etc/furnace
0
0
Fork 0
mirror of https://github.com/tildearrow/furnace.git synced 2024-11-16 09:45:06 +00:00
Code Issues Projects Releases Packages Wiki Activity
furnace/extern/fftw/rdft/scalar/r2cf/r2cf_10.c
tildearrow 54e93db207 GUI: try using FFTW for per-chan osc wave center 
not reliable yet
2022-05-31 03:24:29 -05:00

200 lines
6.3 KiB
C
Raw Blame History

/*
* Copyright (c) 2003, 2007-14 Matteo Frigo
* Copyright (c) 2003, 2007-14 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*
*/
/* This file was automatically generated --- DO NOT EDIT */
/* Generated on Tue Sep 14 10:46:10 EDT 2021 */
#include "rdft/codelet-rdft.h"
#if defined(ARCH_PREFERS_FMA) || defined(ISA_EXTENSION_PREFERS_FMA)
/* Generated by: ../../../genfft/gen_r2cf.native -fma -compact -variables 4 -pipeline-latency 4 -n 10 -name r2cf_10 -include rdft/scalar/r2cf.h */
/*
* This function contains 34 FP additions, 14 FP multiplications,
* (or, 24 additions, 4 multiplications, 10 fused multiply/add),
* 26 stack variables, 4 constants, and 20 memory accesses
*/
#include "rdft/scalar/r2cf.h"
static void r2cf_10(R *R0, R *R1, R *Cr, R *Ci, stride rs, stride csr, stride csi, INT v, INT ivs, INT ovs)
{
DK(KP559016994, +0.559016994374947424102293417182819058860154590);
DK(KP250000000, +0.250000000000000000000000000000000000000000000);
DK(KP618033988, +0.618033988749894848204586834365638117720309180);
DK(KP951056516, +0.951056516295153572116439333379382143405698634);
{
INT i;
for (i = v; i > 0; i = i - 1, R0 = R0 + ivs, R1 = R1 + ivs, Cr = Cr + ovs, Ci = Ci + ovs, MAKE_VOLATILE_STRIDE(40, rs), MAKE_VOLATILE_STRIDE(40, csr), MAKE_VOLATILE_STRIDE(40, csi)) {
E T3, Tt, Td, Tn, Tg, To, Th, Tv, T6, Tq, T9, Tr, Ta, Tu, T1;
E T2;
T1 = R0[0];
T2 = R1[WS(rs, 2)];
T3 = T1 - T2;
Tt = T1 + T2;
{
E Tb, Tc, Te, Tf;
Tb = R0[WS(rs, 2)];
Tc = R1[WS(rs, 4)];
Td = Tb - Tc;
Tn = Tb + Tc;
Te = R0[WS(rs, 3)];
Tf = R1[0];
Tg = Te - Tf;
To = Te + Tf;
}
Th = Td + Tg;
Tv = Tn + To;
{
E T4, T5, T7, T8;
T4 = R0[WS(rs, 1)];
T5 = R1[WS(rs, 3)];
T6 = T4 - T5;
Tq = T4 + T5;
T7 = R0[WS(rs, 4)];
T8 = R1[WS(rs, 1)];
T9 = T7 - T8;
Tr = T7 + T8;
}
Ta = T6 + T9;
Tu = Tq + Tr;
{
E Tl, Tm, Tk, Ti, Tj;
Tl = T6 - T9;
Tm = Tg - Td;
Ci[WS(csi, 1)] = -(KP951056516 * (FNMS(KP618033988, Tm, Tl)));
Ci[WS(csi, 3)] = KP951056516 * (FMA(KP618033988, Tl, Tm));
Tk = Ta - Th;
Ti = Ta + Th;
Tj = FNMS(KP250000000, Ti, T3);
Cr[WS(csr, 1)] = FMA(KP559016994, Tk, Tj);
Cr[WS(csr, 5)] = T3 + Ti;
Cr[WS(csr, 3)] = FNMS(KP559016994, Tk, Tj);
}
{
E Tp, Ts, Ty, Tw, Tx;
Tp = Tn - To;
Ts = Tq - Tr;
Ci[WS(csi, 2)] = KP951056516 * (FNMS(KP618033988, Ts, Tp));
Ci[WS(csi, 4)] = KP951056516 * (FMA(KP618033988, Tp, Ts));
Ty = Tu - Tv;
Tw = Tu + Tv;
Tx = FNMS(KP250000000, Tw, Tt);
Cr[WS(csr, 2)] = FNMS(KP559016994, Ty, Tx);
Cr[0] = Tt + Tw;
Cr[WS(csr, 4)] = FMA(KP559016994, Ty, Tx);
}
}
}
}
static const kr2c_desc desc = { 10, "r2cf_10", { 24, 4, 10, 0 }, &GENUS };
void X(codelet_r2cf_10) (planner *p) { X(kr2c_register) (p, r2cf_10, &desc);
}
#else
/* Generated by: ../../../genfft/gen_r2cf.native -compact -variables 4 -pipeline-latency 4 -n 10 -name r2cf_10 -include rdft/scalar/r2cf.h */
/*
* This function contains 34 FP additions, 12 FP multiplications,
* (or, 28 additions, 6 multiplications, 6 fused multiply/add),
* 26 stack variables, 4 constants, and 20 memory accesses
*/
#include "rdft/scalar/r2cf.h"
static void r2cf_10(R *R0, R *R1, R *Cr, R *Ci, stride rs, stride csr, stride csi, INT v, INT ivs, INT ovs)
{
DK(KP250000000, +0.250000000000000000000000000000000000000000000);
DK(KP559016994, +0.559016994374947424102293417182819058860154590);
DK(KP951056516, +0.951056516295153572116439333379382143405698634);
DK(KP587785252, +0.587785252292473129168705954639072768597652438);
{
INT i;
for (i = v; i > 0; i = i - 1, R0 = R0 + ivs, R1 = R1 + ivs, Cr = Cr + ovs, Ci = Ci + ovs, MAKE_VOLATILE_STRIDE(40, rs), MAKE_VOLATILE_STRIDE(40, csr), MAKE_VOLATILE_STRIDE(40, csi)) {
E Ti, Tt, Ta, Tn, Td, To, Te, Tv, T3, Tq, T6, Tr, T7, Tu, Tg;
E Th;
Tg = R0[0];
Th = R1[WS(rs, 2)];
Ti = Tg - Th;
Tt = Tg + Th;
{
E T8, T9, Tb, Tc;
T8 = R0[WS(rs, 2)];
T9 = R1[WS(rs, 4)];
Ta = T8 - T9;
Tn = T8 + T9;
Tb = R0[WS(rs, 3)];
Tc = R1[0];
Td = Tb - Tc;
To = Tb + Tc;
}
Te = Ta + Td;
Tv = Tn + To;
{
E T1, T2, T4, T5;
T1 = R0[WS(rs, 1)];
T2 = R1[WS(rs, 3)];
T3 = T1 - T2;
Tq = T1 + T2;
T4 = R0[WS(rs, 4)];
T5 = R1[WS(rs, 1)];
T6 = T4 - T5;
Tr = T4 + T5;
}
T7 = T3 + T6;
Tu = Tq + Tr;
{
E Tl, Tm, Tf, Tj, Tk;
Tl = Td - Ta;
Tm = T3 - T6;
Ci[WS(csi, 1)] = FNMS(KP951056516, Tm, KP587785252 * Tl);
Ci[WS(csi, 3)] = FMA(KP587785252, Tm, KP951056516 * Tl);
Tf = KP559016994 * (T7 - Te);
Tj = T7 + Te;
Tk = FNMS(KP250000000, Tj, Ti);
Cr[WS(csr, 1)] = Tf + Tk;
Cr[WS(csr, 5)] = Ti + Tj;
Cr[WS(csr, 3)] = Tk - Tf;
}
{
E Tp, Ts, Ty, Tw, Tx;
Tp = Tn - To;
Ts = Tq - Tr;
Ci[WS(csi, 2)] = FNMS(KP587785252, Ts, KP951056516 * Tp);
Ci[WS(csi, 4)] = FMA(KP951056516, Ts, KP587785252 * Tp);
Ty = KP559016994 * (Tu - Tv);
Tw = Tu + Tv;
Tx = FNMS(KP250000000, Tw, Tt);
Cr[WS(csr, 2)] = Tx - Ty;
Cr[0] = Tt + Tw;
Cr[WS(csr, 4)] = Ty + Tx;
}
}
}
}
static const kr2c_desc desc = { 10, "r2cf_10", { 28, 6, 6, 0 }, &GENUS };
void X(codelet_r2cf_10) (planner *p) { X(kr2c_register) (p, r2cf_10, &desc);
}
#endif
Reference in a new issue View git blame Copy permalink