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
|
/* Ergo, version 3.8.2, a program for linear scaling electronic structure
* calculations.
* Copyright (C) 2023 Elias Rudberg, Emanuel H. Rubensson, Pawel Salek,
* and Anastasia Kruchinina.
*
* 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 3 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, see <http://www.gnu.org/licenses/>.
*
* Primary academic reference:
* Ergo: An open-source program for linear-scaling electronic structure
* calculations,
* Elias Rudberg, Emanuel H. Rubensson, Pawel Salek, and Anastasia
* Kruchinina,
* SoftwareX 7, 107 (2018),
* <http://dx.doi.org/10.1016/j.softx.2018.03.005>
*
* For further information about Ergo, see <http://www.ergoscf.org>.
*/
/* This file belongs to the template_lapack part of the Ergo source
* code. The source files in the template_lapack directory are modified
* versions of files originally distributed as CLAPACK, see the
* Copyright/license notice in the file template_lapack/COPYING.
*/
#ifndef TEMPLATE_LAPACK_LASWP_HEADER
#define TEMPLATE_LAPACK_LASWP_HEADER
template<class Treal>
int template_lapack_laswp(const integer *n, Treal *a, const integer *lda, const integer
*k1, const integer *k2, const integer *ipiv, const integer *incx)
{
/* -- LAPACK auxiliary routine (version 3.0) --
Univ. of Tennessee, Univ. of California Berkeley, NAG Ltd.,
Courant Institute, Argonne National Lab, and Rice University
June 30, 1999
Purpose
=======
DLASWP performs a series of row interchanges on the matrix A.
One row interchange is initiated for each of rows K1 through K2 of A.
Arguments
=========
N (input) INTEGER
The number of columns of the matrix A.
A (input/output) DOUBLE PRECISION array, dimension (LDA,N)
On entry, the matrix of column dimension N to which the row
interchanges will be applied.
On exit, the permuted matrix.
LDA (input) INTEGER
The leading dimension of the array A.
K1 (input) INTEGER
The first element of IPIV for which a row interchange will
be done.
K2 (input) INTEGER
The last element of IPIV for which a row interchange will
be done.
IPIV (input) INTEGER array, dimension (M*abs(INCX))
The vector of pivot indices. Only the elements in positions
K1 through K2 of IPIV are accessed.
IPIV(K) = L implies rows K and L are to be interchanged.
INCX (input) INTEGER
The increment between successive values of IPIV. If IPIV
is negative, the pivots are applied in reverse order.
Further Details
===============
Modified by
R. C. Whaley, Computer Science Dept., Univ. of Tenn., Knoxville, USA
=====================================================================
Interchange row I with row IPIV(I) for each of rows K1 through K2.
Parameter adjustments */
/* System generated locals */
integer a_dim1, a_offset, i__1, i__2, i__3, i__4;
/* Local variables */
Treal temp;
integer i__, j, k, i1, i2, n32, ip, ix, ix0, inc;
#define a_ref(a_1,a_2) a[(a_2)*a_dim1 + a_1]
a_dim1 = *lda;
a_offset = 1 + a_dim1 * 1;
a -= a_offset;
--ipiv;
/* Function Body */
if (*incx > 0) {
ix0 = *k1;
i1 = *k1;
i2 = *k2;
inc = 1;
} else if (*incx < 0) {
ix0 = (1 - *k2) * *incx + 1;
i1 = *k2;
i2 = *k1;
inc = -1;
} else {
return 0;
}
n32 = *n / 32 << 5;
if (n32 != 0) {
i__1 = n32;
for (j = 1; j <= i__1; j += 32) {
ix = ix0;
i__2 = i2;
i__3 = inc;
for (i__ = i1; i__3 < 0 ? i__ >= i__2 : i__ <= i__2; i__ += i__3)
{
ip = ipiv[ix];
if (ip != i__) {
i__4 = j + 31;
for (k = j; k <= i__4; ++k) {
temp = a_ref(i__, k);
a_ref(i__, k) = a_ref(ip, k);
a_ref(ip, k) = temp;
/* L10: */
}
}
ix += *incx;
/* L20: */
}
/* L30: */
}
}
if (n32 != *n) {
++n32;
ix = ix0;
i__1 = i2;
i__3 = inc;
for (i__ = i1; i__3 < 0 ? i__ >= i__1 : i__ <= i__1; i__ += i__3) {
ip = ipiv[ix];
if (ip != i__) {
i__2 = *n;
for (k = n32; k <= i__2; ++k) {
temp = a_ref(i__, k);
a_ref(i__, k) = a_ref(ip, k);
a_ref(ip, k) = temp;
/* L40: */
}
}
ix += *incx;
/* L50: */
}
}
return 0;
/* End of DLASWP */
} /* dlaswp_ */
#undef a_ref
#endif
|