vrev.ll
12.7 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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=arm-eabi -mattr=+neon,+fullfp16 %s -o - | FileCheck %s
define <8 x i8> @test_vrev64D8(<8 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev64D8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.8 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i8> %tmp2
}
define <4 x i16> @test_vrev64D16(<4 x i16>* %A) nounwind {
; CHECK-LABEL: test_vrev64D16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.16 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x i16>, <4 x i16>* %A
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x i16> %tmp2
}
define <4 x half> @test_vrev64Df16(<4 x half>* %A) nounwind {
; CHECK-LABEL: test_vrev64Df16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.16 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x half>, <4 x half>* %A
%tmp2 = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x half> %tmp2
}
define <2 x i32> @test_vrev64D32(<2 x i32>* %A) nounwind {
; CHECK-LABEL: test_vrev64D32:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.32 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <2 x i32>, <2 x i32>* %A
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
ret <2 x i32> %tmp2
}
define <2 x float> @test_vrev64Df(<2 x float>* %A) nounwind {
; CHECK-LABEL: test_vrev64Df:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.32 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <2 x float>, <2 x float>* %A
%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> <i32 1, i32 0>
ret <2 x float> %tmp2
}
define <16 x i8> @test_vrev64Q8(<16 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev64Q8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev64.8 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <16 x i8>, <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
ret <16 x i8> %tmp2
}
define <8 x i16> @test_vrev64Q16(<8 x i16>* %A) nounwind {
; CHECK-LABEL: test_vrev64Q16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev64.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i16>, <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x i16> %tmp2
}
define <8 x half> @test_vrev64Qf16(<8 x half>* %A) nounwind {
; CHECK-LABEL: test_vrev64Qf16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev64.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x half>, <8 x half>* %A
%tmp2 = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x half> %tmp2
}
define <4 x i32> @test_vrev64Q32(<4 x i32>* %A) nounwind {
; CHECK-LABEL: test_vrev64Q32:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev64.32 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x i32>, <4 x i32>* %A
%tmp2 = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x i32> %tmp2
}
define <4 x float> @test_vrev64Qf(<4 x float>* %A) nounwind {
; CHECK-LABEL: test_vrev64Qf:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev64.32 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x float>, <4 x float>* %A
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x float> %tmp2
}
define <8 x i8> @test_vrev32D8(<8 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev32D8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev32.8 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x i8> %tmp2
}
define <4 x i16> @test_vrev32D16(<4 x i16>* %A) nounwind {
; CHECK-LABEL: test_vrev32D16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev32.16 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x i16>, <4 x i16>* %A
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x i16> %tmp2
}
define <4 x half> @test_vrev32Df16(<4 x half>* %A) nounwind {
; CHECK-LABEL: test_vrev32Df16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev32.16 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x half>, <4 x half>* %A
%tmp2 = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x half> %tmp2
}
define <16 x i8> @test_vrev32Q8(<16 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev32Q8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev32.8 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <16 x i8>, <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
ret <16 x i8> %tmp2
}
define <8 x i16> @test_vrev32Q16(<8 x i16>* %A) nounwind {
; CHECK-LABEL: test_vrev32Q16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev32.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i16>, <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x i16> %tmp2
}
define <8 x half> @test_vrev32Qf16(<8 x half>* %A) nounwind {
; CHECK-LABEL: test_vrev32Qf16:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev32.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x half>, <8 x half>* %A
%tmp2 = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x half> %tmp2
}
define <8 x i8> @test_vrev16D8(<8 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev16D8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev16.8 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x i8> %tmp2
}
define <16 x i8> @test_vrev16Q8(<16 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev16Q8:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev16.8 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <16 x i8>, <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
ret <16 x i8> %tmp2
}
; Undef shuffle indices should not prevent matching to VREV:
define <8 x i8> @test_vrev64D8_undef(<8 x i8>* %A) nounwind {
; CHECK-LABEL: test_vrev64D8_undef:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldr d16, [r0]
; CHECK-NEXT: vrev64.8 d16, d16
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 undef, i32 undef, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i8> %tmp2
}
define <8 x i16> @test_vrev32Q16_undef(<8 x i16>* %A) nounwind {
; CHECK-LABEL: test_vrev32Q16_undef:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev32.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x i16>, <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 undef, i32 0, i32 undef, i32 2, i32 5, i32 4, i32 7, i32 undef>
ret <8 x i16> %tmp2
}
define <8 x half> @test_vrev32Qf16_undef(<8 x half>* %A) nounwind {
; CHECK-LABEL: test_vrev32Qf16_undef:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]
; CHECK-NEXT: vrev32.16 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%tmp1 = load <8 x half>, <8 x half>* %A
%tmp2 = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> <i32 undef, i32 0, i32 undef, i32 2, i32 5, i32 4, i32 7, i32 undef>
ret <8 x half> %tmp2
}
; A vcombine feeding a VREV should not obscure things. Radar 8597007.
define void @test_with_vcombine(<4 x float>* %v) nounwind {
; CHECK-LABEL: test_with_vcombine:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.64 {d16, d17}, [r0:128]
; CHECK-NEXT: vadd.f32 d18, d17, d17
; CHECK-NEXT: vrev64.32 d16, d16
; CHECK-NEXT: vrev64.32 d17, d18
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
; CHECK-NEXT: mov pc, lr
%tmp1 = load <4 x float>, <4 x float>* %v, align 16
%tmp2 = bitcast <4 x float> %tmp1 to <2 x double>
%tmp3 = extractelement <2 x double> %tmp2, i32 0
%tmp4 = bitcast double %tmp3 to <2 x float>
%tmp5 = extractelement <2 x double> %tmp2, i32 1
%tmp6 = bitcast double %tmp5 to <2 x float>
%tmp7 = fadd <2 x float> %tmp6, %tmp6
%tmp8 = shufflevector <2 x float> %tmp4, <2 x float> %tmp7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
store <4 x float> %tmp8, <4 x float>* %v, align 16
ret void
}
; The type <2 x i16> is legalized to <2 x i32> and need to be trunc-stored
; to <2 x i16> when stored to memory.
define void @test_vrev64(<4 x i16>* nocapture %source, <2 x i16>* nocapture %dst) nounwind ssp {
; CHECK-LABEL: test_vrev64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]
; CHECK-NEXT: vmov.u16 r0, d17[2]
; CHECK-NEXT: vmov.u16 r2, d17[1]
; CHECK-NEXT: vmov.32 d16[0], r0
; CHECK-NEXT: vmov.32 d16[1], r2
; CHECK-NEXT: vuzp.16 d16, d17
; CHECK-NEXT: vst1.32 {d16[0]}, [r1:32]
; CHECK-NEXT: mov pc, lr
entry:
%0 = bitcast <4 x i16>* %source to <8 x i16>*
%tmp2 = load <8 x i16>, <8 x i16>* %0, align 4
%tmp3 = extractelement <8 x i16> %tmp2, i32 6
%tmp5 = insertelement <2 x i16> undef, i16 %tmp3, i32 0
%tmp9 = extractelement <8 x i16> %tmp2, i32 5
%tmp11 = insertelement <2 x i16> %tmp5, i16 %tmp9, i32 1
store <2 x i16> %tmp11, <2 x i16>* %dst, align 4
ret void
}
; Test vrev of float4
define void @float_vrev64(float* nocapture %source, <4 x float>* nocapture %dest) nounwind noinline ssp {
; CHECK-LABEL: float_vrev64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.i32 q8, #0x0
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: add r0, r1, #176
; CHECK-NEXT: vext.32 q8, q9, q8, #3
; CHECK-NEXT: vrev64.32 q8, q8
; CHECK-NEXT: vst1.32 {d16, d17}, [r0]
; CHECK-NEXT: mov pc, lr
entry:
%0 = bitcast float* %source to <4 x float>*
%tmp2 = load <4 x float>, <4 x float>* %0, align 4
%tmp5 = shufflevector <4 x float> <float 0.000000e+00, float undef, float undef, float undef>, <4 x float> %tmp2, <4 x i32> <i32 0, i32 7, i32 0, i32 0>
%arrayidx8 = getelementptr inbounds <4 x float>, <4 x float>* %dest, i32 11
store <4 x float> %tmp5, <4 x float>* %arrayidx8, align 4
ret void
}
define <4 x i32> @test_vrev32_bswap(<4 x i32> %source) nounwind {
; CHECK-LABEL: test_vrev32_bswap:
; CHECK: @ %bb.0:
; CHECK-NEXT: vmov d17, r2, r3
; CHECK-NEXT: vmov d16, r0, r1
; CHECK-NEXT: vrev32.8 q8, q8
; CHECK-NEXT: vmov r0, r1, d16
; CHECK-NEXT: vmov r2, r3, d17
; CHECK-NEXT: mov pc, lr
%bswap = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %source)
ret <4 x i32> %bswap
}
declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>) nounwind readnone