fhf_10.c

FFTW, a collection of fast C routines to compute the Discrete Fourier Transform in one or more dime

/*
 * Copyright (c) 1997-1999, 2003 Massachusetts Institute of Technology
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */

/* This file was automatically generated --- DO NOT EDIT */
/* Generated on Mon Mar 24 02:08:07 EST 2003 */

#include "fftw-int.h"
#include "fftw.h"

/* Generated by: /homee/stevenj/cvs/fftw/gensrc/genfft -magic-alignment-check -magic-twiddle-load-all -magic-variables 4 -magic-loopi -hc2hc-forward 10 */

/*
 * This function contains 168 FP additions, 84 FP multiplications,
 * (or, 126 additions, 42 multiplications, 42 fused multiply/add),
 * 43 stack variables, and 80 memory accesses
 */
static const fftw_real K250000000 =
FFTW_KONST(+0.250000000000000000000000000000000000000000000);
static const fftw_real K559016994 =
FFTW_KONST(+0.559016994374947424102293417182819058860154590);
static const fftw_real K587785252 =
FFTW_KONST(+0.587785252292473129168705954639072768597652438);
static const fftw_real K951056516 =
FFTW_KONST(+0.951056516295153572116439333379382143405698634);

/*
 * Generator Id's : 
 * $Id: exprdag.ml,v 1.43 2003/03/16 23:43:46 stevenj Exp $
 * $Id: fft.ml,v 1.44 2003/03/16 23:43:46 stevenj Exp $
 * $Id: to_c.ml,v 1.26 2003/03/16 23:43:46 stevenj Exp $
 */

void fftw_hc2hc_forward_10(fftw_real *A, const fftw_complex *W,
			   int iostride, int m, int dist)
{
     int i;
     fftw_real *X;
     fftw_real *Y;
     X = A;
     Y = A + (10 * iostride);
     {
	  fftw_real tmp178;
	  fftw_real tmp181;
	  fftw_real tmp162;
	  fftw_real tmp167;
	  fftw_real tmp165;
	  fftw_real tmp168;
	  fftw_real tmp174;
	  fftw_real tmp183;
	  fftw_real tmp155;
	  fftw_real tmp170;
	  fftw_real tmp158;
	  fftw_real tmp171;
	  fftw_real tmp173;
	  fftw_real tmp182;
	  fftw_real tmp176;
	  fftw_real tmp177;
	  ASSERT_ALIGNED_DOUBLE;
	  tmp176 = X[0];
	  tmp177 = X[5 * iostride];
	  tmp178 = tmp176 - tmp177;
	  tmp181 = tmp176 + tmp177;
	  {
	       fftw_real tmp160;
	       fftw_real tmp161;
	       fftw_real tmp163;
	       fftw_real tmp164;
	       ASSERT_ALIGNED_DOUBLE;
	       tmp160 = X[4 * iostride];
	       tmp161 = X[9 * iostride];
	       tmp162 = tmp160 - tmp161;
	       tmp167 = tmp160 + tmp161;
	       tmp163 = X[6 * iostride];
	       tmp164 = X[iostride];
	       tmp165 = tmp163 - tmp164;
	       tmp168 = tmp163 + tmp164;
	  }
	  tmp174 = tmp162 + tmp165;
	  tmp183 = tmp167 + tmp168;
	  {
	       fftw_real tmp153;
	       fftw_real tmp154;
	       fftw_real tmp156;
	       fftw_real tmp157;
	       ASSERT_ALIGNED_DOUBLE;
	       tmp153 = X[2 * iostride];
	       tmp154 = X[7 * iostride];
	       tmp155 = tmp153 - tmp154;
	       tmp170 = tmp153 + tmp154;
	       tmp156 = X[8 * iostride];
	       tmp157 = X[3 * iostride];
	       tmp158 = tmp156 - tmp157;
	       tmp171 = tmp156 + tmp157;
	  }
	  tmp173 = tmp155 + tmp158;
	  tmp182 = tmp170 + tmp171;
	  {
	       fftw_real tmp159;
	       fftw_real tmp166;
	       fftw_real tmp186;
	       fftw_real tmp184;
	       fftw_real tmp185;
	       ASSERT_ALIGNED_DOUBLE;
	       tmp159 = tmp155 - tmp158;
	       tmp166 = tmp162 - tmp165;
	       Y[-iostride] =
		   -((K951056516 * tmp159) + (K587785252 * tmp166));
	       Y[-3 * iostride] =
		   (K587785252 * tmp159) - (K951056516 * tmp166);
	       tmp186 = K559016994 * (tmp182 - tmp183);
	       tmp184 = tmp182 + tmp183;
	       tmp185 = tmp181 - (K250000000 * tmp184);
	       X[2 * iostride] = tmp185 - tmp186;
	       X[4 * iostride] = tmp186 + tmp185;
	       X[0] = tmp184 + tmp181;
	  }
	  {
	       fftw_real tmp169;
	       fftw_real tmp172;
	       fftw_real tmp175;
	       fftw_real tmp179;
	       fftw_real tmp180;
	       ASSERT_ALIGNED_DOUBLE;
	       tmp169 = tmp167 - tmp168;
	       tmp172 = tmp170 - tmp171;
	       Y[-2 * iostride] =
		   (K951056516 * tmp169) - (K587785252 * tmp172);
	       Y[-4 * iostride] =
		   (K951056516 * tmp172) + (K587785252 * tmp169);
	       tmp175 = K559016994 * (tmp173 - tmp174);
	       tmp179 = tmp173 + tmp174;
	       tmp180 = tmp178 - (K250000000 * tmp179);
	       X[iostride] = tmp175 + tmp180;
	       X[3 * iostride] = tmp180 - tmp175;
	       X[5 * iostride] = tmp179 + tmp178;
	  }
     }
     X = X + dist;
     Y = Y - dist;
     for (i = 2; i < m; i = i + 2, X = X + dist, Y = Y - dist, W = W + 9) {
	  fftw_real tmp39;
	  fftw_real tmp87;
	  fftw_real tmp132;
	  fftw_real tmp144;
	  fftw_real tmp73;
	  fftw_real tmp84;
	  fftw_real tmp85;
	  fftw_real tmp91;
	  fftw_real tmp92;
	  fftw_real tmp93;
	  fftw_real tmp100;
	  fftw_real tmp103;
	  fftw_real tmp128;
	  fftw_real tmp121;
	  fftw_real tmp122;
	  fftw_real tmp142;
	  fftw_real tmp50;
	  fftw_real tmp61;
	  fftw_real tmp62;
	  fftw_real tmp88;
	  fftw_real tmp89;
	  fftw_real tmp90;
	  fftw_real tmp107;
	  fftw_real tmp110;
	  fftw_real tmp127;
	  fftw_real tmp118;
	  fftw_real tmp119;
	  fftw_real tmp141;
	  ASSERT_ALIGNED_DOUBLE;
	  {
	       fftw_real tmp33;
	       fftw_real tmp131;
	       fftw_real tmp38;
	       fftw_real tmp130;
	       ASSERT_ALIGNED_DOUBLE;
	       tmp33 = X[0];
	       tmp131 = Y[-9 * iostride];
	       {
		    fftw_real tmp35;
		    fftw_real tmp37;
		    fftw_real tmp34;
		    fftw_real tmp36;
		    ASSERT_ALIGNED_DOUBLE;
		    tmp35 = X[5 * iostride];
		    tmp37 = Y[-4 * iostride];
		    tmp34 = c_re(W[4]);
		    tmp36 = c_im(W[4]);
		    tmp38 = (tmp34 * tmp35) - (tmp36 * tmp37);
		    tmp130 = (tmp36 * tmp35) + (tmp34 * tmp37);
	       }
	       tmp39 = tmp33 - tmp38;
	       tmp87 = tmp33 + tmp38;
	       tmp132 = tmp130 + tmp131;
	       tmp144 = tmp131 - tmp130;
	  }
	  {
	       fftw_real tmp67;
	       fftw_real tmp98;
	       fftw_real tmp83;
	       fftw_real tmp102;
	       fftw_real tmp72;
	       fftw_real tmp99;
	       fftw_real tmp78;
	       fftw_real tmp101;
	       ASSERT_ALIGNED_DOUBLE;
	       {
		    fftw_real tmp64;
		    fftw_real tmp66;
		    fftw_real tmp63;
		    fftw_real tmp65;
		    ASSERT_ALIGNED_DOUBLE;
		    tmp64 = X[4 * iostride];
		    tmp66 = Y[-5 * iostride];
		    tmp63 = c_re(W[3]);
		    tmp65 = c_im(W[3]);
		    tmp67 = (tmp63 * tmp64) - (tmp65 * tmp66);
		    tmp98 = (tmp65 * tmp64) + (tmp63 * tmp66);
	       }
	       {
		    fftw_real tmp80;
		    fftw_real tmp82;
		    fftw_real tmp79;
		    fftw_real tmp81;
		    ASSERT_ALIGNED_DOUBLE;
		    tmp80 = X[iostride];
		    tmp82 = Y[-8 * iostride];
		    tmp79 = c_re(W[0]);
		    tmp81 = c_im(W[0]);
		    tmp83 = (tmp79 * tmp80) - (tmp81 * tmp82);
		    tmp102 = (tmp81 * tmp80) + (tmp79 * tmp82);
	       }
	       {
		    fftw_real tmp69;
		    fftw_real tmp71;
		    fftw_real tmp68;
		    fftw_real tmp70;
		    ASSERT_ALIGNED_DOUBLE;
		    tmp69 = X[9 * iostride];
		    tmp71 = Y[0];
		    tmp68 = c_re(W[8]);
		    tmp70 = c_im(W[8]);
		    tmp72 = (tmp68 * tmp69) - (tmp70 * tmp71);
		    tmp99 = (tmp70 * tmp69) + (tmp68 * tmp71);
	       }
	       {
		    fftw_real tmp75;
		    fftw_real tmp77;
		    fftw_real tmp74;
		    fftw_real tmp76;
		    ASSERT_ALIGNED_DOUBLE;
		    tmp75 = X[6 * iostride];
		    tmp77 = Y[-3 * iostride];
		    tmp74 = c_re(W[5]);
		    tmp76 = c_im(W[5]);
		    tmp78 = (tmp74 * tmp75) - (tmp76 * tmp77);
		    tmp101 = (tmp76 * tmp75) + (tmp74 * tmp77);
	       }
	       tmp73 = tmp67 - tmp72;
	       tmp84 = tmp78 - tmp83;
	       tmp85 = tmp73 + tmp84;
	       tmp91 = tmp67 + tmp72;
	       tmp92 = tmp78 + tmp83;
	       tmp93 = tmp91 + tmp92;
	       tmp100 = tmp98 + tmp99;
	       tmp103 = tmp101 + tmp102;
	       tmp128 = tmp100 + tmp103;
	       tmp121 = tmp98 - tmp99;
	       tmp122 = tmp101 - tmp102;
	       tmp142 = tmp121 + tmp122;