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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
;
; SABA
;
define <vscale x 16 x i8> @saba_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: saba_b:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%b.sext = sext <vscale x 16 x i8> %b to <vscale x 16 x i16>
%c.sext = sext <vscale x 16 x i8> %c to <vscale x 16 x i16>
%sub = sub <vscale x 16 x i16> %b.sext, %c.sext
%abs = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> %sub, i1 true)
%trunc = trunc <vscale x 16 x i16> %abs to <vscale x 16 x i8>
%add = add <vscale x 16 x i8> %a, %trunc
ret <vscale x 16 x i8> %add
}
define <vscale x 16 x i8> @saba_b_promoted_ops(<vscale x 16 x i8> %a, <vscale x 16 x i1> %b, <vscale x 16 x i1> %c) #0 {
; CHECK-LABEL: saba_b_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z1.b, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z2.b, p1/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: saba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%b.sext = sext <vscale x 16 x i1> %b to <vscale x 16 x i8>
%c.sext = sext <vscale x 16 x i1> %c to <vscale x 16 x i8>
%sub = sub <vscale x 16 x i8> %b.sext, %c.sext
%abs = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> %sub, i1 true)
%add = add <vscale x 16 x i8> %a, %abs
ret <vscale x 16 x i8> %add
}
define <vscale x 16 x i8> @saba_b_from_sabd(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: saba_b_from_sabd:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%1 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
%3 = add <vscale x 16 x i8> %2, %a
ret <vscale x 16 x i8> %3
}
define <vscale x 16 x i8> @saba_b_from_sabd_u(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: saba_b_from_sabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%1 = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
%2 = add <vscale x 16 x i8> %1, %a
ret <vscale x 16 x i8> %2
}
define <vscale x 8 x i16> @saba_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: saba_h:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%b.sext = sext <vscale x 8 x i16> %b to <vscale x 8 x i32>
%c.sext = sext <vscale x 8 x i16> %c to <vscale x 8 x i32>
%sub = sub <vscale x 8 x i32> %b.sext, %c.sext
%abs = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> %sub, i1 true)
%trunc = trunc <vscale x 8 x i32> %abs to <vscale x 8 x i16>
%add = add <vscale x 8 x i16> %a, %trunc
ret <vscale x 8 x i16> %add
}
define <vscale x 8 x i16> @saba_h_promoted_ops(<vscale x 8 x i16> %a, <vscale x 8 x i8> %b, <vscale x 8 x i8> %c) #0 {
; CHECK-LABEL: saba_h_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: sxtb z1.h, p0/m, z1.h
; CHECK-NEXT: sxtb z2.h, p0/m, z2.h
; CHECK-NEXT: saba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%b.sext = sext <vscale x 8 x i8> %b to <vscale x 8 x i16>
%c.sext = sext <vscale x 8 x i8> %c to <vscale x 8 x i16>
%sub = sub <vscale x 8 x i16> %b.sext, %c.sext
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
%add = add <vscale x 8 x i16> %a, %abs
ret <vscale x 8 x i16> %add
}
define <vscale x 8 x i16> @saba_h_from_sabd(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: saba_h_from_sabd:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%1 = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
%3 = add <vscale x 8 x i16> %2, %a
ret <vscale x 8 x i16> %3
}
define <vscale x 8 x i16> @saba_h_from_sabd_u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: saba_h_from_sabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%1 = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
%2 = add <vscale x 8 x i16> %1, %a
ret <vscale x 8 x i16> %2
}
define <vscale x 4 x i32> @saba_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: saba_s:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%b.sext = sext <vscale x 4 x i32> %b to <vscale x 4 x i64>
%c.sext = sext <vscale x 4 x i32> %c to <vscale x 4 x i64>
%sub = sub <vscale x 4 x i64> %b.sext, %c.sext
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
%add = add <vscale x 4 x i32> %a, %trunc
ret <vscale x 4 x i32> %add
}
define <vscale x 4 x i32> @saba_s_promoted_ops(<vscale x 4 x i32> %a, <vscale x 4 x i16> %b, <vscale x 4 x i16> %c) #0 {
; CHECK-LABEL: saba_s_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: sxth z1.s, p0/m, z1.s
; CHECK-NEXT: sxth z2.s, p0/m, z2.s
; CHECK-NEXT: saba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%b.sext = sext <vscale x 4 x i16> %b to <vscale x 4 x i32>
%c.sext = sext <vscale x 4 x i16> %c to <vscale x 4 x i32>
%sub = sub <vscale x 4 x i32> %b.sext, %c.sext
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
%add = add <vscale x 4 x i32> %a, %abs
ret <vscale x 4 x i32> %add
}
define <vscale x 4 x i32> @saba_s_from_sabd(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: saba_s_from_sabd:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%1 = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
%3 = add <vscale x 4 x i32> %2, %a
ret <vscale x 4 x i32> %3
}
define <vscale x 4 x i32> @saba_s_from_sabd_u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: saba_s_from_sabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%1 = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
%2 = add <vscale x 4 x i32> %1, %a
ret <vscale x 4 x i32> %2
}
define <vscale x 2 x i64> @saba_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: saba_d:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%b.sext = sext <vscale x 2 x i64> %b to <vscale x 2 x i128>
%c.sext = sext <vscale x 2 x i64> %c to <vscale x 2 x i128>
%sub = sub <vscale x 2 x i128> %b.sext, %c.sext
%abs = call <vscale x 2 x i128> @llvm.abs.nxv2i128(<vscale x 2 x i128> %sub, i1 true)
%trunc = trunc <vscale x 2 x i128> %abs to <vscale x 2 x i64>
%add = add <vscale x 2 x i64> %a, %trunc
ret <vscale x 2 x i64> %add
}
define <vscale x 2 x i64> @saba_d_promoted_ops(<vscale x 2 x i64> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c) #0 {
; CHECK-LABEL: saba_d_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: sxtw z1.d, p0/m, z1.d
; CHECK-NEXT: sxtw z2.d, p0/m, z2.d
; CHECK-NEXT: saba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%b.sext = sext <vscale x 2 x i32> %b to <vscale x 2 x i64>
%c.sext = sext <vscale x 2 x i32> %c to <vscale x 2 x i64>
%sub = sub <vscale x 2 x i64> %b.sext, %c.sext
%abs = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> %sub, i1 true)
%add = add <vscale x 2 x i64> %a, %abs
ret <vscale x 2 x i64> %add
}
define <vscale x 2 x i64> @saba_d_from_sabd(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: saba_d_from_sabd:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%1 = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
%3 = add <vscale x 2 x i64> %2, %a
ret <vscale x 2 x i64> %3
}
define <vscale x 2 x i64> @saba_d_from_sabd_u(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: saba_d_from_sabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: saba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%1 = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
%2 = add <vscale x 2 x i64> %1, %a
ret <vscale x 2 x i64> %2
}
;
; UABA
;
define <vscale x 16 x i8> @uaba_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: uaba_b:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%b.zext = zext <vscale x 16 x i8> %b to <vscale x 16 x i16>
%c.zext = zext <vscale x 16 x i8> %c to <vscale x 16 x i16>
%sub = sub <vscale x 16 x i16> %b.zext, %c.zext
%abs = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> %sub, i1 true)
%trunc = trunc <vscale x 16 x i16> %abs to <vscale x 16 x i8>
%add = add <vscale x 16 x i8> %a, %trunc
ret <vscale x 16 x i8> %add
}
define <vscale x 16 x i8> @uaba_b_promoted_ops(<vscale x 16 x i8> %a, <vscale x 16 x i1> %b, <vscale x 16 x i1> %c) #0 {
; CHECK-LABEL: uaba_b_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z1.b, p0/z, #1 // =0x1
; CHECK-NEXT: mov z2.b, p1/z, #1 // =0x1
; CHECK-NEXT: uaba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%b.zext = zext <vscale x 16 x i1> %b to <vscale x 16 x i8>
%c.zext = zext <vscale x 16 x i1> %c to <vscale x 16 x i8>
%sub = sub <vscale x 16 x i8> %b.zext, %c.zext
%abs = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> %sub, i1 true)
%add = add <vscale x 16 x i8> %a, %abs
ret <vscale x 16 x i8> %add
}
define <vscale x 16 x i8> @uaba_b_from_uabd(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: uaba_b_from_uabd:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%1 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> %1, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
%3 = add <vscale x 16 x i8> %2, %a
ret <vscale x 16 x i8> %3
}
define <vscale x 16 x i8> @uaba_b_from_uabd_u(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) #0 {
; CHECK-LABEL: uaba_b_from_uabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.b, z1.b, z2.b
; CHECK-NEXT: ret
%1 = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
%2 = add <vscale x 16 x i8> %1, %a
ret <vscale x 16 x i8> %2
}
define <vscale x 8 x i16> @uaba_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: uaba_h:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%b.zext = zext <vscale x 8 x i16> %b to <vscale x 8 x i32>
%c.zext = zext <vscale x 8 x i16> %c to <vscale x 8 x i32>
%sub = sub <vscale x 8 x i32> %b.zext, %c.zext
%abs = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> %sub, i1 true)
%trunc = trunc <vscale x 8 x i32> %abs to <vscale x 8 x i16>
%add = add <vscale x 8 x i16> %a, %trunc
ret <vscale x 8 x i16> %add
}
define <vscale x 8 x i16> @uaba_h_promoted_ops(<vscale x 8 x i16> %a, <vscale x 8 x i8> %b, <vscale x 8 x i8> %c) #0 {
; CHECK-LABEL: uaba_h_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: and z1.h, z1.h, #0xff
; CHECK-NEXT: and z2.h, z2.h, #0xff
; CHECK-NEXT: uaba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%b.zext = zext <vscale x 8 x i8> %b to <vscale x 8 x i16>
%c.zext = zext <vscale x 8 x i8> %c to <vscale x 8 x i16>
%sub = sub <vscale x 8 x i16> %b.zext, %c.zext
%abs = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %sub, i1 true)
%add = add <vscale x 8 x i16> %a, %abs
ret <vscale x 8 x i16> %add
}
define <vscale x 8 x i16> @uaba_h_from_uabd(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: uaba_h_from_uabd:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%1 = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> %1, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
%3 = add <vscale x 8 x i16> %2, %a
ret <vscale x 8 x i16> %3
}
define <vscale x 8 x i16> @uaba_h_from_uabd_u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) #0 {
; CHECK-LABEL: uaba_h_from_uabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.h, z1.h, z2.h
; CHECK-NEXT: ret
%1 = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
%2 = add <vscale x 8 x i16> %1, %a
ret <vscale x 8 x i16> %2
}
define <vscale x 4 x i32> @uaba_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: uaba_s:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%b.zext = zext <vscale x 4 x i32> %b to <vscale x 4 x i64>
%c.zext = zext <vscale x 4 x i32> %c to <vscale x 4 x i64>
%sub = sub <vscale x 4 x i64> %b.zext, %c.zext
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
%add = add <vscale x 4 x i32> %a, %trunc
ret <vscale x 4 x i32> %add
}
define <vscale x 4 x i32> @uaba_s_promoted_ops(<vscale x 4 x i32> %a, <vscale x 4 x i16> %b, <vscale x 4 x i16> %c) #0 {
; CHECK-LABEL: uaba_s_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: and z1.s, z1.s, #0xffff
; CHECK-NEXT: and z2.s, z2.s, #0xffff
; CHECK-NEXT: uaba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%b.zext = zext <vscale x 4 x i16> %b to <vscale x 4 x i32>
%c.zext = zext <vscale x 4 x i16> %c to <vscale x 4 x i32>
%sub = sub <vscale x 4 x i32> %b.zext, %c.zext
%abs = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %sub, i1 true)
%add = add <vscale x 4 x i32> %a, %abs
ret <vscale x 4 x i32> %add
}
define <vscale x 4 x i32> @uaba_s_from_uabd(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: uaba_s_from_uabd:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%1 = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> %1, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
%3 = add <vscale x 4 x i32> %2, %a
ret <vscale x 4 x i32> %3
}
define <vscale x 4 x i32> @uaba_s_from_uabd_u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: uaba_s_from_uabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%1 = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
%2 = add <vscale x 4 x i32> %1, %a
ret <vscale x 4 x i32> %2
}
define <vscale x 2 x i64> @uaba_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: uaba_d:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%b.zext = zext <vscale x 2 x i64> %b to <vscale x 2 x i128>
%c.zext = zext <vscale x 2 x i64> %c to <vscale x 2 x i128>
%sub = sub <vscale x 2 x i128> %b.zext, %c.zext
%abs = call <vscale x 2 x i128> @llvm.abs.nxv2i128(<vscale x 2 x i128> %sub, i1 true)
%trunc = trunc <vscale x 2 x i128> %abs to <vscale x 2 x i64>
%add = add <vscale x 2 x i64> %a, %trunc
ret <vscale x 2 x i64> %add
}
define <vscale x 2 x i64> @uaba_d_promoted_ops(<vscale x 2 x i64> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c) #0 {
; CHECK-LABEL: uaba_d_promoted_ops:
; CHECK: // %bb.0:
; CHECK-NEXT: and z1.d, z1.d, #0xffffffff
; CHECK-NEXT: and z2.d, z2.d, #0xffffffff
; CHECK-NEXT: uaba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%b.zext = zext <vscale x 2 x i32> %b to <vscale x 2 x i64>
%c.zext = zext <vscale x 2 x i32> %c to <vscale x 2 x i64>
%sub = sub <vscale x 2 x i64> %b.zext, %c.zext
%abs = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> %sub, i1 true)
%add = add <vscale x 2 x i64> %a, %abs
ret <vscale x 2 x i64> %add
}
define <vscale x 2 x i64> @uaba_d_from_uabd(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: uaba_d_from_uabd:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%1 = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> %1, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
%3 = add <vscale x 2 x i64> %2, %a
ret <vscale x 2 x i64> %3
}
define <vscale x 2 x i64> @uaba_d_from_uabd_u(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) #0 {
; CHECK-LABEL: uaba_d_from_uabd_u:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%1 = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
%2 = add <vscale x 2 x i64> %1, %a
ret <vscale x 2 x i64> %2
}
; A variant of uaba_s but with the add operands switched.
define <vscale x 4 x i32> @uaba_s_commutative(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) #0 {
; CHECK-LABEL: uaba_s_commutative:
; CHECK: // %bb.0:
; CHECK-NEXT: uaba z0.s, z1.s, z2.s
; CHECK-NEXT: ret
%b.zext = zext <vscale x 4 x i32> %b to <vscale x 4 x i64>
%c.zext = zext <vscale x 4 x i32> %c to <vscale x 4 x i64>
%sub = sub <vscale x 4 x i64> %b.zext, %c.zext
%abs = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> %sub, i1 true)
%trunc = trunc <vscale x 4 x i64> %abs to <vscale x 4 x i32>
%add = add <vscale x 4 x i32> %trunc, %a
ret <vscale x 4 x i32> %add
}
declare <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8>, i1)
declare <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16>, i1)
declare <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16>, i1)
declare <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32>, i1)
declare <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32>, i1)
declare <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64>, i1)
declare <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64>, i1)
declare <vscale x 2 x i128> @llvm.abs.nxv2i128(<vscale x 2 x i128>, i1)
declare <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32)
declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32)
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32)
declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32)
declare <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.sabd.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sabd.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sabd.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sabd.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.uabd.u.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uabd.u.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uabd.u.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uabd.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
attributes #0 = { "target-features"="+neon,+sve,+sve2" }
|
