/* * 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 21:56:41 EDT 2003 */ #include "codelet-rdft.h" /* Generated by: /homee/stevenj/cvs/fftw3.0.1/genfft/gen_r2hc -compact -variables 4 -n 14 -name r2hc_14 -include r2hc.h */ /* * This function contains 62 FP additions, 36 FP multiplications, * (or, 38 additions, 12 multiplications, 24 fused multiply/add), * 29 stack variables, and 28 memory accesses */ /* * Generator Id's : * $Id: r2hc_14.c,v 1.1 2008/10/17 06:12:34 scuri Exp $ * $Id: r2hc_14.c,v 1.1 2008/10/17 06:12:34 scuri Exp $ * $Id: r2hc_14.c,v 1.1 2008/10/17 06:12:34 scuri Exp $ */ #include "r2hc.h" static void r2hc_14(const R *I, R *ro, R *io, stride is, stride ros, stride ios, int v, int ivs, int ovs) { DK(KP900968867, +0.900968867902419126236102319507445051165919162); DK(KP222520933, +0.222520933956314404288902564496794759466355569); DK(KP623489801, +0.623489801858733530525004884004239810632274731); DK(KP433883739, +0.433883739117558120475768332848358754609990728); DK(KP974927912, +0.974927912181823607018131682993931217232785801); DK(KP781831482, +0.781831482468029808708444526674057750232334519); int i; for (i = v; i > 0; i = i - 1, I = I + ivs, ro = ro + ovs, io = io + ovs) { E T3, TB, T6, Tv, Tn, Ts, Tk, Tt, Td, Ty, T9, Tw, Tg, Tz, T1; E T2; T1 = I[0]; T2 = I[WS(is, 7)]; T3 = T1 - T2; TB = T1 + T2; { E T4, T5, Tl, Tm; T4 = I[WS(is, 4)]; T5 = I[WS(is, 11)]; T6 = T4 - T5; Tv = T4 + T5; Tl = I[WS(is, 12)]; Tm = I[WS(is, 5)]; Tn = Tl - Tm; Ts = Tl + Tm; } { E Ti, Tj, Tb, Tc; Ti = I[WS(is, 2)]; Tj = I[WS(is, 9)]; Tk = Ti - Tj; Tt = Ti + Tj; Tb = I[WS(is, 6)]; Tc = I[WS(is, 13)]; Td = Tb - Tc; Ty = Tb + Tc; } { E T7, T8, Te, Tf; T7 = I[WS(is, 10)]; T8 = I[WS(is, 3)]; T9 = T7 - T8; Tw = T7 + T8; Te = I[WS(is, 8)]; Tf = I[WS(is, 1)]; Tg = Te - Tf; Tz = Te + Tf; } { E Tp, Tr, Tq, Ta, To, Th; Tp = Tn - Tk; Tr = Tg - Td; Tq = T9 - T6; io[WS(ios, 1)] = FMA(KP781831482, Tp, KP974927912 * Tq) + (KP433883739 * Tr); io[WS(ios, 5)] = FMA(KP433883739, Tq, KP781831482 * Tr) - (KP974927912 * Tp); io[WS(ios, 3)] = FMA(KP433883739, Tp, KP974927912 * Tr) - (KP781831482 * Tq); Ta = T6 + T9; To = Tk + Tn; Th = Td + Tg; ro[WS(ros, 3)] = FMA(KP623489801, Ta, T3) + FNMA(KP222520933, Th, KP900968867 * To); ro[WS(ros, 7)] = T3 + To + Ta + Th; ro[WS(ros, 1)] = FMA(KP623489801, To, T3) + FNMA(KP900968867, Th, KP222520933 * Ta); ro[WS(ros, 5)] = FMA(KP623489801, Th, T3) + FNMA(KP900968867, Ta, KP222520933 * To); } { E Tu, TA, Tx, TC, TE, TD; Tu = Ts - Tt; TA = Ty - Tz; Tx = Tv - Tw; io[WS(ios, 2)] = FMA(KP974927912, Tu, KP433883739 * Tx) + (KP781831482 * TA); io[WS(ios, 6)] = FMA(KP974927912, Tx, KP433883739 * TA) - (KP781831482 * Tu); io[WS(ios, 4)] = FNMS(KP781831482, Tx, KP974927912 * TA) - (KP433883739 * Tu); TC = Tt + Ts; TE = Tv + Tw; TD = Ty + Tz; ro[WS(ros, 6)] = FMA(KP623489801, TC, TB) + FNMA(KP900968867, TD, KP222520933 * TE); ro[WS(ros, 2)] = FMA(KP623489801, TD, TB) + FNMA(KP900968867, TE, KP222520933 * TC); ro[WS(ros, 4)] = FMA(KP623489801, TE, TB) + FNMA(KP222520933, TD, KP900968867 * TC); ro[0] = TB + TC + TE + TD; } } } static const kr2hc_desc desc = { 14, "r2hc_14", {38, 12, 24, 0}, &GENUS, 0, 0, 0, 0, 0 }; void X(codelet_r2hc_14) (planner *p) { X(kr2hc_register) (p, r2hc_14, &desc); }