小编Tan*_*wal的帖子

我正在使用CUDA添加两个矩阵,并将结果提供给另一个矩阵.我希望利用共享内存功能,为此,我写了以下内容:

#include <stdio.h>
#include <cuda.h>
#define grid 1024
#define BSZ 16

    __global__ void addition(int *dev_a, int *dev_b, int *dev_c)
    {

    __shared__ int as[BSZ][BSZ];
    __shared__ int bs[BSZ][BSZ];

    int by = blockIdx.y;
    int bx = blockIdx.x;

    int cvalue;

    int ty = threadIdx.y;
    int tx = threadIdx.x;

    int row = by * BSZ + ty;
    int col = bx * BSZ + tx;

    as[ty][tx] = dev_a[row*grid + col];
    bs[ty][tx] = dev_b[row*grid + col];
    __syncthreads();

    cvalue = as[ty][tx] + bs[ty][tx];

    __syncthreads();

    dev_c[row*grid + col] …