小编pen*_*jun的帖子

我正在尝试基于Cyclic Reduction我的方法实现一个三对角系统求解器GTS450.

本文阐述了循环减少

Y. Zhang,J.Cohen,JD Owens,"GPU上的快速三对角解算器"

但是,无论我做什么,我的CUDA代码都比顺序代码快得多.总的来说,我的结果512 x 512是7ms在我的i7 3.4GHz上5ms.GPU没有加速!

哪个可能是问题？

#include "cutrid.cuh"
 __global__ void cutrid_RC_1b(double *a,double *b,double *c,double *d,double *x)
{
 int idx_global=blockIdx.x*blockDim.x+threadIdx.x;
 int idx=threadIdx.x;

 __shared__ double asub[512];
 __shared__ double bsub[512];
 __shared__ double csub[512];
 __shared__ double dsub[512];

 double at=0;
 double bt=0;
 double ct=0;
 double dt=0;

 asub[idx]=a[idx_global];
 bsub[idx]=b[idx_global];
 csub[idx]=c[idx_global];
 dsub[idx]=d[idx_global];


 for(int stride=1;stride<N;stride*=2)
  {
    int margin_left,margin_right;
    margin_left=idx-stride;
    margin_right=idx+stride;


    at=(margin_left>=0)?(-csub[idx-stride]*asub[idx]/bsub[idx-stride]):0.f; 

    bt=bsub[idx]+((margin_left>=0)?(-csub[idx-stride]*asub[idx]/bsub[idx-stride]):0.f)
    -((margin_right<512)?asub[idx+stride]*csub[idx]/bsub[idx+stride]:0.f); 

    ct=(margin_right<512)?(-csub[idx+stride]*asub[idx]/bsub[idx+stride]):0.f; 

    dt=dsub[idx]+((margin_left>=0)?(-dsub[idx-stride]*asub[idx]/bsub[idx-stride]):0.f)
    -((margin_right<512)?dsub[idx+stride]*csub[idx]/bsub[idx+stride]:0.f); 

    __syncthreads();
    asub[idx]=at;
    bsub[idx]=bt;
    csub[idx]=ct;
    dsub[idx]=dt;
    __syncthreads();
  } …