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
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
|
// RUN: mlir-opt %s -sparsification -cse -sparse-vectorization="vl=8" -cse -split-input-file | \
// RUN: FileCheck %s --check-prefix=CHECK-ON
// RUN: mlir-opt %s -sparsification -cse -split-input-file | \
// RUN: FileCheck %s --check-prefix=CHECK-OFF
// -----
// Check that we vectorize reductions with ori.
// CHECK-ON-LABEL: func.func @sparse_reduction_ori(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<i13>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i13> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0> : vector<8xi13>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi13>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i13>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<i13>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.broadcast %[[VAL_9]] : i13 to vector<8xi13>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xi13>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xi13>, vector<8xi1>, vector<8xi13> into vector<8xi13>
// CHECK-ON: %[[VAL_19:.*]] = arith.ori %[[VAL_15]], %[[VAL_18]] : vector<8xi13>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xi13>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xi13>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <or>, %[[VAL_22:.*]] : vector<8xi13> into i13
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<i13>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<i13>
// CHECK-ON: return %[[VAL_23]] : tensor<i13>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_ori(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<i13>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i13> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi13>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i13>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<i13>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (i13) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xi13>
// CHECK-OFF: %[[VAL_14:.*]] = arith.ori %[[VAL_12]], %[[VAL_13]] : i13
// CHECK-OFF: scf.yield %[[VAL_14]] : i13
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<i13>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<i13>
// CHECK-OFF: return %[[VAL_16]] : tensor<i13>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_ori(%argx: tensor<i13>,
%arga: tensor<?xi13, #SparseVector>)
-> tensor<i13> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xi13, #SparseVector>)
outs(%argx: tensor<i13>) {
^bb(%a: i13, %x: i13):
%t = arith.ori %x, %a: i13
linalg.yield %t : i13
} -> tensor<i13>
return %0 : tensor<i13>
}
// -----
// Same test as sparse_reduction_ori except that the accumulator is on the
// rhs of the operation. This checks that we can recognize a reduction
// irrespective to where the accumulator appears on commutative operations.
// CHECK-ON-LABEL: func.func @sparse_reduction_ori_accumulator_on_rhs(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<i13>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i13> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0> : vector<8xi13>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi13>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i13>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<i13>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.broadcast %[[VAL_9]] : i13 to vector<8xi13>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xi13>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xi13>, vector<8xi1>, vector<8xi13> into vector<8xi13>
// CHECK-ON: %[[VAL_19:.*]] = arith.ori %[[VAL_18]], %[[VAL_15]] : vector<8xi13>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xi13>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xi13>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <or>, %[[VAL_22:.*]] : vector<8xi13> into i13
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<i13>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<i13>
// CHECK-ON: return %[[VAL_23]] : tensor<i13>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_ori_accumulator_on_rhs(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<i13>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i13> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi13, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi13>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i13>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<i13>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (i13) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xi13>
// CHECK-OFF: %[[VAL_14:.*]] = arith.ori %[[VAL_13]], %[[VAL_12]] : i13
// CHECK-OFF: scf.yield %[[VAL_14]] : i13
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<i13>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<i13>
// CHECK-OFF: return %[[VAL_16]] : tensor<i13>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_ori_accumulator_on_rhs(%argx: tensor<i13>,
%arga: tensor<?xi13, #SparseVector>)
-> tensor<i13> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xi13, #SparseVector>)
outs(%argx: tensor<i13>) {
^bb(%a: i13, %x: i13):
%t = arith.ori %a, %x: i13
linalg.yield %t : i13
} -> tensor<i13>
return %0 : tensor<i13>
}
// -----
// Check that we vectorize reductions with subi.
//
// CHECK-ON-LABEL: func.func @sparse_reduction_subi(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant dense<0> : vector<8xi32>
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.insertelement %[[VAL_9]], %[[VAL_4]]{{\[}}%[[VAL_3]] : index] : vector<8xi32>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xi32>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_4]] : memref<?xi32>, vector<8xi1>, vector<8xi32> into vector<8xi32>
// CHECK-ON: %[[VAL_19:.*]] = arith.subi %[[VAL_15]], %[[VAL_18]] : vector<8xi32>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xi32>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xi32>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <add>, %[[VAL_22:.*]] : vector<8xi32> into i32
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<i32>
// CHECK-ON: return %[[VAL_23]] : tensor<i32>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_subi(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (i32) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xi32>
// CHECK-OFF: %[[VAL_14:.*]] = arith.subi %[[VAL_12]], %[[VAL_13]] : i32
// CHECK-OFF: scf.yield %[[VAL_14]] : i32
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<i32>
// CHECK-OFF: return %[[VAL_16]] : tensor<i32>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_subi(%argx: tensor<i32>,
%arga: tensor<?xi32, #SparseVector>)
-> tensor<i32> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xi32, #SparseVector>)
outs(%argx: tensor<i32>) {
^bb(%a: i32, %x: i32):
%t = arith.subi %x, %a: i32
linalg.yield %t : i32
} -> tensor<i32>
return %0 : tensor<i32>
}
// -----
// Check that we vectorize reductions with xor.
// CHECK-ON-LABEL: func.func @sparse_reduction_xor(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0> : vector<8xi32>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.insertelement %[[VAL_9]], %[[VAL_3]]{{\[}}%[[VAL_4]] : index] : vector<8xi32>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xi32>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xi32>, vector<8xi1>, vector<8xi32> into vector<8xi32>
// CHECK-ON: %[[VAL_19:.*]] = arith.xori %[[VAL_15]], %[[VAL_18]] : vector<8xi32>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xi32>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xi32>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <xor>, %[[VAL_22:.*]] : vector<8xi32> into i32
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<i32>
// CHECK-ON: return %[[VAL_23]] : tensor<i32>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_xor(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (i32) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xi32>
// CHECK-OFF: %[[VAL_14:.*]] = arith.xori %[[VAL_12]], %[[VAL_13]] : i32
// CHECK-OFF: scf.yield %[[VAL_14]] : i32
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<i32>
// CHECK-OFF: return %[[VAL_16]] : tensor<i32>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_xor(%argx: tensor<i32>,
%arga: tensor<?xi32, #SparseVector>)
-> tensor<i32> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xi32, #SparseVector>)
outs(%argx: tensor<i32>) {
^bb(%a: i32, %x: i32):
%t = arith.xori %x, %a: i32
linalg.yield %t : i32
} -> tensor<i32>
return %0 : tensor<i32>
}
// -----
// Check that we vectorize reductions with addi.
// CHECK-ON-LABEL: func.func @sparse_reduction_addi(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0> : vector<8xi32>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.insertelement %[[VAL_9]], %[[VAL_3]]{{\[}}%[[VAL_4]] : index] : vector<8xi32>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xi32>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xi32>, vector<8xi1>, vector<8xi32> into vector<8xi32>
// CHECK-ON: %[[VAL_19:.*]] = arith.addi %[[VAL_15]], %[[VAL_18]] : vector<8xi32>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xi32>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xi32>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <add>, %[[VAL_22:.*]] : vector<8xi32> into i32
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<i32>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<i32>
// CHECK-ON: return %[[VAL_23]] : tensor<i32>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_addi(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<i32>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<i32> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xi32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xi32>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<i32>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (i32) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xi32>
// CHECK-OFF: %[[VAL_14:.*]] = arith.addi %[[VAL_12]], %[[VAL_13]] : i32
// CHECK-OFF: scf.yield %[[VAL_14]] : i32
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<i32>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<i32>
// CHECK-OFF: return %[[VAL_16]] : tensor<i32>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_addi(%argx: tensor<i32>,
%arga: tensor<?xi32, #SparseVector>)
-> tensor<i32> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xi32, #SparseVector>)
outs(%argx: tensor<i32>) {
^bb(%a: i32, %x: i32):
%t = arith.addi %x, %a: i32
linalg.yield %t : i32
} -> tensor<i32>
return %0 : tensor<i32>
}
// -----
// Check that we vectorize reductions with subf.
// CHECK-ON-LABEL: func.func @sparse_reduction_subf(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<f32>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<f32> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0.000000e+00> : vector<8xf32>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xf32>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<f32>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<f32>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.insertelement %[[VAL_9]], %[[VAL_3]]{{\[}}%[[VAL_4]] : index] : vector<8xf32>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xf32>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xf32>, vector<8xi1>, vector<8xf32> into vector<8xf32>
// CHECK-ON: %[[VAL_19:.*]] = arith.subf %[[VAL_15]], %[[VAL_18]] : vector<8xf32>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xf32>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xf32>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <add>, %[[VAL_22:.*]] : vector<8xf32> into f32
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<f32>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<f32>
// CHECK-ON: return %[[VAL_23]] : tensor<f32>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_subf(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<f32>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<f32> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xf32>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<f32>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<f32>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (f32) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xf32>
// CHECK-OFF: %[[VAL_14:.*]] = arith.subf %[[VAL_12]], %[[VAL_13]] : f32
// CHECK-OFF: scf.yield %[[VAL_14]] : f32
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<f32>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<f32>
// CHECK-OFF: return %[[VAL_16]] : tensor<f32>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_subf(%argx: tensor<f32>,
%arga: tensor<?xf32, #SparseVector>)
-> tensor<f32> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xf32, #SparseVector>)
outs(%argx: tensor<f32>) {
^bb(%a: f32, %x: f32):
%t = arith.subf %x, %a: f32
linalg.yield %t : f32
} -> tensor<f32>
return %0 : tensor<f32>
}
// -----
// Check that we vectorize reductions with addf.
// CHECK-ON-LABEL: func.func @sparse_reduction_addf(
// CHECK-ON-SAME: %[[VAL_0:.*]]: tensor<f32>,
// CHECK-ON-SAME: %[[VAL_1:.*]]: tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<f32> {
// CHECK-ON-DAG: %[[VAL_2:.*]] = arith.constant 8 : index
// CHECK-ON-DAG: %[[VAL_3:.*]] = arith.constant dense<0.000000e+00> : vector<8xf32>
// CHECK-ON-DAG: %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-ON-DAG: %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-ON: %[[VAL_6:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-ON: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xf32>
// CHECK-ON: %[[VAL_8:.*]] = bufferization.to_memref %[[VAL_0]] : memref<f32>
// CHECK-ON: %[[VAL_9:.*]] = memref.load %[[VAL_8]][] : memref<f32>
// CHECK-ON: %[[VAL_10:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK-ON: %[[VAL_11:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK-ON: %[[VAL_12:.*]] = vector.insertelement %[[VAL_9]], %[[VAL_3]]{{\[}}%[[VAL_4]] : index] : vector<8xf32>
// CHECK-ON: %[[VAL_13:.*]] = scf.for %[[VAL_14:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_2]] iter_args(%[[VAL_15:.*]] = %[[VAL_12]]) -> (vector<8xf32>) {
// CHECK-ON: %[[VAL_16:.*]] = affine.min #map(%[[VAL_11]], %[[VAL_14]]){{\[}}%[[VAL_2]]]
// CHECK-ON: %[[VAL_17:.*]] = vector.create_mask %[[VAL_16]] : vector<8xi1>
// CHECK-ON: %[[VAL_18:.*]] = vector.maskedload %[[VAL_7]]{{\[}}%[[VAL_14]]], %[[VAL_17]], %[[VAL_3]] : memref<?xf32>, vector<8xi1>, vector<8xf32> into vector<8xf32>
// CHECK-ON: %[[VAL_19:.*]] = arith.addf %[[VAL_15]], %[[VAL_18]] : vector<8xf32>
// CHECK-ON: %[[VAL_20:.*]] = arith.select %[[VAL_17]], %[[VAL_19]], %[[VAL_15]] : vector<8xi1>, vector<8xf32>
// CHECK-ON: scf.yield %[[VAL_20]] : vector<8xf32>
// CHECK-ON: } {"Emitted from" = "linalg.generic"}
// CHECK-ON: %[[VAL_21:.*]] = vector.reduction <add>, %[[VAL_22:.*]] : vector<8xf32> into f32
// CHECK-ON: memref.store %[[VAL_21]], %[[VAL_8]][] : memref<f32>
// CHECK-ON: %[[VAL_23:.*]] = bufferization.to_tensor %[[VAL_8]] : memref<f32>
// CHECK-ON: return %[[VAL_23]] : tensor<f32>
// CHECK-ON: }
//
// CHECK-OFF-LABEL: func.func @sparse_reduction_addf(
// CHECK-OFF-SAME: %[[VAL_0:.*]]: tensor<f32>,
// CHECK-OFF-SAME: %[[VAL_1:.*]]: tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>>) -> tensor<f32> {
// CHECK-OFF-DAG: %[[VAL_2:.*]] = arith.constant 0 : index
// CHECK-OFF-DAG: %[[VAL_3:.*]] = arith.constant 1 : index
// CHECK-OFF: %[[VAL_4:.*]] = sparse_tensor.positions %[[VAL_1]] {level = 0 : index} : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xindex>
// CHECK-OFF: %[[VAL_5:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?xf32, #sparse_tensor.encoding<{ lvlTypes = [ "compressed" ] }>> to memref<?xf32>
// CHECK-OFF: %[[VAL_6:.*]] = bufferization.to_memref %[[VAL_0]] : memref<f32>
// CHECK-OFF: %[[VAL_7:.*]] = memref.load %[[VAL_6]][] : memref<f32>
// CHECK-OFF: %[[VAL_8:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_9:.*]] = memref.load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK-OFF: %[[VAL_10:.*]] = scf.for %[[VAL_11:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] iter_args(%[[VAL_12:.*]] = %[[VAL_7]]) -> (f32) {
// CHECK-OFF: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xf32>
// CHECK-OFF: %[[VAL_14:.*]] = arith.addf %[[VAL_12]], %[[VAL_13]] : f32
// CHECK-OFF: scf.yield %[[VAL_14]] : f32
// CHECK-OFF: } {"Emitted from" = "linalg.generic"}
// CHECK-OFF: memref.store %[[VAL_15:.*]], %[[VAL_6]][] : memref<f32>
// CHECK-OFF: %[[VAL_16:.*]] = bufferization.to_tensor %[[VAL_6]] : memref<f32>
// CHECK-OFF: return %[[VAL_16]] : tensor<f32>
// CHECK-OFF: }
#SparseVector = #sparse_tensor.encoding<{lvlTypes = ["compressed"]}>
#trait = {
indexing_maps = [
affine_map<(i) -> (i)>, // a (in)
affine_map<(i) -> ()> // x (out)
],
iterator_types = ["reduction"]
}
func.func @sparse_reduction_addf(%argx: tensor<f32>,
%arga: tensor<?xf32, #SparseVector>)
-> tensor<f32> {
%0 = linalg.generic #trait
ins(%arga: tensor<?xf32, #SparseVector>)
outs(%argx: tensor<f32>) {
^bb(%a: f32, %x: f32):
%t = arith.addf %x, %a: f32
linalg.yield %t : f32
} -> tensor<f32>
return %0 : tensor<f32>
}
|
