//
// File:       hello.c
//
// Abstract:   A simple "Hello World" compute example showing basic usage of OpenCL which
//             calculates the mathematical square (X[i] = pow(X[i],2)) for a buffer of
//             floating point values.
//             
//
// Version:    <1.0>
//
// Based on Apple "hello.c" example, adapted to work on non-apple systems and
// OpenCL hardware that has a non-power-of-two maximum work group size.
//
// Also use non-exact comparison of floats to prevent false positives in the checking loop.
//
////////////////////////////////////////////////////////////////////////////////
#define HOOK

#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <CL/cl.h>
#include "viv_hook.h"

////////////////////////////////////////////////////////////////////////////////

// Use a static data size for simplicity
//
#define DATA_SIZE (1024)

/* round down to largest power of two smaller or equal than x */
uint32_t flp2(uint32_t x)
{
    x = x | (x >> 1);
    x = x | (x >> 2);
    x = x | (x >> 4);
    x = x | (x >> 8);
    x = x | (x >> 16);
    return x - (x >> 1);
}

////////////////////////////////////////////////////////////////////////////////

// Simple compute kernel which computes the square of an input array 
//
const char *KernelSource = "\n" \
"__kernel void square(                                                       \n" \
"   __global float* input,                                              \n" \
"   __global float* output,                                             \n" \
"   const unsigned int count)                                           \n" \
"{                                                                      \n" \
"   int i = get_global_id(0);                                           \n" \
"   if(i < count)                                                       \n" \
"       output[i] = input[i] * input[i];                                \n" \
"}                                                                      \n" \
"\n";

////////////////////////////////////////////////////////////////////////////////

int main(int argc, char** argv)
{
    int err;                            // error code returned from api calls
      
    float data[DATA_SIZE];              // original data set given to device
    float results[DATA_SIZE];           // results returned from device
    unsigned int correct;               // number of correct results returned

    size_t global;                      // global domain size for our calculation
    size_t local;                       // local domain size for our calculation

    cl_device_id device_id;             // compute device id 
    cl_context context;                 // compute context
    cl_command_queue commands;          // compute command queue
    cl_program program;                 // compute program
    cl_kernel kernel;                   // compute kernel
    
    cl_mem input;                       // device memory used for the input array
    cl_mem output;                      // device memory used for the output array

#ifdef HOOK
    the_hook("/tmp/cl.fdr");
#endif
    
    // Fill our data set with random float values
    //
    int i = 0;
    unsigned int count = DATA_SIZE;
    for(i = 0; i < count; i++)
        data[i] = rand() / (float)RAND_MAX;
    
    // Connect to a compute device
    //
    int gpu = 1;
    err = clGetDeviceIDs(NULL, gpu ? CL_DEVICE_TYPE_GPU : CL_DEVICE_TYPE_CPU, 1, &device_id, NULL);
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to create a device group!\n");
        return EXIT_FAILURE;
    }
  
    // Create a compute context 
    //
    context = clCreateContext(0, 1, &device_id, NULL, NULL, &err);
    if (!context)
    {
        printf("Error: Failed to create a compute context!\n");
        return EXIT_FAILURE;
    }

    // Create a command commands
    //
    commands = clCreateCommandQueue(context, device_id, 0, &err);
    if (!commands)
    {
        printf("Error: Failed to create a command commands!\n");
        return EXIT_FAILURE;
    }

    // Create the compute program from the source buffer
    //
    program = clCreateProgramWithSource(context, 1, (const char **) & KernelSource, NULL, &err);
    if (!program)
    {
        printf("Error: Failed to create compute program!\n");
        return EXIT_FAILURE;
    }

    // Build the program executable
    err = clBuildProgram(program, 0, NULL, 
            "-cl-mad-enable -cl-unsafe-math-optimizations -cl-fast-relaxed-math", 
            NULL, NULL);
    if (err != CL_SUCCESS)
    {
        size_t len;
        char buffer[2048];

        printf("Error: Failed to build program executable!\n");
        clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, sizeof(buffer), buffer, &len);
        printf("%s\n", buffer);
        exit(1);
    }

    // Create the compute kernel in the program we wish to run
    //
    kernel = clCreateKernel(program, "square", &err);
    if (!kernel || err != CL_SUCCESS)
    {
        printf("Error: Failed to create compute kernel!\n");
        exit(1);
    }

    // Create the input and output arrays in device memory for our calculation
    //
    input = clCreateBuffer(context,  CL_MEM_READ_ONLY,  sizeof(float) * count, NULL, NULL);
    output = clCreateBuffer(context, CL_MEM_WRITE_ONLY, sizeof(float) * count, NULL, NULL);
    if (!input || !output)
    {
        printf("Error: Failed to allocate device memory!\n");
        exit(1);
    }    
    
    // Write our data set into the input array in device memory 
    //
    err = clEnqueueWriteBuffer(commands, input, CL_TRUE, 0, sizeof(float) * count, data, 0, NULL, NULL);
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to write to source array!\n");
        exit(1);
    }

    // Set the arguments to our compute kernel
    //
    err = 0;
    err  = clSetKernelArg(kernel, 0, sizeof(cl_mem), &input);
    err |= clSetKernelArg(kernel, 1, sizeof(cl_mem), &output);
    err |= clSetKernelArg(kernel, 2, sizeof(unsigned int), &count);
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to set kernel arguments! %d\n", err);
        exit(1);
    }

    // Get the maximum work group size for executing the kernel on the device
    //
    err = clGetKernelWorkGroupInfo(kernel, device_id, CL_KERNEL_WORK_GROUP_SIZE, sizeof(local), &local, NULL);
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to retrieve kernel work group info! %d\n", err);
        exit(1);
    }

    // Execute the kernel over the entire range of our 1d input data set
    // using the maximum number of work group items for this device
    //
    local = flp2(local);
    global = count;
    printf("global: %i, local: %i\n", global, local);

    err = clEnqueueNDRangeKernel(commands, kernel, 1, NULL, &global, &local, 0, NULL, NULL);
    if (err)
    {
        printf("Error: Failed to execute kernel!\n");
        return EXIT_FAILURE;
    }

    // Wait for the command commands to get serviced before reading back results
    //
    clFinish(commands);

    // Read back the results from the device to verify the output
    //
    err = clEnqueueReadBuffer( commands, output, CL_TRUE, 0, sizeof(float) * count, results, 0, NULL, NULL );  
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to read output array! %d\n", err);
        exit(1);
    }
    
    // Validate our results
    //
    correct = 0;
    for(i = 0; i < count; i++)
    {
        float delta = results[i] - data[i] * data[i];
        if(delta < 1e-6)
            correct++;
    }
    
    // Print a brief summary detailing the results
    //
    printf("Computed '%d/%d' correct values!\n", correct, count);
    
    // Shutdown and cleanup
    //
    clReleaseMemObject(input);
    clReleaseMemObject(output);
    clReleaseProgram(program);
    clReleaseKernel(kernel);
    clReleaseCommandQueue(commands);
    clReleaseContext(context);

#ifdef HOOK
    close_hook();
#endif

    return 0;
}