OpenCl入门getting-started-with-opencl-and-gpu-computing

原文来自于：getting-started-with-opencl-and-gpu-computing/

对整个程序的注释：http://www.kimicat.com/opencl-1/opencl-jiao-xue-yi

但是对CUDA比较熟悉的用户来说，应该不需要看注释就能理解全部的程序

main.cpp

#include <stdio.h>
#include <stdlib.h>
#include <CL/cl.h>
#define MAX_SOURCE_SIZE (0x100000)
int main(void)
{
        // Create the two input vectors
        int i;
        const int LIST_SIZE = 1000;
        int *A = (int*) malloc(sizeof(int) * LIST_SIZE);
        int *B = (int*) malloc(sizeof(int) * LIST_SIZE);
        for (i = 0; i < LIST_SIZE; i++)
        {
                A[i] = i;
                B[i] = LIST_SIZE - i;
        }

        // Load the kernel source code into the array source_str
        FILE *fp;
        char *source_str;
        size_t source_size;
        fp = fopen("vector_add_kernel.cl", "r");

        if (!fp)
        {
                fprintf(stderr, "Failed to load kernel.
");
                exit(1);
        }
        source_str = (char*) malloc(MAX_SOURCE_SIZE);
        source_size = fread(source_str, 1, MAX_SOURCE_SIZE, fp);
        fclose(fp);

        // Get platform and device information
        cl_platform_id platform_id = NULL;
        cl_device_id device_id = NULL;
        cl_uint ret_num_devices;
        cl_uint ret_num_platforms;
        cl_int ret = clGetPlatformIDs(1, &platform_id, &ret_num_platforms);
        ret = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_DEFAULT, 1, &device_id,&ret_num_devices);

        // Create an OpenCL context
        cl_context context = clCreateContext(NULL, 1, &device_id, NULL, NULL, &ret);
        // Create a command queue
        cl_command_queue command_queue = clCreateCommandQueue(context, device_id, 0, &ret);

        // Create memory buffers on the device for each vector
        cl_mem a_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,LIST_SIZE * sizeof(int), NULL, &ret);
        cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,LIST_SIZE * sizeof(int), NULL, &ret);
        cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_WRITE_ONLY,LIST_SIZE * sizeof(int), NULL, &ret);

        // Copy the lists A and B to their respective memory buffers
        ret = clEnqueueWriteBuffer(command_queue, a_mem_obj, CL_TRUE, 0,LIST_SIZE * sizeof(int), A, 0, NULL, NULL);
        ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0,LIST_SIZE * sizeof(int), B, 0, NULL, NULL);

        // Create a program from the kernel source
        cl_program program = clCreateProgramWithSource(context, 1,(const char **) &source_str, (const size_t *) &source_size, &ret);

        // Build the program
        ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
        // Create the OpenCL kernel
        cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
        // Set the arguments of the kernel
        ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &a_mem_obj);
        ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &b_mem_obj);
        ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &c_mem_obj);

        // Execute the OpenCL kernel on the list
        size_t global_item_size = LIST_SIZE; // Process the entire lists
        size_t local_item_size = 1; // Process one item at a time
        ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,&global_item_size, &local_item_size, 0, NULL, NULL);

        // Read the memory buffer C on the device to the local variable C
        int *C = (int*) malloc(sizeof(int) * LIST_SIZE);
        ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0,LIST_SIZE * sizeof(int), C, 0, NULL, NULL);

        // Display the result to the screen
        for (i = 0; i < LIST_SIZE; i++)
                printf("%d + %d = %d
", A[i], B[i], C[i]);

        // Clean up
        ret = clFlush(command_queue);
        ret = clFinish(command_queue);
        ret = clReleaseKernel(kernel);
        ret = clReleaseProgram(program);
        ret = clReleaseMemObject(a_mem_obj);
        ret = clReleaseMemObject(b_mem_obj);
        ret = clReleaseMemObject(c_mem_obj);
        ret = clReleaseCommandQueue(command_queue);
        ret = clReleaseContext(context);

        free(A);
        free(B);
        free(C);

        return 0;

}

vector_add_kernel.cl

__kernel void vector_add(__global const int *A, __global const int *B, __global int *C)
{
    // Get the index of the current element to be processed
    int i = get_global_id(0);
    // Do the operation
    C[i] = A[i] + B[i];
}

之前已经安装好了CUDA的运行环境，这里作者说使用g++ -I/usr/local/cuda/include -L/usr/local/cuda/lib64 -lOpenCL main.cpp -o openclApp命令来执行，结果提示

'clGetPlatformIDs' undefined reference，但是我的include和lib都是正常的，因此，调整编译命令为：

g++  main.cpp -o openclApp -I/usr/local/cuda/include -L/usr/local/cuda/lib64 -lOpenCL

编译通过并运行通过，因此gcc编译选项的顺序也对程序有一定影响（理论上不应该有这个问题）。但是，这个问题使用clang编译就没有任何影响。