1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
|
/*
* 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 22:22:02 EDT 2003 */
#include "codelet-rdft.h"
/* Generated by: /homee/stevenj/cvs/fftw3.0.1/genfft/gen_r2r -compact -variables 4 -redft10 -n 8 -name e10_8 -include r2r.h */
/*
* This function contains 26 FP additions, 16 FP multiplications,
* (or, 20 additions, 10 multiplications, 6 fused multiply/add),
* 27 stack variables, and 16 memory accesses
*/
/*
* Generator Id's :
* $Id: e10_8.c,v 1.1 2008/10/17 06:13:17 scuri Exp $
* $Id: e10_8.c,v 1.1 2008/10/17 06:13:17 scuri Exp $
* $Id: e10_8.c,v 1.1 2008/10/17 06:13:17 scuri Exp $
*/
#include "r2r.h"
static void e10_8_0(const R *I, R *O, stride istride, stride ostride)
{
DK(KP765366864, +0.765366864730179543456919968060797733522689125);
DK(KP1_847759065, +1.847759065022573512256366378793576573644833252);
DK(KP390180644, +0.390180644032256535696569736954044481855383236);
DK(KP1_961570560, +1.961570560806460898252364472268478073947867462);
DK(KP2_000000000, +2.000000000000000000000000000000000000000000000);
DK(KP1_414213562, +1.414213562373095048801688724209698078569671875);
DK(KP1_111140466, +1.111140466039204449485661627897065748749874382);
DK(KP1_662939224, +1.662939224605090474157576755235811513477121624);
DK(KP707106781, +0.707106781186547524400844362104849039284835938);
{
E T3, Tj, Tf, Tk, Ta, Tn, Tc, Tm;
{
E T1, T2, Td, Te;
T1 = I[0];
T2 = I[WS(istride, 7)];
T3 = T1 - T2;
Tj = T1 + T2;
Td = I[WS(istride, 4)];
Te = I[WS(istride, 3)];
Tf = Td - Te;
Tk = Td + Te;
{
E T4, T5, T6, T7, T8, T9;
T4 = I[WS(istride, 2)];
T5 = I[WS(istride, 5)];
T6 = T4 - T5;
T7 = I[WS(istride, 1)];
T8 = I[WS(istride, 6)];
T9 = T7 - T8;
Ta = KP707106781 * (T6 + T9);
Tn = T7 + T8;
Tc = KP707106781 * (T6 - T9);
Tm = T4 + T5;
}
}
{
E Tb, Tg, Tp, Tq;
Tb = T3 - Ta;
Tg = Tc - Tf;
O[WS(ostride, 3)] = FNMS(KP1_111140466, Tg, KP1_662939224 * Tb);
O[WS(ostride, 5)] = FMA(KP1_662939224, Tg, KP1_111140466 * Tb);
Tp = Tj + Tk;
Tq = Tm + Tn;
O[WS(ostride, 4)] = KP1_414213562 * (Tp - Tq);
O[0] = KP2_000000000 * (Tp + Tq);
}
{
E Th, Ti, Tl, To;
Th = T3 + Ta;
Ti = Tf + Tc;
O[WS(ostride, 1)] = FNMS(KP390180644, Ti, KP1_961570560 * Th);
O[WS(ostride, 7)] = FMA(KP1_961570560, Ti, KP390180644 * Th);
Tl = Tj - Tk;
To = Tm - Tn;
O[WS(ostride, 2)] = FNMS(KP765366864, To, KP1_847759065 * Tl);
O[WS(ostride, 6)] = FMA(KP765366864, Tl, KP1_847759065 * To);
}
}
}
static void e10_8(const R *I, R *O, stride is, stride os, int v, int ivs, int ovs)
{
int i;
for (i = v; i > 0; --i) {
e10_8_0(I, O, is, os);
I += ivs;
O += ovs;
}
}
static const kr2r_desc desc = { 8, "e10_8", {20, 10, 6, 0}, &GENUS, REDFT10, 0, 0, 0, 0 };
void X(codelet_e10_8) (planner *p) {
X(kr2r_register) (p, e10_8, &desc);
}
|
