FPGA上的OpenCL程序执行速度比CPU上慢

Question

我正在学习在FPGA上使用opencl并编写了实现Smith–Waterman algorithm的程序。但是结果是CPU上的程序比FPGA上的执行速度快。

这是我的内核代码：

    __kernel void __attribute__ ((reqd_work_group_size(512,512,1)))
krnl_sw(
     __global int* ref,
     __global int* alt,
     __global int* sw,
     const int match,
     const int mismatch,
     const int open,
     const int extend,
     const int ncol,
     const int nrow
     ) {

 int col = get_global_id(0);
 int row = get_global_id(1);

 for (k = 2;k<ncol+nrow-1;k++)
{
    if(col + row == k)
    { 
            up_score = sw[(row - 1)*ncol + col] + extend*(row-1) + open ;
            left_score = sw[row*ncol + col - 1] + extend*(row-1) + open ;
            up_left_score = sw[(row - 1)*ncol + col - 1] + diag_score(ref[col - 1], alt[row - 1], match, mismatch);
            sw[row*ncol + col] = max(up_score, left_score);
            sw[row*ncol + col] = max(up_left_score, sw[row*ncol + col]);

    }
}
  return;
}

cpu上的代码：

for (i = 1;i < ncol;i++)
{
    for (j = 1;j< nrow;j++)
    {
            up_score = sw[j - 1][i] + extend*(j-1)+open;
            left_score = sw[j][i - 1] + extend * (i - 1) + open;
            up_left_score = sw[j - 1][i - 1] + diag_score(ref[i - 1], alt[j - 1], match, mismatch);
            sw[j][i] = max(up_score, left_score);
            sw[j][i] = max(up_left_score, sw[j][i]);

    }
}

内核代码有什么问题吗？