// includes, system
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <unistd.h>

// includes, project
#include <cutil.h>
#include <cutil_inline.h>

// includes, kernels
#include <c_kernel.cu>

////////////////////////////////////////////////////////////////////////////////
// declarations, forward
extern "C"

////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int main(int argc, char** argv) {

    if( cutCheckCmdLineFlag(argc, (const char**)argv, "device") )
		cutilDeviceInit(argc, argv);
	else
		cudaSetDevice( cutGetMaxGflopsDeviceId() );

    unsigned int f_rows = 1024;
    unsigned int f_cols = 1000;
    unsigned int grid_x = 50;
    unsigned int block_x = 20;
    
    unsigned int mem_size = sizeof(float) * f_rows * f_cols;
    unsigned int out_mem_size = sizeof(float) * f_cols * f_cols;

    float *h_idata1 = (float*) malloc(mem_size);
    float *h_idata2 = (float*) malloc(mem_size);

    //pull in the data here

    float *d_idata1, *d_idata2, *d_odata;
    cutilSafeCall( cudaMalloc( (void**) &d_idata1, mem_size));
    cutilSafeCall( cudaMalloc( (void**) &d_idata2, mem_size));
    cutilSafeCall( cudaMalloc( (void**) &d_odata, out_mem_size));

    cutilSafeCall( cudaMemcpy( d_idata1, h_idata1, mem_size,
                                cudaMemcpyHostToDevice) );
    cutilSafeCall( cudaMemcpy( d_idata2, h_idata2, mem_size,
                                cudaMemcpyHostToDevice) );

    // allocate mem for the result on host side
    float* h_odata = (float*) malloc( out_mem_size);

    // setup execution parameters
    dim3  grid( grid_x, grid_x, 1);
    dim3  threads( block_x, block_x, 1);

    unsigned int timer = 0;
    cutilCheckError( cutCreateTimer( &timer));
    cutilCheckError( cutStartTimer( timer));
    
    CKernel<<< grid, threads >>>( d_idata1, d_idata2, d_odata);
  
    cutilSafeCall( cudaMemcpy( h_odata, d_odata, out_mem_size,
                                cudaMemcpyDeviceToHost) );

    cutilCheckError( cutStopTimer( timer));
    printf( "Processing time: %f (ms)\n", cutGetTimerValue( timer));
    cutilCheckError( cutDeleteTimer( timer));

    free (h_idata1);
    free (h_idata2);
    free (h_odata);
    cutilSafeCall(cudaFree(d_idata1));
    cutilSafeCall(cudaFree(d_idata2));
    cutilSafeCall(cudaFree(d_odata));

  return 0;
}