0_Simple__simplePrintf

在设备代码中使用函数 printf()，没有新的认识。

▶ 源代码

#include <stdio.h>
#include <cuda_runtime.h>
#include "device_launch_parameters.h"
#include <helper_functions.h>
#include <helper_cuda.h>

__global__ void testKernel(int val)
{
    printf("[%d, %d]:		Value is:%d
", blockIdx.y*gridDim.x + blockIdx.x, threadIdx.z*blockDim.x*blockDim.y + threadIdx.y*blockDim.x + threadIdx.x, val);
}

int main(int argc, char **argv)
{
    int devID;
    cudaDeviceProp props;
    devID = findCudaDevice(argc, (const char **)argv);
    cudaGetDevice(&devID);
    cudaGetDeviceProperties(&props, devID);
    printf("Device %d: "%s" with Compute %d.%d capability
",devID, props.name, props.major, props.minor);

    dim3 dimGrid(2, 2);
    dim3 dimBlock(2, 2, 2);
    testKernel<<<dimGrid, dimBlock>>>(10);
    cudaDeviceSynchronize();

    getchar();
    return 0;
}

▶ 输出结果

GPU Device 0: "GeForce GTX 1070" with compute capability 6.1

Device 0 : "GeForce GTX 1070" with Compute 6.1 capability
[2, 0] : Value is : 10
[2, 1] : Value is : 10
[2, 2] : Value is : 10
[2, 3] : Value is : 10
[2, 4] : Value is : 10
[2, 5] : Value is : 10
[2, 6] : Value is : 10
[2, 7] : Value is : 10
[3, 0] : Value is : 10
[3, 1] : Value is : 10
[3, 2] : Value is : 10
[3, 3] : Value is : 10
[3, 4] : Value is : 10
[3, 5] : Value is : 10
[3, 6] : Value is : 10
[3, 7] : Value is : 10
[1, 0] : Value is : 10
[1, 1] : Value is : 10
[1, 2] : Value is : 10
[1, 3] : Value is : 10
[1, 4] : Value is : 10
[1, 5] : Value is : 10
[1, 6] : Value is : 10
[1, 7] : Value is : 10
[0, 0] : Value is : 10
[0, 1] : Value is : 10
[0, 2] : Value is : 10
[0, 3] : Value is : 10
[0, 4] : Value is : 10
[0, 5] : Value is : 10
[0, 6] : Value is : 10
[0, 7] : Value is : 10