sve-intrinsics-shifts.ll
17.1 KB
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
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
;
; ASR
;
define <vscale x 16 x i8> @asr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: asr_i8:
; CHECK: asr z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> %pg,
<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> @asr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: asr_i16:
; CHECK: asr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> %pg,
<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> @asr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: asr_i32:
; CHECK: asr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> %pg,
<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> @asr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: asr_i64:
; CHECK: asr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @asr_wide_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: asr_wide_i8:
; CHECK: asr z0.b, p0/m, z0.b, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 2 x i64> %b)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @asr_wide_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: asr_wide_i16:
; CHECK: asr z0.h, p0/m, z0.h, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 2 x i64> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @asr_wide_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: asr_wide_i32:
; CHECK: asr z0.s, p0/m, z0.s, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 2 x i64> %b)
ret <vscale x 4 x i32> %out
}
;
; ASRD
;
define <vscale x 16 x i8> @asrd_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) {
; CHECK-LABEL: asrd_i8:
; CHECK: asrd z0.b, p0/m, z0.b, #1
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.asrd.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
i32 1)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @asrd_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) {
; CHECK-LABEL: asrd_i16:
; CHECK: asrd z0.h, p0/m, z0.h, #2
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.asrd.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
i32 2)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @asrd_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) {
; CHECK-LABEL: asrd_i32:
; CHECK: asrd z0.s, p0/m, z0.s, #31
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.asrd.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
i32 31)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @asrd_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
; CHECK-LABEL: asrd_i64:
; CHECK: asrd z0.d, p0/m, z0.d, #64
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.asrd.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
i32 64)
ret <vscale x 2 x i64> %out
}
;
; INSR
;
define <vscale x 16 x i8> @insr_i8(<vscale x 16 x i8> %a, i8 %b) {
; CHECK-LABEL: insr_i8:
; CHECK: insr z0.b, w0
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.insr.nxv16i8(<vscale x 16 x i8> %a, i8 %b)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @insr_i16(<vscale x 8 x i16> %a, i16 %b) {
; CHECK-LABEL: insr_i16:
; CHECK: insr z0.h, w0
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.insr.nxv8i16(<vscale x 8 x i16> %a, i16 %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @insr_i32(<vscale x 4 x i32> %a, i32 %b) {
; CHECK-LABEL: insr_i32:
; CHECK: insr z0.s, w0
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.insr.nxv4i32(<vscale x 4 x i32> %a, i32 %b)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @insr_i64(<vscale x 2 x i64> %a, i64 %b) {
; CHECK-LABEL: insr_i64:
; CHECK: insr z0.d, x0
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.insr.nxv2i64(<vscale x 2 x i64> %a, i64 %b)
ret <vscale x 2 x i64> %out
}
define <vscale x 8 x half> @insr_f16(<vscale x 8 x half> %a, half %b) {
; CHECK-LABEL: insr_f16:
; CHECK: insr z0.h, h1
; CHECK-NEXT: ret
%out = call <vscale x 8 x half> @llvm.aarch64.sve.insr.nxv8f16(<vscale x 8 x half> %a, half %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @insr_f32(<vscale x 4 x float> %a, float %b) {
; CHECK-LABEL: insr_f32:
; CHECK: insr z0.s, s1
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.insr.nxv4f32(<vscale x 4 x float> %a, float %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @insr_f64(<vscale x 2 x double> %a, double %b) {
; CHECK-LABEL: insr_f64:
; CHECK: insr z0.d, d1
; CHECK-NEXT: ret
%out = call <vscale x 2 x double> @llvm.aarch64.sve.insr.nxv2f64(<vscale x 2 x double> %a, double %b)
ret <vscale x 2 x double> %out
}
;
; LSL
;
define <vscale x 16 x i8> @lsl_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: lsl_i8:
; CHECK: lsl z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.nxv16i8(<vscale x 16 x i1> %pg,
<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> @lsl_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: lsl_i16:
; CHECK: lsl z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> %pg,
<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> @lsl_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: lsl_i32:
; CHECK: lsl z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.nxv4i32(<vscale x 4 x i1> %pg,
<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> @lsl_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsl_i64:
; CHECK: lsl z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsl.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @lsl_wide_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsl_wide_i8:
; CHECK: lsl z0.b, p0/m, z0.b, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 2 x i64> %b)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @lsl_wide_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsl_wide_i16:
; CHECK: lsl z0.h, p0/m, z0.h, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 2 x i64> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @lsl_wide_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsl_wide_i32:
; CHECK: lsl z0.s, p0/m, z0.s, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 2 x i64> %b)
ret <vscale x 4 x i32> %out
}
;
; LSR
;
define <vscale x 16 x i8> @lsr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: lsr_i8:
; CHECK: lsr z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.nxv16i8(<vscale x 16 x i1> %pg,
<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> @lsr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: lsr_i16:
; CHECK: lsr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.nxv8i16(<vscale x 8 x i1> %pg,
<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> @lsr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: lsr_i32:
; CHECK: lsr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.nxv4i32(<vscale x 4 x i1> %pg,
<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> @lsr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsr_i64:
; CHECK: lsr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.lsr.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @lsr_wide_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsr_wide_i8:
; CHECK: lsr z0.b, p0/m, z0.b, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 2 x i64> %b)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @lsr_wide_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsr_wide_i16:
; CHECK: lsr z0.h, p0/m, z0.h, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 2 x i64> %b)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @lsr_wide_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: lsr_wide_i32:
; CHECK: lsr z0.s, p0/m, z0.s, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 2 x i64> %b)
ret <vscale x 4 x i32> %out
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.asr.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.asr.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.asr.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.asr.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.asr.wide.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 2 x i64>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.asrd.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, i32)
declare <vscale x 8 x i16> @llvm.aarch64.sve.asrd.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, i32)
declare <vscale x 4 x i32> @llvm.aarch64.sve.asrd.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.asrd.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i32)
declare <vscale x 16 x i8> @llvm.aarch64.sve.insr.nxv16i8(<vscale x 16 x i8>, i8)
declare <vscale x 8 x i16> @llvm.aarch64.sve.insr.nxv8i16(<vscale x 8 x i16>, i16)
declare <vscale x 4 x i32> @llvm.aarch64.sve.insr.nxv4i32(<vscale x 4 x i32>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.insr.nxv2i64(<vscale x 2 x i64>, i64)
declare <vscale x 8 x half> @llvm.aarch64.sve.insr.nxv8f16(<vscale x 8 x half>, half)
declare <vscale x 4 x float> @llvm.aarch64.sve.insr.nxv4f32(<vscale x 4 x float>, float)
declare <vscale x 2 x double> @llvm.aarch64.sve.insr.nxv2f64(<vscale x 2 x double>, double)
declare <vscale x 16 x i8> @llvm.aarch64.sve.lsl.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.lsl.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.lsl.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.lsl.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.lsl.wide.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 2 x i64>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.lsr.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.lsr.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.lsr.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.lsr.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.lsr.wide.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 2 x i64>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 2 x i64>)