小编bir*_*358的帖子

我尝试使用 cudaStream 开发 sobel 的示例。这是程序：

void SobelStream(void)
{

    cv::Mat imageGrayL2 = cv::imread("/home/xavier/Bureau/Image1.png",0);


    u_int8_t *u8_PtImageHost;
    u_int8_t *u8_PtImageDevice;

    u_int8_t *u8_ptDataOutHost;
    u_int8_t *u8_ptDataOutDevice;

    u_int8_t u8_Used[NB_STREAM];

    u8_ptDataOutHost = (u_int8_t *)malloc(WIDTH*HEIGHT*sizeof(u_int8_t));
    checkCudaErrors(cudaMalloc((void**)&u8_ptDataOutDevice,WIDTH*HEIGHT*sizeof(u_int8_t)));

    u8_PtImageHost = (u_int8_t *)malloc(WIDTH*HEIGHT*sizeof(u_int8_t));
    checkCudaErrors(cudaMalloc((void**)&u8_PtImageDevice,WIDTH*HEIGHT*sizeof(u_int8_t)));


    cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc<unsigned char>();
    checkCudaErrors(cudaMallocArray(&Array_PatchsMaxDevice, &channelDesc,WIDTH,HEIGHT ));
    checkCudaErrors(cudaBindTextureToArray(Image,Array_PatchsMaxDevice));


    dim3 threads(BLOC_X,BLOC_Y);
    dim3 blocks(ceil((float)WIDTH/BLOC_X),ceil((float)HEIGHT/BLOC_Y));

    ClearKernel<<<blocks,threads>>>(u8_ptDataOutDevice,WIDTH,HEIGHT);


    int blockh = HEIGHT/NB_STREAM;


    Stream = (cudaStream_t *) malloc(NB_STREAM * sizeof(cudaStream_t));

    for (int i = 0; i < NB_STREAM; i++)
    {
        checkCudaErrors(cudaStreamCreate(&(Stream[i])));
    }

//    for(int i=0;i<NB_STREAM;i++)
//    {
//        cudaSetDevice(0);
//        cudaStreamCreate(&Stream[i]);
//    } …