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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple aarch64-eabi -mattr=+sve2 -o - | FileCheck --check-prefixes=CHECK %s
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
;============ v2f32
define <vscale x 2 x float> @test_copysign_v2f32_v2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v2f32_v2f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #2147483647
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x float> @llvm.copysign.v2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b)
ret <vscale x 2 x float> %r
}
define <vscale x 2 x float> @test_copysign_v2f32_v2f64(<vscale x 2 x float> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v2f32_v2f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #2147483647
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcvt z1.s, p0/m, z1.d
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fptrunc <vscale x 2 x double> %b to <vscale x 2 x float>
%r = call <vscale x 2 x float> @llvm.copysign.v2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %tmp0)
ret <vscale x 2 x float> %r
}
declare <vscale x 2 x float> @llvm.copysign.v2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0
;============ v4f32
define <vscale x 4 x float> @test_copysign_v4f32_v4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f32_v4f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #2147483647
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.copysign.v4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b)
ret <vscale x 4 x float> %r
}
; SplitVecOp #1
define <vscale x 4 x float> @test_copysign_v4f32_v4f64(<vscale x 4 x float> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f32_v4f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #2147483647
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcvt z2.s, p0/m, z2.d
; CHECK-NEXT: fcvt z1.s, p0/m, z1.d
; CHECK-NEXT: uzp1 z1.s, z1.s, z2.s
; CHECK-NEXT: mov z2.s, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fptrunc <vscale x 4 x double> %b to <vscale x 4 x float>
%r = call <vscale x 4 x float> @llvm.copysign.v4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %tmp0)
ret <vscale x 4 x float> %r
}
declare <vscale x 4 x float> @llvm.copysign.v4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0
;============ v2f64
define <vscale x 2 x double> @test_copysign_v2f64_v232(<vscale x 2 x double> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v2f64_v232:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z2.d, #0x7fffffffffffffff
; CHECK-NEXT: fcvt z1.d, p0/m, z1.s
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fpext <vscale x 2 x float> %b to <vscale x 2 x double>
%r = call <vscale x 2 x double> @llvm.copysign.v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %tmp0)
ret <vscale x 2 x double> %r
}
define <vscale x 2 x double> @test_copysign_v2f64_v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v2f64_v2f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z2.d, #0x7fffffffffffffff
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.copysign.v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b)
ret <vscale x 2 x double> %r
}
declare <vscale x 2 x double> @llvm.copysign.v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0
;============ v4f64
; SplitVecRes mismatched
define <vscale x 4 x double> @test_copysign_v4f64_v4f32(<vscale x 4 x double> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f64_v4f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: uunpkhi z3.d, z2.s
; CHECK-NEXT: uunpklo z2.d, z2.s
; CHECK-NEXT: fcvt z3.d, p0/m, z3.s
; CHECK-NEXT: fcvt z2.d, p0/m, z2.s
; CHECK-NEXT: mov z4.d, #0x7fffffffffffffff
; CHECK-NEXT: bsl z0.d, z0.d, z2.d, z4.d
; CHECK-NEXT: bsl z1.d, z1.d, z3.d, z4.d
; CHECK-NEXT: ret
%tmp0 = fpext <vscale x 4 x float> %b to <vscale x 4 x double>
%r = call <vscale x 4 x double> @llvm.copysign.v4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %tmp0)
ret <vscale x 4 x double> %r
}
; SplitVecRes same
define <vscale x 4 x double> @test_copysign_v4f64_v4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f64_v4f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z4.d, #0x7fffffffffffffff
; CHECK-NEXT: bsl z0.d, z0.d, z2.d, z4.d
; CHECK-NEXT: bsl z1.d, z1.d, z3.d, z4.d
; CHECK-NEXT: ret
%r = call <vscale x 4 x double> @llvm.copysign.v4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b)
ret <vscale x 4 x double> %r
}
declare <vscale x 4 x double> @llvm.copysign.v4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0
;============ v4f16
define <vscale x 4 x half> @test_copysign_v4f16_v4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32767
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%r = call <vscale x 4 x half> @llvm.copysign.v4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b)
ret <vscale x 4 x half> %r
}
define <vscale x 4 x half> @test_copysign_v4f16_v4f32(<vscale x 4 x half> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32767
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: fcvt z1.h, p0/m, z1.s
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fptrunc <vscale x 4 x float> %b to <vscale x 4 x half>
%r = call <vscale x 4 x half> @llvm.copysign.v4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %tmp0)
ret <vscale x 4 x half> %r
}
define <vscale x 4 x half> @test_copysign_v4f16_v4f64(<vscale x 4 x half> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32767
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: fcvt z2.h, p0/m, z2.d
; CHECK-NEXT: fcvt z1.h, p0/m, z1.d
; CHECK-NEXT: uzp1 z1.s, z1.s, z2.s
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fptrunc <vscale x 4 x double> %b to <vscale x 4 x half>
%r = call <vscale x 4 x half> @llvm.copysign.v4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %tmp0)
ret <vscale x 4 x half> %r
}
declare <vscale x 4 x half> @llvm.copysign.v4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0
;============ v8f16
define <vscale x 8 x half> @test_copysign_v8f16_v8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: test_copysign_v8f16_v8f16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32767
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.copysign.v8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b)
ret <vscale x 8 x half> %r
}
define <vscale x 8 x half> @test_copysign_v8f16_v8f32(<vscale x 8 x half> %a, <vscale x 8 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v8f16_v8f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32767
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: fcvt z2.h, p0/m, z2.s
; CHECK-NEXT: fcvt z1.h, p0/m, z1.s
; CHECK-NEXT: uzp1 z1.h, z1.h, z2.h
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: bsl z0.d, z0.d, z1.d, z2.d
; CHECK-NEXT: ret
%tmp0 = fptrunc <vscale x 8 x float> %b to <vscale x 8 x half>
%r = call <vscale x 8 x half> @llvm.copysign.v8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %tmp0)
ret <vscale x 8 x half> %r
}
declare <vscale x 8 x half> @llvm.copysign.v8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0
attributes #0 = { nounwind }
|
