1 /* CalculiX - A 3-dimensional finite element program */
2 /* Copyright (C) 1998-2021 Guido Dhondt */
3
4 /* This program is free software; you can redistribute it and/or */
5 /* modify it under the terms of the GNU General Public License as */
6 /* published by the Free Software Foundation(version 2); */
7 /* */
8
9 /* This program is distributed in the hope that it will be useful, */
10 /* but WITHOUT ANY WARRANTY; without even the implied warranty of */
11 /* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the */
12 /* GNU General Public License for more details. */
13
14 /* You should have received a copy of the GNU General Public License */
15 /* along with this program; if not, write to the Free Software */
16 /* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
17
18 /* A parallel copy of arrays which depent on active element */
19
20
21 #include <unistd.h>
22 #include <stdio.h>
23 #include <math.h>
24 #include <stdlib.h>
25 #include <pthread.h>
26 #include "CalculiX.h"
27
28 static ITG *neapar=NULL,*nebpar=NULL,*mt1,*nactdof1;
29
30 static double *aux21,*veold1;
31
res3parll(ITG * mt,ITG * nactdof,double * aux2,double * veold,ITG * nk,ITG * num_cpus)32 void res3parll(ITG *mt,ITG *nactdof,double *aux2,double *veold,
33 ITG *nk,ITG *num_cpus){
34
35 ITG i,idelta,isum;
36
37 /* variables for multithreading procedure */
38
39 ITG *ithread=NULL;
40
41 pthread_t tid[*num_cpus];
42
43 /* determining the element bounds in each thread */
44
45 NNEW(neapar,ITG,*num_cpus);
46 NNEW(nebpar,ITG,*num_cpus);
47
48 /* dividing the element number range into num_cpus equal numbers of
49 active entries. */
50
51 idelta=(ITG)floor(*nk/(double)(*num_cpus));
52 isum=0;
53 for(i=0;i<*num_cpus;i++){
54 neapar[i]=isum;
55 if(i!=*num_cpus-1){
56 isum+=idelta;
57 }else{
58 isum=*nk;
59 }
60 nebpar[i]=isum;
61 }
62
63 /* create threads and wait */
64
65 mt1=mt;nactdof1=nactdof;aux21=aux2;veold1=veold;
66
67 NNEW(ithread,ITG,*num_cpus);
68
69 for(i=0; i<*num_cpus; i++) {
70 ithread[i]=i;
71 pthread_create(&tid[i], NULL, (void *)res3parllmt, (void *)&ithread[i]);
72 }
73 for(i=0; i<*num_cpus; i++) pthread_join(tid[i], NULL);
74
75 SFREE(ithread);SFREE(neapar);SFREE(nebpar);
76
77 }
78
79 /* subroutine for multithreading of res3parll */
80
res3parllmt(ITG * i)81 void *res3parllmt(ITG *i){
82
83 ITG nea,neb,k,j;
84
85 nea=neapar[*i];
86 neb=nebpar[*i];
87
88 for(k=nea;k<neb;++k){
89 if(nactdof1[*mt1*k]>0){aux21[nactdof1[*mt1*k]-1]=0.;}
90 for(j=1;j<*mt1;++j){
91 if(nactdof1[*mt1*k+j]>0){
92 aux21[nactdof1[*mt1*k+j]-1]=veold1[*mt1*k+j];}
93 }
94 }
95
96 return NULL;
97 }
98