1

我是 OpenCl 的新手，我在运行我的第一个代码时遇到了麻烦。我有一个 ATI 显卡，我已经从这里http://www.thebigblob.com/getting-started-with-opencl-and-gpu-computing/完成了必要的安装。以下是我从该网站上挑选来测试我的设置的代码。

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

#ifdef __APPLE__
#include <OpenCL/opencl.h>
#else
#include <CL/cl.h>
#endif

#define MAX_SOURCE_SIZE (0x100000)

int main(void) {
    // Create the two input vectors
   int i;
const int LIST_SIZE = 1024;
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.\n");
    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_ALL, 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 = 64; // Process in groups of 64
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\n", 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;
}

...按照那里的说明。我不断收到“加载内核失败”，这意味着它无法打开文件。我从哪里获取内核源？有人可以告诉我如何让它运行吗？提前致谢..

gcc -c -I /home/suraj/Desktop/Intern/softwares/AMD-APP-SDK-v2.7-lnx32
/AMD-APP-SDK-v2.7-RC-lnx32/include opencl.c -o oopencl.o

gcc opencl.o -o host -L /home/suraj/Desktop/Intern/softwares/AMD-APP-SDK
-v2.7-lnx32/AMD-APP-SDK-v2.7-RC-lnx32/lib/x86 -l OpenCL
4

1 回答 1

2

I just went through this exercise with this source code as well, and everything worked fine for me. Did you grab the kernel program from github? It is the third program down in the list called "vector_add_kernel.cl". The C program needs the kernel to actually run.

于 2012-05-25T12:42:13.313 回答