GPU-CUDA编程实践（一）

CUDA编程是有一定的流程和套路的

图1 CUDA程序流程

常用CUDA函数说明

1.__host__  cudaError_t  cudaMalloc(void **devPtr, size_t size)

该函数主要用来分配设备上的内存（即显存中的内存）。该函数被声明为了__host__，即表示被host所调用，即在cpu中执行的代码所调用。

返回值：为cudaError_t类型，实质为cudaError的枚举类型，其中定义了一系列的错误代码。如果函数调用成功，则返回cudaSuccess。

第一个参数，void ** 类型，devPtr：用于接受该函数所分配的内存地址

第二个参数，size_t类型，size：指定分配内存的大小，单位为字

2. __host__  cudaError_t  cudaFree(void *devPtr)

该函数用来释放先前在设备上申请的内存空间（通过cudaMalloc、cudaMallocPitch等函数），注意，不能释放通过标准库函数malloc进行申请的内存。

        返回值：为错误代码的类型值

        第一个参数，void**类型，devPtr：指向需要释放的设备内存地址

3.__host__ cudaError_t  cudaMemcpy(void *dst, const void *src, size_t count, enum cudaMemcpyKind kind)

该函数主要用于将不同内存段的数据进行拷贝，内存可用是设备内存，也可用是主机内存

        第一个参数，void*类型，dst：为目的内存地址

        第二个参数，const void *类型，src：源内存地址

        第三个参数，size_t类型，count：将要进行拷贝的字节大小

        第四个参数，enum cudaMemcpyKind类型，kind：拷贝的类型，决定拷贝的方向

cudaMemcpyKind类型如下：

[cpp] view plain copy

1. enum __device_builtin__ cudaMemcpyKind  
2. {  
3.     cudaMemcpyHostToHost          =   0,      /**< Host   -> Host */  
4.     cudaMemcpyHostToDevice        =   1,      /**< Host   -> Device */  
5.     cudaMemcpyDeviceToHost        =   2,      /**< Device -> Host */  
6.     cudaMemcpyDeviceToDevice      =   3,      /**< Device -> Device */  
7.     cudaMemcpyDefault             =   4       /**< Default based unified virtual address space */  
8. };  

cudaMemcpyKind决定了拷贝的方向，即是从主机的内存拷贝至设备内存，还是将设备内存拷贝值主机内存等。cudaMemcpy内部根据拷贝的类型（kind）来决定调用以下的某个函数：

[cpp] view plain copy

1. ::cudaMemcpyHostToHost,   
2. ::cudaMemcpyHostToDevice,   
3. ::cudaMemcpyDeviceToHost,  
4. ::cudaMemcpyDeviceToDevice  
5. 
   

4. __host__ cudaError_t  cudaDeviceReset(void)

该函数销毁当前进程中当前设备上所有的内存分配和重置所有状态，调用该函数达到重新初始该设备的作用。应该注意，在调用该函数时，应该确保该进程中其他host线程不能访问该设备！

下面是一个简单的向量相加的程序

/** * Copyright 1993-2015 NVIDIA Corporation.  All rights reserved. * * Please refer to the NVIDIA end user license agreement (EULA) associated * with this source code for terms and conditions that govern your use of * this software. Any use, reproduction, disclosure, or distribution of * this software and related documentation outside the terms of the EULA * is strictly prohibited. * *//** * Vector addition: C = A + B. * * This sample is a very basic sample that implements element by element * vector addition. It is the same as the sample illustrating Chapter 2 * of the programming guide with some additions like error checking. */#include <stdio.h>// For the CUDA runtime routines (prefixed with "cuda_")#include <cuda_runtime.h>#include <helper_cuda.h>/** * CUDA Kernel Device code * * Computes the vector addition of A and B into C. The 3 vectors have the same * number of elements numElements. */__global__ voidvectorAdd(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];    }}/** * Host main routine */intmain(void){    // 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 = 50000;    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);    }    // 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;    }    // Allocate the device input vector A    float *d_A = NULL;    err = cudaMalloc((void **)&d_A, size);    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);    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");    // 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;}

目前CUDA和OpenCL是最主流的两个GPU编程库，CUDA和OpenCL都是原生支持C/C++的，其它语言想要访问还有些麻烦，比如Java，需要通过JNI来访问CUDA或者OpenCL。基于JNI，现今有各种Java版本的GPU编程库，比如JCUDA等。另一种思路就是语言还是由java来编写，通过一种工具将java转换成C。

图2 GPU编程库