{"id":261897,"date":"2015-07-20T18:57:02","date_gmt":"2015-07-20T14:57:02","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=261897"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=261897","title":{"rendered":"\u041f\u0440\u043e\u0434\u043e\u043b\u0436\u0430\u0435\u043c \u0437\u043d\u0430\u043a\u043e\u043c\u0438\u0442\u044c\u0441\u044f \u0441 Intel Xeon Phi: \u00ab\u0440\u043e\u0434\u043d\u043e\u0439\u00bb \u043a\u043e\u0434"},"content":{"rendered":"

\t\u0412 \u043f\u0440\u043e\u0448\u043b\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435<\/a> \u0431\u044b\u043b\u043e \u043e\u043f\u0438\u0441\u0430\u043d\u043e \u0437\u043d\u0430\u043a\u043e\u043c\u0441\u0442\u0432\u043e \u0441 \u0441\u043e\u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c Intel Xeon Phi \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f offload \u2013 \u043e\u0441\u043d\u043e\u0432\u043d\u043e\u0439 \u043a\u043e\u0434 \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u043d\u0430 \u0445\u043e\u0441\u0442\u0435, \u0430 \u043e\u0442\u0434\u0435\u043b\u044c\u043d\u044b\u0435 \u0431\u043b\u043e\u043a\u0438 \u0432\u044b\u0433\u0440\u0443\u0436\u0430\u044e\u0442\u0441\u044f \u043d\u0430 \u0441\u043e\u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440. \u0412 \u0434\u0430\u043d\u043d\u043e\u0439 \u0437\u0430\u043c\u0435\u0442\u043a\u0435 \u0440\u0430\u0441\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u044e \u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u00ab\u0440\u043e\u0434\u043d\u043e\u0433\u043e\u00bb \u043a\u043e\u0434\u0430, \u0441 \u0446\u0435\u043b\u044c\u044e \u0432\u044b\u044f\u0441\u043d\u0438\u0442\u044c, \u0447\u0442\u043e \u044d\u0442\u043e \u0434\u0430\u0435\u0442 \u0438 \u0447\u0435\u043c \u0433\u0440\u043e\u0437\u0438\u0442. \u0412 \u0437\u0430\u0432\u0435\u0440\u0448\u0435\u043d\u0438\u0438 \u043f\u043e\u0441\u0442\u0430 \u0431\u0443\u0434\u0443\u0442 \u0447\u0435\u0442\u044b\u0440\u0435 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u043a\u0430\u0441\u0430\u0442\u0435\u043b\u044c\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f Fortran \u0438 \u043f\u0440\u0438\u043c\u0435\u0440\u044b \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c.
<\/a>
\u0414\u0430\u043d\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u043d\u0435 \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0440\u0435\u043a\u043b\u0430\u043c\u043e\u0439 \u0438\u043b\u0438 \u0430\u043d\u0442\u0438\u0440\u0435\u043a\u043b\u0430\u043c\u043e\u0439 \u043a\u0430\u043a\u043e\u0433\u043e-\u043b\u0438\u0431\u043e \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0433\u043e \u0438\u043b\u0438 \u0430\u043f\u043f\u0430\u0440\u0430\u0442\u043d\u043e\u0433\u043e \u043f\u0440\u043e\u0434\u0443\u043a\u0442\u0430, \u0430 \u0432\u0441\u0435\u0433\u043e \u043b\u0438\u0448\u044c \u043e\u043f\u0438\u0441\u044b\u0432\u0430\u0435\u0442 \u043b\u0438\u0447\u043d\u044b\u0439 \u043e\u043f\u044b\u0442 \u0430\u0432\u0442\u043e\u0440\u0430.
\u041a\u0430\u043a \u0438 \u0432 \u043f\u0440\u043e\u0448\u043b\u044b\u0439 \u0440\u0430\u0437, \u0431\u0443\u0434\u0435\u043c \u0440\u0430\u0441\u0441\u043c\u0430\u0442\u0440\u0438\u0432\u0430\u0442\u044c \u0437\u0430\u0434\u0430\u0447\u0443 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f \u0442\u0435\u043b (n-body problem). \u0420\u0435\u0448\u0435\u043d\u0438\u0435 \u0437\u0430\u0434\u0430\u0447\u043a\u0438 \u043d\u0430 CPU \u0432\u043e\u0437\u044c\u043c\u0435\u043c \u0438\u0437 \u043f\u0440\u043e\u0448\u043b\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0438, \u0430 \u043f\u043e\u0442\u043e\u043c, \u0435\u0441\u043b\u0438 \u043f\u0440\u0438\u0434\u0435\u0442\u0441\u044f, \u043c\u043e\u0434\u0438\u0444\u0438\u0446\u0438\u0440\u0443\u0435\u043c \u043a\u043e\u0434 \u0434\u043b\u044f \u0437\u0430\u043f\u0443\u0441\u043a\u0430 \u043d\u0430 MIC (\u0434\u0430\u043b\u0435\u0435 MIC-\u043e\u043c \u0431\u0443\u0434\u0435\u043c \u0438\u043c\u0435\u043d\u043e\u0432\u0430\u0442\u044c Intel Xeon Phi). <\/p>\n

\u041f\u0430\u0440\u0430\u043b\u043b\u0435\u043b\u044c\u043d\u044b\u0439 \u043a\u043e\u0434 \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c OpenMP<\/b><\/p>\n
\n
\/*---------------------------------------------------------*\/ \/*                  N-Body simulation benchmark            *\/ \/*                   written by M.S.Ozhgibesov             *\/ \/*                         04 July 2015                    *\/ \/*---------------------------------------------------------*\/ #include <stdio.h> #include <stdlib.h> #include <math.h> #include <string.h> #include <time.h> #include <omp.h>  #define HOSTLEN 50  int numProc;  \/\/ Initial conditions void initCoord(float *rA, float *vA, float *fA, \\                float initDist, int nBod, int nI);  \/\/ Forces acting on each body void forces(float *rA, float *fA, int nBod);  \/\/ Calculate velocities and update coordinates void integration(float *rA, float *vA, float *fA, int nBod);  int main(int argc, const char * argv[]) {    int const nI = 32;               \/\/ Number of bodies in X, Y and Z directions    int const nBod = nI*nI*nI;       \/\/ Total Number of bodies    int const maxIter = 20;          \/\/ Total number of iterations (time steps)    float const initDist = 1.0;      \/\/ Initial distance between the bodies    float *rA;                       \/\/ Coordinates    float *vA;                       \/\/ Velocities    float *fA;                       \/\/ Forces    int iter;    double startTime0, endTime0;    char host[HOSTLEN];     rA = (float*)malloc(3*nBod*sizeof(float));    fA = (float*)malloc(3*nBod*sizeof(float));    vA = (float*)malloc(3*nBod*sizeof(float));     gethostname(host, HOSTLEN);    printf("Host name: %s\\n", host);    numProc = omp_get_num_procs();    printf("Available number of processors: %d\\n", numProc);     \/\/ Setup initial conditions    initCoord(rA, vA, fA, initDist, nBod, nI);     startTime0 = omp_get_wtime();    \/\/ Main loop    for ( iter = 0; iter < maxIter; iter++ ) {       forces(rA, fA, nBod);        integration(rA, vA, fA, nBod);    }     endTime0 = omp_get_wtime();     printf("\\nTotal time = %10.4f [sec]\\n", endTime0 - startTime0);     free(rA);    free(vA);    free(fA); \treturn 0; }  \/\/ Initial conditions void initCoord(float *rA, float *vA, float *fA, \\                float initDist, int nBod, int nI) {    int i, j, k;    float Xi, Yi, Zi;    float *rAx = &rA[     0];        \/\/----    float *rAy = &rA[  nBod];        \/\/ Pointers on X, Y, Z components of coordinates    float *rAz = &rA[2*nBod];        \/\/----    int ii = 0;     memset(fA, 0.0, 3*nBod*sizeof(float));    memset(vA, 0.0, 3*nBod*sizeof(float));     for (i = 0; i < nI; i++) {       Xi = i*initDist;       for (j = 0; j < nI; j++) {          Yi = j*initDist;          for (k = 0; k < nI; k++) {             Zi = k*initDist;             rAx[ii] = Xi;             rAy[ii] = Yi;             rAz[ii] = Zi;             ii++;          }       }    } }  \/\/ Forces acting on each body void forces(float *rA, float *fA, int nBod) {    int i, j;    float Xi, Yi, Zi;    float Xij, Yij, Zij;             \/\/ X[j] - X[i] and so on    float Rij2;                      \/\/ Xij^2+Yij^2+Zij^2    float invRij2, invRij6;          \/\/ 1\/rij^2; 1\/rij^6    float *rAx = &rA[     0];        \/\/----    float *rAy = &rA[  nBod];        \/\/ Pointers on X, Y, Z components of coordinates    float *rAz = &rA[2*nBod];        \/\/----    float *fAx = &fA[     0];        \/\/----    float *fAy = &fA[  nBod];        \/\/ Pointers on X, Y, Z components of forces    float *fAz = &fA[2*nBod];        \/\/----    float magForce;                  \/\/ Force magnitude    float const EPS = 1.E-10;         \/\/ Small value to prevent 0\/0 if i==j     #pragma omp parallel for num_threads(numProc) private(Xi, Yi, Zi, \\                Xij, Yij, Zij, magForce, invRij2, invRij6, j, i)    for (i = 0; i < nBod; i++) {       Xi = rAx[i];       Yi = rAy[i];       Zi = rAz[i];       fAx[i] = 0.0;       fAy[i] = 0.0;       fAz[i] = 0.0;       for (j = 0; j < nBod; j++) {          Xij = rAx[j] - Xi;          Yij = rAy[j] - Yi;          Zij = rAz[j] - Zi;          Rij2 = Xij*Xij + Yij*Yij + Zij*Zij;          invRij2 = Rij2\/((Rij2 + EPS)*(Rij2 + EPS));          invRij6 = invRij2*invRij2*invRij2;          magForce = 6.f*invRij2*(2.f*invRij6 - 1.f)*invRij6;          fAx[i]+= Xij*magForce;          fAy[i]+= Yij*magForce;          fAz[i]+= Zij*magForce;       }    } }  \/\/ Integration of coordinates an velocities void integration(float *rA, float *vA, float *fA, int nBod) {    int i;    float const dt = 0.01;              \/\/ Time step    float const mass = 1.0;             \/\/ mass of a body    float const mdthalf = dt*0.5\/mass;    float *rAx = &rA[     0];    float *rAy = &rA[  nBod];    float *rAz = &rA[2*nBod];    float *vAx = &vA[     0];    float *vAy = &vA[  nBod];    float *vAz = &vA[2*nBod];    float *fAx = &fA[     0];    float *fAy = &fA[  nBod];    float *fAz = &fA[2*nBod];     #pragma omp parallel for num_threads(numProc) private(i)    for (i = 0; i < nBod; i++) {       rAx[i]+= (vAx[i] + fAx[i]*mdthalf)*dt;       rAy[i]+= (vAy[i] + fAy[i]*mdthalf)*dt;       rAz[i]+= (vAz[i] + fAz[i]*mdthalf)*dt;        vAx[i]+= fAx[i]*dt;       vAy[i]+= fAy[i]*dt;       vAz[i]+= fAz[i]*dt;    } } <\/code><\/pre>\n
  <\/div>\n<\/div>\n
  \u041a\u043e\u0434 \u043d\u0430 \u0441\u043e\u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0435 \u043c\u043e\u0436\u043d\u043e \u0437\u0430\u043f\u0443\u0441\u0442\u0438\u0442\u044c \u0434\u0432\u0443\u043c\u044f \u0441\u043f\u043e\u0441\u043e\u0431\u0430\u043c\u0438:  <\/p>\n