aboutsummaryrefslogtreecommitdiff
blob: fa67d92c2ae0edd4a050ad2bf8b2026c182f25e1 (plain)
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
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s
; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t

; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
; WARN-NOT: warning

;
; ABS
;

define <vscale x 16 x i8> @abs_i8(<vscale x 16 x i8> %a, <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b) {
; CHECK-LABEL: abs_i8:
; CHECK: abs z0.b, p0/m, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.abs.nxv16i8(<vscale x 16 x i8> %a,
                                                               <vscale x 16 x i1> %pg,
                                                               <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @abs_i16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b) {
; CHECK-LABEL: abs_i16:
; CHECK: abs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %a,
                                                               <vscale x 8 x i1> %pg,
                                                               <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @abs_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: abs_i32:
; CHECK: abs z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.abs.nxv4i32(<vscale x 4 x i32> %a,
                                                               <vscale x 4 x i1> %pg,
                                                               <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @abs_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: abs_i64:
; CHECK: abs z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.abs.nxv2i64(<vscale x 2 x i64> %a,
                                                               <vscale x 2 x i1> %pg,
                                                               <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

;
; NEG
;

define <vscale x 16 x i8> @neg_i8(<vscale x 16 x i8> %a, <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b) {
; CHECK-LABEL: neg_i8:
; CHECK: neg z0.b, p0/m, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.neg.nxv16i8(<vscale x 16 x i8> %a,
                                                               <vscale x 16 x i1> %pg,
                                                               <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @neg_i16(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b) {
; CHECK-LABEL: neg_i16:
; CHECK: neg z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.neg.nxv8i16(<vscale x 8 x i16> %a,
                                                               <vscale x 8 x i1> %pg,
                                                               <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @neg_i32(<vscale x 4 x i32> %a, <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b) {
; CHECK-LABEL: neg_i32:
; CHECK: neg z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.neg.nxv4i32(<vscale x 4 x i32> %a,
                                                               <vscale x 4 x i1> %pg,
                                                               <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @neg_i64(<vscale x 2 x i64> %a, <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b) {
; CHECK-LABEL: neg_i64:
; CHECK: neg z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.neg.nxv2i64(<vscale x 2 x i64> %a,
                                                               <vscale x 2 x i1> %pg,
                                                               <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

; SDOT

define <vscale x 4 x i32> @sdot_i32(<vscale x 4 x i32> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: sdot_i32:
; CHECK: sdot z0.s, z1.b, z2.b
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sdot.nxv4i32(<vscale x 4 x i32> %a,
                                                                <vscale x 16 x i8> %b,
                                                                <vscale x 16 x i8> %c)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @sdot_i64(<vscale x 2 x i64> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: sdot_i64:
; CHECK: sdot z0.d, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sdot.nxv2i64(<vscale x 2 x i64> %a,
                                                                <vscale x 8 x i16> %b,
                                                                <vscale x 8 x i16> %c)
  ret <vscale x 2 x i64> %out
}

; SDOT (Indexed)

define <vscale x 4 x i32> @sdot_lane_i32(<vscale x 4 x i32> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: sdot_lane_i32:
; CHECK: sdot z0.s, z1.b, z2.b[2]
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sdot.lane.nxv4i32(<vscale x 4 x i32> %a,
                                                                     <vscale x 16 x i8> %b,
                                                                     <vscale x 16 x i8> %c,
                                                                     i32 2)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @sdot_lane_i64(<vscale x 2 x i64> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: sdot_lane_i64:
; CHECK: sdot z0.d, z1.h, z2.h[1]
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sdot.lane.nxv2i64(<vscale x 2 x i64> %a,
                                                                     <vscale x 8 x i16> %b,
                                                                     <vscale x 8 x i16> %c,
                                                                     i32 1)
  ret <vscale x 2 x i64> %out
}

; SQADD

define <vscale x 16 x i8> @sqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sqadd_i8:
; CHECK: sqadd z0.b, z0.b, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.x.nxv16i8(<vscale x 16 x i8> %a,
                                                                   <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @sqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sqadd_i16:
; CHECK: sqadd z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.x.nxv8i16(<vscale x 8 x i16> %a,
                                                                   <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @sqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sqadd_i32:
; CHECK: sqadd z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.x.nxv4i32(<vscale x 4 x i32> %a,
                                                                   <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @sqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sqadd_i64:
; CHECK: sqadd z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.x.nxv2i64(<vscale x 2 x i64> %a,
                                                                   <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

; SQSUB

define <vscale x 16 x i8> @sqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: sqsub_i8:
; CHECK: sqsub z0.b, z0.b, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.x.nxv16i8(<vscale x 16 x i8> %a,
                                                                   <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @sqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: sqsub_i16:
; CHECK: sqsub z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.x.nxv8i16(<vscale x 8 x i16> %a,
                                                                   <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @sqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: sqsub_i32:
; CHECK: sqsub z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.x.nxv4i32(<vscale x 4 x i32> %a,
                                                                   <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @sqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sqsub_i64:
; CHECK: sqsub z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.x.nxv2i64(<vscale x 2 x i64> %a,
                                                                   <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

; UDOT

define <vscale x 4 x i32> @udot_i32(<vscale x 4 x i32> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: udot_i32:
; CHECK: udot z0.s, z1.b, z2.b
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.udot.nxv4i32(<vscale x 4 x i32> %a,
                                                                <vscale x 16 x i8> %b,
                                                                <vscale x 16 x i8> %c)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @udot_i64(<vscale x 2 x i64> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: udot_i64:
; CHECK: udot z0.d, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.udot.nxv2i64(<vscale x 2 x i64> %a,
                                                                <vscale x 8 x i16> %b,
                                                                <vscale x 8 x i16> %c)
  ret <vscale x 2 x i64> %out
}

; UDOT (Indexed)

define <vscale x 4 x i32> @udot_lane_i32(<vscale x 4 x i32> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: udot_lane_i32:
; CHECK: udot z0.s, z1.b, z2.b[2]
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.udot.lane.nxv4i32(<vscale x 4 x i32> %a,
                                                                     <vscale x 16 x i8> %b,
                                                                     <vscale x 16 x i8> %c,
                                                                     i32 2)
  ret <vscale x 4 x i32> %out
}

; UQADD

define <vscale x 16 x i8> @uqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: uqadd_i8:
; CHECK: uqadd z0.b, z0.b, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.x.nxv16i8(<vscale x 16 x i8> %a,
                                                                   <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @uqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: uqadd_i16:
; CHECK: uqadd z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.x.nxv8i16(<vscale x 8 x i16> %a,
                                                                   <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @uqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: uqadd_i32:
; CHECK: uqadd z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.x.nxv4i32(<vscale x 4 x i32> %a,
                                                                   <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @uqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: uqadd_i64:
; CHECK: uqadd z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.x.nxv2i64(<vscale x 2 x i64> %a,
                                                                   <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

; UQSUB

define <vscale x 16 x i8> @uqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: uqsub_i8:
; CHECK: uqsub z0.b, z0.b, z1.b
; CHECK-NEXT: ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.x.nxv16i8(<vscale x 16 x i8> %a,
                                                                   <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @uqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: uqsub_i16:
; CHECK: uqsub z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.x.nxv8i16(<vscale x 8 x i16> %a,
                                                                   <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @uqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: uqsub_i32:
; CHECK: uqsub z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.x.nxv4i32(<vscale x 4 x i32> %a,
                                                                   <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @uqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: uqsub_i64:
; CHECK: uqsub z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.x.nxv2i64(<vscale x 2 x i64> %a,
                                                                   <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

; ADD (tuples)

define <vscale x 4 x i64> @add_i64_tuple2(<vscale x 4 x i64>* %out, <vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2) {
; CHECK-LABEL: add_i64_tuple2
; CHECK: add z0.d, z0.d, z0.d
; CHECK: add z1.d, z1.d, z1.d
  %tuple = tail call <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2)
  %res = add <vscale x 4 x i64> %tuple, %tuple
  ret <vscale x 4 x i64> %res
}

define <vscale x 6 x i64> @add_i64_tuple3(<vscale x 6 x i64>* %out, <vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3) {
; CHECK-LABEL: add_i64_tuple3
; CHECK: add z0.d, z0.d, z0.d
; CHECK: add z1.d, z1.d, z1.d
; CHECK: add z2.d, z2.d, z2.d
  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3)
  %res = add <vscale x 6 x i64> %tuple, %tuple
  ret <vscale x 6 x i64> %res
}

define <vscale x 8 x i64> @add_i64_tuple4(<vscale x 8 x i64>* %out, <vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3, <vscale x 2 x i64> %in4) {
; CHECK-LABEL: add_i64_tuple4
; CHECK: add z0.d, z0.d, z0.d
; CHECK: add z1.d, z1.d, z1.d
; CHECK: add z2.d, z2.d, z2.d
; CHECK: add z3.d, z3.d, z3.d
  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3, <vscale x 2 x i64> %in4)
  %res = add <vscale x 8 x i64> %tuple, %tuple
  ret <vscale x 8 x i64> %res
}


declare <vscale x 16 x i8> @llvm.aarch64.sve.abs.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.abs.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.abs.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.aarch64.sve.neg.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.neg.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.neg.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.neg.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, <vscale x 2 x i64>)

declare <vscale x 4 x i32> @llvm.aarch64.sve.sdot.nxv4i32(<vscale x 4 x i32>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sdot.nxv2i64(<vscale x 2 x i64>, <vscale x 8 x i16>, <vscale x 8 x i16>)

declare <vscale x 4 x i32> @llvm.aarch64.sve.sdot.lane.nxv4i32(<vscale x 4 x i32>, <vscale x 16 x i8>, <vscale x 16 x i8>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sdot.lane.nxv2i64(<vscale x 2 x i64>, <vscale x 8 x i16>, <vscale x 8 x i16>, i32)

declare <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.x.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.x.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.x.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.x.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.x.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.x.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.x.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.x.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 4 x i32> @llvm.aarch64.sve.udot.nxv4i32(<vscale x 4 x i32>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.udot.nxv2i64(<vscale x 2 x i64>, <vscale x 8 x i16>, <vscale x 8 x i16>)

declare <vscale x 4 x i32> @llvm.aarch64.sve.udot.lane.nxv4i32(<vscale x 4 x i32>, <vscale x 16 x i8>, <vscale x 16 x i8>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.udot.lane.nxv2i64(<vscale x 2 x i64>, <vscale x 8 x i16>, <vscale x 8 x i16>, i32)

declare <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.x.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.x.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.x.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.x.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.x.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.x.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.x.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.x.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)

declare <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)