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
|
/* 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_GETRF_HEADER
#define TEMPLATE_LAPACK_GETRF_HEADER
template<class Treal>
int template_lapack_getrf(const integer *m, const integer *n, Treal *a, const integer *
lda, integer *ipiv, integer *info)
{
/* -- LAPACK routine (version 3.0) --
Univ. of Tennessee, Univ. of California Berkeley, NAG Ltd.,
Courant Institute, Argonne National Lab, and Rice University
March 31, 1993
Purpose
=======
DGETRF computes an LU factorization of a general M-by-N matrix A
using partial pivoting with row interchanges.
The factorization has the form
A = P * L * U
where P is a permutation matrix, L is lower triangular with unit
diagonal elements (lower trapezoidal if m > n), and U is upper
triangular (upper trapezoidal if m < n).
This is the right-looking Level 3 BLAS version of the algorithm.
Arguments
=========
M (input) INTEGER
The number of rows of the matrix A. M >= 0.
N (input) INTEGER
The number of columns of the matrix A. N >= 0.
A (input/output) DOUBLE PRECISION array, dimension (LDA,N)
On entry, the M-by-N matrix to be factored.
On exit, the factors L and U from the factorization
A = P*L*U; the unit diagonal elements of L are not stored.
LDA (input) INTEGER
The leading dimension of the array A. LDA >= max(1,M).
IPIV (output) INTEGER array, dimension (min(M,N))
The pivot indices; for 1 <= i <= min(M,N), row i of the
matrix was interchanged with row IPIV(i).
INFO (output) INTEGER
= 0: successful exit
< 0: if INFO = -i, the i-th argument had an illegal value
> 0: if INFO = i, U(i,i) is exactly zero. The factorization
has been completed, but the factor U is exactly
singular, and division by zero will occur if it is used
to solve a system of equations.
=====================================================================
Test the input parameters.
Parameter adjustments */
/* Table of constant values */
integer c__1 = 1;
integer c_n1 = -1;
Treal c_b16 = 1.;
Treal c_b19 = -1.;
/* System generated locals */
integer a_dim1, a_offset, i__1, i__2, i__3, i__4, i__5;
/* Local variables */
integer i__, j;
integer iinfo;
integer jb, nb;
#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 */
*info = 0;
if (*m < 0) {
*info = -1;
} else if (*n < 0) {
*info = -2;
} else if (*lda < maxMACRO(1,*m)) {
*info = -4;
}
if (*info != 0) {
i__1 = -(*info);
template_blas_erbla("GETRF ", &i__1);
return 0;
}
/* Quick return if possible */
if (*m == 0 || *n == 0) {
return 0;
}
/* Determine the block size for this environment. */
nb = template_lapack_ilaenv(&c__1, "DGETRF", " ", m, n, &c_n1, &c_n1, (ftnlen)6, (ftnlen)
1);
if (nb <= 1 || nb >= minMACRO(*m,*n)) {
/* Use unblocked code. */
template_lapack_getf2(m, n, &a[a_offset], lda, &ipiv[1], info);
} else {
/* Use blocked code. */
i__1 = minMACRO(*m,*n);
i__2 = nb;
for (j = 1; i__2 < 0 ? j >= i__1 : j <= i__1; j += i__2) {
/* Computing MIN */
i__3 = minMACRO(*m,*n) - j + 1;
jb = minMACRO(i__3,nb);
/* Factor diagonal and subdiagonal blocks and test for exact
singularity. */
i__3 = *m - j + 1;
template_lapack_getf2(&i__3, &jb, &a_ref(j, j), lda, &ipiv[j], &iinfo);
/* Adjust INFO and the pivot indices. */
if (*info == 0 && iinfo > 0) {
*info = iinfo + j - 1;
}
/* Computing MIN */
i__4 = *m, i__5 = j + jb - 1;
i__3 = minMACRO(i__4,i__5);
for (i__ = j; i__ <= i__3; ++i__) {
ipiv[i__] = j - 1 + ipiv[i__];
/* L10: */
}
/* Apply interchanges to columns 1:J-1. */
i__3 = j - 1;
i__4 = j + jb - 1;
template_lapack_laswp(&i__3, &a[a_offset], lda, &j, &i__4, &ipiv[1], &c__1);
if (j + jb <= *n) {
/* Apply interchanges to columns J+JB:N. */
i__3 = *n - j - jb + 1;
i__4 = j + jb - 1;
template_lapack_laswp(&i__3, &a_ref(1, j + jb), lda, &j, &i__4, &ipiv[1], &
c__1);
/* Compute block row of U. */
i__3 = *n - j - jb + 1;
template_blas_trsm("Left", "Lower", "No transpose", "Unit", &jb, &i__3, &
c_b16, &a_ref(j, j), lda, &a_ref(j, j + jb), lda);
if (j + jb <= *m) {
/* Update trailing submatrix. */
i__3 = *m - j - jb + 1;
i__4 = *n - j - jb + 1;
template_blas_gemm("No transpose", "No transpose", &i__3, &i__4, &jb,
&c_b19, &a_ref(j + jb, j), lda, &a_ref(j, j + jb),
lda, &c_b16, &a_ref(j + jb, j + jb), lda);
}
}
/* L20: */
}
}
return 0;
/* End of DGETRF */
} /* dgetrf_ */
#undef a_ref
#endif
|
