当前位置：首页 > news >正文

CUDA —— 1.1、C++与CUDA混合编程，C++调用cuda自定义类进行运算操作（附：Windows下Vs2017编程环境配置）

news 来源：原创 2025/6/27 9:02:05

运行效果

由于cuda进行运算是非常快的。本文介绍通过C++调用自定义的cuda类接口，将耗时运算操作交由cuda进行计算。

在这里插入图片描述

正问

1、打开vs2017，创建C++空项目，并创建main.cpp写入部分代码

在这里插入图片描述

2、创建cuda文件与头文件

(1)、右键项目名称 - 添加 - 新建项 - Visual C++，分两次分别创建"CUDA 11.4 C/C++ File"与"CUDA 11.4 C/C++ Header"

在这里插入图片描述

(2)、将如下代码分别写入3个代码文件

main.cpp

#include <iostream>#include "main.cuh"int main()
{CudaTest TEST;TEST.RunCalc();system("pause");return 0;
}

CudaTest.cuh

#ifndef MAIN_CUH
#define MAIN_CUH#include "cuda_runtime.h"
#include "device_launch_parameters.h"#include <stdio.h>class CudaTest
{
public:CudaTest();int RunCalc();
};#endif

CudaTest.cu


#include "main.cuh"#include <Windows.h>CudaTest::CudaTest()
{}cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);__global__ void addKernel(int *c, const int *a, const int *b)
{int i = threadIdx.x;c[i] = a[i] + b[i];
}int CudaTest::RunCalc()
{const int arraySize = 5;const int a[arraySize] = { 1, 2, 3, 4, 5 };const int b[arraySize] = { 10, 20, 30, 40, 50 };int c[arraySize] = { 0 };cudaError_t cudaStatus = cudaSuccess;for (unsigned short index = 0; index < 3000; ++index){// Add vectors in parallel.cudaStatus = addWithCuda(c, a, b, arraySize);if (cudaStatus != cudaSuccess) { fprintf(stderr, "addWithCuda failed!"); return 1; }printf("%d --- {1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n", index,c[0], c[1], c[2], c[3], c[4]);Sleep(1);}// 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;
}// Helper function for using CUDA to add vectors in parallel.
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{int *dev_a = 0;int *dev_b = 0;int *dev_c = 0;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?");goto Error;}// Allocate GPU buffers for three vectors (two input, one output)    .cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMalloc failed!");goto Error;}cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMalloc failed!");goto Error;}cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMalloc failed!");goto Error;}// Copy input vectors from host memory to GPU buffers.cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMemcpy failed!");goto Error;}cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMemcpy failed!");goto Error;}// Launch a kernel on the GPU with one thread for each element.addKernel << <1, size >> > (dev_c, dev_a, dev_b);// Check for any errors launching the kernelcudaStatus = cudaGetLastError();if (cudaStatus != cudaSuccess) {fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));goto Error;}// 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);goto Error;}// Copy output vector from GPU buffer to host memory.cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaMemcpy failed!");goto Error;}Error:cudaFree(dev_c);cudaFree(dev_a);cudaFree(dev_b);return cudaStatus;
}