sve-intrinsics-fp-arith-merging.ll
19.9 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
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=sve -mattr=+use-experimental-zeroing-pseudos < %s 2>%t | FileCheck %s
; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
; WARN-NOT: warning
;
; FADD
;
define <vscale x 8 x half> @fadd_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fadd_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fadd z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fadd_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fadd_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fadd z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fadd_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fadd_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fadd z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FMAX
;
define <vscale x 8 x half> @fmax_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmax_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fmax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fmax_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmax_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fmax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fmax_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmax_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fmax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FMAXNM
;
define <vscale x 8 x half> @fmaxnm_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmaxnm_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fmaxnm z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fmaxnm_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmaxnm_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fmaxnm z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fmaxnm_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmaxnm_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fmaxnm z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FMIN
;
define <vscale x 8 x half> @fmin_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmin_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fmin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fmin_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmin_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fmin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fmin_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmin_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fmin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FMINNM
;
define <vscale x 8 x half> @fminnm_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fminnm_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fminnm z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fminnm_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fminnm_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fminnm z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fminnm_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fminnm_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fminnm z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FMUL
;
define <vscale x 8 x half> @fmul_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmul_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fmul z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fmul_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmul_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fmul z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fmul_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmul_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fmul z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FSUB
;
define <vscale x 8 x half> @fsub_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fsub_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fsub z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fsub_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fsub_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fsub z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fsub_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fsub_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fsub z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
;
; FSUBR
;
define <vscale x 8 x half> @fsubr_h_zero(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fsubr_h_zero:
; CHECK: movprfx z0.h, p0/z, z0.h
; CHECK-NEXT: fsubr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> zeroinitializer
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a_z,
<vscale x 8 x half> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fsubr_s_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fsubr_s_zero:
; CHECK: movprfx z0.s, p0/z, z0.s
; CHECK-NEXT: fsubr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a_z,
<vscale x 4 x float> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fsubr_d_zero(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fsubr_d_zero:
; CHECK: movprfx z0.d, p0/z, z0.d
; CHECK-NEXT: fsubr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> zeroinitializer
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a_z,
<vscale x 2 x double> %b)
ret <vscale x 2 x double> %out
}
declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)