CUDA默认示例kernel.cu解析

CUDA默认示例kernel.cu解析

CUDA默认示例kernel.cu代码如下：

// kernel.cu

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

#include <stdio.h>


// GPU 这个函数会被GPU上的多个线程同时执行一次
__global__ void addKernel(int *c, const int *a, const int *b)
{
    int i = threadIdx.x;   // thread在x方向上的索引号
    c[i] = a[i] + b[i];
}


// 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;


    // GPU 设置（默认：0）
    // 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;
    }


    // 为参与运算的数据分配显存空间
    // 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;
    }

    // 数据拷贝（主机 --> 设备）
    // cudaMemcpy(void* dst, const void* src, size_t count, enum cudaMemcpyKind kind);
    // enum __device_builtin__ cudaMemcpyKind {
    //    cudaMemcpyHostToHost = 0,          /* Host   -> Host   */
    //    cudaMemcpyHostToDevice = 1,        /* Host   -> Device */
    //    cudaMemcpyDeviceToHost = 2,        /* Device -> Host   */
    //    cudaMemcpyDeviceToDevice = 3,      /* Device -> Device */
    //    cudaMemcpyDefault = 4              /* Direction of the transfer is inferred from the pointer values. Requires unified virtual addressing */
    // }
    // 
    // 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;
    }

    //*********** 运算 ***********//
    // Launch a kernel on the GPU with one thread for each element.
    addKernel << <1, size >> > (dev_c, dev_a, dev_b);   // 定义1个线程块，size个线程。

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

    // 提供了一个阻塞，用于等待所有的线程都执行完各自的计算任务，然后继续往下执行
    // 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;
    }


    // 数据拷贝（ 设备 --> 主机 ）
    // 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:
    // 释放申请的内存空间
    // cudaDeviceReset用于释放所有申请的显存空间和重置设备状态；
    cudaFree(dev_c);
    cudaFree(dev_a);
    cudaFree(dev_b);

    return cudaStatus;
}


// main
int Main()
{
    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 };

    // Add vectors in parallel.
    cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addWithCuda failed!");
        return 1;
    }

    printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",
        c[0], c[1], c[2], c[3], c[4]);

    // 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;
}


// output #~
// {1,2,3,4,5} + {10,20,30,40,50} = {11,22,33,44,55}

或

将上面代码（kernel.cu）的int Main()行修改为：

// kernel.cu

extern "C" int kernalMain()

并添加 main.cpp 文件，并调用kernalMain()函数。

// main.cpp

#include <iostream>

using namespace std;

extern "C" int kernalMain();

// main
int main()
{
    kernalMain();
    
    return 0;
}

// output #~
// {1,2,3,4,5} + {10,20,30,40,50} = {11,22,33,44,55}

或

// kernel.cu

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

#include <stdio.h>


// GPU 这个函数会被GPU上的多个线程同时执行一次
__global__ void addKernel(int *c, const int *a, const int *b)
{
    int i = threadIdx.x;   // thread在x方向上的索引号
    c[i] = a[i] + b[i];
}


// Helper function for using CUDA to add vectors in parallel.
extern "C" 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;


    // GPU 设置（默认：0）
    // 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;
    }


    // 为参与运算的数据分配显存空间
    // 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;
    }

    // 数据拷贝（主机 --> 设备）
    // cudaMemcpy(void* dst, const void* src, size_t count, enum cudaMemcpyKind kind);
    // enum __device_builtin__ cudaMemcpyKind {
    //    cudaMemcpyHostToHost = 0,          /* Host   -> Host   */
    //    cudaMemcpyHostToDevice = 1,        /* Host   -> Device */
    //    cudaMemcpyDeviceToHost = 2,        /* Device -> Host   */
    //    cudaMemcpyDeviceToDevice = 3,      /* Device -> Device */
    //    cudaMemcpyDefault = 4              /* Direction of the transfer is inferred from the pointer values. Requires unified virtual addressing */
    // }
    // 
    // 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;
    }

    //*********** 运算 ***********//
    // Launch a kernel on the GPU with one thread for each element.
    addKernel <<< 1, size >>> (dev_c, dev_a, dev_b);   // 定义1个线程块，size个线程。

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

    // 提供了一个阻塞，用于等待所有的线程都执行完各自的计算任务，然后继续往下执行
    // 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;
    }


    // 数据拷贝（ 设备 --> 主机 ）
    // 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:
    // 释放申请的内存空间
    // cudaDeviceReset用于释放所有申请的显存空间和重置设备状态；
    cudaFree(dev_c);
    cudaFree(dev_a);
    cudaFree(dev_b);

    return cudaStatus;
}

// main.cpp

#include <iostream>

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

using namespace std;


//extern "C" int kernalMain();
extern "C" cudaError_t addWithCuda(int* c, const int* a, const int* b, unsigned int size);

// main
int main()
{

	 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 };
 
     // Add vectors in parallel.
     cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "addWithCuda failed!");
         return 1;
     }
 
     printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n", c[0], c[1], c[2], c[3], c[4]);
 
     // 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;
}

// output #~
// {1,2,3,4,5} + {10,20,30,40,50} = {11,22,33,44,55}