/* Copyright (c) 2014, Ian Sutton <ian@kremlin.cc>
 *
 * Permission to use, copy, modify, and/or distribute this software for
 * any purpose with or without fee is hereby granted, provided that the
 * above copyright notice and this permission notice appear in all
 * copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
 * WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE
 * AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
 * DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
 * PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
 * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
 * PERFORMANCE OF THIS SOFTWARE.
 *
 * This code implements a simple matrix operation in C, to be
 * cross-compiled into Loongson MIPS 32-bit instructions.
 */

#ifdef DEBUG
#include <stdio.h>
#endif

#include "proto.h"

int main(int argc, char *argv[]) {

    #ifdef HARDCODED_OPERANDS

    /* volatile, otherwise GCC optimizations muddy things up. 'a' and
     * 'b' are our starting matricies */
    volatile int a[MS][MS] = {
                                { 1, 2, 3},
                                { 4, 5, 6},
                                { 7, 8, 9}
                             };

    volatile int b[MS][MS] = {
                                { 1, 4, 7},
                                { 2, 5, 8},
                                { 3, 6, 9}
                             };
    #endif

    /* 'd' and 'c' are matricies that store the result of the
     * combinations of 'a' and 'b' prior to multiplication */
    volatile int c[MS][MS], d[MS][MS];

    /* where our resultant matrix is stored */
    volatile int result[MS][MS];

    /* zero-out our result buffers */
    matrix_init0(c);
    matrix_init0(d);
    matrix_init0(result);

    /* first we combine A + B and store it in C */
    matrix_add(a, b, c);

    /* then we subtract A - B and store it in D */
    matrix_sub(a, b, d);

    /* finally, we multiply A * B and store it in result */
    matrix_mult(a, b, result);

    #ifdef DEBUG

    printf("Matrix A:\n");
    matrix_print(a);

    printf("\nMatrix B:\n");
    matrix_print(b);

    printf("\nAdded Matrix (A + B) -> C:\n");
    matrix_print(c);

    printf("\nSubtracted Matrix (A - B) -> D:\n");  
    matrix_print(d);

    printf("\nMultiplied Matrix (C * D) -> Result:\n");
    matrix_print(result);

    #endif

    return 0;
}

static void matrix_add(volatile int op1[MS][MS], volatile int op2[MS][MS], volatile int result_buf[MS][MS]) {

    int i, j;

    i = 0;
    j = 0;

    for(; i < MS; i++) {

        j = 0;

        for(; j < MS; j++)
            result_buf[i][j] = op1[i][j] + op2[i][j];
    }
}

static void matrix_sub(volatile int op1[MS][MS], volatile int op2[MS][MS], volatile int result_buf[MS][MS]) {

    int i, j;

    i = 0;
    j = 0;

    for(; i < MS; i++) {

        j = 0;

        for(; j < MS; j++)
            result_buf[i][j] = op1[i][j] - op2[i][j];
    }
}

static void matrix_mult(volatile int op1[MS][MS], volatile int op2[MS][MS], volatile int result_buf[MS][MS]) {
    
    int i, j, k;

    i = 0;
    j = 0;
    k = 0;

    for(; i < MS; i++) {

        j = 0;

        for(; j < MS; j++) {

            k = 0;

            for(; k < MS; k++)
                result_buf[i][j] += op1[i][k] * op2[k][j];
        }
    }
}

static void matrix_init0(volatile int matrix[MS][MS]) {

    int i, j;

    i = 0;
    j = 0;

    for(; i < MS; i++) {

        j = 0;

        for(; j < MS; j++)
            matrix[i][j] = 0;
    }
}

#ifdef DEBUG
static void matrix_print(volatile int matrix[MS][MS]) {

    int i,j; 

    i = 0;
    j = 0;

    printf("\t┌────────────┐\n");

    for(; i < MS; i++) {

        printf("\t│");
        j = 0;

        for(; j < MS; j++) {

            printf("%3d", matrix[i][j]);

            if(j + 1 != MS)
                printf(" ");
        }

        printf(" │\n");
    }

    printf("\t└────────────┘\n");
}
#endif