Blockchain的鱼和熊掌系列（22） 之基于CUDA的客户端哈希并行化处理示例

1. 测试代码 “sample.cu”

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

using namespace std;  

__global__ void Add(int *a, int *b, int *c){  
    c[0] = a[0]+b[0];  
}  

int main(void) {    

    // Declare variables  
    int addResult;  
    int *devicePointerA;  
    int *devicePointerB;  
    int *devicePointerC;  

    //Create two integers. (Host)  
    int a = 5;  
    int b = 9;  

    // Allocate device memory for these two integers and their add result. (Device)  
    cudaMalloc(&devicePointerA, sizeof(int));  
    cudaMalloc(&devicePointerB, sizeof(int));  
    cudaMalloc(&devicePointerC, sizeof(int));  

    // Copy these two integers to the device memory. (Host)  
    cudaMemcpy(devicePointerA, &a, sizeof(int), cudaMemcpyHostToDevice);  
    cudaMemcpy(devicePointerB, &b, sizeof(int), cudaMemcpyHostToDevice);  

    // Call the kernel to add these two integers together. (Device)  
    Add<<<1, 1>>>(devicePointerA, devicePointerB, devicePointerC);  

    // Copy the result back to the host memory. (Device)  
    cudaMemcpy(&addResult, devicePointerC, sizeof(int), cudaMemcpyDeviceToHost);  

    // Print out the result. (Host)  
    printf("The add result is %d \n", addResult);  

    // Free the device memory. (Device)  
    cudaFree(devicePointerA);  
    cudaFree(devicePointerB);  

    return 0;    
}    

2. 客户端（Laptop with GeForce 940MX inside）上测试

nvcc sample.cu -o sample
./sample

3. 服务器端（Server with Tesla P100 inside）上测试

nvcc sample.cu -o sample
./sample

注：nvcc编译器的使用语法类似gcc/g++

参考
http://blog.csdn.net/canhui_wang/article/details/51584862