need help with gpu code

m4 Chrennikov

2012 2 4

0 个回答

6 次查看（30 天）

0 个投票

Im trying to use mutex in my code with no luck. Matlab says that kernel reaches timeout.

kernel:

__global__ void getGrid(    int*   mask,
                int*  mutex  )  {
      unsigned int idx = blockIdx.x * blockDim.x + threadIdx.x;
      while( idx < 100 ){
        while( atomicCAS( mutex, 0, 1 ) != 0 );
          mask[ idx ] = idx;
        atomicExch( mutex, 0 );
        //*mutex = 0;
        //while( atomicCAS( mutex, idx, idx + 1 ) != idx );
        idx += blockDim.x * gridDim.x;
        }
      }

script:

mutex       = parallel.gpu.GPUArray.zeros('int32');
kern0 = parallel.gpu.CUDAKernel('testkern.ptx', 'testkern.cu');
kern0.ThreadBlockSize = [256 1 1];
kern0.GridSize = [7*20 1];
mask = parallel.gpu.GPUArray.zeros(int32(256*7*20),int32(1),'int32');
tic
[mask mutex] = feval(kern0, mask, mutex);
toc