2
* Copyright (c) 2003 Matteo Frigo
3
* Copyright (c) 2003 Massachusetts Institute of Technology
5
* This program is free software; you can redistribute it and/or modify
6
* it under the terms of the GNU General Public License as published by
7
* the Free Software Foundation; either version 2 of the License, or
8
* (at your option) any later version.
10
* This program is distributed in the hope that it will be useful,
11
* but WITHOUT ANY WARRANTY; without even the implied warranty of
12
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13
* GNU General Public License for more details.
15
* You should have received a copy of the GNU General Public License
16
* along with this program; if not, write to the Free Software
17
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
21
/* This file was automatically generated --- DO NOT EDIT */
22
/* Generated on Sat Jul 5 21:40:41 EDT 2003 */
24
#include "codelet-dft.h"
26
/* Generated by: /homee/stevenj/cvs/fftw3.0.1/genfft/gen_notw_c -simd -compact -variables 4 -sign 1 -n 5 -name n2bv_5 -with-ostride 2 -include n2b.h */
29
* This function contains 16 FP additions, 6 FP multiplications,
30
* (or, 13 additions, 3 multiplications, 3 fused multiply/add),
31
* 18 stack variables, and 10 memory accesses
35
* $Id: algsimp.ml,v 1.7 2003/03/15 20:29:42 stevenj Exp $
36
* $Id: fft.ml,v 1.2 2003/03/15 20:29:42 stevenj Exp $
37
* $Id: gen_notw_c.ml,v 1.9 2003/04/16 21:21:53 athena Exp $
42
static void n2bv_5(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, int v, int ivs, int ovs)
44
DVK(KP250000000, +0.250000000000000000000000000000000000000000000);
45
DVK(KP587785252, +0.587785252292473129168705954639072768597652438);
46
DVK(KP951056516, +0.951056516295153572116439333379382143405698634);
47
DVK(KP559016994, +0.559016994374947424102293417182819058860154590);
54
for (i = v; i > 0; i = i - VL, xi = xi + (VL * ivs), xo = xo + (VL * ovs)) {
56
Tb = LD(&(xi[0]), ivs, &(xi[0]));
58
V T1, T2, T8, T4, T5, T9;
59
T1 = LD(&(xi[WS(is, 1)]), ivs, &(xi[WS(is, 1)]));
60
T2 = LD(&(xi[WS(is, 4)]), ivs, &(xi[0]));
62
T4 = LD(&(xi[WS(is, 2)]), ivs, &(xi[0]));
63
T5 = LD(&(xi[WS(is, 3)]), ivs, &(xi[WS(is, 1)]));
68
Ta = VMUL(LDK(KP559016994), VSUB(T8, T9));
70
ST(&(xo[0]), VADD(Tb, Tc), ovs, &(xo[0]));
73
T7 = VBYI(VFMA(LDK(KP951056516), T3, VMUL(LDK(KP587785252), T6)));
74
Tf = VBYI(VFNMS(LDK(KP951056516), T6, VMUL(LDK(KP587785252), T3)));
75
Td = VFNMS(LDK(KP250000000), Tc, Tb);
78
ST(&(xo[2]), VADD(T7, Te), ovs, &(xo[2]));
79
ST(&(xo[6]), VSUB(Tg, Tf), ovs, &(xo[2]));
80
ST(&(xo[8]), VSUB(Te, T7), ovs, &(xo[0]));
81
ST(&(xo[4]), VADD(Tf, Tg), ovs, &(xo[0]));
87
static const kdft_desc desc = { 5, "n2bv_5", {13, 3, 3, 0}, &GENUS, 0, 2, 0, 0 };
88
void X(codelet_n2bv_5) (planner *p) {
89
X(kdft_register) (p, n2bv_5, &desc);