/usr/include/fflas-ffpack/fflas/fflas_level1.inl is in fflas-ffpack-common 2.2.2-5.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | /* -*- mode: C++; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
// vim:sts=8:sw=8:ts=8:noet:sr:cino=>s,f0,{0,g0,(0,\:0,t0,+0,=s
/*
* Copyright (C) 2014 the FFLAS-FFPACK group
*
* Written by Brice Boyer (briceboyer) <boyer.brice@gmail.com>
*
*
* ========LICENCE========
* This file is part of the library FFLAS-FFPACK.
*
* FFLAS-FFPACK is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
* ========LICENCE========
*.
*/
/** @file fflas/fflas_level1.h
* @brief Vector operations
* or anything of \f$n\f$ complexity
*/
#ifndef __FFLASFFPACK_fflas_fflas_level1_INL
#define __FFLASFFPACK_fflas_fflas_level1_INL
namespace FFLAS {
//---------------------------------------------------------------------
// Level 1 routines
//---------------------------------------------------------------------
/** freduce
* \f$x \gets x mod F\f$.
* @param F field
* @param n size of the vectors
* \param X vector in \p F
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
*/
template<class Field>
void
freduce (const Field& F, const size_t n,
typename Field::Element_ptr X, const size_t incX);
/** freduce
* \f$x \gets y mod F\f$.
* @param F field
* @param n size of the vectors
* \param Y vector of \p Element
* \param incY stride of \p Y
* \param X vector in \p F
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
*/
template<class Field>
void
freduce (const Field& F, const size_t n,
typename Field::ConstElement_ptr Y, const size_t incY,
typename Field::Element_ptr X, const size_t incX);
/** finit
* \f$x \gets y mod F\f$.
* @param F field
* @param n size of the vectors
* \param Y vector of \p OtherElement
* \param incY stride of \p Y
* \param X vector in \p F
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
*/
template<class Field, class OtherElement_ptr>
void
finit (const Field& F, const size_t n,
const OtherElement_ptr Y, const size_t incY,
typename Field::Element_ptr X, const size_t incX);
/** fconvert
* \f$x \gets y mod F\f$.
* @param F field
* @param n size of the vectors
* \param Y vector of \p F
* \param incY stride of \p Y
* \param X vector in \p OtherElement
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
*/
template<class Field, class OtherElement_ptr>
void
fconvert (const Field& F, const size_t n,
OtherElement_ptr X, const size_t incX,
typename Field::ConstElement_ptr Y, const size_t incY)
{
OtherElement_ptr Xi = X ;
typename Field::ConstElement_ptr Yi = Y ;
for (; Xi < X+n*incX; Xi+=incX, Yi += incY )
F.convert( *Xi , *Yi);
}
/** fnegin
* \f$x \gets - x\f$.
* @param F field
* @param n size of the vectors
* \param X vector in \p F
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
*/
template<class Field>
void
fnegin (const Field& F, const size_t n,
typename Field::Element_ptr X, const size_t incX)
{
typename Field::Element_ptr Xi = X ;
for (; Xi < X+n*incX; Xi+=incX )
F.negin( *Xi );
}
/** fneg
* \f$x \gets - y\f$.
* @param F field
* @param n size of the vectors
* \param X vector in \p F
* \param incX stride of \p X
* \param Y vector in \p F
* \param incY stride of \p Y
* @bug use cblas_(d)scal when possible
*/
template<class Field>
void
fneg (const Field& F, const size_t n,
typename Field::ConstElement_ptr Y, const size_t incY,
typename Field::Element_ptr X, const size_t incX)
{
typename Field::Element_ptr Xi = X ;
typename Field::ConstElement_ptr Yi = Y ;
for (; Xi < X+n*incX; Xi+=incX,Yi+=incY )
F.neg( *Xi, *Yi );
}
/** \brief fzero : \f$A \gets 0 \f$.
* @param F field
* @param n number of elements to zero
* \param X vector in \p F
* \param incX stride of \p X
*/
template<class Field>
void
fzero (const Field& F, const size_t n,
typename Field::Element_ptr X, const size_t incX)
{
if (incX == 1) { // contigous data
// memset(X,(int)F.zero,n); // might be bogus ?
for (size_t i = 0 ; i < n ; ++i)
F.assign(*(X+i), F.zero);
}
else { // not contiguous (strided)
for (size_t i = 0 ; i < n ; ++i)
F.assign(*(X+i*incX), F.zero);
}
}
/** \brief frand : \f$A \gets random \f$.
* @param F field
* @param G randomiterator
* @param n number of elements to randomize
* \param X vector in \p F
* \param incX stride of \p X
*/
template<class Field, class RandIter>
void
frand (const Field& F, RandIter& G, const size_t n,
typename Field::Element_ptr X, const size_t incX)
{
if (incX == 1) { // contigous data
// memset(X,(int)F.zero,n); // might be bogus ?
for (size_t i = 0 ; i < n ; ++i)
G.random(*(X+i));
}
else { // not contiguous (strided)
for (size_t i = 0 ; i < n ; ++i)
G.random(*(X+i*incX));
}
}
/** \brief fiszero : test \f$X = 0 \f$.
* @param F field
* @param n vector dimension
* \param X vector in \p F
* \param incX increment of \p X
*/
template<class Field>
bool
fiszero (const Field& F, const size_t n,
typename Field::ConstElement_ptr X, const size_t incX)
{
bool res=true;
for (size_t i = 0 ; i < n ; ++i)
res &= F.isZero (X [i*incX]);
return res;
}
/** \brief fequal : test \f$X = Y \f$.
* @param F field
* @param n vector dimension
* \param X vector in \p F
* \param incX increment of \p X
* \param Y vector in \p F
* \param incY increment of \p Y
*/
template<class Field>
bool
fequal (const Field& F, const size_t n,
typename Field::ConstElement_ptr X, const size_t incX,
typename Field::ConstElement_ptr Y, const size_t incY)
{
bool res=true;
for (size_t i = 0 ; i < n ; ++i)
res &= F.areEqual (X [i*incX], Y [i*incY]);
return res;
}
/** \brief fassign : \f$x \gets y \f$.
* X is preallocated
* @todo variant for triagular matrix
* @param F field
* @param N size of the vectors
* \param [out] X vector in \p F
* \param incX stride of \p X
* \param [in] Y vector in \p F
* \param incY stride of \p Y
*/
template<class Field>
void
fassign (const Field& F, const size_t N,
typename Field::ConstElement_ptr Y, const size_t incY ,
typename Field::Element_ptr X, const size_t incX);
/** fscalin
* \f$x \gets \alpha \cdot x\f$.
* @param F field
* @param n size of the vectors
* @param alpha scalar
* \param X vector in \p F
* \param incX stride of \p X
* @bug use cblas_(d)scal when possible
* @internal
* @todo check if comparison with +/-1,0 is necessary.
*/
template<class Field>
void
fscalin (const Field& F, const size_t n, const typename Field::Element alpha,
typename Field::Element_ptr X, const size_t incX);
/** fscal
* \f$y \gets \alpha \cdot x\f$.
* @param F field
* @param n size of the vectors
* @param alpha scalar
* \param[in] X vector in \p F
* \param incX stride of \p X
* \param[out] Y vector in \p F
* \param incY stride of \p Y
* @bug use cblas_(d)scal when possible
* @internal
* @todo check if comparison with +/-1,0 is necessary.
*/
template<class Field>
void
fscal (const Field& F, const size_t n
, const typename Field::Element alpha
, typename Field::ConstElement_ptr X, const size_t incX
, typename Field::Element_ptr Y, const size_t incY);
/** \brief faxpy : \f$y \gets \alpha \cdot x + y\f$.
* @param F field
* @param N size of the vectors
* @param alpha scalar
* \param[in] X vector in \p F
* \param incX stride of \p X
* \param[in,out] Y vector in \p F
* \param incY stride of \p Y
*/
template<class Field>
void
faxpy (const Field& F, const size_t N,
const typename Field::Element alpha,
typename Field::ConstElement_ptr X, const size_t incX,
typename Field::Element_ptr Y, const size_t incY );
/** \brief faxpby : \f$y \gets \alpha \cdot x + \beta \cdot y\f$.
* @param F field
* @param N size of the vectors
* @param alpha scalar
* \param[in] X vector in \p F
* \param incX stride of \p X
* \param beta scalar
* \param[in,out] Y vector in \p F
* \param incY stride of \p Y
* \note this is a catlas function
*/
template<class Field>
void
faxpby (const Field& F, const size_t N,
const typename Field::Element alpha,
typename Field::ConstElement_ptr X, const size_t incX,
const typename Field::Element beta,
typename Field::Element_ptr Y, const size_t incY );
/** \brief fdot: dot product \f$x^T y\f$.
* @param F field
* @param N size of the vectors
* \param X vector in \p F
* \param incX stride of \p X
* \param Y vector in \p F
* \param incY stride of \p Y
*/
template<class Field>
typename Field::Element
fdot (const Field& F, const size_t N,
typename Field::ConstElement_ptr X, const size_t incX,
typename Field::ConstElement_ptr Y, const size_t incY );
/** \brief fswap: \f$ X \leftrightarrow Y\f$.
* @bug use cblas_dswap when double
* @param F field
* @param N size of the vectors
* \param X vector in \p F
* \param incX stride of \p X
* \param Y vector in \p F
* \param incY stride of \p Y
*/
template<class Field>
void
fswap (const Field& F, const size_t N, typename Field::Element_ptr X, const size_t incX,
typename Field::Element_ptr Y, const size_t incY )
{
typename Field::Element tmp; F.init(tmp);
typename Field::Element_ptr Xi = X;
typename Field::Element_ptr Yi=Y;
for (; Xi < X+N*incX; Xi+=incX, Yi+=incY ){
F.assign( tmp, *Xi );
F.assign( *Xi, *Yi );
F.assign( *Yi, tmp );
}
}
template <class Field>
void
pfadd (const Field & F, const size_t M, const size_t N,
typename Field::ConstElement_ptr A, const size_t lda,
typename Field::ConstElement_ptr B, const size_t ldb,
typename Field::Element_ptr C, const size_t ldc, const size_t numths);
template <class Field>
void
pfsub (const Field & F, const size_t M, const size_t N,
typename Field::ConstElement_ptr A, const size_t lda,
typename Field::ConstElement_ptr B, const size_t ldb,
typename Field::Element_ptr C, const size_t ldc, const size_t numths);
template <class Field>
void
pfaddin (const Field& F, const size_t M, const size_t N,
typename Field::ConstElement_ptr B, const size_t ldb,
typename Field::Element_ptr C, const size_t ldc, size_t numths);
template <class Field>
void
pfsubin (const Field& F, const size_t M, const size_t N,
typename Field::ConstElement_ptr B, const size_t ldb,
typename Field::Element_ptr C, const size_t ldc, size_t numths);
template <class Field>
void
fadd (const Field& F, const size_t N,
typename Field::ConstElement_ptr A, const size_t inca,
typename Field::ConstElement_ptr B, const size_t incb,
typename Field::Element_ptr C, const size_t incc);
template <class Field>
void
fsub (const Field& F, const size_t N,
typename Field::ConstElement_ptr A, const size_t inca,
typename Field::ConstElement_ptr B, const size_t incb,
typename Field::Element_ptr C, const size_t incc);
template <class Field>
void
faddin (const Field& F, const size_t N,
typename Field::ConstElement_ptr B, const size_t incb,
typename Field::Element_ptr C, const size_t incc);
template <class Field>
void
fsubin (const Field& F, const size_t N,
typename Field::ConstElement_ptr B, const size_t incb,
typename Field::Element_ptr C, const size_t incc);
template <class Field>
void
fadd (const Field& F, const size_t N,
typename Field::ConstElement_ptr A, const size_t inca,
const typename Field::Element alpha,
typename Field::ConstElement_ptr B, const size_t incb,
typename Field::Element_ptr C, const size_t incc);
} // FFLAS
#endif // __FFLASFFPACK_fflas_fflas_level1_INL
|