CUDA C编程入门-不同的grid和block大小对CUDA内建的变量的影响，以及如何确定Thread ID

int printf(const char *format[, arg, ...]);

kernel<<<Dg, Db, Ns, S >>>

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>

__global__ void MyKernel()
{
    printf("(%d,%d,%d) (%d, %d, %d) (%d, %d, %d) (%d, %d, %d) %d\n",
        gridDim.x, gridDim.y, gridDim.z, 
        blockDim.x, blockDim.y, blockDim.z,
        blockIdx.x, blockIdx.y, blockIdx.z,
        threadIdx.x, threadIdx.y, threadIdx.z,
        warpSize);
}

int main()
{
    cudaError_t cudaStatus;

    // Choose which GPU to run on, change this on a multi-GPU system.
    cudaStatus = cudaSetDevice(0);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaSetDevice failed! Do you have a CUDA-capable GPU installed?");
    }
    printf("gridDim | blockDim | blockIdx | threadIdx | warpSize\n");
    dim3 gridSize(2, 3, 1);
    dim3 blockSize(2, 2, 1);
    // Launch a kernel on the GPU with one thread for each element.
    MyKernel<<<gridSize, blockSize>>>();

    // Check for any errors launching the kernel
    cudaStatus = cudaGetLastError();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addKernel launch failed: %s\n",         cudaGetErrorString(cudaStatus));
    }

    // cudaDeviceSynchronize waits for the kernel to finish, and returns
    // any errors encountered during the launch.
    cudaStatus = cudaDeviceSynchronize();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
    }

    // cudaDeviceReset must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
    cudaStatus = cudaDeviceReset();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceReset failed!");
        return 1;
    }

    return 0;
}