c++ - CUDA blockDim.y始终== 1

我总是得到blockdim.y == 1。无论我在numBlocks中设置什么值，我总是会得到相同的结果。

__global__ void CalcVideo(unsigned char *original, unsigned char *candidate, int *answer)
{
    printf("block id.x = %d blockid.y=%d blockdim.x = %d blockdim.y = %d Thread id= %d \n",
        blockIdx.x, blockIdx.y, blockDim.x, blockDim.y, threadIdx.x );
}

int ORIGINAL_FRAMES = 3;
int CANDIDATE_FRAMES = 2;
int FRAME_LENGHT = 3;

dim3 numBlocks(ORIGINAL_FRAMES, CANDIDATE_FRAMES);
    dim3 threadsPerBlock(3);  // 64 threads

CalcVideo << <numBlocks, threadsPerBlock >> >(original_device, candidate_device, answer_device);

y.blokcs的数量正确执行，但是为什么程序给我的blockdim.y大小错误？

block id.x = 1 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 1 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 1 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 2
block id.x = 1 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 1 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 1 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 2
block id.x = 0 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 0 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 0 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 2
block id.x = 0 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 0 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 0 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 2
block id.x = 2 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 2 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 2 blockid.y=1 blockdim.x = 3 blockdim.y = 1 Thread id= 2
block id.x = 2 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 0
block id.x = 2 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 1
block id.x = 2 blockid.y=0 blockdim.x = 3 blockdim.y = 1 Thread id= 2

最佳答案

blockDim存储一个块的尺寸。在您的情况下，您要传递threadsPerBlock作为块维度，从而使其成为3 x 1 x 1。内核调用的第一个参数numBlocks(在您的情况下)控制块网格的尺寸-您可以在内核中以gridDim的形式访问它。

旁注:我认为问题中块的数量和数量极少，仅用于测试目的，因为它们会使实践中的GPU使用率极低。

关于c++ - CUDA blockDim.y始终== 1，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/34197497/