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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt < %s -interleaved-access -S | FileCheck %s --check-prefix=NEON
; RUN: opt < %s -interleaved-access -mtriple=aarch64-linux-gnu -mattr=+sve -force-streaming-compatible-sve -S | FileCheck %s --check-prefix=SVE-FIXED
target triple = "aarch64-linux-gnu"
define { <16 x i8>, <16 x i8> } @deinterleave_i8_factor2(ptr %ptr) {
; NEON-LABEL: define { <16 x i8>, <16 x i8> } @deinterleave_i8_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld2.v16i8.p0(ptr [[PTR]])
; NEON-NEXT: ret { <16 x i8>, <16 x i8> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <16 x i8>, <16 x i8> } @deinterleave_i8_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0:[0-9]+]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <32 x i8>, ptr [[PTR]], align 1
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <16 x i8>, <16 x i8> } @llvm.experimental.vector.deinterleave2.v32i8(<32 x i8> [[LOAD]])
; SVE-FIXED-NEXT: ret { <16 x i8>, <16 x i8> } [[DEINTERLEAVE]]
;
%load = load <32 x i8>, ptr %ptr, align 1
%deinterleave = tail call { <16 x i8>, <16 x i8> } @llvm.experimental.vector.deinterleave2.v32i8(<32 x i8> %load)
ret { <16 x i8>, <16 x i8> } %deinterleave
}
define { <8 x i16>, <8 x i16> } @deinterleave_i16_factor2(ptr %ptr) {
; NEON-LABEL: define { <8 x i16>, <8 x i16> } @deinterleave_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[PTR]])
; NEON-NEXT: ret { <8 x i16>, <8 x i16> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <8 x i16>, <8 x i16> } @deinterleave_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <16 x i16>, ptr [[PTR]], align 2
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <8 x i16>, <8 x i16> } @llvm.experimental.vector.deinterleave2.v16i16(<16 x i16> [[LOAD]])
; SVE-FIXED-NEXT: ret { <8 x i16>, <8 x i16> } [[DEINTERLEAVE]]
;
%load = load <16 x i16>, ptr %ptr, align 2
%deinterleave = tail call { <8 x i16>, <8 x i16> } @llvm.experimental.vector.deinterleave2.v16i16(<16 x i16> %load)
ret { <8 x i16>, <8 x i16> } %deinterleave
}
define { <4 x i32>, <4 x i32> } @deinterleave_8xi32_factor2(ptr %ptr) {
; NEON-LABEL: define { <4 x i32>, <4 x i32> } @deinterleave_8xi32_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[PTR]])
; NEON-NEXT: ret { <4 x i32>, <4 x i32> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <4 x i32>, <4 x i32> } @deinterleave_8xi32_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <8 x i32>, ptr [[PTR]], align 4
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <4 x i32>, <4 x i32> } @llvm.experimental.vector.deinterleave2.v8i32(<8 x i32> [[LOAD]])
; SVE-FIXED-NEXT: ret { <4 x i32>, <4 x i32> } [[DEINTERLEAVE]]
;
%load = load <8 x i32>, ptr %ptr, align 4
%deinterleave = tail call { <4 x i32>, <4 x i32> } @llvm.experimental.vector.deinterleave2.v8i32(<8 x i32> %load)
ret { <4 x i32>, <4 x i32> } %deinterleave
}
define { <2 x i64>, <2 x i64> } @deinterleave_i64_factor2(ptr %ptr) {
; NEON-LABEL: define { <2 x i64>, <2 x i64> } @deinterleave_i64_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld2.v2i64.p0(ptr [[PTR]])
; NEON-NEXT: ret { <2 x i64>, <2 x i64> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <2 x i64>, <2 x i64> } @deinterleave_i64_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x i64>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x i64>, <2 x i64> } @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> [[LOAD]])
; SVE-FIXED-NEXT: ret { <2 x i64>, <2 x i64> } [[DEINTERLEAVE]]
;
%load = load <4 x i64>, ptr %ptr, align 8
%deinterleave = tail call { <2 x i64>, <2 x i64> } @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> %load)
ret { <2 x i64>, <2 x i64> } %deinterleave
}
define { <4 x float>, <4 x float> } @deinterleave_float_factor2(ptr %ptr) {
; NEON-LABEL: define { <4 x float>, <4 x float> } @deinterleave_float_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <4 x float>, <4 x float> } @llvm.aarch64.neon.ld2.v4f32.p0(ptr [[PTR]])
; NEON-NEXT: ret { <4 x float>, <4 x float> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <4 x float>, <4 x float> } @deinterleave_float_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <8 x float>, ptr [[PTR]], align 4
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <4 x float>, <4 x float> } @llvm.experimental.vector.deinterleave2.v8f32(<8 x float> [[LOAD]])
; SVE-FIXED-NEXT: ret { <4 x float>, <4 x float> } [[DEINTERLEAVE]]
;
%load = load <8 x float>, ptr %ptr, align 4
%deinterleave = tail call { <4 x float>, <4 x float> } @llvm.experimental.vector.deinterleave2.v8f32(<8 x float> %load)
ret { <4 x float>, <4 x float> } %deinterleave
}
define { <2 x double>, <2 x double> } @deinterleave_double_factor2(ptr %ptr) {
; NEON-LABEL: define { <2 x double>, <2 x double> } @deinterleave_double_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x double>, <2 x double> } @llvm.aarch64.neon.ld2.v2f64.p0(ptr [[PTR]])
; NEON-NEXT: ret { <2 x double>, <2 x double> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <2 x double>, <2 x double> } @deinterleave_double_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x double>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x double>, <2 x double> } @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> [[LOAD]])
; SVE-FIXED-NEXT: ret { <2 x double>, <2 x double> } [[DEINTERLEAVE]]
;
%load = load <4 x double>, ptr %ptr, align 8
%deinterleave = tail call { <2 x double>, <2 x double> } @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> %load)
ret { <2 x double>, <2 x double> } %deinterleave
}
define { <2 x ptr>, <2 x ptr> } @deinterleave_ptr_factor2(ptr %ptr) {
; NEON-LABEL: define { <2 x ptr>, <2 x ptr> } @deinterleave_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x ptr>, <2 x ptr> } @llvm.aarch64.neon.ld2.v2p0.p0(ptr [[PTR]])
; NEON-NEXT: ret { <2 x ptr>, <2 x ptr> } [[LDN]]
;
; SVE-FIXED-LABEL: define { <2 x ptr>, <2 x ptr> } @deinterleave_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x ptr>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x ptr>, <2 x ptr> } @llvm.experimental.vector.deinterleave2.v4p0(<4 x ptr> [[LOAD]])
; SVE-FIXED-NEXT: ret { <2 x ptr>, <2 x ptr> } [[DEINTERLEAVE]]
;
%load = load <4 x ptr>, ptr %ptr, align 8
%deinterleave = tail call { <2 x ptr>, <2 x ptr> } @llvm.experimental.vector.deinterleave2.v4p0(<4 x ptr> %load)
ret { <2 x ptr>, <2 x ptr> } %deinterleave
}
define void @interleave_i8_factor2(ptr %ptr, <16 x i8> %l, <16 x i8> %r) {
; NEON-LABEL: define void @interleave_i8_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <16 x i8> [[L:%.*]], <16 x i8> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v16i8.p0(<16 x i8> [[L]], <16 x i8> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i8_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <16 x i8> [[L:%.*]], <16 x i8> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <32 x i8> @llvm.experimental.vector.interleave2.v32i8(<16 x i8> [[L]], <16 x i8> [[R]])
; SVE-FIXED-NEXT: store <32 x i8> [[INTERLEAVE]], ptr [[PTR]], align 1
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <32 x i8> @llvm.experimental.vector.interleave2.v32i8(<16 x i8> %l, <16 x i8> %r)
store <32 x i8> %interleave, ptr %ptr, align 1
ret void
}
define void @interleave_i16_factor2(ptr %ptr, <8 x i16> %l, <8 x i16> %r) {
; NEON-LABEL: define void @interleave_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <8 x i16> [[L:%.*]], <8 x i16> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v8i16.p0(<8 x i16> [[L]], <8 x i16> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <8 x i16> [[L:%.*]], <8 x i16> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16> [[L]], <8 x i16> [[R]])
; SVE-FIXED-NEXT: store <16 x i16> [[INTERLEAVE]], ptr [[PTR]], align 2
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16> %l, <8 x i16> %r)
store <16 x i16> %interleave, ptr %ptr, align 2
ret void
}
define void @interleave_i32_factor2(ptr %ptr, <4 x i32> %l, <4 x i32> %r) {
; NEON-LABEL: define void @interleave_i32_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <4 x i32> [[L:%.*]], <4 x i32> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v4i32.p0(<4 x i32> [[L]], <4 x i32> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i32_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <4 x i32> [[L:%.*]], <4 x i32> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32> [[L]], <4 x i32> [[R]])
; SVE-FIXED-NEXT: store <8 x i32> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32> %l, <4 x i32> %r)
store <8 x i32> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_i64_factor2(ptr %ptr, <2 x i64> %l, <2 x i64> %r) {
; NEON-LABEL: define void @interleave_i64_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x i64> [[L:%.*]], <2 x i64> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2i64.p0(<2 x i64> [[L]], <2 x i64> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i64_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x i64> [[L:%.*]], <2 x i64> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64> [[L]], <2 x i64> [[R]])
; SVE-FIXED-NEXT: store <4 x i64> [[INTERLEAVE]], ptr [[PTR]], align 8
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64> %l, <2 x i64> %r)
store <4 x i64> %interleave, ptr %ptr, align 8
ret void
}
define void @interleave_float_factor2(ptr %ptr, <4 x float> %l, <4 x float> %r) {
; NEON-LABEL: define void @interleave_float_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <4 x float> [[L:%.*]], <4 x float> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v4f32.p0(<4 x float> [[L]], <4 x float> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_float_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <4 x float> [[L:%.*]], <4 x float> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float> [[L]], <4 x float> [[R]])
; SVE-FIXED-NEXT: store <8 x float> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float> %l, <4 x float> %r)
store <8 x float> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_double_factor2(ptr %ptr, <2 x double> %l, <2 x double> %r) {
; NEON-LABEL: define void @interleave_double_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x double> [[L:%.*]], <2 x double> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2f64.p0(<2 x double> [[L]], <2 x double> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_double_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x double> [[L:%.*]], <2 x double> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double> [[L]], <2 x double> [[R]])
; SVE-FIXED-NEXT: store <4 x double> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double> %l, <2 x double> %r)
store <4 x double> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_ptr_factor2(ptr %ptr, <2 x ptr> %l, <2 x ptr> %r) {
; NEON-LABEL: define void @interleave_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x ptr> [[L:%.*]], <2 x ptr> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[L]], <2 x ptr> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x ptr> [[L:%.*]], <2 x ptr> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x ptr> @llvm.experimental.vector.interleave2.v4p0(<2 x ptr> [[L]], <2 x ptr> [[R]])
; SVE-FIXED-NEXT: store <4 x ptr> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x ptr> @llvm.experimental.vector.interleave2.v4p0(<2 x ptr> %l, <2 x ptr> %r)
store <4 x ptr> %interleave, ptr %ptr, align 4
ret void
}
define { <16 x i16>, <16 x i16> } @deinterleave_wide_i16_factor2(ptr %ptr) #0 {
; NEON-LABEL: define { <16 x i16>, <16 x i16> } @deinterleave_wide_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[TMP1:%.*]] = getelementptr <8 x i16>, ptr [[PTR]], i64 0
; NEON-NEXT: [[LDN:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[TMP1]])
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 0
; NEON-NEXT: [[TMP3:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> poison, <8 x i16> [[TMP2]], i64 0)
; NEON-NEXT: [[TMP4:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 1
; NEON-NEXT: [[TMP5:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> poison, <8 x i16> [[TMP4]], i64 0)
; NEON-NEXT: [[TMP6:%.*]] = getelementptr <8 x i16>, ptr [[PTR]], i64 2
; NEON-NEXT: [[LDN1:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[TMP6]])
; NEON-NEXT: [[TMP7:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN1]], 0
; NEON-NEXT: [[TMP8:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> [[TMP3]], <8 x i16> [[TMP7]], i64 8)
; NEON-NEXT: [[TMP9:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN1]], 1
; NEON-NEXT: [[TMP10:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> [[TMP5]], <8 x i16> [[TMP9]], i64 8)
; NEON-NEXT: [[TMP11:%.*]] = insertvalue { <16 x i16>, <16 x i16> } poison, <16 x i16> [[TMP8]], 0
; NEON-NEXT: [[TMP12:%.*]] = insertvalue { <16 x i16>, <16 x i16> } [[TMP11]], <16 x i16> [[TMP10]], 1
; NEON-NEXT: ret { <16 x i16>, <16 x i16> } [[TMP12]]
;
; SVE-FIXED-LABEL: define { <16 x i16>, <16 x i16> } @deinterleave_wide_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <32 x i16>, ptr [[PTR]], align 2
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <16 x i16>, <16 x i16> } @llvm.experimental.vector.deinterleave2.v32i16(<32 x i16> [[LOAD]])
; SVE-FIXED-NEXT: ret { <16 x i16>, <16 x i16> } [[DEINTERLEAVE]]
;
%load = load <32 x i16>, ptr %ptr, align 2
%deinterleave = tail call { <16 x i16>, <16 x i16> } @llvm.experimental.vector.deinterleave2.v32i16(<32 x i16> %load)
ret { <16 x i16>, <16 x i16> } %deinterleave
}
define void @interleave_wide_ptr_factor2(ptr %ptr, <8 x ptr> %l, <8 x ptr> %r) {
; NEON-LABEL: define void @interleave_wide_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <8 x ptr> [[L:%.*]], <8 x ptr> [[R:%.*]]) {
; NEON-NEXT: [[TMP1:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 0
; NEON-NEXT: [[TMP2:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 0)
; NEON-NEXT: [[TMP3:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 0)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP2]], <2 x ptr> [[TMP3]], ptr [[TMP1]])
; NEON-NEXT: [[TMP4:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 2
; NEON-NEXT: [[TMP5:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 2)
; NEON-NEXT: [[TMP6:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 2)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP5]], <2 x ptr> [[TMP6]], ptr [[TMP4]])
; NEON-NEXT: [[TMP7:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 4
; NEON-NEXT: [[TMP8:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 4)
; NEON-NEXT: [[TMP9:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 4)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP8]], <2 x ptr> [[TMP9]], ptr [[TMP7]])
; NEON-NEXT: [[TMP10:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 6
; NEON-NEXT: [[TMP11:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 6)
; NEON-NEXT: [[TMP12:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 6)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP11]], <2 x ptr> [[TMP12]], ptr [[TMP10]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_wide_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <8 x ptr> [[L:%.*]], <8 x ptr> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <16 x ptr> @llvm.experimental.vector.interleave2.v16p0(<8 x ptr> [[L]], <8 x ptr> [[R]])
; SVE-FIXED-NEXT: store <16 x ptr> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <16 x ptr> @llvm.experimental.vector.interleave2.v16p0(<8 x ptr> %l, <8 x ptr> %r)
store <16 x ptr> %interleave, ptr %ptr, align 4
ret void
}
declare { <16 x i8>, <16 x i8> } @llvm.experimental.vector.deinterleave2.v32i8(<32 x i8>)
declare { <8 x i16>, <8 x i16> } @llvm.experimental.vector.deinterleave2.v16i16(<16 x i16>)
declare { <4 x i32>, <4 x i32> } @llvm.experimental.vector.deinterleave2.v8i32(<8 x i32>)
declare { <2 x i64>, <2 x i64> } @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64>)
declare { <4 x float>, <4 x float> } @llvm.experimental.vector.deinterleave2.v8f32(<8 x float>)
declare { <2 x double>, <2 x double> } @llvm.experimental.vector.deinterleave2.v4f64(<4 x double>)
declare { <2 x ptr>, <2 x ptr> } @llvm.experimental.vector.deinterleave2.v4p0(<4 x ptr>)
declare { <16 x i16>, <16 x i16> } @llvm.experimental.vector.deinterleave2.v32i16(<32 x i16>)
declare <32 x i8> @llvm.experimental.vector.interleave2.v32i8(<16 x i8>, <16 x i8>)
declare <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16>, <8 x i16>)
declare <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32>, <4 x i32>)
declare <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64>, <2 x i64>)
declare <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float>, <4 x float>)
declare <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double>, <2 x double>)
declare <4 x ptr> @llvm.experimental.vector.interleave2.v4p0(<2 x ptr>, <2 x ptr>)
declare <16 x ptr> @llvm.experimental.vector.interleave2.v16p0(<8 x ptr>, <8 x ptr>)
|
