/* * Copyright (c) 2003 Matteo Frigo * Copyright (c) 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 Sat Jul 5 21:29:32 EDT 2003 */ #include "codelet-dft.h" /* Generated by: /homee/stevenj/cvs/fftw3.0.1/genfft/gen_notw -compact -variables 4 -n 6 -name n1_6 -include n.h */ /* * This function contains 36 FP additions, 8 FP multiplications, * (or, 32 additions, 4 multiplications, 4 fused multiply/add), * 23 stack variables, and 24 memory accesses */ /* * Generator Id's : * $Id: n1_6.c,v 1.1 2008/10/17 06:11:09 scuri Exp $ * $Id: n1_6.c,v 1.1 2008/10/17 06:11:09 scuri Exp $ * $Id: n1_6.c,v 1.1 2008/10/17 06:11:09 scuri Exp $ */ #include "n.h" static void n1_6(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, int v, int ivs, int ovs) { DK(KP866025403, +0.866025403784438646763723170752936183471402627); DK(KP500000000, +0.500000000000000000000000000000000000000000000); int i; for (i = v; i > 0; i = i - 1, ri = ri + ivs, ii = ii + ivs, ro = ro + ovs, io = io + ovs) { E T3, Tb, Tq, Tx, T6, Tc, T9, Td, Ta, Te, Ti, Tu, Tl, Tv, Tr; E Ty; { E T1, T2, To, Tp; T1 = ri[0]; T2 = ri[WS(is, 3)]; T3 = T1 - T2; Tb = T1 + T2; To = ii[0]; Tp = ii[WS(is, 3)]; Tq = To - Tp; Tx = To + Tp; } { E T4, T5, T7, T8; T4 = ri[WS(is, 2)]; T5 = ri[WS(is, 5)]; T6 = T4 - T5; Tc = T4 + T5; T7 = ri[WS(is, 4)]; T8 = ri[WS(is, 1)]; T9 = T7 - T8; Td = T7 + T8; } Ta = T6 + T9; Te = Tc + Td; { E Tg, Th, Tj, Tk; Tg = ii[WS(is, 2)]; Th = ii[WS(is, 5)]; Ti = Tg - Th; Tu = Tg + Th; Tj = ii[WS(is, 4)]; Tk = ii[WS(is, 1)]; Tl = Tj - Tk; Tv = Tj + Tk; } Tr = Ti + Tl; Ty = Tu + Tv; ro[WS(os, 3)] = T3 + Ta; io[WS(os, 3)] = Tq + Tr; ro[0] = Tb + Te; io[0] = Tx + Ty; { E Tf, Tm, Tn, Ts; Tf = FNMS(KP500000000, Ta, T3); Tm = KP866025403 * (Ti - Tl); ro[WS(os, 5)] = Tf - Tm; ro[WS(os, 1)] = Tf + Tm; Tn = KP866025403 * (T9 - T6); Ts = FNMS(KP500000000, Tr, Tq); io[WS(os, 1)] = Tn + Ts; io[WS(os, 5)] = Ts - Tn; } { E Tt, Tw, Tz, TA; Tt = FNMS(KP500000000, Te, Tb); Tw = KP866025403 * (Tu - Tv); ro[WS(os, 2)] = Tt - Tw; ro[WS(os, 4)] = Tt + Tw; Tz = FNMS(KP500000000, Ty, Tx); TA = KP866025403 * (Td - Tc); io[WS(os, 2)] = Tz - TA; io[WS(os, 4)] = TA + Tz; } } } static const kdft_desc desc = { 6, "n1_6", {32, 4, 4, 0}, &GENUS, 0, 0, 0, 0 }; void X(codelet_n1_6) (planner *p) { X(kdft_register) (p, n1_6, &desc); }