作业示例（开发者）¶

#include <omp.h>
#include <stdio.h>
#include <stdlib.h>

int main (int argc, char *argv[])
{
int nthreads, tid;

  /* Fork a team of threads giving them their own copies of variables */
  #pragma omp parallel private(nthreads, tid)
    {

     /* Obtain thread number */
     tid = omp_get_thread_num();
     printf("Hello World from thread = %d\n", tid);

     /* Only master thread does this */
     if (tid == 0)
       {
        nthreads = omp_get_num_threads();
        printf("Number of threads = %d\n", nthreads);
       }

     }  /* All threads join master thread and disband */
}

#include <mpi.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>

#define MAX_HOSTNAME_LENGTH 256

int main(int argc, char *argv[])
{
    int pid;
    char hostname[MAX_HOSTNAME_LENGTH];

    int numprocs;
    int rank;

    int rc;

    /* Initialize MPI. Pass reference to the command line to
     * allow MPI to take any arguments it needs
     */
    rc = MPI_Init(&argc, &argv);

    /* It's always good to check the return values on MPI calls */
    if (rc != MPI_SUCCESS)
    {
        fprintf(stderr, "MPI_Init failed\n");
        return 1;
    }

    /* Get the number of processes and the rank of this process */
    MPI_Comm_size(MPI_COMM_WORLD, &numprocs);
    MPI_Comm_rank(MPI_COMM_WORLD, &rank);

    /* let's see who we are to the "outside world" - what host and what PID */
    gethostname(hostname, MAX_HOSTNAME_LENGTH);
    pid = getpid();

    /* say who we are */
    printf("Rank %d of %d has pid %5d on %s\n", rank, numprocs, pid, hostname);
    fflush(stdout);

    /* allow MPI to clean up after itself */
    MPI_Finalize();
    return 0;
}

#include <stdio.h>
#include <mpi.h>
#include <omp.h>

int main(int argc, char *argv[]) {
  int numprocs, rank, namelen;
  char processor_name[MPI_MAX_PROCESSOR_NAME];
  int iam = 0, np = 1;

  MPI_Init(&argc, &argv);
  MPI_Comm_size(MPI_COMM_WORLD, &numprocs);
  MPI_Comm_rank(MPI_COMM_WORLD, &rank);
  MPI_Get_processor_name(processor_name, &namelen);

  #pragma omp parallel default(shared) private(iam, np)
  {
    np = omp_get_num_threads();
    iam = omp_get_thread_num();
    printf("Hello from thread %d out of %d from process %d out of %d on %s\n",
           iam, np, rank, numprocs, processor_name);
  }

  MPI_Finalize();
}

//Example 2. Application Using C and CUBLAS: 0-based indexing
//-----------------------------------------------------------
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <cuda_runtime.h>
#include "cublas_v2.h"
#define M 6
#define N 5
#define IDX2C(i,j,ld) (((j)*(ld))+(i))

static __inline__ void modify (cublasHandle_t handle, float *m, int ldm, int n, int p, int q, float alpha, float beta){
    cublasSscal (handle, n-p, &alpha, &m[IDX2C(p,q,ldm)], ldm);
    cublasSscal (handle, ldm-p, &beta, &m[IDX2C(p,q,ldm)], 1);
}

int main (void){
    cudaError_t cudaStat;
    cublasStatus_t stat;
    cublasHandle_t handle;
    int i, j;
    float* devPtrA;
    float* a = 0;
    a = (float *)malloc (M * N * sizeof (*a));
    if (!a) {
        printf ("host memory allocation failed");
        return EXIT_FAILURE;
    }
    for (j = 0; j < N; j++) {
        for (i = 0; i < M; i++) {
            a[IDX2C(i,j,M)] = (float)(i * M + j + 1);
        }
    }
    cudaStat = cudaMalloc ((void**)&devPtrA, M*N*sizeof(*a));
    if (cudaStat != cudaSuccess) {
        printf ("device memory allocation failed");
        return EXIT_FAILURE;
    }
    stat = cublasCreate(&handle);
    if (stat != CUBLAS_STATUS_SUCCESS) {
        printf ("CUBLAS initialization failed\n");
        return EXIT_FAILURE;
    }
    stat = cublasSetMatrix (M, N, sizeof(*a), a, M, devPtrA, M);
    if (stat != CUBLAS_STATUS_SUCCESS) {
        printf ("data download failed");
        cudaFree (devPtrA);
        cublasDestroy(handle);
        return EXIT_FAILURE;
    }
    modify (handle, devPtrA, M, N, 1, 2, 16.0f, 12.0f);
    stat = cublasGetMatrix (M, N, sizeof(*a), devPtrA, M, a, M);
    if (stat != CUBLAS_STATUS_SUCCESS) {
        printf ("data upload failed");
        cudaFree (devPtrA);
        cublasDestroy(handle);
        return EXIT_FAILURE;
    }
    cudaFree (devPtrA);
    cublasDestroy(handle);
    for (j = 0; j < N; j++) {
        for (i = 0; i < M; i++) {
            printf ("%7.0f", a[IDX2C(i,j,M)]);
        }
        printf ("\n");
    }
    free(a);
    return EXIT_SUCCESS;
}