不能使用cuda进入__global__函数

Question

我在Nsight上编写了一个编译并可以执行的代码但是第一次启动无法完成。

奇怪的是，当我在调试模式下运行它时，它运行得很好，但速度太慢了。

以下是进入访问GPU的函数之前的代码部分（我认为有一个我找不到的错误）：

void parallelAction (int * dataReturned, char * data, unsigned char * descBase, int range, int cardBase, int streamIdx)
{
    size_t inputBytes = range*128*sizeof(unsigned char);
    size_t baseBytes = cardBase*128*sizeof(unsigned char);
    size_t outputBytes = range*sizeof(int);

    unsigned char * data_d;
    unsigned char * descBase_d;
    int * cardBase_d;
    int * dataReturned_d;

    cudaMalloc((void **) &data_d, inputBytes);  
    cudaMalloc((void **) &descBase_d, baseBytes);
    cudaMalloc((void **) &cardBase_d, sizeof(int));
    cudaMalloc((void **) &dataReturned_d, outputBytes);

    int blockSize = 196;
    int nBlocks = range/blockSize + (range%blockSize == 0?0:1);

    cudaMemcpy(data_d, data, inputBytes, cudaMemcpyHostToDevice);
    cudaMemcpy(descBase_d, descBase, baseBytes, cudaMemcpyHostToDevice);
    cudaMemcpy(cardBase_d, &cardBase, sizeof(int), cudaMemcpyHostToDevice);

    FindClosestDescriptor<<< nBlocks, blockSize >>>(dataReturned_d, data_d, descBase_d, cardBase_d);

    cudaMemcpy(dataReturned, dataReturned_d, outputBytes, cudaMemcpyDeviceToHost);

    cudaFree(data_d);
    cudaFree(descBase_d);
    cudaFree(cardBase_d);
    cudaFree(dataReturned_d);
}

进入GPU的功能（我不认为错误在这里）：

__global__ void FindClosestDescriptor(int * dataReturned, unsigned char * data, unsigned char * base, int *cardBase)
{
    int idx = blockDim.x * blockIdx.x + threadIdx.x;
    unsigned char descriptor1[128], descriptor2[128];
    int part = 0;
    int result = 0;
    int winner = 0;
    int minDistance = 0;
    int itelimit = *cardBase;
    for (int k = 0; k < 128; k++)
    {
        descriptor1[k] = data[idx*128+k];

    }
    // initialize minDistance
    for (int k = 0; k < 128; k++)
    {
        descriptor2[k] = base[k];
    }

    for (int k = 0; k < 128; k++)
    {
        part = (descriptor1[k]-descriptor2[k]);
        part *= part;
        minDistance += part;
    }

    // test all descriptors in the base :
    for (int i = 1; i < itelimit; i++)
    {
        result = 0;
        for (int k = 0; k < 128; k++)
        {
            descriptor2[k] = base[i*128+k];
            // Calculate squared l2 distance :
            part = (descriptor1[k]-descriptor2[k]);
            part *= part;
            result += part;
        }

        // Compare to minDistance
        if (result < minDistance)
        {
            minDistance = result;
            winner = i;
        }
    }

    // Write the result in dataReturned
    dataReturned[idx] = winner;
}

如果你能帮助我，请提前感谢你。

编辑：最后一个cudaMemcpy返回错误“启动超时并被终止”。

Answer 1

linux有一个看门狗机制。如果你的内核运行了很长时间（你说它在调试模式下很慢）你可以点击linux看门狗，并收到“启动超时并被终止”错误。

在这种情况下，您可以尝试几种方法。选项涵盖here。