2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012, by the GROMACS development team, led by
5 * David van der Spoel, Berk Hess, Erik Lindahl, and including many
6 * others, as listed in the AUTHORS file in the top-level source
7 * directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
38 #include <types/simple.h>
42 F77_FUNC(sgemm,SGEMM)(const char *transa,
56 const char tra=toupper(*transa);
57 const char trb=toupper(*transb);
60 int nrowa,ncola,nrowb;
69 float alpha = *alpha__;
85 if(m==0 || n==0 || (( fabs(alpha)<GMX_FLOAT_MIN || k==0) && fabs(beta-1.0)<GMX_FLOAT_EPS))
88 if(fabs(alpha)<GMX_FLOAT_MIN) {
89 if(fabs(beta)<GMX_FLOAT_MIN) {
106 if(fabs(beta)<GMX_FLOAT_MIN) {
109 } else if(fabs(beta-1.0)>GMX_FLOAT_EPS) {
111 c[j*(ldc)+i] *= beta;
114 if( fabs(b[ j*(ldb) + l ])>GMX_FLOAT_MIN) {
115 temp = alpha * b[ j*(ldb) + l ];
117 c[j*(ldc)+i] += temp * a[l*(lda)+i];
122 /* transpose A, but not B */
127 temp += a[i*(lda)+l] * b[j*(ldb)+l];
128 if(fabs(beta)<GMX_FLOAT_MIN)
129 c[j*(ldc)+i] = alpha * temp;
131 c[j*(ldc)+i] = alpha * temp + beta * c[j*(ldc)+i];
139 /* transpose B, but not A */
142 if(fabs(beta)<GMX_FLOAT_MIN) {
145 } else if(fabs(beta-1.0)>GMX_FLOAT_EPS) {
147 c[j*(ldc)+i] *= beta;
150 if( fabs(b[ l*(ldb) + j ])>GMX_FLOAT_MIN) {
151 temp = alpha * b[ l*(ldb) + j ];
153 c[j*(ldc)+i] += temp * a[l*(lda)+i];
159 /* Transpose both A and B */
164 temp += a[i*(lda)+l] * b[l*(ldb)+j];
165 if(fabs(beta)<GMX_FLOAT_MIN)
166 c[j*(ldc)+i] = alpha * temp;
168 c[j*(ldc)+i] = alpha * temp + beta * c[j*(ldc)+i];