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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -aarch64-sve-vector-bits-min=256 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_EQ_256
; RUN: llc -aarch64-sve-vector-bits-min=512 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_256
target triple = "aarch64-unknown-linux-gnu"
; REVB pattern for shuffle v32i8 -> v16i16
define void @test_revbv16i16(<32 x i8>* %a) #0 {
; CHECK-LABEL: test_revbv16i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.b, vl32
; CHECK-NEXT: ptrue p1.h
; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: revb z0.h, p1/m, z0.h
; CHECK-NEXT: st1b { z0.b }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <32 x i8>, <32 x i8>* %a
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14, i32 17, i32 16, i32 19, i32 18, i32 21, i32 20, i32 23, i32 22, i32 undef, i32 24, i32 27, i32 undef, i32 29, i32 28, i32 undef, i32 undef>
store <32 x i8> %tmp2, <32 x i8>* %a
ret void
}
; REVB pattern for shuffle v32i8 -> v8i32
define void @test_revbv8i32(<32 x i8>* %a) #0 {
; CHECK-LABEL: test_revbv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.b, vl32
; CHECK-NEXT: ptrue p1.s
; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: revb z0.s, p1/m, z0.s
; CHECK-NEXT: st1b { z0.b }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <32 x i8>, <32 x i8>* %a
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12, i32 19, i32 18, i32 17, i32 16, i32 23, i32 22, i32 21, i32 20, i32 27, i32 undef, i32 undef, i32 undef, i32 31, i32 30, i32 29, i32 undef>
store <32 x i8> %tmp2, <32 x i8>* %a
ret void
}
; REVB pattern for shuffle v32i8 -> v4i64
define void @test_revbv4i64(<32 x i8>* %a) #0 {
; CHECK-LABEL: test_revbv4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.b, vl32
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: revb z0.d, p1/m, z0.d
; CHECK-NEXT: st1b { z0.b }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <32 x i8>, <32 x i8>* %a
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 31, i32 30, i32 29, i32 undef, i32 27, i32 undef, i32 undef, i32 undef>
store <32 x i8> %tmp2, <32 x i8>* %a
ret void
}
; REVH pattern for shuffle v16i16 -> v8i32
define void @test_revhv8i32(<16 x i16>* %a) #0 {
; CHECK-LABEL: test_revhv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h, vl16
; CHECK-NEXT: ptrue p1.s
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: revh z0.s, p1/m, z0.s
; CHECK-NEXT: st1h { z0.h }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <16 x i16>, <16 x i16>* %a
%tmp2 = shufflevector <16 x i16> %tmp1, <16 x i16> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
store <16 x i16> %tmp2, <16 x i16>* %a
ret void
}
; REVH pattern for shuffle v16f16 -> v8f32
define void @test_revhv8f32(<16 x half>* %a) #0 {
; CHECK-LABEL: test_revhv8f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h, vl16
; CHECK-NEXT: ptrue p1.s
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: revh z0.s, p1/m, z0.s
; CHECK-NEXT: st1h { z0.h }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <16 x half>, <16 x half>* %a
%tmp2 = shufflevector <16 x half> %tmp1, <16 x half> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
store <16 x half> %tmp2, <16 x half>* %a
ret void
}
; REVH pattern for shuffle v16i16 -> v4i64
define void @test_revhv4i64(<16 x i16>* %a) #0 {
; CHECK-LABEL: test_revhv4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h, vl16
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: revh z0.d, p1/m, z0.d
; CHECK-NEXT: st1h { z0.h }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <16 x i16>, <16 x i16>* %a
%tmp2 = shufflevector <16 x i16> %tmp1, <16 x i16> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
store <16 x i16> %tmp2, <16 x i16>* %a
ret void
}
; REVW pattern for shuffle v8i32 -> v4i64
define void @test_revwv4i64(<8 x i32>* %a) #0 {
; CHECK-LABEL: test_revwv4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl8
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: revw z0.d, p1/m, z0.d
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <8 x i32>, <8 x i32>* %a
%tmp2 = shufflevector <8 x i32> %tmp1, <8 x i32> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
store <8 x i32> %tmp2, <8 x i32>* %a
ret void
}
; REVW pattern for shuffle v8f32 -> v4f64
define void @test_revwv4f64(<8 x float>* %a) #0 {
; CHECK-LABEL: test_revwv4f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl8
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: revw z0.d, p1/m, z0.d
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <8 x float>, <8 x float>* %a
%tmp2 = shufflevector <8 x float> %tmp1, <8 x float> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
store <8 x float> %tmp2, <8 x float>* %a
ret void
}
; Don't use SVE for 128-bit vectors
define <16 x i8> @test_revv16i8(<16 x i8>* %a) #0 {
; CHECK-LABEL: test_revv16i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ldr q0, [x0]
; CHECK-NEXT: rev64 v0.16b, v0.16b
; CHECK-NEXT: ret
%tmp1 = load <16 x i8>, <16 x i8>* %a
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
ret <16 x i8> %tmp2
}
; REVW pattern for shuffle two v8i32 inputs with the second input available.
define void @test_revwv8i32v8i32(<8 x i32>* %a, <8 x i32>* %b) #0 {
; CHECK-LABEL: test_revwv8i32v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl8
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x1]
; CHECK-NEXT: revw z0.d, p1/m, z0.d
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <8 x i32>, <8 x i32>* %a
%tmp2 = load <8 x i32>, <8 x i32>* %b
%tmp3 = shufflevector <8 x i32> %tmp1, <8 x i32> %tmp2, <8 x i32> <i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
store <8 x i32> %tmp3, <8 x i32>* %a
ret void
}
; REVH pattern for shuffle v32i16 with 256 bits and 512 bits SVE.
define void @test_revhv32i16(<32 x i16>* %a) #0 {
; VBITS_EQ_256-LABEL: test_revhv32i16:
; VBITS_EQ_256: // %bb.0:
; VBITS_EQ_256-NEXT: mov x8, #16
; VBITS_EQ_256-NEXT: ptrue p0.h, vl16
; VBITS_EQ_256-NEXT: ptrue p1.d
; VBITS_EQ_256-NEXT: ld1h { z0.h }, p0/z, [x0, x8, lsl #1]
; VBITS_EQ_256-NEXT: ld1h { z1.h }, p0/z, [x0]
; VBITS_EQ_256-NEXT: revh z0.d, p1/m, z0.d
; VBITS_EQ_256-NEXT: revh z1.d, p1/m, z1.d
; VBITS_EQ_256-NEXT: st1h { z0.h }, p0, [x0, x8, lsl #1]
; VBITS_EQ_256-NEXT: st1h { z1.h }, p0, [x0]
; VBITS_EQ_256-NEXT: ret
;
; VBITS_GE_256-LABEL: test_revhv32i16:
; VBITS_GE_256: // %bb.0:
; VBITS_GE_256-NEXT: ptrue p0.h, vl32
; VBITS_GE_256-NEXT: ptrue p1.d
; VBITS_GE_256-NEXT: ld1h { z0.h }, p0/z, [x0]
; VBITS_GE_256-NEXT: revh z0.d, p1/m, z0.d
; VBITS_GE_256-NEXT: st1h { z0.h }, p0, [x0]
; VBITS_GE_256-NEXT: ret
%tmp1 = load <32 x i16>, <32 x i16>* %a
%tmp2 = shufflevector <32 x i16> %tmp1, <32 x i16> undef, <32 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12, i32 19, i32 18, i32 17, i32 16, i32 23, i32 22, i32 21, i32 20, i32 27, i32 undef, i32 undef, i32 undef, i32 31, i32 30, i32 29, i32 undef>
store <32 x i16> %tmp2, <32 x i16>* %a
ret void
}
; Only support to reverse bytes / halfwords / words within elements
define void @test_rev_elts_fail(<4 x i64>* %a) #1 {
; CHECK-LABEL: test_rev_elts_fail:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: sub x9, sp, #48
; CHECK-NEXT: mov x29, sp
; CHECK-NEXT: and sp, x9, #0xffffffffffffffe0
; CHECK-NEXT: .cfi_def_cfa w29, 16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0]
; CHECK-NEXT: mov z1.d, z0.d[2]
; CHECK-NEXT: mov z2.d, z0.d[3]
; CHECK-NEXT: mov x10, v0.d[1]
; CHECK-NEXT: fmov x8, d1
; CHECK-NEXT: fmov x9, d2
; CHECK-NEXT: fmov x11, d0
; CHECK-NEXT: stp x9, x8, [sp, #16]
; CHECK-NEXT: stp x10, x11, [sp]
; CHECK-NEXT: ld1d { z0.d }, p0/z, [sp]
; CHECK-NEXT: st1d { z0.d }, p0, [x0]
; CHECK-NEXT: mov sp, x29
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%tmp1 = load <4 x i64>, <4 x i64>* %a
%tmp2 = shufflevector <4 x i64> %tmp1, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
store <4 x i64> %tmp2, <4 x i64>* %a
ret void
}
; REV instruction will reverse the order of all elements in the vector.
; When the vector length and the target register size are inconsistent,
; the correctness of generated REV instruction for shuffle pattern cannot be guaranteed.
; sve-vector-bits-min=256, sve-vector-bits-max is not set, REV inst can't be generated.
define void @test_revv8i32(<8 x i32>* %a) #0 {
; CHECK-LABEL: test_revv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: sub x9, sp, #48
; CHECK-NEXT: mov x29, sp
; CHECK-NEXT: and sp, x9, #0xffffffffffffffe0
; CHECK-NEXT: .cfi_def_cfa w29, 16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.s, vl8
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: mov w8, v0.s[1]
; CHECK-NEXT: mov w9, v0.s[2]
; CHECK-NEXT: mov w11, v0.s[3]
; CHECK-NEXT: fmov w10, s0
; CHECK-NEXT: mov z1.s, z0.s[4]
; CHECK-NEXT: mov z2.s, z0.s[5]
; CHECK-NEXT: mov z3.s, z0.s[6]
; CHECK-NEXT: mov z0.s, z0.s[7]
; CHECK-NEXT: stp w8, w10, [sp, #24]
; CHECK-NEXT: fmov w10, s1
; CHECK-NEXT: fmov w8, s2
; CHECK-NEXT: stp w11, w9, [sp, #16]
; CHECK-NEXT: fmov w9, s3
; CHECK-NEXT: fmov w11, s0
; CHECK-NEXT: stp w8, w10, [sp, #8]
; CHECK-NEXT: stp w11, w9, [sp]
; CHECK-NEXT: ld1w { z0.s }, p0/z, [sp]
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: mov sp, x29
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%tmp1 = load <8 x i32>, <8 x i32>* %a
%tmp2 = shufflevector <8 x i32> %tmp1, <8 x i32> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
store <8 x i32> %tmp2, <8 x i32>* %a
ret void
}
; REV pattern for v32i8 shuffle with vscale_range(2,2)
define void @test_revv32i8_vl256(<32 x i8>* %a) #1 {
; CHECK-LABEL: test_revv32i8_vl256:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.b
; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: rev z0.b, z0.b
; CHECK-NEXT: st1b { z0.b }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <32 x i8>, <32 x i8>* %a
%tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
store <32 x i8> %tmp2, <32 x i8>* %a
ret void
}
; REV pattern for v16i16 shuffle with vscale_range(2,2)
define void @test_revv16i16_vl256(<16 x i16>* %a) #1 {
; CHECK-LABEL: test_revv16i16_vl256:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: rev z0.h, z0.h
; CHECK-NEXT: st1h { z0.h }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <16 x i16>, <16 x i16>* %a
%tmp2 = shufflevector <16 x i16> %tmp1, <16 x i16> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
store <16 x i16> %tmp2, <16 x i16>* %a
ret void
}
; REV pattern for v8f32 shuffle with vscale_range(2,2)
define void @test_revv8f32_vl256(<8 x float>* %a) #1 {
; CHECK-LABEL: test_revv8f32_vl256:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: rev z0.s, z0.s
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <8 x float>, <8 x float>* %a
%tmp2 = shufflevector <8 x float> %tmp1, <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
store <8 x float> %tmp2, <8 x float>* %a
ret void
}
; REV pattern for v4f64 shuffle with vscale_range(2,2)
define void @test_revv4f64_vl256(<4 x double>* %a) #1 {
; CHECK-LABEL: test_revv4f64_vl256:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0]
; CHECK-NEXT: rev z0.d, z0.d
; CHECK-NEXT: st1d { z0.d }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <4 x double>, <4 x double>* %a
%tmp2 = shufflevector <4 x double> %tmp1, <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
store <4 x double> %tmp2, <4 x double>* %a
ret void
}
; REV pattern for shuffle two v8i32 inputs with the second input available, vscale_range(2,2).
define void @test_revv8i32v8i32(<8 x i32>* %a, <8 x i32>* %b) #1 {
; CHECK-LABEL: test_revv8i32v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x1]
; CHECK-NEXT: rev z0.s, z0.s
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%tmp1 = load <8 x i32>, <8 x i32>* %a
%tmp2 = load <8 x i32>, <8 x i32>* %b
%tmp3 = shufflevector <8 x i32> %tmp1, <8 x i32> %tmp2, <8 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
store <8 x i32> %tmp3, <8 x i32>* %a
ret void
}
; Illegal REV pattern.
define void @test_rev_fail(<16 x i16>* %a) #1 {
; CHECK-LABEL: test_rev_fail:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: sub x9, sp, #48
; CHECK-NEXT: mov x29, sp
; CHECK-NEXT: and sp, x9, #0xffffffffffffffe0
; CHECK-NEXT: .cfi_def_cfa w29, 16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: mov z1.h, z0.h[8]
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: fmov w9, s1
; CHECK-NEXT: mov z5.h, z0.h[12]
; CHECK-NEXT: mov z2.h, z0.h[9]
; CHECK-NEXT: mov z3.h, z0.h[10]
; CHECK-NEXT: mov z4.h, z0.h[11]
; CHECK-NEXT: fmov w11, s2
; CHECK-NEXT: strh w9, [sp, #30]
; CHECK-NEXT: fmov w9, s5
; CHECK-NEXT: fmov w12, s3
; CHECK-NEXT: strh w8, [sp, #14]
; CHECK-NEXT: fmov w8, s4
; CHECK-NEXT: mov z6.h, z0.h[13]
; CHECK-NEXT: mov z7.h, z0.h[14]
; CHECK-NEXT: mov z16.h, z0.h[15]
; CHECK-NEXT: umov w10, v0.h[1]
; CHECK-NEXT: strh w9, [sp, #22]
; CHECK-NEXT: umov w9, v0.h[2]
; CHECK-NEXT: strh w11, [sp, #28]
; CHECK-NEXT: fmov w11, s6
; CHECK-NEXT: strh w12, [sp, #26]
; CHECK-NEXT: fmov w12, s7
; CHECK-NEXT: strh w8, [sp, #24]
; CHECK-NEXT: fmov w8, s16
; CHECK-NEXT: strh w10, [sp, #12]
; CHECK-NEXT: strh w11, [sp, #20]
; CHECK-NEXT: umov w11, v0.h[3]
; CHECK-NEXT: strh w12, [sp, #18]
; CHECK-NEXT: umov w12, v0.h[4]
; CHECK-NEXT: strh w8, [sp, #16]
; CHECK-NEXT: umov w8, v0.h[5]
; CHECK-NEXT: umov w10, v0.h[6]
; CHECK-NEXT: strh w9, [sp, #10]
; CHECK-NEXT: umov w9, v0.h[7]
; CHECK-NEXT: strh w11, [sp, #8]
; CHECK-NEXT: strh w12, [sp, #6]
; CHECK-NEXT: strh w8, [sp, #4]
; CHECK-NEXT: strh w10, [sp, #2]
; CHECK-NEXT: strh w9, [sp]
; CHECK-NEXT: ld1h { z0.h }, p0/z, [sp]
; CHECK-NEXT: st1h { z0.h }, p0, [x0]
; CHECK-NEXT: mov sp, x29
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%tmp1 = load <16 x i16>, <16 x i16>* %a
%tmp2 = shufflevector <16 x i16> %tmp1, <16 x i16> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
store <16 x i16> %tmp2, <16 x i16>* %a
ret void
}
; Don't use SVE for 128-bit shuffle with two inputs
define void @test_revv8i16v8i16(<8 x i16>* %a, <8 x i16>* %b, <16 x i16>* %c) #1 {
; CHECK-LABEL: test_revv8i16v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT: sub x9, sp, #48
; CHECK-NEXT: mov x29, sp
; CHECK-NEXT: and sp, x9, #0xffffffffffffffe0
; CHECK-NEXT: .cfi_def_cfa w29, 16
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: mov x8, sp
; CHECK-NEXT: ldr q0, [x1]
; CHECK-NEXT: orr x9, x8, #0x1e
; CHECK-NEXT: orr x10, x8, #0x1c
; CHECK-NEXT: ldr q1, [x0]
; CHECK-NEXT: orr x12, x8, #0x10
; CHECK-NEXT: orr x11, x8, #0x18
; CHECK-NEXT: str h0, [sp, #22]
; CHECK-NEXT: st1 { v0.h }[4], [x9]
; CHECK-NEXT: orr x9, x8, #0xe
; CHECK-NEXT: st1 { v0.h }[5], [x10]
; CHECK-NEXT: orr x10, x8, #0xc
; CHECK-NEXT: st1 { v0.h }[3], [x12]
; CHECK-NEXT: mov w12, #26
; CHECK-NEXT: st1 { v1.h }[4], [x9]
; CHECK-NEXT: orr x9, x8, #0x8
; CHECK-NEXT: st1 { v0.h }[7], [x11]
; CHECK-NEXT: orr x11, x8, #0x2
; CHECK-NEXT: st1 { v1.h }[5], [x10]
; CHECK-NEXT: orr x10, x8, #0x4
; CHECK-NEXT: st1 { v1.h }[7], [x9]
; CHECK-NEXT: orr x9, x8, x12
; CHECK-NEXT: st1 { v1.h }[2], [x11]
; CHECK-NEXT: mov w11, #10
; CHECK-NEXT: st1 { v1.h }[1], [x10]
; CHECK-NEXT: mov w10, #18
; CHECK-NEXT: st1 { v0.h }[6], [x9]
; CHECK-NEXT: mov w9, #20
; CHECK-NEXT: orr x9, x8, x9
; CHECK-NEXT: orr x10, x8, x10
; CHECK-NEXT: st1 { v1.h }[3], [x8]
; CHECK-NEXT: orr x8, x8, x11
; CHECK-NEXT: str h1, [sp, #6]
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: st1 { v0.h }[1], [x9]
; CHECK-NEXT: st1 { v0.h }[2], [x10]
; CHECK-NEXT: st1 { v1.h }[6], [x8]
; CHECK-NEXT: ld1h { z0.h }, p0/z, [sp]
; CHECK-NEXT: st1h { z0.h }, p0, [x2]
; CHECK-NEXT: mov sp, x29
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
%tmp1 = load <8 x i16>, <8 x i16>* %a
%tmp2 = load <8 x i16>, <8 x i16>* %b
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
store <16 x i16> %tmp3, <16 x i16>* %c
ret void
}
attributes #0 = { "target-features"="+sve" }
attributes #1 = { "target-features"="+sve" vscale_range(2,2) }
|
