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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+sve -o - | FileCheck %s
target triple = "aarch64"
; 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: ptrue p0.d
; CHECK-NEXT: fcmla z4.d, p0/m, z0.d, z2.d, #0
; CHECK-NEXT: fcmla z5.d, p0/m, z1.d, z3.d, #0
; CHECK-NEXT: fcmla z4.d, p0/m, z0.d, z2.d, #90
; CHECK-NEXT: fcmla z5.d, p0/m, z1.d, z3.d, #90
; CHECK-NEXT: mov z0.d, z4.d
; CHECK-NEXT: mov z1.d, z5.d
; CHECK-NEXT: ret
entry:
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.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.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 fast <vscale x 2 x double> %3, %0
%5 = fmul fast <vscale x 2 x double> %2, %1
%6 = fadd fast <vscale x 2 x double> %4, %5
%7 = fmul fast <vscale x 2 x double> %2, %0
%strided.vec31 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
%8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec31, 0
%9 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec31, 1
%10 = fadd fast <vscale x 2 x double> %8, %7
%11 = fmul fast <vscale x 2 x double> %3, %1
%12 = fsub fast <vscale x 2 x double> %10, %11
%13 = fadd fast <vscale x 2 x double> %6, %9
%interleaved.vec = tail call <vscale x 4 x double> @llvm.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: movi v24.2d, #0000000000000000
; CHECK-NEXT: movi v25.2d, #0000000000000000
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcmla z25.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, z0.d, z2.d, #0
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #0
; CHECK-NEXT: fcmla z25.d, p0/m, z6.d, z4.d, #90
; CHECK-NEXT: fcmla z24.d, p0/m, z7.d, z5.d, #90
; CHECK-NEXT: fcmla z25.d, p0/m, z0.d, z2.d, #90
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #90
; CHECK-NEXT: mov z0.d, z25.d
; CHECK-NEXT: mov z1.d, z24.d
; CHECK-NEXT: ret
entry:
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.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.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 fast <vscale x 2 x double> %3, %0
%5 = fmul fast <vscale x 2 x double> %2, %1
%6 = fmul fast <vscale x 2 x double> %2, %0
%7 = fmul fast <vscale x 2 x double> %3, %1
%strided.vec54 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
%8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 0
%9 = 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.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
%10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 0
%11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 1
%12 = fmul fast <vscale x 2 x double> %11, %8
%13 = fmul fast <vscale x 2 x double> %10, %9
%14 = fmul fast <vscale x 2 x double> %10, %8
%15 = fmul fast <vscale x 2 x double> %11, %9
%16 = fadd fast <vscale x 2 x double> %15, %7
%17 = fadd fast <vscale x 2 x double> %14, %6
%18 = fsub fast <vscale x 2 x double> %17, %16
%19 = fadd fast <vscale x 2 x double> %4, %5
%20 = fadd fast <vscale x 2 x double> %19, %13
%21 = fadd fast <vscale x 2 x double> %20, %12
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %18, <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: movi v24.2d, #0000000000000000
; CHECK-NEXT: movi v25.2d, #0000000000000000
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcmla z25.d, p0/m, z6.d, z4.d, #270
; CHECK-NEXT: fcmla z24.d, p0/m, z7.d, z5.d, #270
; CHECK-NEXT: fcmla z25.d, p0/m, z0.d, z2.d, #0
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #0
; CHECK-NEXT: fcmla z25.d, p0/m, z6.d, z4.d, #180
; CHECK-NEXT: fcmla z24.d, p0/m, z7.d, z5.d, #180
; CHECK-NEXT: fcmla z25.d, p0/m, z0.d, z2.d, #90
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #90
; CHECK-NEXT: mov z0.d, z25.d
; CHECK-NEXT: mov z1.d, z24.d
; CHECK-NEXT: ret
entry:
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.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.vec54 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
%2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 0
%3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec54, 1
%4 = fmul fast <vscale x 2 x double> %3, %0
%5 = fmul fast <vscale x 2 x double> %2, %1
%6 = fmul fast <vscale x 2 x double> %2, %0
%7 = fmul fast <vscale x 2 x double> %3, %1
%strided.vec56 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
%8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 0
%9 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec56, 1
%strided.vec58 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
%10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec58, 0
%11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec58, 1
%12 = fmul fast <vscale x 2 x double> %11, %9
%13 = fmul fast <vscale x 2 x double> %10, %8
%14 = fadd fast <vscale x 2 x double> %13, %7
%15 = fadd fast <vscale x 2 x double> %12, %6
%16 = fsub fast <vscale x 2 x double> %15, %14
%17 = fmul fast <vscale x 2 x double> %10, %9
%18 = fmul fast <vscale x 2 x double> %11, %8
%19 = fadd fast <vscale x 2 x double> %18, %17
%20 = fadd fast <vscale x 2 x double> %4, %5
%21 = fsub fast <vscale x 2 x double> %20, %19
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %16, <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: movi v24.2d, #0000000000000000
; CHECK-NEXT: movi v25.2d, #0000000000000000
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcmla z25.d, p0/m, z0.d, z2.d, #0
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #0
; CHECK-NEXT: fcmla z25.d, p0/m, z0.d, z2.d, #90
; CHECK-NEXT: fcmla z24.d, p0/m, z1.d, z3.d, #90
; CHECK-NEXT: fcmla z25.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, z4.d, z6.d, #270
; CHECK-NEXT: fcmla z24.d, p0/m, z5.d, z7.d, #270
; CHECK-NEXT: mov z0.d, z25.d
; CHECK-NEXT: mov z1.d, z24.d
; CHECK-NEXT: ret
entry:
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.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.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 fast <vscale x 2 x double> %3, %0
%5 = fmul fast <vscale x 2 x double> %2, %1
%6 = fmul fast <vscale x 2 x double> %2, %0
%strided.vec62 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
%7 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec62, 0
%8 = 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.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
%9 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec64, 0
%10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec64, 1
%11 = fmul fast <vscale x 2 x double> %10, %7
%12 = fmul fast <vscale x 2 x double> %9, %7
%13 = fmul fast <vscale x 2 x double> %10, %8
%14 = fmul fast <vscale x 2 x double> %3, %1
%15 = fsub fast <vscale x 2 x double> %6, %14
%16 = fadd fast <vscale x 2 x double> %15, %12
%17 = fadd fast <vscale x 2 x double> %16, %13
%18 = fadd fast <vscale x 2 x double> %4, %5
%19 = fmul fast <vscale x 2 x double> %9, %8
%20 = fsub fast <vscale x 2 x double> %18, %19
%21 = fadd fast <vscale x 2 x double> %20, %11
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %17, <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, z2.d, z3.d
; CHECK-NEXT: uzp2 z25.d, z0.d, z1.d
; CHECK-NEXT: uzp1 z2.d, z2.d, z3.d
; CHECK-NEXT: uzp1 z0.d, z0.d, z1.d
; CHECK-NEXT: uzp2 z1.d, z4.d, z5.d
; CHECK-NEXT: uzp1 z26.d, z6.d, z7.d
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: uzp1 z4.d, z4.d, z5.d
; CHECK-NEXT: uzp2 z5.d, z6.d, z7.d
; CHECK-NEXT: fmul z3.d, z2.d, z25.d
; CHECK-NEXT: fmul z25.d, z24.d, z25.d
; CHECK-NEXT: fmla z3.d, p0/m, z24.d, z0.d
; CHECK-NEXT: movprfx z24, z25
; CHECK-NEXT: fmla z24.d, p0/m, z26.d, z1.d
; CHECK-NEXT: movprfx z6, z24
; CHECK-NEXT: fmla z6.d, p0/m, z5.d, z4.d
; CHECK-NEXT: fmla z3.d, p0/m, z26.d, z4.d
; CHECK-NEXT: fnmsb z2.d, p0/m, z0.d, z6.d
; CHECK-NEXT: fmsb z1.d, p0/m, z5.d, z3.d
; CHECK-NEXT: zip1 z0.d, z2.d, z1.d
; CHECK-NEXT: zip2 z1.d, z2.d, z1.d
; CHECK-NEXT: ret
entry:
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.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.vec80 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
%2 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec80, 0
%3 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec80, 1
%4 = fmul fast <vscale x 2 x double> %3, %0
%5 = fmul fast <vscale x 2 x double> %2, %1
%6 = fmul fast <vscale x 2 x double> %2, %0
%7 = fmul fast <vscale x 2 x double> %3, %1
%strided.vec82 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %c)
%8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec82, 0
%9 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec82, 1
%strided.vec84 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %d)
%10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec84, 0
%11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec84, 1
%12 = fmul fast <vscale x 2 x double> %10, %8
%13 = fmul fast <vscale x 2 x double> %10, %9
%14 = fmul fast <vscale x 2 x double> %11, %8
%15 = fadd fast <vscale x 2 x double> %13, %7
%16 = fadd fast <vscale x 2 x double> %15, %14
%17 = fsub fast <vscale x 2 x double> %6, %16
%18 = fadd fast <vscale x 2 x double> %4, %5
%19 = fadd fast <vscale x 2 x double> %18, %12
%20 = fmul fast <vscale x 2 x double> %11, %9
%21 = fsub fast <vscale x 2 x double> %19, %20
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %17, <vscale x 2 x double> %21)
ret <vscale x 4 x double> %interleaved.vec
}
declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double>)
declare <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
