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
|
; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=!sqrt,!vec-sqrt | FileCheck %s --check-prefix=FAULT
; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=sqrt,vec-sqrt | FileCheck %s
; RUN: llc < %s -mtriple=aarch64 -mattr=neon,-use-reverse-square-root | FileCheck %s --check-prefix=FAULT
; RUN: llc < %s -mtriple=aarch64 -mattr=neon,+use-reverse-square-root | FileCheck %s
declare float @llvm.sqrt.f32(float) #1
declare double @llvm.sqrt.f64(double) #1
declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) #1
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #1
declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) #1
define float @fsqrt(float %a) #0 {
%1 = tail call fast float @llvm.sqrt.f32(float %a)
ret float %1
; FAULT-LABEL: fsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: fsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define <2 x float> @f2sqrt(<2 x float> %a) #0 {
%1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a) #2
ret <2 x float> %1
; FAULT-LABEL: f2sqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: f2sqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: mov
; CHECK-NEXT: frsqrte
}
define <4 x float> @f4sqrt(<4 x float> %a) #0 {
%1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a) #2
ret <4 x float> %1
; FAULT-LABEL: f4sqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: f4sqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: mov
; CHECK-NEXT: frsqrte
}
define double @dsqrt(double %a) #0 {
%1 = tail call fast double @llvm.sqrt.f64(double %a)
ret double %1
; FAULT-LABEL: dsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: dsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define <2 x double> @d2sqrt(<2 x double> %a) #0 {
%1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a) #2
ret <2 x double> %1
; FAULT-LABEL: d2sqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: d2sqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: mov
; CHECK-NEXT: frsqrte
}
define float @frsqrt(float %a) #0 {
%1 = tail call fast float @llvm.sqrt.f32(float %a)
%2 = fdiv fast float 1.000000e+00, %1
ret float %2
; FAULT-LABEL: frsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: frsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define <2 x float> @f2rsqrt(<2 x float> %a) #0 {
%1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a) #2
%2 = fdiv fast <2 x float> <float 1.000000e+00, float 1.000000e+00>, %1
ret <2 x float> %2
; FAULT-LABEL: f2rsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: f2rsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define <4 x float> @f4rsqrt(<4 x float> %a) #0 {
%1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a) #2
%2 = fdiv fast <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %1
ret <4 x float> %2
; FAULT-LABEL: f4rsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: f4rsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define double @drsqrt(double %a) #0 {
%1 = tail call fast double @llvm.sqrt.f64(double %a)
%2 = fdiv fast double 1.000000e+00, %1
ret double %2
; FAULT-LABEL: drsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: drsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
define <2 x double> @d2rsqrt(<2 x double> %a) #0 {
%1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a) #2
%2 = fdiv fast <2 x double> <double 1.000000e+00, double 1.000000e+00>, %1
ret <2 x double> %2
; FAULT-LABEL: d2rsqrt:
; FAULT-NEXT: BB#0
; FAULT-NEXT: fsqrt
; CHECK-LABEL: d2rsqrt:
; CHECK-NEXT: BB#0
; CHECK-NEXT: fmov
; CHECK-NEXT: frsqrte
}
attributes #0 = { nounwind "unsafe-fp-math"="true" }
|
