<?x?xf32>
return %matmul : tensor<?x?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_forall %0
by num_threads = [0, 0, 5], tile_sizes = [] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// CHECK-DAG: #[[MAP0:.*]] = affine_map<(d0)[s0] -> (-(d0 * (s0 ceildiv 5)) + s0, s0 ceildiv 5)>
// CHECK-DAG: #[[MAP1:.*]] = affine_map<(d0) -> (0, d0)>
// CHECK-DAG: #[[MAP2:.*]] = affine_map<(d0)[s0] -> (d0 * (s0 ceildiv 5))>
// CHECK-DAG: #[[MAP3:.*]] = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
// CHECK-DAG: #[[MAP4:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
// CHECK: func @matmul_tile_parallel(%[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?x?xf32>, %[[ARG2:.+]]: tensor<?x?xf32>
// CHECK-DAG: %[[I:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
// CHECK-DAG: %[[D0:.*]] = tensor.dim %[[ARG0]], %[[C0]] : tensor<?x?xf32>
// CHECK-DAG: %[[D1:.*]] = tensor.dim %[[ARG0]], %[[C1]] : tensor<?x?xf32>
// CHECK-DAG: %[[D2:.*]] = tensor.dim %[[ARG1]], %[[C1]] : tensor<?x?xf32>
// CHECK-DAG: %[[D3:.*]] = tensor.dim %[[ARG2]], %[[C0]] : tensor<?x?xf32>
// CHECK-DAG: %[[D4:.*]] = tensor.dim %[[ARG2]], %[[C1]] : tensor<?x?xf32>
// CHECK: %[[E:.*]] = tensor.empty(%[[D3]], %[[D4]]) : tensor<?x?x5xf32>
// CHECK: %[[F:.*]] = linalg.fill ins(%[[I]] : f32) outs(%[[E]] : tensor<?x?x5xf32>) -> tensor<?x?x5xf32>
// CHECK: %[[L:.*]] = scf.forall (%[[IV:.+]]) in (5) shared_outs(%[[ARG3:.+]] = %[[F]]) -> (tensor<?x?x5xf32>) {
// CHECK-DAG: %[[TS0:.+]] = affine.min #[[MAP0]](%[[IV]])[%[[D1]]]
// CHECK-DAG: %[[TS1:.+]] = affine.max #[[MAP1]](%[[TS0]])
// CHECK-DAG: %[[ET:.+]] = tensor.extract_slice %[[ARG3:.+]][0, 0, %[[IV]]] [%[[D0]], %[[D2]], 1] [1, 1, 1] : tensor<?x?x5xf32> to tensor<?x?xf32>
// CHECK: %[[TINDEX:.+]] = affine.apply #[[MAP2]](%[[IV]])[%[[D1]]]
// CHECK: %[[INCHUNKA:.+]] = tensor.extract_slice %[[ARG0]][0, %[[TINDEX]]] [%[[D0]], %[[TS1]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[INCHUNKB:.+]] = tensor.extract_slice %[[ARG1]][%[[TINDEX]], 0] [%[[TS1]], %[[D2]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[TEMPEXT:.+]] = tensor.extract_slice %[[ET]][0, 0] [%[[D0]], %[[D2]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[PARTIAL:.+]] = linalg.matmul ins(%[[INCHUNKA]], %[[INCHUNKB]] : tensor<?x?xf32>, tensor<?x?xf32>) outs(%[[TEMPEXT]] : tensor<?x?xf32>) -> tensor<?x?xf32>
// CHECK: scf.forall.in_parallel {
// CHECK: tensor.parallel_insert_slice %[[PARTIAL]] into %[[ARG3]][0, 0, %[[IV]]] [%[[D0]], %[[D2]], 1] [1, 1, 1] : tensor<?x?xf32> into tensor<?x?x5xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[R:.*]] = linalg.generic {indexing_maps = [#[[MAP3]], #[[MAP4]]], iterator_types = ["parallel", "parallel", "reduction"]} ins(%[[L]] : tensor<?x?x5xf32>) outs(%[[ARG2]] : tensor<?x?xf32>) {
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?x?xf32>
// CHECK: return %[[R]] : tensor<?x?xf32>
// -----
func.func @reduction_tile_parallel_cyclic_dist(
%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%1 = arith.mulf %arg7, %arg7 : f32
%2 = arith.addf %1, %arg9 : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_forall %0
by num_threads = [0, 5], tile_sizes = [0, 3], mapping = [#gpu.thread<x>] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// CHECK-DAG: #[[MAP0:.*]] = affine_map<()[s0] -> (s0 * 3)>
// CHECK-DAG: #[[MAP1:.*]] = affine_map<(d0)[s0] -> (-d0 + s0, 3)>
// CHECK-DAG: #[[MAP2:.*]] = affine_map<(d0, d1) -> (d0, d1)>
// CHECK-DAG: #[[MAP3:.*]] = affine_map<(d0, d1) -> (d0)>
// CHECK: func @reduction_tile_parallel_cyclic_dist(%[[ARG0:.+]]: tensor<?x?xf32>, %[[ARG1:.+]]: tensor<?xf32>
// CHECK-DAG: %[[I:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
// CHECK-DAG: %[[C15:.*]] = arith.constant 15 : index
// CHECK-DAG: %[[D0:.*]] = tensor.dim %[[ARG0]], %[[C0]] : tensor<?x?xf32>
// CHECK-DAG: %[[D2:.*]] = tensor.dim %[[ARG1]], %[[C0]] : tensor<?xf32>
// CHECK: %[[E:.*]] = tensor.empty(%[[D2]]) : tensor<?x5xf32>
// CHECK: %[[F:.*]] = linalg.fill ins(%[[I]] : f32) outs(%[[E]] : tensor<?x5xf32>) -> tensor<?x5xf32>
// CHECK: %[[L:.*]] = scf.forall (%[[IV:.+]]) in (5) shared_outs(%[[ARG3:.+]] = %[[F]]) -> (tensor<?x5xf32>) {
// CHECK: %[[ET:.+]] = tensor.extract_slice %[[ARG3:.+]][0, %[[IV]]] [%[[D0]], 1] [1, 1] : tensor<?x5xf32> to tensor<?xf32>
// CHECK: %[[D1:.*]] = tensor.dim %[[ARG0]], %[[C1]] : tensor<?x?xf32>
// CHECK: %[[LB:.+]] = affine.apply #[[MAP0]]()[%[[IV]]]
// CHECK: %[[CARRY:.+]] = scf.for %[[IV1:.+]] = %[[LB]] to %[[D1]] step %[[C15]] iter_args(%[[ACC:.+]] = %[[ET]]) -> (tensor<?xf32>) {
// CHECK: %[[TS0:.+]] = affine.min #[[MAP1]](%[[IV1]])[%[[D1]]]
// CHECK: %[[D3:.+]] = tensor.dim %[[ACC]], %[[C0]] : tensor<?xf32>
// CHECK: %[[INCHUNK:.+]] = tensor.extract_slice %[[ARG0]][0, %[[IV1]]] [%[[D0]], %[[TS0]]] [1, 1] : tensor<?x?xf32> to tensor<?x?xf32>
// CHECK: %[[TEMPEXT:.+]] = tensor.extract_slice %[[ACC]][0] [%[[D3]]] [1] : tensor<?xf32> to tensor<?xf32>
// CHECK: %[[PARTIAL:.+]] = linalg.generic {indexing_maps = [#[[MAP2]], #[[MAP3]]], iterator_types = ["parallel", "reduction"]} ins(%[[INCHUNK]] : tensor<?x?xf32>) outs(%[[TEMPEXT]] : tensor<?xf32>) {
// CHECK: arith.mulf
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?xf32>
// CHECK: %[[INS:.+]] = tensor.insert_slice %[[PARTIAL]] into %[[ACC]][0] [%[[D3]]] [1] : tensor<?xf32> into tensor<?xf32>
// CHECK: scf.yield %[[INS]] : tensor<?xf32>
// CHECK: }
// CHECK: scf.forall.in_parallel {
// CHECK: tensor.parallel_insert_slice %[[CARRY]] into %[[ARG3]][0, %[[IV]]] [%[[D0]], 1] [1, 1] : tensor<?xf32> into tensor<?x5xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[R:.*]] = linalg.generic {indexing_maps = [#[[MAP2]], #[[MAP3]]], iterator_types = ["parallel", "reduction"]} ins(%[[L]] : tensor<?x5xf32>) outs(%[[ARG1]] : tensor<?xf32>) {
// CHECK: arith.addf
// CHECK: linalg.yield
// CHECK: } -> tensor<?xf32>
// CHECK: return %[[R]] : tensor<?xf32>
// -----
func.func @reduction_tile_parallel_cyclic_dist(
%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%1 = arith.mulf %arg7, %arg7 : f32
%2 = arith.addf %1, %arg9 : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_forall %0
by num_threads = [0, 5], tile_sizes = [0, 3], mapping = [#gpu.thread<x>] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
// CHECK: expecting fill
// CHECK-NEXT: linalg.fill
transform.print %1 {name = "expecting fill"} : !transform.any_op
// CHECK: expecting parallel reduction
// CHECK-NEXT: linalg.generic
// CHECK: iterator_types = ["parallel", "reduction"]
transform.print %2 {name = "expecting parallel reduction"} : !transform.any_op
// CHECK: expecting parallel reduction
// CHECK-NEXT: linalg.generic
// CHECK: iterator_types = ["parallel", "reduction"]
transform.print %3 {name = "expecting parallel reduction"} : !transform.any_op
}
// -----
func.func @reduction_untiled_forall(
%arg0: tensor<?x?xf32>, %out: tensor<?xf32>) -> tensor<?xf32> {
// expected-note @below {{target operation}}
%red = linalg.generic {indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
affine_map<(d0, d1) -> (d0)>],
iterator_types = ["parallel", "reduction"]}
ins(%arg0 : tensor<?x?xf32>)
outs(%out : tensor<?xf32>) {
^bb0(%arg7: f32, %arg9: f32):
%1 = arith.mulf %arg7, %arg7 : f32
%2 = arith.addf %1, %arg9 : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %red : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg1: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
// expected-error @below {{could not tile reduction}}
%loop, %1, %2, %3 = transform.structured.tile_reduction_using_forall %0
by num_threads = [5], tile_sizes = [3], mapping = [#gpu.thread<x>] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
// -----
#map = affine_map<(d0, d1) -> (d0, d1)>
#map1 = affine_map<(d0, d1) -> (d0)>
module {
func.func @fail_for_float_neutral(%arg0: tensor<?x?xf32>, %arg1: tensor<?xf32>) -> tensor<?xf32> {
// expected-error @below {{'linalg.generic' op Failed to get an identity value for the reduction operation.}}
// expected-note @below {{when applied to this op}}
%0 = linalg.generic {indexing_maps = [#map, #map1], iterator_types = ["parallel", "reduction"]} ins(%arg0 : tensor<?x?xf32>) outs(%arg1 : tensor<?xf32>) {
^bb0(%in: f32, %out: f32):
%1 = llvm.fmul %in, %in : f32
// expected-error @below {{Unknown neutral element for:}}
%2 = llvm.fadd %1, %out : f32
linalg.yield %2 : f32
} -> tensor<?xf32>
return %0 : tensor<?xf32>
}
transform.sequence failures(propagate) {
^bb0(%arg0: !transform.any_op):
%0 = transform.structured.match ops{["linalg.generic"]} in %arg0 : (!transform.any_op) -> !transform.any_op
// expected-error @below {{transform.structured.tile_reduction_using_scf failed to apply}}
%for_op, %fill_op, %split_linalg_op, %combining_linalg_op = transform.structured.tile_reduction_using_scf %0 by tile_sizes = [0, 5] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
}
|
