File: complex-deinterleaving-add-mull-scalable-contract.ll

package info (click to toggle)
llvm-toolchain-17 1%3A17.0.6-22
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,799,624 kB
  • sloc: cpp: 6,428,607; ansic: 1,383,196; asm: 793,408; python: 223,504; objc: 75,364; f90: 60,502; lisp: 33,869; pascal: 15,282; sh: 9,684; perl: 7,453; ml: 4,937; awk: 3,523; makefile: 2,889; javascript: 2,149; xml: 888; fortran: 619; cs: 573
file content (273 lines) | stat: -rw-r--r-- 16,464 bytes parent folder | download | duplicates (2)
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+sve -o - | FileCheck %s

target triple = "aarch64-unknown-linux-gnu"

; a * b + c
define <vscale x 4 x double> @mull_add(<vscale x 4 x double> %a, <vscale x 4 x double> %b, <vscale x 4 x double> %c) {
; CHECK-LABEL: mull_add:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    uzp2 z6.d, z2.d, z3.d
; CHECK-NEXT:    uzp2 z7.d, z0.d, z1.d
; CHECK-NEXT:    uzp1 z0.d, z0.d, z1.d
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    uzp1 z1.d, z2.d, z3.d
; CHECK-NEXT:    fmul z2.d, z0.d, z6.d
; CHECK-NEXT:    fmla z2.d, p0/m, z7.d, z1.d
; CHECK-NEXT:    fmul z3.d, z7.d, z6.d
; CHECK-NEXT:    fnmsb z0.d, p0/m, z1.d, z3.d
; CHECK-NEXT:    uzp2 z1.d, z4.d, z5.d
; CHECK-NEXT:    uzp1 z3.d, z4.d, z5.d
; CHECK-NEXT:    fadd z3.d, z3.d, z0.d
; CHECK-NEXT:    fadd z1.d, z2.d, z1.d
; CHECK-NEXT:    zip1 z0.d, z3.d, z1.d
; CHECK-NEXT:    zip2 z1.d, z3.d, z1.d
; CHECK-NEXT:    ret
entry:
  %strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
  %0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
  %1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
  %strided.vec29 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
  %2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec29, 0
  %3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec29, 1
  %4 = fmul contract <vscale x 2 x double> %0, %3
  %5 = fmul contract <vscale x 2 x double> %1, %2
  %6 = fadd contract <vscale x 2 x double> %5, %4
  %7 = fmul contract <vscale x 2 x double> %0, %2
  %8 = fmul contract <vscale x 2 x double> %1, %3
  %9 = fsub contract <vscale x 2 x double> %7, %8
  %strided.vec31 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
  %10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec31, 0
  %11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec31, 1
  %12 = fadd contract <vscale x 2 x double> %10, %9
  %13 = fadd contract <vscale x 2 x double> %6, %11
  %interleaved.vec = tail call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %12, <vscale x 2 x double> %13)
  ret <vscale x 4 x double> %interleaved.vec
}

; a * b + c * d
define <vscale x 4 x double> @mul_add_mull(<vscale x 4 x double> %a, <vscale x 4 x double> %b, <vscale x 4 x double> %c, <vscale x 4 x double> %d) {
; CHECK-LABEL: mul_add_mull:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov z24.d, #0 // =0x0
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    mov z25.d, z24.d
; CHECK-NEXT:    mov z26.d, z24.d
; CHECK-NEXT:    mov z27.d, z24.d
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #0
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #0
; CHECK-NEXT:    fcmla z27.d, p0/m, z6.d, z4.d, #0
; CHECK-NEXT:    fcmla z24.d, p0/m, z7.d, z5.d, #0
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #90
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #90
; CHECK-NEXT:    fcmla z27.d, p0/m, z6.d, z4.d, #90
; CHECK-NEXT:    fcmla z24.d, p0/m, z7.d, z5.d, #90
; CHECK-NEXT:    fadd z0.d, z25.d, z27.d
; CHECK-NEXT:    fadd z1.d, z26.d, z24.d
; CHECK-NEXT:    ret
entry:
  %strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
  %0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
  %1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
  %strided.vec52 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
  %2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec52, 0
  %3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec52, 1
  %4 = fmul contract <vscale x 2 x double> %0, %3
  %5 = fmul contract <vscale x 2 x double> %1, %2
  %6 = fadd contract <vscale x 2 x double> %5, %4
  %7 = fmul contract <vscale x 2 x double> %0, %2
  %8 = fmul contract <vscale x 2 x double> %1, %3
  %9 = fsub contract <vscale x 2 x double> %7, %8
  %strided.vec54 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
  %10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 0
  %11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 1
  %strided.vec56 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
  %12 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 0
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 1
  %14 = fmul contract <vscale x 2 x double> %10, %13
  %15 = fmul contract <vscale x 2 x double> %11, %12
  %16 = fadd contract <vscale x 2 x double> %15, %14
  %17 = fmul contract <vscale x 2 x double> %10, %12
  %18 = fmul contract <vscale x 2 x double> %11, %13
  %19 = fsub contract <vscale x 2 x double> %17, %18
  %20 = fadd contract <vscale x 2 x double> %9, %19
  %21 = fadd contract <vscale x 2 x double> %6, %16
  %interleaved.vec = tail call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %20, <vscale x 2 x double> %21)
  ret <vscale x 4 x double> %interleaved.vec
}

; a * b - c * d
define <vscale x 4 x double> @mul_sub_mull(<vscale x 4 x double> %a, <vscale x 4 x double> %b, <vscale x 4 x double> %c, <vscale x 4 x double> %d) {
; CHECK-LABEL: mul_sub_mull:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov z24.d, #0 // =0x0
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    mov z25.d, z24.d
; CHECK-NEXT:    mov z26.d, z24.d
; CHECK-NEXT:    mov z27.d, z24.d
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #0
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #0
; CHECK-NEXT:    fcmla z27.d, p0/m, z6.d, z4.d, #0
; CHECK-NEXT:    fcmla z24.d, p0/m, z7.d, z5.d, #0
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #90
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #90
; CHECK-NEXT:    fcmla z27.d, p0/m, z6.d, z4.d, #90
; CHECK-NEXT:    fcmla z24.d, p0/m, z7.d, z5.d, #90
; CHECK-NEXT:    fsub z0.d, z25.d, z27.d
; CHECK-NEXT:    fsub z1.d, z26.d, z24.d
; CHECK-NEXT:    ret
entry:
  %strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
  %0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
  %1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
  %strided.vec52 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
  %2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec52, 0
  %3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec52, 1
  %4 = fmul contract <vscale x 2 x double> %0, %3
  %5 = fmul contract <vscale x 2 x double> %1, %2
  %6 = fadd contract <vscale x 2 x double> %5, %4
  %7 = fmul contract <vscale x 2 x double> %0, %2
  %8 = fmul contract <vscale x 2 x double> %1, %3
  %9 = fsub contract <vscale x 2 x double> %7, %8
  %strided.vec54 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
  %10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 0
  %11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 1
  %strided.vec56 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
  %12 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 0
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 1
  %14 = fmul contract <vscale x 2 x double> %10, %13
  %15 = fmul contract <vscale x 2 x double> %11, %12
  %16 = fadd contract <vscale x 2 x double> %15, %14
  %17 = fmul contract <vscale x 2 x double> %10, %12
  %18 = fmul contract <vscale x 2 x double> %11, %13
  %19 = fsub contract <vscale x 2 x double> %17, %18
  %20 = fsub contract <vscale x 2 x double> %9, %19
  %21 = fsub contract <vscale x 2 x double> %6, %16
  %interleaved.vec = tail call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %20, <vscale x 2 x double> %21)
  ret <vscale x 4 x double> %interleaved.vec
}

; a * b + conj(c) * d
define <vscale x 4 x double> @mul_conj_mull(<vscale x 4 x double> %a, <vscale x 4 x double> %b, <vscale x 4 x double> %c, <vscale x 4 x double> %d) {
; CHECK-LABEL: mul_conj_mull:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov z24.d, #0 // =0x0
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    mov z25.d, z24.d
; CHECK-NEXT:    mov z26.d, z24.d
; CHECK-NEXT:    mov z27.d, z24.d
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #0
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #0
; CHECK-NEXT:    fcmla z27.d, p0/m, z4.d, z6.d, #0
; CHECK-NEXT:    fcmla z24.d, p0/m, z5.d, z7.d, #0
; CHECK-NEXT:    fcmla z25.d, p0/m, z2.d, z0.d, #90
; CHECK-NEXT:    fcmla z26.d, p0/m, z3.d, z1.d, #90
; CHECK-NEXT:    fcmla z27.d, p0/m, z4.d, z6.d, #270
; CHECK-NEXT:    fcmla z24.d, p0/m, z5.d, z7.d, #270
; CHECK-NEXT:    fadd z0.d, z25.d, z27.d
; CHECK-NEXT:    fadd z1.d, z26.d, z24.d
; CHECK-NEXT:    ret
entry:
  %strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
  %0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
  %1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
  %strided.vec60 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
  %2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec60, 0
  %3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec60, 1
  %4 = fmul contract <vscale x 2 x double> %0, %3
  %5 = fmul contract <vscale x 2 x double> %1, %2
  %6 = fadd contract <vscale x 2 x double> %5, %4
  %7 = fmul contract <vscale x 2 x double> %0, %2
  %8 = fmul contract <vscale x 2 x double> %1, %3
  %9 = fsub contract <vscale x 2 x double> %7, %8
  %strided.vec62 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
  %10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec62, 0
  %11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec62, 1
  %strided.vec64 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
  %12 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec64, 0
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec64, 1
  %14 = fmul contract <vscale x 2 x double> %10, %13
  %15 = fmul contract <vscale x 2 x double> %11, %12
  %16 = fsub contract <vscale x 2 x double> %14, %15
  %17 = fmul contract <vscale x 2 x double> %10, %12
  %18 = fmul contract <vscale x 2 x double> %11, %13
  %19 = fadd contract <vscale x 2 x double> %17, %18
  %20 = fadd contract <vscale x 2 x double> %9, %19
  %21 = fadd contract <vscale x 2 x double> %6, %16
  %interleaved.vec = tail call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %20, <vscale x 2 x double> %21)
  ret <vscale x 4 x double> %interleaved.vec
}

; a + b + 1i * c * d
define <vscale x 4 x double> @mul_add_rot_mull(<vscale x 4 x double> %a, <vscale x 4 x double> %b, <vscale x 4 x double> %c, <vscale x 4 x double> %d) {
; CHECK-LABEL: mul_add_rot_mull:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    uzp2 z24.d, z4.d, z5.d
; CHECK-NEXT:    mov z26.d, #0 // =0x0
; CHECK-NEXT:    mov z25.d, z24.d
; CHECK-NEXT:    and z26.d, z26.d, #0x7fffffffffffffff
; CHECK-NEXT:    and z25.d, z25.d, #0x8000000000000000
; CHECK-NEXT:    uzp2 z27.d, z0.d, z1.d
; CHECK-NEXT:    uzp1 z0.d, z0.d, z1.d
; CHECK-NEXT:    uzp1 z1.d, z4.d, z5.d
; CHECK-NEXT:    orr z5.d, z26.d, z25.d
; CHECK-NEXT:    uzp1 z4.d, z2.d, z3.d
; CHECK-NEXT:    fadd z5.d, z1.d, z5.d
; CHECK-NEXT:    and z1.d, z1.d, #0x8000000000000000
; CHECK-NEXT:    orr z1.d, z26.d, z1.d
; CHECK-NEXT:    uzp2 z2.d, z2.d, z3.d
; CHECK-NEXT:    fsub z1.d, z1.d, z24.d
; CHECK-NEXT:    uzp2 z24.d, z6.d, z7.d
; CHECK-NEXT:    fmul z3.d, z0.d, z2.d
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    uzp1 z6.d, z6.d, z7.d
; CHECK-NEXT:    fmul z7.d, z1.d, z24.d
; CHECK-NEXT:    fmla z3.d, p0/m, z27.d, z4.d
; CHECK-NEXT:    fmla z7.d, p0/m, z6.d, z5.d
; CHECK-NEXT:    fmul z2.d, z27.d, z2.d
; CHECK-NEXT:    fmul z5.d, z5.d, z24.d
; CHECK-NEXT:    fnmsb z0.d, p0/m, z4.d, z2.d
; CHECK-NEXT:    fnmsb z1.d, p0/m, z6.d, z5.d
; CHECK-NEXT:    fadd z1.d, z0.d, z1.d
; CHECK-NEXT:    fadd z2.d, z3.d, z7.d
; CHECK-NEXT:    zip1 z0.d, z1.d, z2.d
; CHECK-NEXT:    zip2 z1.d, z1.d, z2.d
; CHECK-NEXT:    ret
entry:
  %strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
  %0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
  %1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
  %strided.vec78 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
  %2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec78, 0
  %3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec78, 1
  %4 = fmul contract <vscale x 2 x double> %0, %3
  %5 = fmul contract <vscale x 2 x double> %1, %2
  %6 = fadd contract <vscale x 2 x double> %5, %4
  %7 = fmul contract <vscale x 2 x double> %0, %2
  %8 = fmul contract <vscale x 2 x double> %1, %3
  %9 = fsub contract <vscale x 2 x double> %7, %8
  %strided.vec80 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
  %10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec80, 0
  %11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec80, 1
  %12 = tail call contract <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> %11)
  %13 = fadd contract <vscale x 2 x double> %10, %12
  %14 = tail call contract <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> %10)
  %15 = fsub contract <vscale x 2 x double> %14, %11
  %strided.vec82 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
  %16 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec82, 0
  %17 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec82, 1
  %18 = fmul contract <vscale x 2 x double> %15, %17
  %19 = fmul contract <vscale x 2 x double> %16, %13
  %20 = fadd contract <vscale x 2 x double> %19, %18
  %21 = fmul contract <vscale x 2 x double> %15, %16
  %22 = fmul contract <vscale x 2 x double> %13, %17
  %23 = fsub contract <vscale x 2 x double> %21, %22
  %24 = fadd contract <vscale x 2 x double> %9, %23
  %25 = fadd contract <vscale x 2 x double> %6, %20
  %interleaved.vec = tail call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %24, <vscale x 2 x double> %25)
  ret <vscale x 4 x double> %interleaved.vec
}

declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double>)
declare <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)