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
119
120
121
122
123
124
125
126
127
128
|
/*
* 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 21:58:14 EDT 2003 */
#include "codelet-rdft.h"
/* Generated by: /homee/stevenj/cvs/fftw3.0.1/genfft/gen_r2hc -compact -variables 4 -n 12 -name r2hcII_12 -dft-II -include r2hcII.h */
/*
* This function contains 43 FP additions, 12 FP multiplications,
* (or, 39 additions, 8 multiplications, 4 fused multiply/add),
* 28 stack variables, and 24 memory accesses
*/
/*
* Generator Id's :
* $Id: r2hcII_12.c,v 1.1 2008/10/17 06:12:34 scuri Exp $
* $Id: r2hcII_12.c,v 1.1 2008/10/17 06:12:34 scuri Exp $
* $Id: r2hcII_12.c,v 1.1 2008/10/17 06:12:34 scuri Exp $
*/
#include "r2hcII.h"
static void r2hcII_12(const R *I, R *ro, R *io, stride is, stride ros, stride ios, int v, int ivs, int ovs)
{
DK(KP353553390, +0.353553390593273762200422181052424519642417969);
DK(KP707106781, +0.707106781186547524400844362104849039284835938);
DK(KP612372435, +0.612372435695794524549321018676472847991486870);
DK(KP500000000, +0.500000000000000000000000000000000000000000000);
DK(KP866025403, +0.866025403784438646763723170752936183471402627);
int i;
for (i = v; i > 0; i = i - 1, I = I + ivs, ro = ro + ovs, io = io + ovs) {
E Tx, Tg, T4, Tz, Ty, Tj, TA, T9, Tm, Tl, Te, Tp, To, Tf, TE;
E TF;
{
E T1, T3, T2, Th, Ti;
T1 = I[0];
T3 = I[WS(is, 4)];
T2 = I[WS(is, 8)];
Tx = KP866025403 * (T2 + T3);
Tg = FMA(KP500000000, T3 - T2, T1);
T4 = T1 + T2 - T3;
Tz = I[WS(is, 6)];
Th = I[WS(is, 10)];
Ti = I[WS(is, 2)];
Ty = Th + Ti;
Tj = KP866025403 * (Th - Ti);
TA = FMA(KP500000000, Ty, Tz);
}
{
E T5, T6, T7, T8;
T5 = I[WS(is, 3)];
T6 = I[WS(is, 11)];
T7 = I[WS(is, 7)];
T8 = T6 - T7;
T9 = T5 + T8;
Tm = KP612372435 * (T6 + T7);
Tl = FNMS(KP353553390, T8, KP707106781 * T5);
}
{
E Td, Ta, Tb, Tc;
Td = I[WS(is, 9)];
Ta = I[WS(is, 5)];
Tb = I[WS(is, 1)];
Tc = Ta - Tb;
Te = Tc - Td;
Tp = FMA(KP353553390, Tc, KP707106781 * Td);
To = KP612372435 * (Ta + Tb);
}
Tf = KP707106781 * (T9 + Te);
ro[WS(ros, 1)] = T4 - Tf;
ro[WS(ros, 4)] = T4 + Tf;
TE = KP707106781 * (Te - T9);
TF = Tz - Ty;
io[WS(ios, 4)] = TE - TF;
io[WS(ios, 1)] = TE + TF;
{
E Tk, TB, Tr, Tw, Tn, Tq;
Tk = Tg - Tj;
TB = Tx - TA;
Tn = Tl - Tm;
Tq = To - Tp;
Tr = Tn + Tq;
Tw = Tn - Tq;
ro[WS(ros, 5)] = Tk - Tr;
io[WS(ios, 2)] = Tw + TB;
ro[0] = Tk + Tr;
io[WS(ios, 3)] = Tw - TB;
}
{
E Ts, TD, Tv, TC, Tt, Tu;
Ts = Tg + Tj;
TD = Tx + TA;
Tt = To + Tp;
Tu = Tm + Tl;
Tv = Tt - Tu;
TC = Tu + Tt;
ro[WS(ros, 3)] = Ts - Tv;
io[WS(ios, 5)] = TD - TC;
ro[WS(ros, 2)] = Ts + Tv;
io[0] = -(TC + TD);
}
}
}
static const kr2hc_desc desc = { 12, "r2hcII_12", {39, 8, 4, 0}, &GENUS, 0, 0, 0, 0, 0 };
void X(codelet_r2hcII_12) (planner *p) {
X(kr2hcII_register) (p, r2hcII_12, &desc);
}
|
