__kernel void vector_add(__global float *A, __global float *B, __global float *C) {
    
    // Get the index of the current element
    int i = get_global_id(0);

    // Do the operation
    C[i] = sqrt(A[i]) * sqrt(B[i]);
}

#include <cstdlib>
#include <iostream>
#include <chrono>
#include <math.h>
#ifdef __APPLE__
    #include "OpenCL/opencl.h"
#else
    #include "CL/cl.h"
#endif

#define MAX_SOURCE_SIZE (0x100000)

using namespace std;

void cpu(const int size) 
{
    // Create the two input vectors
    int i;
    float *A = (float*)malloc(sizeof(int)*size);
    float *B = (float*)malloc(sizeof(int)*size);
    for(i = 0; i < size; i++) {
        A[i] = i;
        B[i] = size - i;
    }
    
    // Calculate C on CPU
    float *C = (float*)malloc(sizeof(int)*size);
    for(i = 0; i < size; i++) {
        C[i] = sqrt(A[i]) * sqrt(B[i]); 
    }
    
    // Display the result to the screen
    for(i = 0; i < size; i++) {
        //printf("sqrt(%f) * sqrt(%f) = %f\n", A[i], B[i], C[i]);
    }
    
    free(A);
    free(B);
    free(C);
}

void gpu(const int size) 
{
    // Create the two input vectors
    int i;
    float *A = (float*)malloc(sizeof(int)*size);
    float *B = (float*)malloc(sizeof(int)*size);
    for(i = 0; i < size; i++) {
        A[i] = i;
        B[i] = 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, 
            size * sizeof(int), NULL, &ret);
    cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,
            size * sizeof(int), NULL, &ret);
    cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_WRITE_ONLY, 
            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,
            size * sizeof(int), A, 0, NULL, NULL);
    ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0, 
            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 = 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
    float *C = (float*)malloc(sizeof(int)*size);
    ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0, 
            size * sizeof(int), C, 0, NULL, NULL);

    // Display the result to the screen
    for(i = 0; i < size; i++) {
        //printf("sqrt(%f) * sqrt(%f) = %f\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);
}

int main(void)
{
    
    typedef std::chrono::high_resolution_clock Time;
    typedef std::chrono::milliseconds ms;
    typedef std::chrono::duration<float> fsec;
    
    int size = 1024 * 1024 * 1024;
    
    auto cpu_start = Time::now();
    cpu(size);
    auto cpu_finish = Time::now();
    ms cpu_diff = std::chrono::duration_cast<ms>(cpu_finish - cpu_start);
    
    auto gpu_start = Time::now();
    gpu(size);
    auto gpu_finish = Time::now();
    ms gpu_diff = std::chrono::duration_cast<ms>(gpu_finish - gpu_start);
    
    printf("CPU: %ld ms, GPU: %ld ms\n", cpu_diff, gpu_diff);
    
    return 0;
    
}