NVIDIA-GPU-Bootcamp-Training/hpc/openacc/English/C/source_code/lab3/solutions/tile/laplace2d.c

/* Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *  * Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *  * Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *  * Neither the name of NVIDIA CORPORATION nor the names of its
 *    contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <math.h>
#include <stdlib.h>
#include <string.h>

#define OFFSET(x, y, m) (((x)*(m)) + (y))

void initialize(double *restrict A, double *restrict Anew, int m, int n)
{
    memset(A, 0, n * m * sizeof(double));
    memset(Anew, 0, n * m * sizeof(double));

    for(int i = 0; i < m; i++){
        A[i] = 1.0;
        Anew[i] = 1.0;
    }

}

double calcNext(double *restrict A, double *restrict Anew, int m, int n)
{
    double error = 0.0;
    #pragma acc parallel loop reduction(max:error) copyin(A[:n*m]) copyout(Anew[:n*m]) tile(32,4)
    for( int j = 1; j < n-1; j++)
    {
        for( int i = 1; i < m-1; i++ )
        {
            Anew[OFFSET(j, i, m)] = 0.25 * ( A[OFFSET(j, i+1, m)] + A[OFFSET(j, i-1, m)]
                                           + A[OFFSET(j-1, i, m)] + A[OFFSET(j+1, i, m)]);
            error = fmax( error, fabs(Anew[OFFSET(j, i, m)] - A[OFFSET(j, i , m)]));
        }
    }
    return error;
}
        
void swap(double *restrict A, double *restrict Anew, int m, int n)
{
    #pragma acc parallel loop copyin(Anew[:n*m]) copyout(A[:n*m]) tile(32,4)
    for( int j = 1; j < n-1; j++)
    {
        for( int i = 1; i < m-1; i++ )
        {
            A[OFFSET(j, i, m)] = Anew[OFFSET(j, i, m)];    
        }
    }
}

void deallocate(double *restrict A, double *restrict Anew)
{
    free(A);
    free(Anew);
}