Index

参考：https://blog.csdn.net/dcrmg/article/details/54867507

int blockId = blockIdx.x + blockIdx.y * gridDim.x
                     + gridDim.x * gridDim.y * blockIdx.z;
int threadId = blockId * (blockDim.x * blockDim.y * blockDim.z)
                       + (threadIdx.z * (blockDim.x * blockDim.y))
                       + (threadIdx.y * blockDim.x) + threadIdx.x;