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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zvfh,+zvfbfmin | FileCheck %s
; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zvfh,+zvfbfmin | FileCheck %s
; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zvfhmin,+zvfbfmin | FileCheck %s
; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zvfhmin,+zvfbfmin | FileCheck %s
; Integers
define {<16 x i1>, <16 x i1>} @vector_deinterleave_load_v16i1_v32i1(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v16i1_v32i1:
; CHECK: # %bb.0:
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
; CHECK-NEXT: vlm.v v0, (a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: vmerge.vim v9, v8, 1, v0
; CHECK-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
; CHECK-NEXT: vslidedown.vi v0, v0, 2
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vnsrl.wi v10, v9, 0
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vnsrl.wi v9, v9, 8
; CHECK-NEXT: vnsrl.wi v11, v8, 0
; CHECK-NEXT: vnsrl.wi v8, v8, 8
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vslideup.vi v10, v11, 8
; CHECK-NEXT: vslideup.vi v9, v8, 8
; CHECK-NEXT: vmsne.vi v0, v10, 0
; CHECK-NEXT: vmsne.vi v8, v9, 0
; CHECK-NEXT: ret
%vec = load <32 x i1>, ptr %p
%deinterleaved.results = call {<16 x i1>, <16 x i1>} @llvm.vector.deinterleave2.v32i1(<32 x i1> %vec)
%t0 = extractvalue { <16 x i1>, <16 x i1> } %deinterleaved.results, 0
%t1 = extractvalue { <16 x i1>, <16 x i1> } %deinterleaved.results, 1
%res0 = insertvalue { <16 x i1>, <16 x i1> } undef, <16 x i1> %t0, 0
%res1 = insertvalue { <16 x i1>, <16 x i1> } %res0, <16 x i1> %t1, 1
ret {<16 x i1>, <16 x i1>} %res1
}
define {<16 x i8>, <16 x i8>} @vector_deinterleave_load_v16i8_v32i8(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v16i8_v32i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlseg2e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <32 x i8>, ptr %p
%deinterleaved.results = call {<16 x i8>, <16 x i8>} @llvm.vector.deinterleave2.v32i8(<32 x i8> %vec)
%t0 = extractvalue { <16 x i8>, <16 x i8> } %deinterleaved.results, 0
%t1 = extractvalue { <16 x i8>, <16 x i8> } %deinterleaved.results, 1
%res0 = insertvalue { <16 x i8>, <16 x i8> } undef, <16 x i8> %t0, 0
%res1 = insertvalue { <16 x i8>, <16 x i8> } %res0, <16 x i8> %t1, 1
ret {<16 x i8>, <16 x i8>} %res1
}
; Shouldn't be lowered to vlseg because it's unaligned
define {<8 x i16>, <8 x i16>} @vector_deinterleave_load_v8i16_v16i16_align1(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v8i16_v16i16_align1:
; CHECK: # %bb.0:
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
; CHECK-NEXT: vle8.v v10, (a0)
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vnsrl.wi v8, v10, 0
; CHECK-NEXT: vnsrl.wi v9, v10, 16
; CHECK-NEXT: ret
%vec = load <16 x i16>, ptr %p, align 1
%deinterleaved.results = call {<8 x i16>, <8 x i16>} @llvm.vector.deinterleave2.v16i16(<16 x i16> %vec)
%t0 = extractvalue { <8 x i16>, <8 x i16> } %deinterleaved.results, 0
%t1 = extractvalue { <8 x i16>, <8 x i16> } %deinterleaved.results, 1
%res0 = insertvalue { <8 x i16>, <8 x i16> } undef, <8 x i16> %t0, 0
%res1 = insertvalue { <8 x i16>, <8 x i16> } %res0, <8 x i16> %t1, 1
ret {<8 x i16>, <8 x i16>} %res1
}
define {<8 x i16>, <8 x i16>} @vector_deinterleave_load_v8i16_v16i16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v8i16_v16i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <16 x i16>, ptr %p
%deinterleaved.results = call {<8 x i16>, <8 x i16>} @llvm.vector.deinterleave2.v16i16(<16 x i16> %vec)
%t0 = extractvalue { <8 x i16>, <8 x i16> } %deinterleaved.results, 0
%t1 = extractvalue { <8 x i16>, <8 x i16> } %deinterleaved.results, 1
%res0 = insertvalue { <8 x i16>, <8 x i16> } undef, <8 x i16> %t0, 0
%res1 = insertvalue { <8 x i16>, <8 x i16> } %res0, <8 x i16> %t1, 1
ret {<8 x i16>, <8 x i16>} %res1
}
define {<4 x i32>, <4 x i32>} @vector_deinterleave_load_v4i32_vv8i32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v4i32_vv8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vlseg2e32.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <8 x i32>, ptr %p
%deinterleaved.results = call {<4 x i32>, <4 x i32>} @llvm.vector.deinterleave2.v8i32(<8 x i32> %vec)
%t0 = extractvalue { <4 x i32>, <4 x i32> } %deinterleaved.results, 0
%t1 = extractvalue { <4 x i32>, <4 x i32> } %deinterleaved.results, 1
%res0 = insertvalue { <4 x i32>, <4 x i32> } undef, <4 x i32> %t0, 0
%res1 = insertvalue { <4 x i32>, <4 x i32> } %res0, <4 x i32> %t1, 1
ret {<4 x i32>, <4 x i32>} %res1
}
define {<2 x i64>, <2 x i64>} @vector_deinterleave_load_v2i64_v4i64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v2i64_v4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vlseg2e64.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <4 x i64>, ptr %p
%deinterleaved.results = call {<2 x i64>, <2 x i64>} @llvm.vector.deinterleave2.v4i64(<4 x i64> %vec)
%t0 = extractvalue { <2 x i64>, <2 x i64> } %deinterleaved.results, 0
%t1 = extractvalue { <2 x i64>, <2 x i64> } %deinterleaved.results, 1
%res0 = insertvalue { <2 x i64>, <2 x i64> } undef, <2 x i64> %t0, 0
%res1 = insertvalue { <2 x i64>, <2 x i64> } %res0, <2 x i64> %t1, 1
ret {<2 x i64>, <2 x i64>} %res1
}
; Floats
define {<2 x bfloat>, <2 x bfloat>} @vector_deinterleave_load_v2bf16_v4bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v2bf16_v4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <4 x bfloat>, ptr %p
%deinterleaved.results = call {<2 x bfloat>, <2 x bfloat>} @llvm.vector.deinterleave2.v4bf16(<4 x bfloat> %vec)
%t0 = extractvalue { <2 x bfloat>, <2 x bfloat> } %deinterleaved.results, 0
%t1 = extractvalue { <2 x bfloat>, <2 x bfloat> } %deinterleaved.results, 1
%res0 = insertvalue { <2 x bfloat>, <2 x bfloat> } undef, <2 x bfloat> %t0, 0
%res1 = insertvalue { <2 x bfloat>, <2 x bfloat> } %res0, <2 x bfloat> %t1, 1
ret {<2 x bfloat>, <2 x bfloat>} %res1
}
define {<4 x bfloat>, <4 x bfloat>} @vector_deinterleave_load_v4bf16_v8bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v4bf16_v8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <8 x bfloat>, ptr %p
%deinterleaved.results = call {<4 x bfloat>, <4 x bfloat>} @llvm.vector.deinterleave2.v8bf16(<8 x bfloat> %vec)
%t0 = extractvalue { <4 x bfloat>, <4 x bfloat> } %deinterleaved.results, 0
%t1 = extractvalue { <4 x bfloat>, <4 x bfloat> } %deinterleaved.results, 1
%res0 = insertvalue { <4 x bfloat>, <4 x bfloat> } undef, <4 x bfloat> %t0, 0
%res1 = insertvalue { <4 x bfloat>, <4 x bfloat> } %res0, <4 x bfloat> %t1, 1
ret {<4 x bfloat>, <4 x bfloat>} %res1
}
define {<2 x half>, <2 x half>} @vector_deinterleave_load_v2f16_v4f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v2f16_v4f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <4 x half>, ptr %p
%deinterleaved.results = call {<2 x half>, <2 x half>} @llvm.vector.deinterleave2.v4f16(<4 x half> %vec)
%t0 = extractvalue { <2 x half>, <2 x half> } %deinterleaved.results, 0
%t1 = extractvalue { <2 x half>, <2 x half> } %deinterleaved.results, 1
%res0 = insertvalue { <2 x half>, <2 x half> } undef, <2 x half> %t0, 0
%res1 = insertvalue { <2 x half>, <2 x half> } %res0, <2 x half> %t1, 1
ret {<2 x half>, <2 x half>} %res1
}
define {<4 x half>, <4 x half>} @vector_deinterleave_load_v4f16_v8f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v4f16_v8f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <8 x half>, ptr %p
%deinterleaved.results = call {<4 x half>, <4 x half>} @llvm.vector.deinterleave2.v8f16(<8 x half> %vec)
%t0 = extractvalue { <4 x half>, <4 x half> } %deinterleaved.results, 0
%t1 = extractvalue { <4 x half>, <4 x half> } %deinterleaved.results, 1
%res0 = insertvalue { <4 x half>, <4 x half> } undef, <4 x half> %t0, 0
%res1 = insertvalue { <4 x half>, <4 x half> } %res0, <4 x half> %t1, 1
ret {<4 x half>, <4 x half>} %res1
}
define {<2 x float>, <2 x float>} @vector_deinterleave_load_v2f32_v4f32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v2f32_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vlseg2e32.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <4 x float>, ptr %p
%deinterleaved.results = call {<2 x float>, <2 x float>} @llvm.vector.deinterleave2.v4f32(<4 x float> %vec)
%t0 = extractvalue { <2 x float>, <2 x float> } %deinterleaved.results, 0
%t1 = extractvalue { <2 x float>, <2 x float> } %deinterleaved.results, 1
%res0 = insertvalue { <2 x float>, <2 x float> } undef, <2 x float> %t0, 0
%res1 = insertvalue { <2 x float>, <2 x float> } %res0, <2 x float> %t1, 1
ret {<2 x float>, <2 x float>} %res1
}
define {<8 x bfloat>, <8 x bfloat>} @vector_deinterleave_load_v8bf16_v16bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v8bf16_v16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <16 x bfloat>, ptr %p
%deinterleaved.results = call {<8 x bfloat>, <8 x bfloat>} @llvm.vector.deinterleave2.v16bf16(<16 x bfloat> %vec)
%t0 = extractvalue { <8 x bfloat>, <8 x bfloat> } %deinterleaved.results, 0
%t1 = extractvalue { <8 x bfloat>, <8 x bfloat> } %deinterleaved.results, 1
%res0 = insertvalue { <8 x bfloat>, <8 x bfloat> } undef, <8 x bfloat> %t0, 0
%res1 = insertvalue { <8 x bfloat>, <8 x bfloat> } %res0, <8 x bfloat> %t1, 1
ret {<8 x bfloat>, <8 x bfloat>} %res1
}
define {<8 x half>, <8 x half>} @vector_deinterleave_load_v8f16_v16f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v8f16_v16f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vlseg2e16.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <16 x half>, ptr %p
%deinterleaved.results = call {<8 x half>, <8 x half>} @llvm.vector.deinterleave2.v16f16(<16 x half> %vec)
%t0 = extractvalue { <8 x half>, <8 x half> } %deinterleaved.results, 0
%t1 = extractvalue { <8 x half>, <8 x half> } %deinterleaved.results, 1
%res0 = insertvalue { <8 x half>, <8 x half> } undef, <8 x half> %t0, 0
%res1 = insertvalue { <8 x half>, <8 x half> } %res0, <8 x half> %t1, 1
ret {<8 x half>, <8 x half>} %res1
}
define {<4 x float>, <4 x float>} @vector_deinterleave_load_v4f32_v8f32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v4f32_v8f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vlseg2e32.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <8 x float>, ptr %p
%deinterleaved.results = call {<4 x float>, <4 x float>} @llvm.vector.deinterleave2.v8f32(<8 x float> %vec)
%t0 = extractvalue { <4 x float>, <4 x float> } %deinterleaved.results, 0
%t1 = extractvalue { <4 x float>, <4 x float> } %deinterleaved.results, 1
%res0 = insertvalue { <4 x float>, <4 x float> } undef, <4 x float> %t0, 0
%res1 = insertvalue { <4 x float>, <4 x float> } %res0, <4 x float> %t1, 1
ret {<4 x float>, <4 x float>} %res1
}
define {<2 x double>, <2 x double>} @vector_deinterleave_load_v2f64_v4f64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_v2f64_v4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vlseg2e64.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <4 x double>, ptr %p
%deinterleaved.results = call {<2 x double>, <2 x double>} @llvm.vector.deinterleave2.v4f64(<4 x double> %vec)
%t0 = extractvalue { <2 x double>, <2 x double> } %deinterleaved.results, 0
%t1 = extractvalue { <2 x double>, <2 x double> } %deinterleaved.results, 1
%res0 = insertvalue { <2 x double>, <2 x double> } undef, <2 x double> %t0, 0
%res1 = insertvalue { <2 x double>, <2 x double> } %res0, <2 x double> %t1, 1
ret {<2 x double>, <2 x double>} %res1
}
define { <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor3(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor3:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg3e8.v v6, (a0)
; CHECK-NEXT: ret
%vec = load <24 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave3(<24 x i8> %vec)
%t0 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 0
%t1 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 1
%t2 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 2
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 0
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 0
ret { <8 x i8>, <8 x i8>, <8 x i8> } %res2
}
define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor4(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg4e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <32 x i8>, ptr %p
%d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave4(<32 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3
}
define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor5(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor5:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg5e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <40 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave5(<40 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4
}
define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor6(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor6:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg6e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <48 x i8>, ptr %p
%d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave6(<48 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
%res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5
}
define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor7(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor7:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg7e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <56 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave7(<56 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
%t6 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 6
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
%res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
%res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5, <8 x i8> %t6, 6
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res6
}
define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor8(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg8e8.v v8, (a0)
; CHECK-NEXT: vmv1r.v v15, v14
; CHECK-NEXT: ret
%vec = load <64 x i8>, ptr %p
%d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave8(<64 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
%t6 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 6
%t7 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 7
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
%res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
%res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5, <8 x i8> %t6, 6
%res7 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res6, <8 x i8> %t6, 7
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res7
}
|
