Ubuntu 16.04开发CUDA程序入门（一）

• 环境：ubuntu 16.04+NVIDIA-SMI 378.13+cmake 3.5.1+CUDA 8.0+KDevelop 4.7.3

环境配置

1. NVIDIA驱动、cmake、CUDA配置方法见：ubuntu 16.04 配置运行 Kintinuous
2. KDevelop配置：命令行输入 sudo apt-get install kdevelop

参考文献

1. 刘金硕等.基于CUDA的并行程序设计.科学出版社.2014
2. linux下使cmake编译cuda: http://blog.csdn.net/u012839187/article/details/45887737 .
3. CUDA Example: /home/luhaiyan/NVIDIA_CUDA-8.0_Samples/0_Simple/vectorAdd/vectorAdd.cu

数组相加-程序代码

• 打开KDevelop，新建工程，“New From Template…”-“Standard”-“Terminal”，“Application Name:”处填写“cuda_test”，“Location:”为默认的“/home/luhaiyan/projects”。
• 在cuda_test工程下新建文件“test_cuda_fun.cu”，“test_cuda_fun.cu”文件内容为^[2][3]：

#include <stdio.h>  
#include <stdlib.h>  
#include <cuda_runtime.h> 

//设备端代码
__global__ void vectorAdd(const float *A, const float *B, float *C, int numElements)  
{  
  int i = blockDim.x * blockIdx.x + threadIdx.x;

    if (i < numElements)
    {
        C[i] = A[i] + B[i];
    }
}  

//主机端代码
extern "C" int func() // 注意这里定义形式  
{
  // Error code to check return values for CUDA calls
    cudaError_t err = cudaSuccess;

    // Print the vector length to be used, and compute its size
    int numElements = 3;
    size_t size = numElements * sizeof(float);
    printf("[Vector addition of %d elements]\n", numElements);

    // Allocate the host input vector A
    float *h_A = (float *)malloc(size);

    // Allocate the host input vector B
    float *h_B = (float *)malloc(size);

    // Allocate the host output vector C
    float *h_C = (float *)malloc(size);

    // Verify that allocations succeeded
    if (h_A == NULL || h_B == NULL || h_C == NULL)
    {
        fprintf(stderr, "Failed to allocate host vectors!\n");
        exit(EXIT_FAILURE);
    }

    printf("Index    h_A       h_B\n");
    // Initialize the host input vectors
    for (int i = 0; i < numElements; ++i)
    {
        h_A[i] = rand()/(float)RAND_MAX;
        h_B[i] = rand()/(float)RAND_MAX;
    printf("Index %d: %f  %f\n",i,h_A[i],h_B[i]);
    }
    printf("\n");

    // Allocate the device input vector A
    float *d_A = NULL;
    err = cudaMalloc((void **)&d_A, size);//分配一维的线性存储空间

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device input vector B
    float *d_B = NULL;
    err = cudaMalloc((void **)&d_B, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device output vector C
    float *d_C = NULL;
    err = cudaMalloc((void **)&d_C, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the host input vectors A and B in host memory to the device input vectors in
    // device memory
    printf("Copy input data from the host memory to the CUDA device\n");
    err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);//将一维线性存储器的数据从主机端传输到设备端

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Launch the Vector Add CUDA Kernel
    int threadsPerBlock = 256;
    int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
    printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);
    err = cudaGetLastError();

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the device result vector in device memory to the host result vector
    // in host memory.
    printf("Copy output data from the CUDA device to the host memory\n");
    err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Verify that the result vector is correct
    for (int i = 0; i < numElements; ++i)
    {
        if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-5)
        {
            fprintf(stderr, "Result verification failed at element %d!\n", i);
            exit(EXIT_FAILURE);
        }
    }

    printf("Test PASSED\n\n");

    printf("vectorAdd_Result:\n");
    for(int i=0;i<numElements;i++)
      printf("Index %d: %f\n",i,h_C[i]);
    printf("\n");
    // Free device global memory
    err = cudaFree(d_A);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_B);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_C);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Free host memory
    free(h_A);
    free(h_B);
    free(h_C);

    printf("Done\n");
    return 0;
}

• “main.cpp”文件内容为：

#include <iostream>    
using namespace std;      
extern "C" int func(); //注意这里的声明    
int main()    
{    
    func();    
    return 0;    
}    

• “CMakeLists.txt”文件内容为：

cmake_minimum_required(VERSION 2.6)
project(cuda_test)

find_package(CUDA REQUIRED)
include_directories(${CUDA_INCLUDE_DIRS})

CUDA_ADD_EXECUTABLE(test_cuda main.cpp test_cuda_fun.cu)  

• 右击“cuda_test”工程，点击“build”
  

• build后的整体工程结果
  

  

• 命令行输入

cd '/home/luhaiyan/projects/cuda_test/build' 
./test_cuda

• 运行结果: