-
Notifications
You must be signed in to change notification settings - Fork 5
/
qwsintrin_double.h
168 lines (160 loc) · 5.77 KB
/
qwsintrin_double.h
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
//****************************************************************************************
//
// Copyright (c) 2015-2020, Yoshifumi Nakamura <[email protected]>
// Copyright (c) 2015-2020, Yuta Mukai <[email protected]>
// Copyright (c) 2018-2020, Ken-Ichi Ishikawa <[email protected]>
// Copyright (c) 2019-2020, Issaku Kanamori <[email protected]>
//
//
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer listed
// in this license in the documentation and/or other materials
// provided with the distribution.
//
// * Neither the name of the copyright holders nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
//----------------------------------------------------------------------------------------
// ACKNOWLEDGMENT
//
// This software has been developed in a co-design working group for the lattice QCD
// supported by MEXT's programs for the Development and Improvement for the Next
// Generation Ultra High-Speed Computer System, under its Subsidies for Operating the
// Specific Advanced Large Research Facilities, and Priority Issue 9
// (Elucidation of the Fundamental Laws and Evolution of the Universe) to be tackled by
// using the Supercomputer Fugaku.
//
//****************************************************************************************
#ifndef QWS_INTRINSICS_DOUBLE
#define QWS_INTRINSICS_DOUBLE
//=0;
inline rvecd_t fzero_d(void) __attribute__((always_inline));
inline rvecd_t fzero_d(void){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = 0;}
return tmp;
}
//=a;
inline rvecd_t fcopy_d(const rvecd_t &a) __attribute__((always_inline));
inline rvecd_t fcopy_d(const rvecd_t &a){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i];}
return tmp;
}
//=-a;
inline rvecd_t mfcopy_d(const rvecd_t &a) __attribute__((always_inline));
inline rvecd_t mfcopy_d(const rvecd_t &a){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] =-a.v[i];}
return tmp;
}
//a[v]=a;
inline rvecd_t fload1_d(const double &a) __attribute__((always_inline));
inline rvecd_t fload1_d(const double &a){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a;}
return tmp;
}
// a+b;
inline rvecd_t fadd_d(const rvecd_t &a, const rvecd_t &b) __attribute__((always_inline));
inline rvecd_t fadd_d(const rvecd_t &a, const rvecd_t &b){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i]+b.v[i];}
return tmp;
}
// a-b;
inline rvecd_t fsub_d(const rvecd_t &a, const rvecd_t &b) __attribute__((always_inline));
inline rvecd_t fsub_d(const rvecd_t &a, const rvecd_t &b){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i]-b.v[i];}
return tmp;
}
// a*b;
inline rvecd_t fmul_d(const rvecd_t &a, const rvecd_t &b) __attribute__((always_inline));
inline rvecd_t fmul_d(const rvecd_t &a, const rvecd_t &b){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i]*b.v[i];}
return tmp;
}
// a*b+c;
inline rvecd_t fmadd_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c) __attribute__((always_inline));
inline rvecd_t fmadd_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i]*b.v[i]+c.v[i];}
return tmp;
}
//-a*b+c;
inline rvecd_t fnmadd_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c) __attribute__((always_inline));
inline rvecd_t fnmadd_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] =-a.v[i]*b.v[i]+c.v[i];}
return tmp;
}
// a*b-c;
inline rvecd_t fmsub_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c) __attribute__((always_inline));
inline rvecd_t fmsub_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] = a.v[i]*b.v[i]-c.v[i];}
return tmp;
}
//-a*b-c;
inline rvecd_t fnmsub_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c) __attribute__((always_inline));
inline rvecd_t fnmsub_d(const rvecd_t &a, const rvecd_t &b,const rvecd_t &c){
int i;
rvecd_t tmp;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp.v[i] =-a.v[i]*b.v[i]-c.v[i];}
return tmp;
}
//=sum(a);
inline double fsum_d(const rvecd_t &a) __attribute__((always_inline));
inline double fsum_d(const rvecd_t &a){
int i;
double tmp=0;
#pragma loop nounroll
for (i=0;i<VLEND;i++){tmp += a.v[i];}
return tmp;
}
#endif