/usr/include/code_saturne/cs_blas.h is in code-saturne-include 3.3.2-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #ifndef __CS_BLAS_H__
#define __CS_BLAS_H__
/*============================================================================
* Portability and fallback layer for BLAS functions
*============================================================================*/
/*
This file is part of Code_Saturne, a general-purpose CFD tool.
Copyright (C) 1998-2014 EDF S.A.
This program is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation; either version 2 of the License, or (at your option) any later
version.
This program is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
details.
You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc., 51 Franklin
Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
/*----------------------------------------------------------------------------*/
#include "cs_defs.h"
/*----------------------------------------------------------------------------
* External library headers
*----------------------------------------------------------------------------*/
/*----------------------------------------------------------------------------
* Local headers
*----------------------------------------------------------------------------*/
#include "cs_base.h"
/*----------------------------------------------------------------------------*/
BEGIN_C_DECLS
/*============================================================================
* Macro definitions
*============================================================================*/
/*============================================================================
* Public function prototypes for Fortran API
*============================================================================*/
/* Return the dot product of 2 vectors: x.y */
double CS_PROCF(csdot, CSDOT)(const cs_int_t *n,
const cs_real_t *x,
const cs_real_t *y);
/* Return the global residual of 2 extensiv vectors: x.y */
double CS_PROCF(csres, CSRES)(const cs_int_t *n,
const cs_real_t *vol,
const cs_real_t *x,
const cs_real_t *y);
/*============================================================================
* Public function prototypes or wrapper macros
*============================================================================*/
/*----------------------------------------------------------------------------
* Constant times a vector plus a vector: y <-- ax + y
*
* parameters:
* n <-- size of arrays x and y
* a <-- multiplier for x
* x <-- array of floating-point values
* y <-- array of floating-point values
*----------------------------------------------------------------------------*/
void
cs_axpy(cs_lnum_t n,
double a,
const cs_real_t *x,
cs_real_t *restrict y);
/*----------------------------------------------------------------------------
* Return the dot product of 2 vectors: x.y
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
* y<-- array of floating-point values
*
* returns:
* dot product
*----------------------------------------------------------------------------*/
double
cs_dot(cs_lnum_t n,
const cs_real_t *x,
const cs_real_t *y);
/*----------------------------------------------------------------------------
* Return the global resildual of 2 extensive vectors:
* 1/sum(vol) . sum(X.Y/vol)
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* vol <-- array of floating-point values
* x <-- array of floating-point values
* y <-- array of floating-point values
*
* returns:
* dot product
*----------------------------------------------------------------------------*/
double
cs_gres(cs_lnum_t n,
const cs_real_t *vol,
const cs_real_t *x,
const cs_real_t *y);
/*----------------------------------------------------------------------------
* Return dot products of a vector with itself: x.x
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
*
* returns:
* dot product
*----------------------------------------------------------------------------*/
double
cs_dot_xx(cs_lnum_t n,
const cs_real_t *x);
/*----------------------------------------------------------------------------
* Return the double dot product of 2 vectors: x.x, and x.y
*
* The products could be computed separately, but computing them
* simultaneously adds more optimization opportunities and possibly better
* cache behavior.
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
* y <-- array of floating-point values
* xx --> x.x dot product
* xy --> x.y dot product
*----------------------------------------------------------------------------*/
void
cs_dot_xx_xy(cs_lnum_t n,
const cs_real_t *restrict x,
const cs_real_t *restrict y,
double *xx,
double *xy);
/*----------------------------------------------------------------------------
* Return the double dot product of 3 vectors: x.y, and y.z
*
* The products could be computed separately, but computing them
* simultaneously adds more optimization opportunities and possibly better
* cache behavior.
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
* y <-- array of floating-point values
* z <-- array of floating-point values
* xy --> x.y dot product
* yz --> x.z dot product
*----------------------------------------------------------------------------*/
void
cs_dot_xy_yz(cs_lnum_t n,
const cs_real_t *restrict x,
const cs_real_t *restrict y,
const cs_real_t *restrict z,
double *xx,
double *xy);
/*----------------------------------------------------------------------------
* Return 3 dot products of 3 vectors: x.y, x.y, and y.z
*
* The products could be computed separately, but computing them
* simultaneously adds more optimization opportunities and possibly better
* cache behavior.
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
* y <-- array of floating-point values
* z <-- array of floating-point values
* xx --> x.y dot product
* xy --> x.y dot product
* yz --> y.z dot product
*----------------------------------------------------------------------------*/
void
cs_dot_xx_xy_yz(cs_lnum_t n,
const cs_real_t *restrict x,
const cs_real_t *restrict y,
const cs_real_t *restrict z,
double *xx,
double *xy,
double *yz);
/*----------------------------------------------------------------------------
* Return the global dot product of 2 vectors: x.y
*
* In parallel mode, the local results are summed on the default
* global communicator.
*
* For better precision, a superblock algorithm is used.
*
* parameters:
* n <-- size of arrays x and y
* x <-- array of floating-point values
* y <-- array of floating-point values
*
* returns:
* dot product
*----------------------------------------------------------------------------*/
double
cs_gdot(cs_lnum_t n,
const cs_real_t *x,
const cs_real_t *y);
/*----------------------------------------------------------------------------*/
END_C_DECLS
#endif /* __CS_BLAS_H__ */
|