使用MPI-IO和笛卡尔拓扑编写分布式数组

时间:2015-11-05 05:41:27

标签: c multidimensional-array parallel-processing mpi hpc

我有一个MPI代码,它实现了2D域分解,以计算PDE的数值解法。目前,我为每个进程编写了某些2D分布式数组(例如array_x - > proc000x.bin)。我想将其减少为单个二进制文件。

array_0,array_1,

array_2,array_3,

假设上面说明了具有4个进程(2x2)的笛卡尔拓扑。每个2D阵列具有尺寸(nx + 2,nz + 2)。 +2表示"鬼"为了沟通目的,各层都添加了各层。

我想提取主数组(省略ghost层)并将它们写入单个二进制文件,其顺序类似于

array_0,array_1,array_2,array_3 - > output.bin

如果可能的话,最好把它写成好像我可以访问全局网格并逐行写,即

array_0的第0行,array_1的第0行,array_1的array_0 row_1的第1行....

下面的尝试尝试文件array_test.c中的两种输出格式的前者

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

/* 2D array allocation */
float **alloc2D(int rows, int cols);

float **alloc2D(int rows, int cols) {
  int i, j; 
  float *data = malloc(rows * cols * sizeof(float));
  float **arr2D = malloc(rows * sizeof(float *));

  for (i = 0; i < rows; i++) {
    arr2D[i] = &(data[i * cols]);
  }                 
  /* Initialize to zero */
  for (i= 0; i < rows; i++) {
     for (j=0; j < cols; j++) {
        arr2D[i][j] = 0.0;      
     }                               
  }                    
  return arr2D;
}   

int main(void) {

   /* Creates 5x5 array of floats with padding layers and 
   * attempts to write distributed arrays */

   /* Run toy example with 4 processes */
   int i, j, row, col;
   int nx = 5, ny = 5, npad = 1;
   int my_rank, nproc=4;
   int dim[2] = {2, 2}; /* 2x2 cartesian grid */
   int period[2] = {0, 0};
   int coord[2];
   int reorder = 1;
   float **A = NULL;
   MPI_Comm grid_Comm;

   /* Initialize MPI */
   MPI_Init(NULL, NULL);
   MPI_Comm_size(MPI_COMM_WORLD, &nproc);
   MPI_Comm_rank(MPI_COMM_WORLD, &my_rank);

   /* Establish cartesian topology */
   MPI_Cart_create(MPI_COMM_WORLD, 2, dim, period, reorder, &grid_Comm);

   /* Get cartesian grid indicies of processes */
   MPI_Cart_coords(grid_Comm, my_rank, 2, coord);
   row = coord[1];
   col = coord[0];

   /* Add ghost layers */
   nx += 2 * npad;
   ny += 2 * npad;
   A = alloc2D(nx, ny);

   /* Create derived datatype for interior grid (output grid) */
   MPI_Datatype grid;
   int start[2] = {npad, npad};
   int arrsize[2] = {nx, ny};
   int gridsize[2] = {nx - 2 * npad, ny - 2 * npad};

   MPI_Type_create_subarray(2, arrsize, gridsize,
                            start, MPI_ORDER_C, MPI_FLOAT, &grid);
   MPI_Type_commit(&grid);

   /* Fill interior grid */
   for (i = npad; i < nx-npad; i++) {
      for (j = npad; j < ny-npad; j++) {
         A[i][j] = my_rank + i;
      }
   }

   /* MPI IO */
   MPI_File fh;
   MPI_Status status;
   char file_name[100];
   int N, offset;

   sprintf(file_name, "output.bin");
   MPI_File_open(grid_Comm, file_name, MPI_MODE_CREATE | MPI_MODE_WRONLY,
              MPI_INFO_NULL, &fh);

   N = (nx - 2 * npad) * (ny - 2 *npad);
   offset = (row * 2 + col) * N * sizeof(float);
   MPI_File_set_view(fh, offset, MPI_FLOAT, grid, "native",
                     MPI_INFO_NULL);
   MPI_File_write_all(fh, &A[0][0], N, MPI_FLOAT, MPI_STATUS_IGNORE);
   MPI_File_close(&fh);

   /* Cleanup */
   free(A[0]);
   free(A);
   MPI_Type_free(&grid);
   MPI_Finalize();

   return 0;

}

使用

进行编译
mpicc -o array_test array_test.c  

运行
mpiexec -n 4 array_test

当代码编译并运行时,输出不正确。我假设我在这种情况下误解了派生数据类型和文件写入的使用。我很感激帮助搞清楚我的错误。

1 个答案:

答案 0 :(得分:3)

您在此处犯的错误是文件视图错误。您可以使用与要写入的本地数据相对应的掩码,而不是创建表示当前处理器负责的文件共享的类型。

您实际上需要考虑两个非常不同的掩码

  1. 本地数据的掩码,不包括光晕层;和
  2. 全局数据的掩码,因为它应该整理到文件中。
  3. 前者对应于这种布局:
    data and halo boundary
    在这里,您要在深蓝色的给定进程的文件上输出的数据,以及不应该在文件上写入的光晕层是浅蓝色。

    后者对应于这种布局:
    file layout
    这里,每种颜色对应于来自不同过程的本地数据,分布在2D笛卡尔网格上。

    要了解为达到最终结果需要创建的内容,您必须反思:

    1. 您对IO例程的最终调用应为MPI_File_write_all(fh, &A[0][0], 1, interior, MPI_STATUS_IGNORE);。因此,您必须定义interior类型,以排除光晕边界。幸运的是,您创建的类型grid已经完全正确。所以我们会用它。
    2. 但是现在,您必须拥有该文件的视图才能进行此MPI_Fie_write_all()调用。所以视图必须如第二张图所述。因此,我们将创建一个代表它的新MPI类型。为此,MPI_Type_create_subarray()就是我们所需要的。
    3. 以下是此功能的概要:

      int MPI_Type_create_subarray(int ndims,
                                   const int array_of_sizes[],
                                   const int array_of_subsizes[],
                                   const int array_of_starts[],
                                   int order,
                                   MPI_Datatype oldtype,
                                   MPI_Datatype *newtype)
      
         Create a datatype for a subarray of a regular, multidimensional array
      
      INPUT PARAMETERS
        ndims   - number of array dimensions (positive integer)
        array_of_sizes
                - number of elements of type oldtype in each
                  dimension of the full array (array of positive integers)
        array_of_subsizes
                - number of elements of type oldtype in each dimension of
                  the subarray (array of positive integers)
        array_of_starts
                - starting coordinates of the subarray in each dimension
                  (array of nonnegative integers)
        order   - array storage order flag (state)
        oldtype - array element datatype (handle)
      
      OUTPUT PARAMETERS
        newtype - new datatype (handle)
      

      对于我们的2D笛卡尔文件视图,以下是我们对这些输入参数的需求:

      • ndims:2,网格为2D
      • array_of_sizes:这些是要输出的全局数组的维度,即{ nnx*dim[0], nny*dim[1] }
      • array_of_subsizes:这些是要输出的数据的本地份额的维度,即{ nnx, nny }
      • array_of_start:这些是本地共享到全局网格的x,y起始坐标,即{ nnx*coord[0], nny*coord[1] }
      • order:排序为C,因此必须为MPI_ORDER_C
      • oldtype:数据为float,因此必须为MPI_FLOAT

      现在我们有了文件视图的类型,我们只需将其应用于MPI_File_set_view(fh, 0, MPI_FLOAT, view, "native", MPI_INFO_NULL);并完成魔术。

      您的完整代码变为:

      #include <stdio.h>
      #include <mpi.h>
      #include <stdlib.h>
      
      /* 2D array allocation */
      float **alloc2D(int rows, int cols);
      
      float **alloc2D(int rows, int cols) {
        int i, j; 
        float *data = malloc(rows * cols * sizeof(float));
        float **arr2D = malloc(rows * sizeof(float *));
      
        for (i = 0; i < rows; i++) {
          arr2D[i] = &(data[i * cols]);
        }                 
        /* Initialize to zero */
        for (i= 0; i < rows; i++) {
           for (j=0; j < cols; j++) {
              arr2D[i][j] = 0.0;      
           }                               
        }                    
        return arr2D;
      }   
      
      int main(void) {
      
         /* Creates 5x5 array of floats with padding layers and 
         * attempts to write distributed arrays */
      
         /* Run toy example with 4 processes */
         int i, j, row, col;
         int nx = 5, ny = 5, npad = 1;
         int my_rank, nproc=4;
         int dim[2] = {2, 2}; /* 2x2 cartesian grid */
         int period[2] = {0, 0};
         int coord[2];
         int reorder = 1;
         float **A = NULL;
         MPI_Comm grid_Comm;
      
         /* Initialize MPI */
         MPI_Init(NULL, NULL);
         MPI_Comm_size(MPI_COMM_WORLD, &nproc);
         MPI_Comm_rank(MPI_COMM_WORLD, &my_rank);
      
         /* Establish cartesian topology */
         MPI_Cart_create(MPI_COMM_WORLD, 2, dim, period, reorder, &grid_Comm);
      
         /* Get cartesian grid indicies of processes */
         MPI_Cart_coords(grid_Comm, my_rank, 2, coord);
         row = coord[1];
         col = coord[0];
      
         /* Add ghost layers */
         nx += 2 * npad;
         ny += 2 * npad;
         A = alloc2D(nx, ny);
      
         /* Create derived datatype for interior grid (output grid) */
         MPI_Datatype grid;
         int start[2] = {npad, npad};
         int arrsize[2] = {nx, ny};
         int gridsize[2] = {nx - 2 * npad, ny - 2 * npad};
      
         MPI_Type_create_subarray(2, arrsize, gridsize,
                                  start, MPI_ORDER_C, MPI_FLOAT, &grid);
         MPI_Type_commit(&grid);
      
         /* Fill interior grid */
         for (i = npad; i < nx-npad; i++) {
            for (j = npad; j < ny-npad; j++) {
               A[i][j] = my_rank + i;
            }
         }
      
         /* Create derived type for file view */
         MPI_Datatype view;
         int nnx = nx-2*npad, nny = ny-2*npad; 
         int startV[2] = { coord[0]*nnx, coord[1]*nny };
         int arrsizeV[2] = { dim[0]*nnx, dim[1]*nny };
         int gridsizeV[2] = { nnx, nny };
      
         MPI_Type_create_subarray(2, arrsizeV, gridsizeV,
                                  startV, MPI_ORDER_C, MPI_FLOAT, &view);
         MPI_Type_commit(&view);
      
         /* MPI IO */
         MPI_File fh;
      
         MPI_File_open(grid_Comm, "output.bin", MPI_MODE_CREATE | MPI_MODE_WRONLY,
                       MPI_INFO_NULL, &fh);
      
         MPI_File_set_view(fh, 0, MPI_FLOAT, view, "native", MPI_INFO_NULL);
         MPI_File_write_all(fh, &A[0][0], 1, grid, MPI_STATUS_IGNORE);
         MPI_File_close(&fh);
      
         /* Cleanup */
         free(A[0]);
         free(A);
         MPI_Type_free(&view);
         MPI_Type_free(&grid);
         MPI_Finalize();
      
         return 0;
      
      }