Um exemplo simples com o OpenCL

estou a seguir o próximo tutorial para executar o meu primeiro programa OpenCL. https://medium.com/@pratikone/opencl-on-visual-studio-configuration-tutorial-for-the-confused-3ec1c2b5f0ca

o resultado da soma, no entanto, não é 1024 no meu caso, como deveria ser. A soma de dois números é igual a 0 (Release) ou -842150451 (Debug) no meu caso. Isto é, uma parte da saída se parece com isto:

1000+24 = 0

1001+23 = 0

1002+22 = 0

o meu adaptador de ecrã é Nvidia Geforce 8400. A instalação do CUDA SDK também terminou com sucesso.

Aqui estão os ficheiros de código:

Main.cpp

#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) {
    printf("started running\n");

    // 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 );
    printf("kernel loading done\n");
    // Get platform and device information
    cl_device_id device_id = NULL;   
    cl_uint ret_num_devices;
    cl_uint ret_num_platforms;
    
    
    cl_int ret = clGetPlatformIDs(0, NULL, &ret_num_platforms);
    cl_platform_id *platforms = NULL;
    platforms = (cl_platform_id*)malloc(ret_num_platforms*sizeof(cl_platform_id));

    ret = clGetPlatformIDs(ret_num_platforms, platforms, NULL);
    printf("ret at %d is %d\n", __LINE__, ret);

    ret = clGetDeviceIDs( platforms[1], CL_DEVICE_TYPE_ALL, 1, 
            &device_id, &ret_num_devices);
    printf("ret at %d is %d\n", __LINE__, ret);
    // Create an OpenCL context
    cl_context context = clCreateContext( NULL, 1, &device_id, NULL, NULL, &ret);
    printf("ret at %d is %d\n", __LINE__, ret);

    // Create a command queue
    cl_command_queue command_queue = clCreateCommandQueue(context, device_id, 0, &ret);
    printf("ret at %d is %d\n", __LINE__, 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);
    printf("ret at %d is %d\n", __LINE__, ret);

    ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0, 
            LIST_SIZE * sizeof(int), B, 0, NULL, NULL);
    printf("ret at %d is %d\n", __LINE__, ret);
 
    printf("before building\n");
    // Create a program from the kernel source
    cl_program program = clCreateProgramWithSource(context, 1, 
            (const char **)&source_str, (const size_t *)&source_size, &ret);
    printf("ret at %d is %d\n", __LINE__, ret);
 
    // Build the program
    ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
    printf("ret at %d is %d\n", __LINE__, ret);

    printf("after building\n");
    // Create the OpenCL kernel
    cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
    printf("ret at %d is %d\n", __LINE__, ret);
 
    // Set the arguments of the kernel
    ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&a_mem_obj);
    printf("ret at %d is %d\n", __LINE__, ret);

    ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&b_mem_obj);
    printf("ret at %d is %d\n", __LINE__, ret);

    ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *)&c_mem_obj);
    printf("ret at %d is %d\n", __LINE__, ret);

    //added this to fix garbage output problem
    //ret = clSetKernelArg(kernel, 3, sizeof(int), &LIST_SIZE);
 
    printf("before execution\n");
    // Execute the OpenCL kernel on the list
    size_t global_item_size = LIST_SIZE; // Process the entire lists
    size_t local_item_size = 64; // Divide work items into groups of 64
    ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL, 
            &global_item_size, &local_item_size, 0, NULL, NULL);
 printf("after execution\n");
    // 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);
 printf("after copying\n");
    // 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;
}

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];
}