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
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64 -mattr=+sve | FileCheck %s
; Float
declare <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f32.nxv2i32(<vscale x 2 x float>)
declare <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f32.nxv4i32(<vscale x 4 x float>)
declare <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f32.nxv8i32(<vscale x 8 x float>)
declare <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f32.nxv4i16(<vscale x 4 x float>)
declare <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f32.nxv8i16(<vscale x 8 x float>)
declare <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f32.nxv2i64(<vscale x 2 x float>)
declare <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f32.nxv4i64(<vscale x 4 x float>)
define <vscale x 2 x i32> @test_signed_v2f32_v2i32(<vscale x 2 x float> %f) {
; CHECK-LABEL: test_signed_v2f32_v2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov w8, #1333788671 // =0x4f7fffff
; CHECK-NEXT: mov z1.s, w8
; CHECK-NEXT: fcmge p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.d, p0/m, z0.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z0.s, z1.s
; CHECK-NEXT: mov z0.d, #0xffffffff
; CHECK-NEXT: mov z2.d, p1/m, #0 // =0x0
; CHECK-NEXT: sel z0.d, p0, z0.d, z2.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f32.nxv2i32(<vscale x 2 x float> %f)
ret <vscale x 2 x i32> %x
}
define <vscale x 4 x i32> @test_signed_v4f32_v4i32(<vscale x 4 x float> %f) {
; CHECK-LABEL: test_signed_v4f32_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #1333788671 // =0x4f7fffff
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: fcmge p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.s, p0/m, z0.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z0.s, z2.s
; CHECK-NEXT: mov z1.s, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.s, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f32.nxv4i32(<vscale x 4 x float> %f)
ret <vscale x 4 x i32> %x
}
define <vscale x 8 x i32> @test_signed_v8f32_v8i32(<vscale x 8 x float> %f) {
; CHECK-LABEL: test_signed_v8f32_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #1333788671 // =0x4f7fffff
; CHECK-NEXT: mov z4.s, w8
; CHECK-NEXT: fcmge p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: fcmge p2.s, p0/z, z1.s, #0.0
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.s, p0/m, z0.s
; CHECK-NEXT: movprfx z3, z1
; CHECK-NEXT: fcvtzu z3.s, p0/m, z1.s
; CHECK-NEXT: fcmgt p3.s, p0/z, z0.s, z4.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z1.s, z4.s
; CHECK-NEXT: mov z2.s, p1/m, #0 // =0x0
; CHECK-NEXT: mov z3.s, p2/m, #0 // =0x0
; CHECK-NEXT: mov z2.s, p3/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z3.s, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z2.d
; CHECK-NEXT: mov z1.d, z3.d
; CHECK-NEXT: ret
%x = call <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f32.nxv8i32(<vscale x 8 x float> %f)
ret <vscale x 8 x i32> %x
}
define <vscale x 4 x i16> @test_signed_v4f32_v4i16(<vscale x 4 x float> %f) {
; CHECK-LABEL: test_signed_v4f32_v4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #65280 // =0xff00
; CHECK-NEXT: movk w8, #18303, lsl #16
; CHECK-NEXT: fcmge p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: mov z1.s, w8
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.s, p0/m, z0.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z0.s, z1.s
; CHECK-NEXT: mov z0.s, #65535 // =0xffff
; CHECK-NEXT: mov z2.s, p1/m, #0 // =0x0
; CHECK-NEXT: sel z0.s, p0, z0.s, z2.s
; CHECK-NEXT: ret
%x = call <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f32.nxv4i16(<vscale x 4 x float> %f)
ret <vscale x 4 x i16> %x
}
define <vscale x 8 x i16> @test_signed_v8f32_v8i16(<vscale x 8 x float> %f) {
; CHECK-LABEL: test_signed_v8f32_v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #65280 // =0xff00
; CHECK-NEXT: movk w8, #18303, lsl #16
; CHECK-NEXT: fcmge p1.s, p0/z, z1.s, #0.0
; CHECK-NEXT: fcmge p2.s, p0/z, z0.s, #0.0
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: movprfx z3, z1
; CHECK-NEXT: fcvtzu z3.s, p0/m, z1.s
; CHECK-NEXT: movprfx z4, z0
; CHECK-NEXT: fcvtzu z4.s, p0/m, z0.s
; CHECK-NEXT: fcmgt p3.s, p0/z, z1.s, z2.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z0.s, z2.s
; CHECK-NEXT: mov z0.s, #65535 // =0xffff
; CHECK-NEXT: mov z3.s, p1/m, #0 // =0x0
; CHECK-NEXT: mov z4.s, p2/m, #0 // =0x0
; CHECK-NEXT: sel z1.s, p3, z0.s, z3.s
; CHECK-NEXT: sel z0.s, p0, z0.s, z4.s
; CHECK-NEXT: uzp1 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%x = call <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f32.nxv8i16(<vscale x 8 x float> %f)
ret <vscale x 8 x i16> %x
}
define <vscale x 2 x i64> @test_signed_v2f32_v2i64(<vscale x 2 x float> %f) {
; CHECK-LABEL: test_signed_v2f32_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov w8, #1602224127 // =0x5f7fffff
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: fcmge p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.d, p0/m, z0.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z0.s, z2.s
; CHECK-NEXT: mov z1.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f32.nxv2i64(<vscale x 2 x float> %f)
ret <vscale x 2 x i64> %x
}
define <vscale x 4 x i64> @test_signed_v4f32_v4i64(<vscale x 4 x float> %f) {
; CHECK-LABEL: test_signed_v4f32_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: uunpklo z2.d, z0.s
; CHECK-NEXT: uunpkhi z3.d, z0.s
; CHECK-NEXT: mov w8, #1602224127 // =0x5f7fffff
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z4.s, w8
; CHECK-NEXT: fcmge p1.s, p0/z, z2.s, #0.0
; CHECK-NEXT: fcmge p2.s, p0/z, z3.s, #0.0
; CHECK-NEXT: movprfx z0, z2
; CHECK-NEXT: fcvtzu z0.d, p0/m, z2.s
; CHECK-NEXT: movprfx z1, z3
; CHECK-NEXT: fcvtzu z1.d, p0/m, z3.s
; CHECK-NEXT: fcmgt p3.s, p0/z, z2.s, z4.s
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.s, p0/z, z3.s, z4.s
; CHECK-NEXT: mov z0.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z0.d, p3/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z1.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ret
%x = call <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f32.nxv4i64(<vscale x 4 x float> %f)
ret <vscale x 4 x i64> %x
}
; Double
declare <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f64.nxv2i32(<vscale x 2 x double>)
declare <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f64.nxv4i32(<vscale x 4 x double>)
declare <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f64.nxv8i32(<vscale x 8 x double>)
declare <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f64.nxv4i16(<vscale x 4 x double>)
declare <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f64.nxv8i16(<vscale x 8 x double>)
declare <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f64.nxv2i64(<vscale x 2 x double>)
declare <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f64.nxv4i64(<vscale x 4 x double>)
define <vscale x 2 x i32> @test_signed_v2f64_v2i32(<vscale x 2 x double> %f) {
; CHECK-LABEL: test_signed_v2f64_v2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #281474974613504 // =0xffffffe00000
; CHECK-NEXT: movk x8, #16879, lsl #48
; CHECK-NEXT: fcmge p1.d, p0/z, z0.d, #0.0
; CHECK-NEXT: mov z1.d, x8
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.d, p0/m, z0.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z0.d, z1.d
; CHECK-NEXT: mov z0.d, #0xffffffff
; CHECK-NEXT: mov z2.d, p1/m, #0 // =0x0
; CHECK-NEXT: sel z0.d, p0, z0.d, z2.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f64.nxv2i32(<vscale x 2 x double> %f)
ret <vscale x 2 x i32> %x
}
define <vscale x 4 x i32> @test_signed_v4f64_v4i32(<vscale x 4 x double> %f) {
; CHECK-LABEL: test_signed_v4f64_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #281474974613504 // =0xffffffe00000
; CHECK-NEXT: movk x8, #16879, lsl #48
; CHECK-NEXT: fcmge p1.d, p0/z, z1.d, #0.0
; CHECK-NEXT: fcmge p2.d, p0/z, z0.d, #0.0
; CHECK-NEXT: mov z2.d, x8
; CHECK-NEXT: movprfx z3, z1
; CHECK-NEXT: fcvtzu z3.d, p0/m, z1.d
; CHECK-NEXT: movprfx z4, z0
; CHECK-NEXT: fcvtzu z4.d, p0/m, z0.d
; CHECK-NEXT: fcmgt p3.d, p0/z, z1.d, z2.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z0.d, z2.d
; CHECK-NEXT: mov z0.d, #0xffffffff
; CHECK-NEXT: mov z3.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z4.d, p2/m, #0 // =0x0
; CHECK-NEXT: sel z1.d, p3, z0.d, z3.d
; CHECK-NEXT: sel z0.d, p0, z0.d, z4.d
; CHECK-NEXT: uzp1 z0.s, z0.s, z1.s
; CHECK-NEXT: ret
%x = call <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f64.nxv4i32(<vscale x 4 x double> %f)
ret <vscale x 4 x i32> %x
}
define <vscale x 8 x i32> @test_signed_v8f64_v8i32(<vscale x 8 x double> %f) {
; CHECK-LABEL: test_signed_v8f64_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: str p6, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: str p5, [sp, #6, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: str p4, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #281474974613504 // =0xffffffe00000
; CHECK-NEXT: movk x8, #16879, lsl #48
; CHECK-NEXT: fcmge p1.d, p0/z, z1.d, #0.0
; CHECK-NEXT: fcmge p2.d, p0/z, z0.d, #0.0
; CHECK-NEXT: fcmge p3.d, p0/z, z3.d, #0.0
; CHECK-NEXT: fcmge p4.d, p0/z, z2.d, #0.0
; CHECK-NEXT: movprfx z5, z1
; CHECK-NEXT: fcvtzu z5.d, p0/m, z1.d
; CHECK-NEXT: mov z4.d, x8
; CHECK-NEXT: movprfx z6, z0
; CHECK-NEXT: fcvtzu z6.d, p0/m, z0.d
; CHECK-NEXT: movprfx z7, z3
; CHECK-NEXT: fcvtzu z7.d, p0/m, z3.d
; CHECK-NEXT: movprfx z24, z2
; CHECK-NEXT: fcvtzu z24.d, p0/m, z2.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p5.d, p0/z, z1.d, z4.d
; CHECK-NEXT: fcmgt p6.d, p0/z, z0.d, z4.d
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: mov z0.d, #0xffffffff
; CHECK-NEXT: not p3.b, p0/z, p3.b
; CHECK-NEXT: mov z5.d, p1/m, #0 // =0x0
; CHECK-NEXT: fcmgt p1.d, p0/z, z3.d, z4.d
; CHECK-NEXT: not p4.b, p0/z, p4.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z2.d, z4.d
; CHECK-NEXT: mov z6.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z7.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z24.d, p4/m, #0 // =0x0
; CHECK-NEXT: sel z1.d, p5, z0.d, z5.d
; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z2.d, p6, z0.d, z6.d
; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z0.d, z7.d
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z4.d, p0, z0.d, z24.d
; CHECK-NEXT: uzp1 z0.s, z2.s, z1.s
; CHECK-NEXT: uzp1 z1.s, z4.s, z3.s
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%x = call <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f64.nxv8i32(<vscale x 8 x double> %f)
ret <vscale x 8 x i32> %x
}
define <vscale x 4 x i16> @test_signed_v4f64_v4i16(<vscale x 4 x double> %f) {
; CHECK-LABEL: test_signed_v4f64_v4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #281337537757184 // =0xffe000000000
; CHECK-NEXT: movk x8, #16623, lsl #48
; CHECK-NEXT: fcmge p1.d, p0/z, z1.d, #0.0
; CHECK-NEXT: fcmge p2.d, p0/z, z0.d, #0.0
; CHECK-NEXT: mov z2.d, x8
; CHECK-NEXT: movprfx z3, z1
; CHECK-NEXT: fcvtzu z3.d, p0/m, z1.d
; CHECK-NEXT: movprfx z4, z0
; CHECK-NEXT: fcvtzu z4.d, p0/m, z0.d
; CHECK-NEXT: fcmgt p3.d, p0/z, z1.d, z2.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z0.d, z2.d
; CHECK-NEXT: mov z0.d, #65535 // =0xffff
; CHECK-NEXT: mov z3.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z4.d, p2/m, #0 // =0x0
; CHECK-NEXT: sel z1.d, p3, z0.d, z3.d
; CHECK-NEXT: sel z0.d, p0, z0.d, z4.d
; CHECK-NEXT: uzp1 z0.s, z0.s, z1.s
; CHECK-NEXT: ret
%x = call <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f64.nxv4i16(<vscale x 4 x double> %f)
ret <vscale x 4 x i16> %x
}
define <vscale x 8 x i16> @test_signed_v8f64_v8i16(<vscale x 8 x double> %f) {
; CHECK-LABEL: test_signed_v8f64_v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: str p6, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: str p5, [sp, #6, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: str p4, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #281337537757184 // =0xffe000000000
; CHECK-NEXT: movk x8, #16623, lsl #48
; CHECK-NEXT: fcmge p1.d, p0/z, z3.d, #0.0
; CHECK-NEXT: fcmge p2.d, p0/z, z2.d, #0.0
; CHECK-NEXT: fcmge p3.d, p0/z, z1.d, #0.0
; CHECK-NEXT: fcmge p4.d, p0/z, z0.d, #0.0
; CHECK-NEXT: movprfx z5, z3
; CHECK-NEXT: fcvtzu z5.d, p0/m, z3.d
; CHECK-NEXT: mov z4.d, x8
; CHECK-NEXT: movprfx z6, z2
; CHECK-NEXT: fcvtzu z6.d, p0/m, z2.d
; CHECK-NEXT: movprfx z7, z1
; CHECK-NEXT: fcvtzu z7.d, p0/m, z1.d
; CHECK-NEXT: movprfx z24, z0
; CHECK-NEXT: fcvtzu z24.d, p0/m, z0.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p5.d, p0/z, z3.d, z4.d
; CHECK-NEXT: fcmgt p6.d, p0/z, z2.d, z4.d
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: mov z2.d, #65535 // =0xffff
; CHECK-NEXT: not p3.b, p0/z, p3.b
; CHECK-NEXT: mov z5.d, p1/m, #0 // =0x0
; CHECK-NEXT: fcmgt p1.d, p0/z, z1.d, z4.d
; CHECK-NEXT: not p4.b, p0/z, p4.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z0.d, z4.d
; CHECK-NEXT: mov z6.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z7.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z24.d, p4/m, #0 // =0x0
; CHECK-NEXT: sel z0.d, p5, z2.d, z5.d
; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z1.d, p6, z2.d, z6.d
; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z2.d, z7.d
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z2.d, p0, z2.d, z24.d
; CHECK-NEXT: uzp1 z0.s, z1.s, z0.s
; CHECK-NEXT: uzp1 z1.s, z2.s, z3.s
; CHECK-NEXT: uzp1 z0.h, z1.h, z0.h
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%x = call <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f64.nxv8i16(<vscale x 8 x double> %f)
ret <vscale x 8 x i16> %x
}
define <vscale x 2 x i64> @test_signed_v2f64_v2i64(<vscale x 2 x double> %f) {
; CHECK-LABEL: test_signed_v2f64_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #4895412794951729151 // =0x43efffffffffffff
; CHECK-NEXT: mov z2.d, x8
; CHECK-NEXT: fcmge p1.d, p0/z, z0.d, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.d, p0/m, z0.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z0.d, z2.d
; CHECK-NEXT: mov z1.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f64.nxv2i64(<vscale x 2 x double> %f)
ret <vscale x 2 x i64> %x
}
define <vscale x 4 x i64> @test_signed_v4f64_v4i64(<vscale x 4 x double> %f) {
; CHECK-LABEL: test_signed_v4f64_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov x8, #4895412794951729151 // =0x43efffffffffffff
; CHECK-NEXT: mov z4.d, x8
; CHECK-NEXT: fcmge p1.d, p0/z, z0.d, #0.0
; CHECK-NEXT: fcmge p2.d, p0/z, z1.d, #0.0
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.d, p0/m, z0.d
; CHECK-NEXT: movprfx z3, z1
; CHECK-NEXT: fcvtzu z3.d, p0/m, z1.d
; CHECK-NEXT: fcmgt p3.d, p0/z, z0.d, z4.d
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.d, p0/z, z1.d, z4.d
; CHECK-NEXT: mov z2.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z3.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z2.d, p3/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z3.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z2.d
; CHECK-NEXT: mov z1.d, z3.d
; CHECK-NEXT: ret
%x = call <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f64.nxv4i64(<vscale x 4 x double> %f)
ret <vscale x 4 x i64> %x
}
; half
declare <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f16.nxv2i32(<vscale x 2 x half>)
declare <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f16.nxv4i32(<vscale x 4 x half>)
declare <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f16.nxv8i32(<vscale x 8 x half>)
declare <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f16.nxv4i16(<vscale x 4 x half>)
declare <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f16.nxv8i16(<vscale x 8 x half>)
declare <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f16.nxv2i64(<vscale x 2 x half>)
declare <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f16.nxv4i64(<vscale x 4 x half>)
define <vscale x 2 x i32> @test_signed_v2f16_v2i32(<vscale x 2 x half> %f) {
; CHECK-LABEL: test_signed_v2f16_v2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: mov z1.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z0.h, #0.0
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.d, p0/m, z0.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z0.h, z1.h
; CHECK-NEXT: mov z0.d, #0xffffffff
; CHECK-NEXT: mov z2.d, p1/m, #0 // =0x0
; CHECK-NEXT: sel z0.d, p0, z0.d, z2.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i32> @llvm.fptoui.sat.nxv2f16.nxv2i32(<vscale x 2 x half> %f)
ret <vscale x 2 x i32> %x
}
define <vscale x 4 x i32> @test_signed_v4f16_v4i32(<vscale x 4 x half> %f) {
; CHECK-LABEL: test_signed_v4f16_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z0.h, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.s, p0/m, z0.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z0.h, z2.h
; CHECK-NEXT: mov z1.s, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.s, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 4 x i32> @llvm.fptoui.sat.nxv4f16.nxv4i32(<vscale x 4 x half> %f)
ret <vscale x 4 x i32> %x
}
define <vscale x 8 x i32> @test_signed_v8f16_v8i32(<vscale x 8 x half> %f) {
; CHECK-LABEL: test_signed_v8f16_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: uunpklo z2.s, z0.h
; CHECK-NEXT: uunpkhi z3.s, z0.h
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov z4.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z2.h, #0.0
; CHECK-NEXT: fcmge p2.h, p0/z, z3.h, #0.0
; CHECK-NEXT: movprfx z0, z2
; CHECK-NEXT: fcvtzu z0.s, p0/m, z2.h
; CHECK-NEXT: movprfx z1, z3
; CHECK-NEXT: fcvtzu z1.s, p0/m, z3.h
; CHECK-NEXT: fcmgt p3.h, p0/z, z2.h, z4.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z3.h, z4.h
; CHECK-NEXT: mov z0.s, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.s, p2/m, #0 // =0x0
; CHECK-NEXT: mov z0.s, p3/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z1.s, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ret
%x = call <vscale x 8 x i32> @llvm.fptoui.sat.nxv8f16.nxv8i32(<vscale x 8 x half> %f)
ret <vscale x 8 x i32> %x
}
define <vscale x 4 x i16> @test_signed_v4f16_v4i16(<vscale x 4 x half> %f) {
; CHECK-LABEL: test_signed_v4f16_v4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: mov z1.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z0.h, #0.0
; CHECK-NEXT: movprfx z2, z0
; CHECK-NEXT: fcvtzu z2.s, p0/m, z0.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z0.h, z1.h
; CHECK-NEXT: mov z0.s, #65535 // =0xffff
; CHECK-NEXT: mov z2.s, p1/m, #0 // =0x0
; CHECK-NEXT: sel z0.s, p0, z0.s, z2.s
; CHECK-NEXT: ret
%x = call <vscale x 4 x i16> @llvm.fptoui.sat.nxv4f16.nxv4i16(<vscale x 4 x half> %f)
ret <vscale x 4 x i16> %x
}
define <vscale x 8 x i16> @test_signed_v8f16_v8i16(<vscale x 8 x half> %f) {
; CHECK-LABEL: test_signed_v8f16_v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z0.h, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.h, p0/m, z0.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z0.h, z2.h
; CHECK-NEXT: mov z1.h, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.h, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 8 x i16> @llvm.fptoui.sat.nxv8f16.nxv8i16(<vscale x 8 x half> %f)
ret <vscale x 8 x i16> %x
}
define <vscale x 2 x i64> @test_signed_v2f16_v2i64(<vscale x 2 x half> %f) {
; CHECK-LABEL: test_signed_v2f16_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z0.h, #0.0
; CHECK-NEXT: movprfx z1, z0
; CHECK-NEXT: fcvtzu z1.d, p0/m, z0.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z0.h, z2.h
; CHECK-NEXT: mov z1.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%x = call <vscale x 2 x i64> @llvm.fptoui.sat.nxv2f16.nxv2i64(<vscale x 2 x half> %f)
ret <vscale x 2 x i64> %x
}
define <vscale x 4 x i64> @test_signed_v4f16_v4i64(<vscale x 4 x half> %f) {
; CHECK-LABEL: test_signed_v4f16_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: uunpklo z2.d, z0.s
; CHECK-NEXT: uunpkhi z3.d, z0.s
; CHECK-NEXT: mov w8, #31743 // =0x7bff
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z4.h, w8
; CHECK-NEXT: fcmge p1.h, p0/z, z2.h, #0.0
; CHECK-NEXT: fcmge p2.h, p0/z, z3.h, #0.0
; CHECK-NEXT: movprfx z0, z2
; CHECK-NEXT: fcvtzu z0.d, p0/m, z2.h
; CHECK-NEXT: movprfx z1, z3
; CHECK-NEXT: fcvtzu z1.d, p0/m, z3.h
; CHECK-NEXT: fcmgt p3.h, p0/z, z2.h, z4.h
; CHECK-NEXT: not p1.b, p0/z, p1.b
; CHECK-NEXT: not p2.b, p0/z, p2.b
; CHECK-NEXT: fcmgt p0.h, p0/z, z3.h, z4.h
; CHECK-NEXT: mov z0.d, p1/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z0.d, p3/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z1.d, p0/m, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ret
%x = call <vscale x 4 x i64> @llvm.fptoui.sat.nxv4f16.nxv4i64(<vscale x 4 x half> %f)
ret <vscale x 4 x i64> %x
}
|
