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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+complxnum,+neon -o - | FileCheck %s
target triple = "aarch64"
; Expected to transform
; *p = (a * b);
; return (a * b) * a;
define <4 x float> @mul_triangle(<4 x float> %a, <4 x float> %b, ptr %p) {
; CHECK-LABEL: mul_triangle:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: movi v3.2d, #0000000000000000
; CHECK-NEXT: movi v2.2d, #0000000000000000
; CHECK-NEXT: fcmla v3.4s, v1.4s, v0.4s, #0
; CHECK-NEXT: fcmla v3.4s, v1.4s, v0.4s, #90
; CHECK-NEXT: fcmla v2.4s, v0.4s, v3.4s, #0
; CHECK-NEXT: str q3, [x0]
; CHECK-NEXT: fcmla v2.4s, v0.4s, v3.4s, #90
; CHECK-NEXT: mov v0.16b, v2.16b
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec35 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec37 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec38 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec37, %strided.vec
%1 = fmul fast <2 x float> %strided.vec38, %strided.vec35
%2 = fsub fast <2 x float> %0, %1
%3 = fmul fast <2 x float> %2, %strided.vec35
%4 = fmul fast <2 x float> %strided.vec38, %strided.vec
%5 = fmul fast <2 x float> %strided.vec35, %strided.vec37
%6 = fadd fast <2 x float> %4, %5
%otheruse = shufflevector <2 x float> %2, <2 x float> %6, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x float> %otheruse, ptr %p
%7 = fmul fast <2 x float> %6, %strided.vec
%8 = fadd fast <2 x float> %3, %7
%9 = fmul fast <2 x float> %2, %strided.vec
%10 = fmul fast <2 x float> %6, %strided.vec35
%11 = fsub fast <2 x float> %9, %10
%interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to not transform. Shows that external use prevents deinterleaving.
; *p = (a * b).real();
; return (a * b) * a;
define <4 x float> @mul_triangle_external_use(<4 x float> %a, <4 x float> %b, ptr %p) {
; CHECK-LABEL: mul_triangle_external_use:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v2.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: ext v3.16b, v1.16b, v1.16b, #8
; CHECK-NEXT: zip2 v4.2s, v0.2s, v2.2s
; CHECK-NEXT: zip1 v0.2s, v0.2s, v2.2s
; CHECK-NEXT: zip1 v5.2s, v1.2s, v3.2s
; CHECK-NEXT: zip2 v1.2s, v1.2s, v3.2s
; CHECK-NEXT: fmul v2.2s, v4.2s, v5.2s
; CHECK-NEXT: fmul v3.2s, v1.2s, v4.2s
; CHECK-NEXT: fmla v2.2s, v0.2s, v1.2s
; CHECK-NEXT: fneg v1.2s, v3.2s
; CHECK-NEXT: fmul v3.2s, v2.2s, v4.2s
; CHECK-NEXT: fmla v1.2s, v0.2s, v5.2s
; CHECK-NEXT: fmul v5.2s, v2.2s, v0.2s
; CHECK-NEXT: str d2, [x0]
; CHECK-NEXT: fneg v3.2s, v3.2s
; CHECK-NEXT: fmla v5.2s, v4.2s, v1.2s
; CHECK-NEXT: fmla v3.2s, v0.2s, v1.2s
; CHECK-NEXT: zip1 v0.4s, v3.4s, v5.4s
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec35 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec37 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec38 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec37, %strided.vec
%1 = fmul fast <2 x float> %strided.vec38, %strided.vec35
%2 = fsub fast <2 x float> %0, %1
%3 = fmul fast <2 x float> %2, %strided.vec35
%4 = fmul fast <2 x float> %strided.vec38, %strided.vec
%5 = fmul fast <2 x float> %strided.vec35, %strided.vec37
%6 = fadd fast <2 x float> %4, %5
store <2 x float> %6, ptr %p
%7 = fmul fast <2 x float> %6, %strided.vec
%8 = fadd fast <2 x float> %3, %7
%9 = fmul fast <2 x float> %2, %strided.vec
%10 = fmul fast <2 x float> %6, %strided.vec35
%11 = fsub fast <2 x float> %9, %10
%interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to transform partially (only d * c). Shows that external use of shufflevector does not prevent deinterleaving.
; *p1 = (a * b).real();
; *p2 = (a * b) * c;
; return d * c;
define <4 x float> @multiple_muls_shuffle_external(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, ptr %p1, ptr %p2) {
; CHECK-LABEL: multiple_muls_shuffle_external:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v5.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: ext v6.16b, v1.16b, v1.16b, #8
; CHECK-NEXT: movi v4.2d, #0000000000000000
; CHECK-NEXT: zip2 v7.2s, v0.2s, v5.2s
; CHECK-NEXT: zip1 v0.2s, v0.2s, v5.2s
; CHECK-NEXT: zip1 v16.2s, v1.2s, v6.2s
; CHECK-NEXT: zip2 v1.2s, v1.2s, v6.2s
; CHECK-NEXT: ext v6.16b, v2.16b, v2.16b, #8
; CHECK-NEXT: fcmla v4.4s, v3.4s, v2.4s, #0
; CHECK-NEXT: fmul v5.2s, v16.2s, v7.2s
; CHECK-NEXT: fmul v7.2s, v1.2s, v7.2s
; CHECK-NEXT: fcmla v4.4s, v3.4s, v2.4s, #90
; CHECK-NEXT: fmla v5.2s, v0.2s, v1.2s
; CHECK-NEXT: fneg v1.2s, v7.2s
; CHECK-NEXT: zip1 v7.2s, v2.2s, v6.2s
; CHECK-NEXT: zip2 v6.2s, v2.2s, v6.2s
; CHECK-NEXT: fmla v1.2s, v0.2s, v16.2s
; CHECK-NEXT: fmul v17.2s, v7.2s, v5.2s
; CHECK-NEXT: fmul v0.2s, v6.2s, v5.2s
; CHECK-NEXT: str d1, [x0]
; CHECK-NEXT: fmla v17.2s, v1.2s, v6.2s
; CHECK-NEXT: fneg v16.2s, v0.2s
; CHECK-NEXT: mov v0.16b, v4.16b
; CHECK-NEXT: fmla v16.2s, v1.2s, v7.2s
; CHECK-NEXT: st2 { v16.2s, v17.2s }, [x1]
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec88 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec90 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec91 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec91, %strided.vec
%1 = fmul fast <2 x float> %strided.vec90, %strided.vec88
%2 = fadd fast <2 x float> %0, %1
%3 = fmul fast <2 x float> %strided.vec90, %strided.vec
%4 = fmul fast <2 x float> %strided.vec91, %strided.vec88
%5 = fsub fast <2 x float> %3, %4
store <2 x float> %5, ptr %p1
%strided.vec93 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec94 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%6 = fmul fast <2 x float> %strided.vec94, %5
%7 = fmul fast <2 x float> %strided.vec93, %2
%8 = fadd fast <2 x float> %6, %7
%9 = fmul fast <2 x float> %strided.vec93, %5
%10 = fmul fast <2 x float> %strided.vec94, %2
%11 = fsub fast <2 x float> %9, %10
%interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x float> %interleaved.vec, ptr %p2
%strided.vec96 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec97 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%12 = fmul fast <2 x float> %strided.vec96, %strided.vec94
%13 = fmul fast <2 x float> %strided.vec97, %strided.vec93
%14 = fadd fast <2 x float> %13, %12
%15 = fmul fast <2 x float> %strided.vec96, %strided.vec93
%16 = fmul fast <2 x float> %strided.vec97, %strided.vec94
%17 = fsub fast <2 x float> %15, %16
%interleaved.vec98 = shufflevector <2 x float> %17, <2 x float> %14, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec98
}
; Same as above but data are loaded from memory instead of being passes as arguments.
; Expected to transform partially (only d * c).
; Shows that ld2 is not generated for `c` although it used by both complex `d * c` and non-complex `(a * b) * c` instruction chains.
define <4 x float> @multiple_muls_shuffle_external_with_loads(ptr %ptr_a, ptr %ptr_b, ptr %ptr_c, ptr %ptr_d, ptr %p1, ptr %p2) {
; CHECK-LABEL: multiple_muls_shuffle_external_with_loads:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ld2 { v1.2s, v2.2s }, [x0]
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: ld2 { v3.2s, v4.2s }, [x1]
; CHECK-NEXT: fmul v5.2s, v4.2s, v2.2s
; CHECK-NEXT: fmul v7.2s, v3.2s, v2.2s
; CHECK-NEXT: fneg v5.2s, v5.2s
; CHECK-NEXT: fmla v7.2s, v1.2s, v4.2s
; CHECK-NEXT: fmla v5.2s, v1.2s, v3.2s
; CHECK-NEXT: str d5, [x4]
; CHECK-NEXT: ldr q6, [x2]
; CHECK-NEXT: ext v16.16b, v6.16b, v6.16b, #8
; CHECK-NEXT: zip1 v1.2s, v6.2s, v16.2s
; CHECK-NEXT: zip2 v2.2s, v6.2s, v16.2s
; CHECK-NEXT: fmul v4.2s, v1.2s, v7.2s
; CHECK-NEXT: fmul v7.2s, v2.2s, v7.2s
; CHECK-NEXT: fmla v4.2s, v5.2s, v2.2s
; CHECK-NEXT: fneg v3.2s, v7.2s
; CHECK-NEXT: fmla v3.2s, v5.2s, v1.2s
; CHECK-NEXT: st2 { v3.2s, v4.2s }, [x5]
; CHECK-NEXT: ldr q1, [x3]
; CHECK-NEXT: fcmla v0.4s, v1.4s, v6.4s, #0
; CHECK-NEXT: fcmla v0.4s, v1.4s, v6.4s, #90
; CHECK-NEXT: ret
entry:
%a = load <4 x float>, ptr %ptr_a
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec88 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%b = load <4 x float>, ptr %ptr_b
%strided.vec90 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec91 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec91, %strided.vec
%1 = fmul fast <2 x float> %strided.vec90, %strided.vec88
%2 = fadd fast <2 x float> %0, %1
%3 = fmul fast <2 x float> %strided.vec90, %strided.vec
%4 = fmul fast <2 x float> %strided.vec91, %strided.vec88
%5 = fsub fast <2 x float> %3, %4
store <2 x float> %5, ptr %p1
%c = load <4 x float>, ptr %ptr_c
%strided.vec93 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec94 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%6 = fmul fast <2 x float> %strided.vec94, %5
%7 = fmul fast <2 x float> %strided.vec93, %2
%8 = fadd fast <2 x float> %6, %7
%9 = fmul fast <2 x float> %strided.vec93, %5
%10 = fmul fast <2 x float> %strided.vec94, %2
%11 = fsub fast <2 x float> %9, %10
%interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x float> %interleaved.vec, ptr %p2
%d = load <4 x float>, ptr %ptr_d
%strided.vec96 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec97 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%12 = fmul fast <2 x float> %strided.vec96, %strided.vec94
%13 = fmul fast <2 x float> %strided.vec97, %strided.vec93
%14 = fadd fast <2 x float> %13, %12
%15 = fmul fast <2 x float> %strided.vec96, %strided.vec93
%16 = fmul fast <2 x float> %strided.vec97, %strided.vec94
%17 = fsub fast <2 x float> %15, %16
%interleaved.vec98 = shufflevector <2 x float> %17, <2 x float> %14, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec98
}
; Expected to not transform. Shows that external use prevents deinterleaving whole chain.
; *p1 = (a * b).real();
; *p2 = (a * b) * (d * c);
; return d * c;
define <4 x float> @multiple_muls_mul_external(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, ptr %p1, ptr %p2) {
; CHECK-LABEL: multiple_muls_mul_external:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v5.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: ext v6.16b, v1.16b, v1.16b, #8
; CHECK-NEXT: ext v4.16b, v3.16b, v3.16b, #8
; CHECK-NEXT: ext v7.16b, v2.16b, v2.16b, #8
; CHECK-NEXT: zip2 v16.2s, v0.2s, v5.2s
; CHECK-NEXT: zip2 v17.2s, v1.2s, v6.2s
; CHECK-NEXT: zip1 v0.2s, v0.2s, v5.2s
; CHECK-NEXT: zip1 v1.2s, v1.2s, v6.2s
; CHECK-NEXT: zip1 v18.2s, v2.2s, v7.2s
; CHECK-NEXT: zip2 v2.2s, v2.2s, v7.2s
; CHECK-NEXT: zip2 v7.2s, v3.2s, v4.2s
; CHECK-NEXT: zip1 v3.2s, v3.2s, v4.2s
; CHECK-NEXT: fmul v19.2s, v16.2s, v17.2s
; CHECK-NEXT: fmul v5.2s, v18.2s, v7.2s
; CHECK-NEXT: fmul v6.2s, v2.2s, v7.2s
; CHECK-NEXT: fneg v4.2s, v19.2s
; CHECK-NEXT: fmul v7.2s, v0.2s, v17.2s
; CHECK-NEXT: fmla v5.2s, v3.2s, v2.2s
; CHECK-NEXT: fneg v2.2s, v6.2s
; CHECK-NEXT: fmla v4.2s, v1.2s, v0.2s
; CHECK-NEXT: fmla v7.2s, v1.2s, v16.2s
; CHECK-NEXT: fmla v2.2s, v3.2s, v18.2s
; CHECK-NEXT: fmul v17.2s, v4.2s, v5.2s
; CHECK-NEXT: fmul v0.2s, v7.2s, v5.2s
; CHECK-NEXT: str d4, [x0]
; CHECK-NEXT: fmla v17.2s, v2.2s, v7.2s
; CHECK-NEXT: fneg v16.2s, v0.2s
; CHECK-NEXT: zip1 v0.4s, v2.4s, v5.4s
; CHECK-NEXT: fmla v16.2s, v2.2s, v4.2s
; CHECK-NEXT: st2 { v16.2s, v17.2s }, [x1]
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec126 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec128 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec129 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul nnan ninf contract <2 x float> %strided.vec, %strided.vec129
%1 = fmul nnan ninf contract <2 x float> %strided.vec126, %strided.vec128
%2 = fadd nnan ninf contract <2 x float> %1, %0
%3 = fmul nnan ninf contract <2 x float> %strided.vec, %strided.vec128
%4 = fmul nnan ninf contract <2 x float> %strided.vec126, %strided.vec129
%5 = fsub nnan ninf contract <2 x float> %3, %4
store <2 x float> %5, ptr %p1
%strided.vec131 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec132 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec134 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec135 = shufflevector <4 x float> %d, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%6 = fmul nnan ninf contract <2 x float> %strided.vec131, %strided.vec135
%7 = fmul nnan ninf contract <2 x float> %strided.vec132, %strided.vec134
%8 = fadd nnan ninf contract <2 x float> %7, %6
%9 = fmul nnan ninf contract <2 x float> %strided.vec131, %strided.vec134
%10 = fmul nnan ninf contract <2 x float> %strided.vec132, %strided.vec135
%11 = fsub nnan ninf contract <2 x float> %9, %10
%12 = fmul nnan ninf contract <2 x float> %5, %8
%13 = fmul nnan ninf contract <2 x float> %2, %11
%14 = fadd nnan ninf contract <2 x float> %13, %12
%15 = fmul nnan ninf contract <2 x float> %5, %11
%16 = fmul nnan ninf contract <2 x float> %2, %8
%17 = fsub nnan ninf contract <2 x float> %15, %16
%interleaved.vec = shufflevector <2 x float> %17, <2 x float> %14, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x float> %interleaved.vec, ptr %p2
%interleaved.vec136 = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec136
}
; Expected to transform. Shows that composite common subexpression is not generated twice.
; u[i] = a[i] * b[i] - (c[i] * d[i] + g[i] * h[i]);
; v[i] = e[i] * f[i] + (c[i] * d[i] + g[i] * h[i]);
define void @mul_add_common_mul_add_mul(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double> %d, <4 x double> %e, <4 x double> %f, <4 x double> %g, <4 x double> %h, ptr %p1, ptr %p2) {
; CHECK-LABEL: mul_add_common_mul_add_mul:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ldp q17, q16, [sp, #64]
; CHECK-NEXT: movi v20.2d, #0000000000000000
; CHECK-NEXT: movi v21.2d, #0000000000000000
; CHECK-NEXT: movi v24.2d, #0000000000000000
; CHECK-NEXT: movi v25.2d, #0000000000000000
; CHECK-NEXT: ldp q19, q18, [sp, #96]
; CHECK-NEXT: fcmla v24.2d, v2.2d, v0.2d, #0
; CHECK-NEXT: fcmla v25.2d, v3.2d, v1.2d, #0
; CHECK-NEXT: fcmla v20.2d, v19.2d, v17.2d, #0
; CHECK-NEXT: fcmla v24.2d, v2.2d, v0.2d, #90
; CHECK-NEXT: fcmla v21.2d, v18.2d, v16.2d, #0
; CHECK-NEXT: ldp q23, q22, [sp, #32]
; CHECK-NEXT: fcmla v20.2d, v19.2d, v17.2d, #90
; CHECK-NEXT: fcmla v25.2d, v3.2d, v1.2d, #90
; CHECK-NEXT: fcmla v21.2d, v18.2d, v16.2d, #90
; CHECK-NEXT: fcmla v20.2d, v6.2d, v4.2d, #0
; CHECK-NEXT: ldp q1, q0, [sp]
; CHECK-NEXT: fcmla v21.2d, v7.2d, v5.2d, #0
; CHECK-NEXT: fcmla v20.2d, v6.2d, v4.2d, #90
; CHECK-NEXT: fcmla v21.2d, v7.2d, v5.2d, #90
; CHECK-NEXT: fsub v2.2d, v24.2d, v20.2d
; CHECK-NEXT: fcmla v20.2d, v1.2d, v23.2d, #0
; CHECK-NEXT: fsub v3.2d, v25.2d, v21.2d
; CHECK-NEXT: fcmla v21.2d, v0.2d, v22.2d, #0
; CHECK-NEXT: fcmla v20.2d, v1.2d, v23.2d, #90
; CHECK-NEXT: stp q2, q3, [x0]
; CHECK-NEXT: fcmla v21.2d, v0.2d, v22.2d, #90
; CHECK-NEXT: stp q20, q21, [x1]
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec123 = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%strided.vec125 = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec126 = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x double> %strided.vec125, %strided.vec
%1 = fmul fast <2 x double> %strided.vec126, %strided.vec
%2 = fmul fast <2 x double> %strided.vec125, %strided.vec123
%3 = fadd fast <2 x double> %1, %2
%strided.vec128 = shufflevector <4 x double> %c, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec129 = shufflevector <4 x double> %c, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%strided.vec131 = shufflevector <4 x double> %d, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec132 = shufflevector <4 x double> %d, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%4 = fmul fast <2 x double> %strided.vec131, %strided.vec128
%5 = fmul fast <2 x double> %strided.vec132, %strided.vec129
%6 = fmul fast <2 x double> %strided.vec132, %strided.vec128
%7 = fmul fast <2 x double> %strided.vec131, %strided.vec129
%8 = fsub fast <2 x double> %4, %5
%strided.vec134 = shufflevector <4 x double> %g, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec135 = shufflevector <4 x double> %g, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%strided.vec137 = shufflevector <4 x double> %h, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec138 = shufflevector <4 x double> %h, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%9 = fmul fast <2 x double> %strided.vec138, %strided.vec134
%10 = fmul fast <2 x double> %strided.vec137, %strided.vec135
%11 = fmul fast <2 x double> %strided.vec137, %strided.vec134
%12 = fmul fast <2 x double> %strided.vec135, %strided.vec138
%13 = fsub fast <2 x double> %11, %12
%14 = fadd fast <2 x double> %13, %8
%15 = fadd fast <2 x double> %6, %7
%16 = fadd fast <2 x double> %15, %9
%17 = fadd fast <2 x double> %16, %10
%18 = fmul fast <2 x double> %strided.vec126, %strided.vec123
%19 = fadd fast <2 x double> %18, %14
%20 = fsub fast <2 x double> %0, %19
%21 = fsub fast <2 x double> %3, %17
%interleaved.vec = shufflevector <2 x double> %20, <2 x double> %21, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x double> %interleaved.vec, ptr %p1, align 8
%strided.vec140 = shufflevector <4 x double> %e, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec141 = shufflevector <4 x double> %e, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%strided.vec143 = shufflevector <4 x double> %f, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%strided.vec144 = shufflevector <4 x double> %f, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%22 = fmul fast <2 x double> %strided.vec143, %strided.vec140
%23 = fmul fast <2 x double> %strided.vec144, %strided.vec140
%24 = fmul fast <2 x double> %strided.vec143, %strided.vec141
%25 = fadd fast <2 x double> %22, %14
%26 = fmul fast <2 x double> %strided.vec144, %strided.vec141
%27 = fsub fast <2 x double> %25, %26
%28 = fadd fast <2 x double> %24, %17
%29 = fadd fast <2 x double> %28, %23
%interleaved.vec145 = shufflevector <2 x double> %27, <2 x double> %29, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x double> %interleaved.vec145, ptr %p2, align 8
ret void
}
|
