sve2-bitwise-ternary.ll
15.1 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
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
;
; EOR3 (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @eor3_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: eor3_i8
; CHECK: eor3 z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @eor3_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: eor3_i16
; CHECK: eor3 z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @eor3_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: eor3_i32
; CHECK: eor3 z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @eor3_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: eor3_i64
; CHECK: eor3 z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; BCAX (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @bcax_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: bcax_i8
; CHECK: bcax z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @bcax_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: bcax_i16
; CHECK: bcax z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @bcax_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: bcax_i32
; CHECK: bcax z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @bcax_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: bcax_i64
; CHECK: bcax z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; BSL (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @bsl_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: bsl_i8
; CHECK: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @bsl_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: bsl_i16
; CHECK: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @bsl_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: bsl_i32
; CHECK: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @bsl_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: bsl_i64
; CHECK: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; BSL1N (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @bsl1n_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: bsl1n_i8
; CHECK: bsl1n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @bsl1n_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: bsl1n_i16
; CHECK: bsl1n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @bsl1n_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: bsl1n_i32
; CHECK: bsl1n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @bsl1n_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: bsl1n_i64
; CHECK: bsl1n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; BSL2N (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @bsl2n_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: bsl2n_i8
; CHECK: bsl2n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @bsl2n_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: bsl2n_i16
; CHECK: bsl2n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @bsl2n_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: bsl2n_i32
; CHECK: bsl2n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @bsl2n_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: bsl2n_i64
; CHECK: bsl2n z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; NBSL (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @nbsl_i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c) {
; CHECK-LABEL: nbsl_i8
; CHECK: nbsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @nbsl_i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c) {
; CHECK-LABEL: nbsl_i16
; CHECK: nbsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @nbsl_i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c) {
; CHECK-LABEL: nbsl_i32
; CHECK: nbsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @nbsl_i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c) {
; CHECK-LABEL: nbsl_i64
; CHECK: nbsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %res
}
;
; XAR (vector, bitwise, unpredicated)
;
define <vscale x 16 x i8> @xar_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: xar_b:
; CHECK: xar z0.b, z0.b, z1.b, #1
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.xar.nxv16i8(<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
i32 1)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @xar_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: xar_h:
; CHECK: xar z0.h, z0.h, z1.h, #2
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.xar.nxv8i16(<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
i32 2)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @xar_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: xar_s:
; CHECK: xar z0.s, z0.s, z1.s, #3
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.xar.nxv4i32(<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
i32 3)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @xar_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: xar_d:
; CHECK: xar z0.d, z0.d, z1.d, #4
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.xar.nxv2i64(<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
i32 4)
ret <vscale x 2 x i64> %out
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.xar.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, i32)
declare <vscale x 8 x i16> @llvm.aarch64.sve.xar.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, i32)
declare <vscale x 4 x i32> @llvm.aarch64.sve.xar.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.xar.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, i32)