如何消除CUDA中的连续段

我的内核中有一个连续的部分，它确实在减慢速度。然而，我不知道如何摆脱内部循环。有什么建议吗

__global__ void myKernel( int keep, int inc, int width, int* d_Xnum,
 int* d_Xco, bool* d_Xvalid,int* d_A )
{
  int i = blockIdx.x * blockDim.x + threadIdx.x;
  int j = blockIdx.y * blockDim.y + threadIdx.y;

  int k1;

  if( i < keep && j <= i){
    int counter = 0;

    for(k1 = 0; k1 < inc; k1++){
      if(d_Xvalid[j*inc + k1] == 0)
         counter += (d_Xvalid[i*inc + d_Xco[j*width + k1]]);
    }

    d_A[i*keep+j] = inc - d_Xnum[i] - counter;
  }
}

---

keep

约为9000，而

inc

约为20000

这并不是您问题的确切答案，但它可能可以优化您的代码，并可能有助于您对

k1

求和进行并行缩减，因为您可以去掉

if（imyKernel（…）

Done！从数学上讲，它非常聪明，但我不明白为什么启动更多线程会比代码慢…@Manolete:它已经工作了吗？线程以扭曲的形式发送到gpu（目前每个扭曲有32个线程）。当线程没有执行任何操作时，它们仍然必须等待其扭曲中的线程完成该操作，从而占据可以计算所需内容的线程的位置。大多数情况下（尽管并非总是如此）许多非活动线程意味着较慢的代码@JeanMoniuc:它可以工作，但有时会给出错误的结果。我们是否遗漏了一些东西？我已经对它进行了少量调试，它工作正常，但我不明白为什么它会随机失败。。。

         ...
  int t = 32;
  int b = keep/(32)+1;
  int b2 = (inc/32)+1;
  dim3 thread (t, t);
  dim3 block (b, inc);

  // kernel call
  myKernel<<<block, thread>>>(k, inc, width, d_Xnum,
                  d_Xco, d_Xvalid, d_A);
  cudaThreadSynchronize();
            ...

__global__ void myKernel( int keep, int inc, int width, int* d_Xnum,
int* d_Xco, bool* d_Xvalid,int* d_A )
{
  int k = blockIdx.x * blockDim.x + threadIdx.x;
  int i = (int)(sqrt(0.25+2.0*k)-0.5); 
  int j = k - i*(i+1)/2;

  int k1;
  if( i < keep && j < inc){
    int counter = 0;

    for(k1 = 0; k1 < inc; k1++){
      if(d_Xvalid[j*inc + k1] == 0)
         counter += (d_Xvalid[i*inc + d_Xco[j*width + k1]]);
    }

    d_A[i*keep+j] = inc - d_Xnum[i] - counter;
  }
}

_________________________________
| i = 0 | i = 0 | i = 0 | i = 0 |
| j = 0 |   -   |   -   |   -   |
_________________________________
| i = 1 | i = 1 | i = 1 | i = 1 |
| j = 0 | j = 1 |   -   |   -   |
_________________________________
| i = 2 | i = 2 | i = 2 | i = 2 |
| j = 0 | j = 1 | j = 2 |   -   |
_________________________________
| i = 3 | i = 3 | i = 3 | i = 3 |
| j = 0 | j = 1 | j = 2 | j = 3 |
_________________________________

_________________________________________________________________________________
| k = 0 | k = 0 | k = 1 | k = 0 | k = 1 | k = 2 | k = 0 | k = 1 | k = 2 | k = 3 |
| i = 0 | i = 1 | i = 1 | i = 2 | i = 2 | i = 2 | i = 3 | i = 3 | i = 3 | i = 3 |
| j = 0 | j = 0 | j = 1 | j = 0 | j = 1 | j = 2 | j = 0 | j = 1 | j = 2 | j = 3 |
_________________________________________________________________________________