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
|
/*
* utils/split-indices.cc
*
* Copyright 2018 by Medical Research Council
* Author: Paul Emsley
*
* This program 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 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, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#include <iostream>
#include "split-indices.hh"
// split and fill indices
void
coot::split_indices(std::vector<std::vector<unsigned int> > *indices,
unsigned int n_items,
unsigned int n_threads) {
indices->resize(n_threads);
unsigned int n_per_thread = n_items/n_threads + 1;
if ((n_items % n_threads) == 0)
n_per_thread = n_items/n_threads;
for (std::size_t i=0; i<n_threads; i++)
indices->at(i).reserve(n_per_thread);
unsigned int idx = 0;
for (unsigned int i=0; i<n_items; i++) {
indices->at(idx).push_back(i);
idx++;
if (idx == n_threads)
idx = 0;
}
}
std::vector<std::pair<unsigned int, unsigned int> >
coot::atom_index_ranges(unsigned int n_atoms, unsigned int n_threads) {
std::vector<std::pair<unsigned int, unsigned int> > v;
if (n_threads == 0) n_threads = 1;
unsigned int npt = n_atoms/n_threads;
if (n_threads > n_atoms) {
// 2224 processors and 98 sections... say.
for (unsigned int i=0; i<n_atoms; i++) {
std::pair p(i, i+1);
v.push_back(p);
}
} else {
if ((n_atoms % n_threads) == 0) {
// divides exactly
for (std::size_t i=0; i<n_threads; i++) {
unsigned int v1 = i*npt;
unsigned int v2 = (i+1)*npt;
std::pair<unsigned int, unsigned int> p(v1, v2);
v.push_back(p);
}
} else {
if (n_threads == 1) {
unsigned int v1 = 0;
unsigned int v2 = n_atoms;
std::pair<unsigned int, unsigned int> p(v1, v2);
v.push_back(p);
} else {
if (n_threads == 2) {
// we know that it doesn't divide exactly
unsigned int v1 = 0;
unsigned int v2 = n_atoms/2;
std::pair<unsigned int, unsigned int> p0(v1, v2);
v.push_back(p0);
v1 = n_atoms/2;
v2 = n_atoms;
std::pair<unsigned int, unsigned int> p1(v1, v2);
v.push_back(p1);
} else {
// the final thread picks up the scraps (if any) (consider 25 atoms, 6 threads)
// 20210812-PE also consider 10 atoms 8 threads
// Also what about 4 atoms and 10 threds?
// I need a test function for this.
npt = n_atoms/(n_threads-1);
if (false)
std::cout << "debug:: atom_index_ranges() n_atoms " << n_atoms
<< " n_threads " << n_threads << " n_per_thread " << npt << std::endl;
for (std::size_t i=0; i<(n_threads-1); i++) {
unsigned int v1 = i*npt;
unsigned int v2 = (i+1)*npt;
std::pair<unsigned int, unsigned int> p(v1, v2);
v.push_back(p);
}
// scraps for the last thread
unsigned int v1 = (n_threads-1)*npt;
unsigned int v2 = n_atoms;
if (v2 > v1) {
std::pair<unsigned int, unsigned int> p(v1, v2);
v.push_back(p);
}
}
}
}
}
return v;
}
|
