相关疑难解决方法(0)

我编写了一个CUDA4 Bayer demosaicing例程,但它比单线程CPU代码慢,运行在16核GTS250上.
Blocksize是(16,16),图像变暗是16的倍数 - 但改变它不会改善它.

我做了什么明显愚蠢的事吗？

--------------- calling routine ------------------
uchar4 *d_output;
size_t num_bytes; 

cudaGraphicsMapResources(1, &cuda_pbo_resource, 0);    
cudaGraphicsResourceGetMappedPointer((void **)&d_output, &num_bytes, cuda_pbo_resource);

// Do the conversion, leave the result in the PBO fordisplay
kernel_wrapper( imageWidth, imageHeight, blockSize, gridSize, d_output );

cudaGraphicsUnmapResources(1, &cuda_pbo_resource, 0);

--------------- cuda -------------------------------
texture<uchar, 2, cudaReadModeElementType> tex;
cudaArray *d_imageArray = 0;

__global__ void convertGRBG(uchar4 *d_output, uint width, uint height)
{
    uint x = __umul24(blockIdx.x, blockDim.x) + threadIdx.x;
    uint y = __umul24(blockIdx.y, blockDim.y) + threadIdx.y;
    uint i = …