/* nag_dgemm (f16yac) Example Program.
 *
 * Copyright 2005 Numerical Algorithms Group.
 *
 * Mark 8, 2005.
 */

#include <stdio.h>
#include <nag.h>
#include <nag_stdlib.h>
#include <nagf16.h>
#include <nagx04.h>

int main(int argc, char *argv[])
{
  FILE          *fpin, *fpout;
  char          *outfile = 0;

  /* Scalars */
  double        alpha, beta;
  Integer       exit_status, i, j, k, m, n, pda, pdb, pdc;

  /* Arrays */
  double        *a = 0, *b = 0, *c = 0;
  char          nag_enum_arg[40];

  /* Nag Types */
  NagError      fail;
  Nag_OrderType order;
  Nag_TransType transa;
  Nag_TransType transb;

#ifdef NAG_COLUMN_MAJOR
#define A(I, J) a[(J-1)*pda + I - 1]
#define B(I, J) b[(J-1)*pdb + I - 1]
#define C(I, J) c[(J-1)*pdc + I - 1]
  order = Nag_ColMajor;
#else
#define A(I, J) a[(I-1)*pda + J - 1]
#define B(I, J) b[(I-1)*pdb + J - 1]
#define C(I, J) c[(I-1)*pdc + J - 1]
  order = Nag_RowMajor;
#endif

  exit_status = 0;
  INIT_FAIL(fail);

  /* Check for command-line IO options */
  fpin = nag_example_file_io(argc, argv, "-data", NULL);
  fpout = nag_example_file_io(argc, argv, "-results", NULL);
  (void) nag_example_file_io(argc, argv, "-nag_write", &outfile);

  fprintf(fpout, "nag_dgemm (f16yac) Example Program Results\n\n");

  /* Skip heading in data file */
  fscanf(fpin, "%*[^\n] ");

  /* Read the problem dimensions */
  fscanf(fpin, "%ld%ld%ld%*[^\n] ",
         &m, &n, &k);

  /* Read the transpose parameters */
  fscanf(fpin, "%s%*[^\n] ", nag_enum_arg);
  /* nag_enum_name_to_value(x04nac).
   * Converts NAG enum member name to value
   */
  transa = (Nag_TransType) nag_enum_name_to_value(nag_enum_arg);
  fscanf(fpin, "%s%*[^\n] ", nag_enum_arg);
  /* nag_enum_name_to_value(x04nac).
   * Converts NAG enum member name to value
   */
  transb = (Nag_TransType) nag_enum_name_to_value(nag_enum_arg);
  /* Read scalar parameters */
  fscanf(fpin, "%lf%lf%*[^\n] ", &alpha, &beta);

#ifdef NAG_COLUMN_MAJOR
  pdc = m;
  if (transa == Nag_NoTrans && transb == Nag_NoTrans)
    {
      pda = m;
      pdb = k;
    }
  else if ((transa == Nag_Trans || transa == Nag_ConjTrans)
          && transb == Nag_NoTrans)
    {
      pda = k;
      pdb = k;
    }
  else if (transa == Nag_NoTrans &&
           (transb == Nag_Trans || transb == Nag_ConjTrans))
    {
      pda = m;
      pdb = n;
    }
  else
    {
      pda = k;
      pdb = n;
    }
#else
  pdc = n;
  if (transa == Nag_NoTrans && transb == Nag_NoTrans)
    {
      pda = k;
      pdb = n;
    }
  else if ((transa == Nag_Trans || transa == Nag_ConjTrans)
          && transb == Nag_NoTrans)
    {
      pda = m;
      pdb = n;
    }
  else if (transa == Nag_NoTrans &&
           (transb == Nag_Trans || transb == Nag_ConjTrans))
    {
      pda = k;
      pdb = k;
    }
  else
    {
      pda = m;
      pdb = k;
    }
#endif

  if (m > 0 && n > 0)
    {
      /* Allocate memory */
      if (!(a = NAG_ALLOC(m*k, double)) ||
          !(b = NAG_ALLOC(n*k, double)) ||
          !(c = NAG_ALLOC(m*n, double)))
        {
          fprintf(fpout, "Allocation failure\n");
          exit_status = -1;
          goto END;
        }
    }
  else
    {
      fprintf(fpout, "Invalid m, n or k\n");
      exit_status = 1;
      return exit_status;
    }

  /* Input matrix A */
  if (transa == Nag_NoTrans)
    {
      for (i = 1; i <= m; ++i)
        {
          for (j = 1; j <= k; ++j)
            fscanf(fpin, "%lf", &A(i, j));
          fscanf(fpin, "%*[^\n] ");
        }
    }
  else
    {
      for (i = 1; i <= k; ++i)
        {
          for (j = 1; j <= m; ++j)
            fscanf(fpin, "%lf", &A(i, j));
          fscanf(fpin, "%*[^\n] ");
        }
    }

  /* Input matrix B */
  if (transb == Nag_NoTrans)
    {
      for (i = 1; i <= k; ++i)
        {
          for (j = 1; j <= n; ++j)
            fscanf(fpin, "%lf", &B(i, j));
          fscanf(fpin, "%*[^\n] ");
        }
    }
  else
    {
      for (i = 1; i <= n; ++i)
        {
          for (j = 1; j <= k; ++j)
            fscanf(fpin, "%lf", &B(i, j));
          fscanf(fpin, "%*[^\n] ");
        }
    }

  /* Input matrix C */
  for (i = 1; i <= m; ++i)
    {
      for (j = 1; j <= n; ++j)
        fscanf(fpin, "%lf", &C(i, j));
      fscanf(fpin, "%*[^\n] ");
    }

  /* nag_dgemm(f16yac).
   * Matrix-matrix multiply.
   *
   */
  nag_dgemm(order, transa, transb, m, n, k, alpha, a, pda,
            b, pdb, beta, c, pdc, &fail);
  if (fail.code != NE_NOERROR)
    {
      fprintf(fpout, "Error from nag_dgemm.\n%s\n", fail.message);
      exit_status = 1;
      goto END;
    }

  /* Print result */
  /* nag_gen_real_mat_print (x04cac).
   * Print real general matrix (easy-to-use)
   */
  if (outfile) fclose(fpout);
  nag_gen_real_mat_print(order, Nag_GeneralMatrix, Nag_NonUnitDiag,
                         m, n, c, pdc, "Matrix Matrix Product",
                         outfile, &fail);
  if (outfile && !(fpout = fopen(outfile, "a")))
    {
      exit_status = 2;
      goto END;
    }
  if (fail.code != NE_NOERROR)
    {
      fprintf(fpout, "Error from nag_gen_real_mat_print (x04cac).\n%s\n",
              fail.message);
      exit_status = 1;
      goto END;
    }

 END:
  if (fpin != stdin) fclose(fpin);
  if (fpout != stdout) fclose(fpout);
  if (a) NAG_FREE(a);
  if (b) NAG_FREE(b);
  if (c) NAG_FREE(c);

  return exit_status;
}