src/fftw/fhf_4.c

   1 /*
   2  * Copyright (c) 1997-1999 Massachusetts Institute of Technology
   3  *
   4  * This program is free software; you can redistribute it and/or modify
   5  * it under the terms of the GNU General Public License as published by
   6  * the Free Software Foundation; either version 2 of the License, or
   7  * (at your option) any later version.
   8  *
   9  * This program is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12  * GNU General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU General Public License
  15  * along with this program; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  17  *
  18  */
  19
  20 /* This file was automatically generated --- DO NOT EDIT */
  21 /* Generated on Tue May 18 13:55:29 EDT 1999 */
  22
  23 #include <fftw-int.h>
  24 #include <fftw.h>
  25
  26 /* Generated by: ./genfft -magic-alignment-check -magic-twiddle-load-all -magic-variables 4 -magic-loopi -hc2hc-forward 4 */
  27
  28 /*
  29  * This function contains 34 FP additions, 14 FP multiplications,
  30  * (or, 28 additions, 8 multiplications, 6 fused multiply/add),
  31  * 15 stack variables, and 32 memory accesses
  32  */
  33 static const fftw_real K707106781 = FFTW_KONST(+0.707106781186547524400844362104849039284835938);
  34
  35 /*
  36  * Generator Id's :
  37  * $Id$
  38  * $Id$
  39  * $Id$
  40  */
  41
  42 void fftw_hc2hc_forward_4(fftw_real *A, const fftw_complex *W, int iostride, int m, int dist)
  43 {
  44      int i;
  45      fftw_real *X;
  46      fftw_real *Y;
  47      X = A;
  48      Y = A + (4 * iostride);
  49      {
  50           fftw_real tmp35;
  51           fftw_real tmp36;
  52           fftw_real tmp37;
  53           fftw_real tmp38;
  54           fftw_real tmp39;
  55           fftw_real tmp40;
  56           ASSERT_ALIGNED_DOUBLE();
  57           tmp35 = X[0];
  58           tmp36 = X[2 * iostride];
  59           tmp37 = tmp35 + tmp36;
  60           tmp38 = X[iostride];
  61           tmp39 = X[3 * iostride];
  62           tmp40 = tmp38 + tmp39;
  63           X[iostride] = tmp35 - tmp36;
  64           Y[-iostride] = -(tmp38 - tmp39);
  65           X[2 * iostride] = tmp37 - tmp40;
  66           X[0] = tmp37 + tmp40;
  67      }
  68      X = X + dist;
  69      Y = Y - dist;
  70      for (i = 2; i < m; i = i + 2, X = X + dist, Y = Y - dist, W = W + 3) {
  71           fftw_real tmp7;
  72           fftw_real tmp30;
  73           fftw_real tmp12;
  74           fftw_real tmp29;
  75           fftw_real tmp18;
  76           fftw_real tmp26;
  77           fftw_real tmp23;
  78           fftw_real tmp27;
  79           ASSERT_ALIGNED_DOUBLE();
  80           tmp7 = X[0];
  81           tmp30 = Y[-3 * iostride];
  82           {
  83                fftw_real tmp9;
  84                fftw_real tmp11;
  85                fftw_real tmp8;
  86                fftw_real tmp10;
  87                ASSERT_ALIGNED_DOUBLE();
  88                tmp9 = X[2 * iostride];
  89                tmp11 = Y[-iostride];
  90                tmp8 = c_re(W[1]);
  91                tmp10 = c_im(W[1]);
  92                tmp12 = (tmp8 * tmp9) - (tmp10 * tmp11);
  93                tmp29 = (tmp10 * tmp9) + (tmp8 * tmp11);
  94           }
  95           {
  96                fftw_real tmp15;
  97                fftw_real tmp17;
  98                fftw_real tmp14;
  99                fftw_real tmp16;
 100                ASSERT_ALIGNED_DOUBLE();
 101                tmp15 = X[iostride];
 102                tmp17 = Y[-2 * iostride];
 103                tmp14 = c_re(W[0]);
 104                tmp16 = c_im(W[0]);
 105                tmp18 = (tmp14 * tmp15) - (tmp16 * tmp17);
 106                tmp26 = (tmp16 * tmp15) + (tmp14 * tmp17);
 107           }
 108           {
 109                fftw_real tmp20;
 110                fftw_real tmp22;
 111                fftw_real tmp19;
 112                fftw_real tmp21;
 113                ASSERT_ALIGNED_DOUBLE();
 114                tmp20 = X[3 * iostride];
 115                tmp22 = Y[0];
 116                tmp19 = c_re(W[2]);
 117                tmp21 = c_im(W[2]);
 118                tmp23 = (tmp19 * tmp20) - (tmp21 * tmp22);
 119                tmp27 = (tmp21 * tmp20) + (tmp19 * tmp22);
 120           }
 121           {
 122                fftw_real tmp13;
 123                fftw_real tmp24;
 124                fftw_real tmp33;
 125                fftw_real tmp34;
 126                ASSERT_ALIGNED_DOUBLE();
 127                tmp13 = tmp7 + tmp12;
 128                tmp24 = tmp18 + tmp23;
 129                Y[-2 * iostride] = tmp13 - tmp24;
 130                X[0] = tmp13 + tmp24;
 131                tmp33 = tmp18 - tmp23;
 132                tmp34 = tmp30 - tmp29;
 133                X[3 * iostride] = -(tmp33 + tmp34);
 134                Y[-iostride] = tmp34 - tmp33;
 135           }
 136           {
 137                fftw_real tmp31;
 138                fftw_real tmp32;
 139                fftw_real tmp25;
 140                fftw_real tmp28;
 141                ASSERT_ALIGNED_DOUBLE();
 142                tmp31 = tmp29 + tmp30;
 143                tmp32 = tmp26 + tmp27;
 144                X[2 * iostride] = -(tmp31 - tmp32);
 145                Y[0] = tmp32 + tmp31;
 146                tmp25 = tmp7 - tmp12;
 147                tmp28 = tmp26 - tmp27;
 148                Y[-3 * iostride] = tmp25 - tmp28;
 149                X[iostride] = tmp25 + tmp28;
 150           }
 151      }
 152      if (i == m) {
 153           fftw_real tmp1;
 154           fftw_real tmp6;
 155           fftw_real tmp4;
 156           fftw_real tmp5;
 157           fftw_real tmp2;
 158           fftw_real tmp3;
 159           ASSERT_ALIGNED_DOUBLE();
 160           tmp1 = X[0];
 161           tmp6 = X[2 * iostride];
 162           tmp2 = X[iostride];
 163           tmp3 = X[3 * iostride];
 164           tmp4 = K707106781 * (tmp2 - tmp3);
 165           tmp5 = K707106781 * (tmp2 + tmp3);
 166           X[iostride] = tmp1 - tmp4;
 167           X[0] = tmp1 + tmp4;
 168           Y[0] = -(tmp5 + tmp6);
 169           Y[-iostride] = tmp6 - tmp5;
 170      }
 171 }
 172
 173 static const int twiddle_order[] =
 174 {1, 2, 3};
 175 fftw_codelet_desc fftw_hc2hc_forward_4_desc =
 176 {
 177      "fftw_hc2hc_forward_4",
 178      (void (*)()) fftw_hc2hc_forward_4,
 179      4,
 180      FFTW_FORWARD,
 181      FFTW_HC2HC,
 182      91,
 183      3,
 184      twiddle_order,
 185 };