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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2 -verify-machineinstrs < %s | FileCheck %s
;
; Move Multi-Vector From Tile (Read) x2
;
; Horizontal
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @za_read_horiz_vg2_b(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.b, z1.b }, za0h.b[w12, 0:1]
; CHECK-NEXT: mov { z0.b, z1.b }, za0h.b[w12, 14:15]
; CHECK-NEXT: ret
%res = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg2.nxv16i8(i32 0, i32 %slice)
%slice.14 = add i32 %slice, 14
%res2 = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg2.nxv16i8(i32 0, i32 %slice.14)
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %res2
}
define { <vscale x 8 x i16>, <vscale x 8 x i16> } @za_read_horiz_vg2_h(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0h.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1h.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg2.nxv8i16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg2.nxv8i16(i32 1, i32 %slice.6)
ret { <vscale x 8 x i16>, <vscale x 8 x i16> } %res2
}
define { <vscale x 8 x half>, <vscale x 8 x half> } @za_read_horiz_vg2_f16(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0h.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1h.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg2.nxv8f16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg2.nxv8f16(i32 1, i32 %slice.6)
ret { <vscale x 8 x half>, <vscale x 8 x half> } %res2
}
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @za_read_horiz_vg2_bf16(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0h.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1h.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg2.nxv8bf16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg2.nxv8bf16(i32 1, i32 %slice.6)
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res2
}
define { <vscale x 4 x i32>, <vscale x 4 x i32> } @za_read_horiz_vg2_s(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s, z1.s }, za0h.s[w12, 0:1]
; CHECK-NEXT: mov { z0.s, z1.s }, za3h.s[w12, 2:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.hor.vg2.nxv4i32(i32 0, i32 %slice)
%slice.2 = add i32 %slice, 2
%res2 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.hor.vg2.nxv4i32(i32 3, i32 %slice.2)
ret { <vscale x 4 x i32>, <vscale x 4 x i32> } %res2
}
define { <vscale x 4 x float>, <vscale x 4 x float> } @za_read_horiz_vg2_f32(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s, z1.s }, za0h.s[w12, 0:1]
; CHECK-NEXT: mov { z0.s, z1.s }, za3h.s[w12, 2:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.hor.vg2.nxv4f32(i32 0, i32 %slice)
%slice.2 = add i32 %slice, 2
%res2 = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.hor.vg2.nxv4f32(i32 3, i32 %slice.2)
ret { <vscale x 4 x float>, <vscale x 4 x float> } %res2
}
define { <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_horiz_vg2_d(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za0h.d[w12, 0:1]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.hor.vg2.nxv2i64(i32 0, i32 %slice)
ret { <vscale x 2 x i64>, <vscale x 2 x i64> } %res
}
define { <vscale x 2 x double>, <vscale x 2 x double> } @za_read_horiz_vg2_f64(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg2_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za0h.d[w12, 0:1]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.hor.vg2.nxv2f64(i32 0, i32 %slice)
ret { <vscale x 2 x double>, <vscale x 2 x double> } %res
}
; Vertical
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @za_read_vert_vg2_b(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.b, z1.b }, za0v.b[w12, 0:1]
; CHECK-NEXT: mov { z0.b, z1.b }, za0v.b[w12, 14:15]
; CHECK-NEXT: ret
%res = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg2.nxv16i8(i32 0, i32 %slice)
%slice.14 = add i32 %slice, 14
%res2 = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg2.nxv16i8(i32 0, i32 %slice.14)
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %res2
}
define { <vscale x 8 x i16>, <vscale x 8 x i16> } @za_read_vert_vg2_h(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0v.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1v.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg2.nxv8i16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg2.nxv8i16(i32 1, i32 %slice.6)
ret { <vscale x 8 x i16>, <vscale x 8 x i16> } %res2
}
define { <vscale x 8 x half>, <vscale x 8 x half> } @za_read_vert_vg2_f16(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0v.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1v.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg2.nxv8f16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg2.nxv8f16(i32 1, i32 %slice.6)
ret { <vscale x 8 x half>, <vscale x 8 x half> } %res2
}
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @za_read_vert_vg2_bf16(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h, z1.h }, za0v.h[w12, 0:1]
; CHECK-NEXT: mov { z0.h, z1.h }, za1v.h[w12, 6:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg2.nxv8bf16(i32 0, i32 %slice)
%slice.6 = add i32 %slice, 6
%res2 = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg2.nxv8bf16(i32 1, i32 %slice.6)
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res2
}
define { <vscale x 4 x i32>, <vscale x 4 x i32> } @za_read_vert_vg2_s(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s, z1.s }, za0v.s[w12, 0:1]
; CHECK-NEXT: mov { z0.s, z1.s }, za3v.s[w12, 2:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.ver.vg2.nxv4i32(i32 0, i32 %slice)
%slice.2 = add i32 %slice, 2
%res2 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.ver.vg2.nxv4i32(i32 3, i32 %slice.2)
ret { <vscale x 4 x i32>, <vscale x 4 x i32> } %res2
}
define { <vscale x 4 x float>, <vscale x 4 x float> } @za_read_vert_vg2_f32(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s, z1.s }, za0v.s[w12, 0:1]
; CHECK-NEXT: mov { z0.s, z1.s }, za3v.s[w12, 2:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.ver.vg2.nxv4f32(i32 0, i32 %slice)
%slice.2 = add i32 %slice, 2
%res2 = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.ver.vg2.nxv4f32(i32 3, i32 %slice.2)
ret { <vscale x 4 x float>, <vscale x 4 x float> } %res2
}
define { <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_vert_vg2_d(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za0v.d[w12, 0:1]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.ver.vg2.nxv2i64(i32 0, i32 %slice)
ret { <vscale x 2 x i64>, <vscale x 2 x i64> } %res
}
define { <vscale x 2 x double>, <vscale x 2 x double> } @za_read_vert_vg2_f64(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg2_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za0v.d[w12, 0:1]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.ver.vg2.nxv2f64(i32 0, i32 %slice)
ret { <vscale x 2 x double>, <vscale x 2 x double> } %res
}
;
; Move Multi-Vector From Tile (Read) x4
;
; Horizontal
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @za_read_horiz_vg4_b(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.b - z3.b }, za0h.b[w12, 0:3]
; CHECK-NEXT: mov { z0.b - z3.b }, za0h.b[w12, 12:15]
; CHECK-NEXT: ret
%res = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg4.nxv16i8(i32 0, i32 %slice)
%slice.12 = add i32 %slice, 12
%res2 = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg4.nxv16i8(i32 0, i32 %slice.12)
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %res2
}
define { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @za_read_horiz_vg4_h(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0h.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1h.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg4.nxv8i16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg4.nxv8i16(i32 1, i32 %slice.4)
ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } %res2
}
define { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @za_read_horiz_vg4_f16(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0h.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1h.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg4.nxv8f16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg4.nxv8f16(i32 1, i32 %slice.4)
ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } %res2
}
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @za_read_horiz_vg4_bf16(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0h.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1h.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg4.nxv8bf16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg4.nxv8bf16(i32 1, i32 %slice.4)
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res2
}
define { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @za_read_horiz_vg4_s(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s - z3.s }, za0h.s[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.hor.vg4.nxv4i32(i32 0, i32 %slice)
ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %res
}
define { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @za_read_horiz_vg4_f32(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s - z3.s }, za0h.s[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.hor.vg4.nxv4f32(i32 0, i32 %slice)
ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } %res
}
define { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_horiz_vg4_d(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za0h.d[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.hor.vg4.nxv2i64(i32 0, i32 %slice)
ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } %res
}
define { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @za_read_horiz_vg4_f64(i32 %slice) {
; CHECK-LABEL: za_read_horiz_vg4_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za0h.d[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.hor.vg4.nxv2f64(i32 0, i32 %slice)
ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %res
}
; Vertical
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @za_read_vert_vg4_b(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.b - z3.b }, za0v.b[w12, 0:3]
; CHECK-NEXT: mov { z0.b - z3.b }, za0v.b[w12, 12:15]
; CHECK-NEXT: ret
%res = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg4.nxv16i8(i32 0, i32 %slice)
%slice.12 = add i32 %slice, 12
%res2 = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg4.nxv16i8(i32 0, i32 %slice.12)
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %res2
}
define { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @za_read_vert_vg4_h(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0v.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1v.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg4.nxv8i16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg4.nxv8i16(i32 1, i32 %slice.4)
ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } %res2
}
define { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @za_read_vert_vg4_f16(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0v.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1v.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg4.nxv8f16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg4.nxv8f16(i32 1, i32 %slice.4)
ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } %res2
}
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @za_read_vert_vg4_bf16(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.h - z3.h }, za0v.h[w12, 0:3]
; CHECK-NEXT: mov { z0.h - z3.h }, za1v.h[w12, 4:7]
; CHECK-NEXT: ret
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg4.nxv8bf16(i32 0, i32 %slice)
%slice.4 = add i32 %slice, 4
%res2 = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg4.nxv8bf16(i32 1, i32 %slice.4)
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res2
}
define { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @za_read_vert_vg4_s(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s - z3.s }, za0v.s[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.ver.vg4.nxv4i32(i32 0, i32 %slice)
ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %res
}
define { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @za_read_vert_vg4_f32(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.s - z3.s }, za0v.s[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.ver.vg4.nxv4f32(i32 0, i32 %slice)
ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } %res
}
define { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_vert_vg4_d(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za0v.d[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.ver.vg4.nxv2i64(i32 0, i32 %slice)
ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } %res
}
define { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @za_read_vert_vg4_f64(i32 %slice) {
; CHECK-LABEL: za_read_vert_vg4_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w12, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za0v.d[w12, 0:3]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.ver.vg4.nxv2f64(i32 0, i32 %slice)
ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %res
}
; Move Multi-Vector From ZA (Read) x2
define { <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_vg1x2_d(i32 %slice) {
; CHECK-LABEL: za_read_vg1x2_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za.d[w8, 0, vgx2]
; CHECK-NEXT: mov { z0.d, z1.d }, za.d[w8, 7, vgx2]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x2.nxv2i64(i32 %slice)
%slice.7 = add i32 %slice, 7
%res2 = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x2.nxv2i64(i32 %slice.7)
ret { <vscale x 2 x i64>, <vscale x 2 x i64> } %res2
}
define { <vscale x 2 x double>, <vscale x 2 x double> } @za_read_vg1x2_f64(i32 %slice) {
; CHECK-LABEL: za_read_vg1x2_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, w0
; CHECK-NEXT: mov { z0.d, z1.d }, za.d[w8, 0, vgx2]
; CHECK-NEXT: mov { z0.d, z1.d }, za.d[w8, 7, vgx2]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x2.nxv2f64(i32 %slice)
%slice.7 = add i32 %slice, 7
%res2 = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x2.nxv2f64(i32 %slice.7)
ret { <vscale x 2 x double>, <vscale x 2 x double> } %res2
}
; Move Multi-Vector From ZA (Read) x4
define { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @za_read_vg1x4_d(i32 %slice) {
; CHECK-LABEL: za_read_vg1x4_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za.d[w8, 0, vgx4]
; CHECK-NEXT: mov { z0.d - z3.d }, za.d[w8, 7, vgx4]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x4.nxv2i64(i32 %slice)
%slice.7 = add i32 %slice, 7
%res2 = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x4.nxv2i64(i32 %slice.7)
ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } %res2
}
define { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @za_read_vg1x4_f64(i32 %slice) {
; CHECK-LABEL: za_read_vg1x4_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, w0
; CHECK-NEXT: mov { z0.d - z3.d }, za.d[w8, 0, vgx4]
; CHECK-NEXT: mov { z0.d - z3.d }, za.d[w8, 7, vgx4]
; CHECK-NEXT: ret
%res = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x4.nxv2f64(i32 %slice)
%slice.7 = add i32 %slice, 7
%res2 = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x4.nxv2f64(i32 %slice.7)
ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %res2
}
declare { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg2.nxv16i8(i32, i32)
declare { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg2.nxv8i16(i32, i32)
declare { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg2.nxv8f16(i32, i32)
declare { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg2.nxv8bf16(i32, i32)
declare { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.hor.vg2.nxv4i32(i32, i32)
declare { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.hor.vg2.nxv4f32(i32, i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.hor.vg2.nxv2i64(i32, i32)
declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.hor.vg2.nxv2f64(i32, i32)
declare { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.hor.vg4.nxv16i8(i32, i32)
declare { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.hor.vg4.nxv8i16(i32, i32)
declare { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.hor.vg4.nxv8f16(i32, i32)
declare { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.hor.vg4.nxv8bf16(i32, i32)
declare { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.hor.vg4.nxv4i32(i32, i32)
declare { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.hor.vg4.nxv4f32(i32, i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.hor.vg4.nxv2i64(i32, i32)
declare { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.hor.vg4.nxv2f64(i32, i32)
declare { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg2.nxv16i8(i32, i32)
declare { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg2.nxv8i16(i32, i32)
declare { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg2.nxv8f16(i32, i32)
declare { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg2.nxv8bf16(i32, i32)
declare { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.ver.vg2.nxv4i32(i32, i32)
declare { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.ver.vg2.nxv4f32(i32, i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.ver.vg2.nxv2i64(i32, i32)
declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.ver.vg2.nxv2f64(i32, i32)
declare { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.read.ver.vg4.nxv16i8(i32, i32)
declare { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.read.ver.vg4.nxv8i16(i32, i32)
declare { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.read.ver.vg4.nxv8f16(i32, i32)
declare { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.read.ver.vg4.nxv8bf16(i32, i32)
declare { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.read.ver.vg4.nxv4i32(i32, i32)
declare { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.read.ver.vg4.nxv4f32(i32, i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.ver.vg4.nxv2i64(i32, i32)
declare { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.ver.vg4.nxv2f64(i32, i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x2.nxv2i64(i32)
declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x2.nxv2f64(i32)
declare { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.read.vg1x4.nxv2i64(i32)
declare { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.read.vg1x4.nxv2f64(i32)
|
