多线程、OpenMP、C

Question

我在论坛上看到了下面的一些代码，但当我开始编译它时，我得到了一些错误。我想把从#pragma scop到#pragma endscop的区域平行。

/* Main computational kernel. The whole function will be timed,
including the call and return. */
static
void kernel_fdtd_2d(int tmax,
        int nx,
        int ny,
        DATA_TYPE POLYBENCH_2D(ex,NX,NY,nx,ny),
        DATA_TYPE POLYBENCH_2D(ey,NX,NY,nx,ny),
        DATA_TYPE POLYBENCH_2D(hz,NX,NY,nx,ny),
        DATA_TYPE POLYBENCH_1D(_fict_,TMAX,tmax))
{
int t, i, j;
#pragma scop
#pragma omp parallel private (t,i,j)
{
 #pragma omp master
 {
  for (t = 0; t < _PB_TMAX; t++)
  {
   #pragma omp for
   for (j = 0; j < _PB_NY; j++)
      ey[0][j] = _fict_[t];
    #pragma omp barrier
    #pragma omp for collapse(2) schedule(static)
    for (i = 1; i < _PB_NX; i++)
      for (j = 0; j < _PB_NY; j++)
        ey[i][j] = ey[i][j] - 0.5*(hz[i][j]-hz[i-1][j]);
    #pragma omp barrier
    #pragma omp for collapse(2) schedule(static)
    for (i = 0; i < _PB_NX; i++)
      for (j = 1; j < _PB_NY; j++)
        ex[i][j] = ex[i][j] - 0.5*(hz[i][j]-hz[i][j-1]);
    #pragma omp barrier
    #pragma omp for collapse(2) schedule(static)
    for (i = 0; i < _PB_NX - 1; i++)
      for (j = 0; j < _PB_NY - 1; j++)
        hz[i][j] = hz[i][j] - 0.7*  (ex[i][j+1] - ex[i][j] + ey[i+1][j] - ey[i][j]);
    #pragma omp barrier
  }
}
}
#pragma endscop
}


int main(int argc, char** argv)
 {
 /* Retrieve problem size. */
 int tmax = TMAX;
 int nx = NX;
 int ny = NY;

 /* Variable declaration/allocation. */
 POLYBENCH_2D_ARRAY_DECL(ex,DATA_TYPE,NX,NY,nx,ny);
 POLYBENCH_2D_ARRAY_DECL(ey,DATA_TYPE,NX,NY,nx,ny);
 POLYBENCH_2D_ARRAY_DECL(hz,DATA_TYPE,NX,NY,nx,ny);
 POLYBENCH_1D_ARRAY_DECL(_fict_,DATA_TYPE,TMAX,tmax);

 /* Initialize array(s). */
 init_array (tmax, nx, ny,
      POLYBENCH_ARRAY(ex),
      POLYBENCH_ARRAY(ey),
      POLYBENCH_ARRAY(hz),
      POLYBENCH_ARRAY(_fict_));

 /* Start timer. */
 polybench_start_instruments;

 /* Run kernel. */
 kernel_fdtd_2d (tmax, nx, ny,
      POLYBENCH_ARRAY(ex),
      POLYBENCH_ARRAY(ey),
      POLYBENCH_ARRAY(hz),
      POLYBENCH_ARRAY(_fict_));


  /* Stop and print timer. */
  polybench_stop_instruments;
  polybench_print_instruments;

  /* Prevent dead-code elimination. All live-out data must be printed
  by the function call in argument. */
   polybench_prevent_dce(print_array(nx, ny, POLYBENCH_ARRAY(ex),
                POLYBENCH_ARRAY(ey),
                POLYBENCH_ARRAY(hz)));

   /* Be clean. */
   POLYBENCH_FREE_ARRAY(ex);
   POLYBENCH_FREE_ARRAY(ey);
   POLYBENCH_FREE_ARRAY(hz);
   POLYBENCH_FREE_ARRAY(_fict_);

   return 0;
   }

错误如下：

stencils/fdtd-2d/fdtd-2dp.c:80:9: error: work-sharing region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp for ^

stencils/fdtd-2d/fdtd-2dp.c:83:9: error: barrier region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp barrier ^

stencils/fdtd-2d/fdtd-2dp.c:84:9: error: work-sharing region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp for collapse(2) schedule(static) ^

stencils/fdtd-2d/fdtd-2dp.c:88:9: error: barrier region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp barrier ^

stencils/fdtd-2d/fdtd-2dp.c:89:9: error: work-sharing region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp for collapse(2) schedule(static) ^

stencils/fdtd-2d/fdtd-2dp.c:93:9: error: barrier region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp barrier ^

stencils/fdtd-2d/fdtd-2dp.c:94:9: error: work-sharing region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp for collapse(2) schedule(static) ^

stencils/fdtd-2d/fdtd-2dp.c:98:9: error: barrier region may not be closely nested inside of work-sharing, critical, ordered, master or explicit task region #pragma omp barrier ^

如果对我如何编译这篇文章有任何帮助..

Answer 1

老实说，这是非常糟糕的OpenMP代码。它不会在整个算法中考虑数据使用情况。你可能想要的是：

int t, i, j;
#pragma omp parallel private (t,i,j)
{
    for (t = 0; t < _PB_TMAX; t++)
    {
        #pragma omp for nowait
        for (j = 0; j < _PB_NY; j++)
            ey[0][j] = _fict_[t];

        #pragma omp for collapse(2) nowait schedule(static)
        for (i = 1; i < _PB_NX; i++)
             for (j = 0; j < _PB_NY; j++)
                 ey[i][j] = ey[i][j] - 0.5*(hz[i][j]-hz[i-1][j]);

        #pragma omp for collapse(2) schedule(static)
        for (i = 0; i < _PB_NX; i++)
            for (j = 1; j < _PB_NY; j++)
                 ex[i][j] = ex[i][j] - 0.5*(hz[i][j]-hz[i][j-1]);

        // #pragma omp barrier <- Implicit if nowait not specified

        #pragma omp for collapse(2) schedule(static)
        for (i = 0; i < _PB_NX - 1; i++)
            for (j = 0; j < _PB_NY - 1; j++)
                hz[i][j] = hz[i][j] - 0.7*(ex[i][j+1] - ex[i][j] + ey[i+1][j] - ey[i][j]);

        // #pragma omp barrier <- Implicit if nowait not specified
    }
}

这些障碍应该被移除，因为它们在for循环结束后是隐式的，而没有指定nowait。

此外，我认为前两个障碍应该完全消除，因为前三个循环之间没有线程依赖--如果一个线程完成了它的一部分循环，并立即启动了下一个循环的一部分，就不会出现竞态条件。您可以添加nowait子句来覆盖omp for指令末尾的隐式屏障。

最后，如果_PB_NX和_PB_NY都很大，那么您不太可能通过折叠嵌套循环来获得任何好处。我可以想象，删除collapse(2)可以略微提高整体函数的性能。

希望这能有所帮助。

Answer 2

从代码中删除#pragma omp master语句。这将修复编译问题。您可能不想在主线程中“只”运行该块，因为那样您将不会从使用Open MP中获得任何性能优势。