/usr/include/libint2/OSVRR_xs_xs.h is in libint2-dev 2.3.0~beta3-2.
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 | /*
* This file is a part of Libint.
* Copyright (C) 2004-2014 Edward F. Valeev
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Library General Public License, version 2,
* as published by the Free Software Foundation.
*
* 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 Library General Public License
* along with this program. If not, see http://www.gnu.org/licenses/.
*
*/
#ifndef _libint2_src_lib_libint_osvrrxsxs_h_
#define _libint2_src_lib_libint_osvrrxsxs_h_
#include <cstdlib>
#include <libint2.h>
#include <util_types.h>
#include <libint2/cgshell_ordering.h>
namespace libint2 {
template <int part, int La, int Lc, bool unit_b, bool vectorize> struct OSVRR_xs_xs {
static void compute(const Libint_t* inteval,
LIBINT2_REALTYPE* target,
const LIBINT2_REALTYPE* src0,
const LIBINT2_REALTYPE* src1,
const LIBINT2_REALTYPE* src2,
const LIBINT2_REALTYPE* src3,
const LIBINT2_REALTYPE* src4);
};
/** builds (a 0|c0)^(m)
src0 = (a-10|c0)^(m) // ignored if unit_b is true
src1 = (a-10|c0)^(m+1)
src2 = (a-20|c0)^(m)
src3 = (a-20|c0)^(m+1)
src4 = (a-10|c-10)^(m+1)
**/
template <int La, int Lc,
bool unit_b,
bool vectorize> struct OSVRR_xs_xs<0,La,Lc,unit_b,vectorize> {
static void compute(const Libint_t* inteval,
LIBINT2_REALTYPE* target,
const LIBINT2_REALTYPE* src0,
const LIBINT2_REALTYPE* src1,
const LIBINT2_REALTYPE* src2,
const LIBINT2_REALTYPE* src3,
const LIBINT2_REALTYPE* src4) {
// works for (ds|ps) and higher
assert(not (La < 2 || Lc < 1));
const unsigned int veclen = vectorize ? inteval->veclen : 1;
const unsigned int Nc = INT_NCART(Lc);
const unsigned int NcV = Nc * veclen;
int ax, ay, az;
FOR_CART(ax, ay, az, La)
int a[3]; a[0] = ax; a[1] = ay; a[2] = az;
enum XYZ {x=0, y=1, z=2};
// Build along x, if possible
XYZ xyz = z;
if (ay != 0) xyz = y;
if (ax != 0) xyz = x;
--a[xyz];
// redirect
const LIBINT2_REALTYPE *PA, *WP;
switch(xyz) {
case x:
#if LIBINT2_DEFINED(eri,PA_x)
if (not unit_b) PA = inteval->PA_x;
#endif
WP = inteval->WP_x;
break;
case y:
#if LIBINT2_DEFINED(eri,PA_y)
if (not unit_b) PA = inteval->PA_y;
#endif
WP = inteval->WP_y;
break;
case z:
#if LIBINT2_DEFINED(eri,PA_z)
if (not unit_b) PA = inteval->PA_z;
#endif
WP = inteval->WP_z;
break;
}
const unsigned int iam1 = INT_CARTINDEX(La-1,a[0],a[1]);
const unsigned int am10c0_offset = iam1 * NcV;
const LIBINT2_REALTYPE* src0_ptr = unit_b ? 0 : src0 + am10c0_offset;
const LIBINT2_REALTYPE* src1_ptr = src1 + am10c0_offset;
// if a-2_xyz exists, include (a-2_xyz 0 | c 0)
if (a[xyz] > 0) {
--a[xyz];
const unsigned int iam2 = INT_CARTINDEX(La-2,a[0],a[1]);
const unsigned int am20c0_offset = iam2 * NcV;
++a[xyz];
const LIBINT2_REALTYPE* src2_ptr = src2 + am20c0_offset;
const LIBINT2_REALTYPE* src3_ptr = src3 + am20c0_offset;
const LIBINT2_REALTYPE axyz = (LIBINT2_REALTYPE)a[xyz];
unsigned int cv = 0;
for(unsigned int c = 0; c < Nc; ++c) {
for(unsigned int v=0; v<veclen; ++v, ++cv) {
LIBINT2_REALTYPE value = WP[v] * src1_ptr[cv] + axyz * inteval->oo2z[v] * (src2_ptr[cv] - inteval->roz[v] * src3_ptr[cv]);
if (not unit_b) value += PA[v] * src0_ptr[cv];
target[cv] = value;
}
}
#if LIBINT2_FLOP_COUNT
inteval->nflops[0] += (unit_b ? 6 : 8) * NcV;
#endif
}
else {
unsigned int cv = 0;
for(unsigned int c = 0; c < Nc; ++c) {
for(unsigned int v=0; v<veclen; ++v, ++cv) {
LIBINT2_REALTYPE value = WP[v] * src1_ptr[cv];
if (not unit_b) value += PA[v] * src0_ptr[cv];
target[cv] = value;
}
}
#if LIBINT2_FLOP_COUNT
inteval->nflops[0] += (unit_b ? 1 : 3) * NcV;
#endif
}
{
const unsigned int Ncm1 = INT_NCART(Lc-1);
const unsigned int Ncm1V = Ncm1 * veclen;
const unsigned int am10cm10_offset = iam1 * Ncm1V;
const LIBINT2_REALTYPE* src4_ptr = src4 + am10cm10_offset;
// loop over c-1 shell and include (a-1_xyz 0 | c-1_xyz 0) to (a 0 | c 0)
int cx, cy, cz;
FOR_CART(cx, cy, cz, Lc-1)
int c[3]; c[0] = cx; c[1] = cy; c[2] = cz;
++c[xyz];
const unsigned int cc = INT_CARTINDEX(Lc,c[0],c[1]);
const unsigned int cc_offset = cc * veclen;
LIBINT2_REALTYPE* tptr = target + cc_offset;
const LIBINT2_REALTYPE cxyz = (LIBINT2_REALTYPE)c[xyz];
for(unsigned int v=0; v<veclen; ++v) {
tptr[v] += cxyz * inteval->oo2ze[v] * src4_ptr[v];
}
#if LIBINT2_FLOP_COUNT
inteval->nflops[0] += 3 * veclen;
#endif
src4_ptr += veclen;
END_FOR_CART
}
target += NcV;
END_FOR_CART
/** Number of flops = ??? */
//inteval->nflops[0] = inteval->nflops[0] + 222 * 1 * 1 * veclen;
}
};
// Ahlrichs' extension of OS VRR
template <int part, int La, int Lc, bool vectorize> struct OSAVRR_xs_xs {
static void compute(const Libint_t* inteval,
LIBINT2_REALTYPE* target,
const LIBINT2_REALTYPE* src1,
const LIBINT2_REALTYPE* src4);
};
/** builds (a 0|c0)^(m)
src1 = (a-10|c0)^(m+1)
src4 = (a-10|c-10)^(m+1)
**/
template <int La, int Lc, bool vectorize> struct OSAVRR_xs_xs<0,La,Lc,vectorize> {
static void compute(const Libint_t* inteval,
LIBINT2_REALTYPE* target,
const LIBINT2_REALTYPE* src1,
const LIBINT2_REALTYPE* src4) {
// works for (ps|ps) and higher
assert(not (La < 1 || Lc < 1));
const unsigned int veclen = vectorize ? inteval->veclen : 1;
const unsigned int Nc = INT_NCART(Lc);
const unsigned int NcV = Nc * veclen;
int ax, ay, az;
FOR_CART(ax, ay, az, La)
int a[3]; a[0] = ax; a[1] = ay; a[2] = az;
enum XYZ {x=0, y=1, z=2};
// Build along x, if possible
XYZ xyz = z;
if (ay != 0) xyz = y;
if (ax != 0) xyz = x;
--a[xyz];
// redirect
const LIBINT2_REALTYPE *WP;
switch(xyz) {
case x:
WP = inteval->WP_x;
break;
case y:
WP = inteval->WP_y;
break;
case z:
WP = inteval->WP_z;
break;
}
const unsigned int iam1 = INT_CARTINDEX(La-1,a[0],a[1]);
const unsigned int am10c0_offset = iam1 * NcV;
const LIBINT2_REALTYPE* src1_ptr = src1 + am10c0_offset;
{
unsigned int cv = 0;
for(unsigned int c = 0; c < Nc; ++c) {
for(unsigned int v=0; v<veclen; ++v, ++cv) {
target[cv] = WP[v] * src1_ptr[cv];
}
}
#if LIBINT2_FLOP_COUNT
inteval->nflops[0] += NcV;
#endif
}
{
const unsigned int Ncm1 = INT_NCART(Lc-1);
const unsigned int Ncm1V = Ncm1 * veclen;
const unsigned int am10cm10_offset = iam1 * Ncm1V;
const LIBINT2_REALTYPE* src4_ptr = src4 + am10cm10_offset;
// loop over c-1 shell and include (a-1_xyz 0 | c-1_xyz 0) to (a 0 | c 0)
int cx, cy, cz;
FOR_CART(cx, cy, cz, Lc-1)
int c[3]; c[0] = cx; c[1] = cy; c[2] = cz;
++c[xyz];
const unsigned int cc = INT_CARTINDEX(Lc,c[0],c[1]);
const unsigned int cc_offset = cc * veclen;
LIBINT2_REALTYPE* tptr = target + cc_offset;
const LIBINT2_REALTYPE cxyz = (LIBINT2_REALTYPE)c[xyz];
for(unsigned int v=0; v<veclen; ++v) {
tptr[v] += cxyz * inteval->oo2ze[v] * src4_ptr[v];
}
#if LIBINT2_FLOP_COUNT
inteval->nflops[0] += 3 * veclen;
#endif
src4_ptr += veclen;
END_FOR_CART
}
target += NcV;
END_FOR_CART
/** Number of flops = ??? */
//inteval->nflops[0] = inteval->nflops[0] + 222 * 1 * 1 * veclen;
}
};
};
#endif // header guard
|