slapin/ogre-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updates

Browse Source
This commit is contained in:
Sergey Lapin
2025-07-12 12:17:44 +03:00
parent c759f60ff7
commit 792e1b937a
3507 changed files with 492613 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
fftw-3.3.10/dft/scalar/codelets/n1_4.c Normal file
View File

@@ -0,0 +1,138 @@
/*
* 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 10:44:24 EDT 2021 */
#include "dft/codelet-dft.h"
#if defined(ARCH_PREFERS_FMA) || defined(ISA_EXTENSION_PREFERS_FMA)
/* Generated by: ../../../genfft/gen_notw.native -fma -compact -variables 4 -pipeline-latency 4 -n 4 -name n1_4 -include dft/scalar/n.h */
/*
* This function contains 16 FP additions, 0 FP multiplications,
* (or, 16 additions, 0 multiplications, 0 fused multiply/add),
* 13 stack variables, 0 constants, and 16 memory accesses
*/
#include "dft/scalar/n.h"
static void n1_4(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs)
{
{
INT i;
for (i = v; i > 0; i = i - 1, ri = ri + ivs, ii = ii + ivs, ro = ro + ovs, io = io + ovs, MAKE_VOLATILE_STRIDE(16, is), MAKE_VOLATILE_STRIDE(16, os)) {
E T3, Tb, T9, Tf, T6, Ta, Te, Tg;
{
E T1, T2, T7, T8;
T1 = ri[0];
T2 = ri[WS(is, 2)];
T3 = T1 + T2;
Tb = T1 - T2;
T7 = ii[0];
T8 = ii[WS(is, 2)];
T9 = T7 - T8;
Tf = T7 + T8;
}
{
E T4, T5, Tc, Td;
T4 = ri[WS(is, 1)];
T5 = ri[WS(is, 3)];
T6 = T4 + T5;
Ta = T4 - T5;
Tc = ii[WS(is, 1)];
Td = ii[WS(is, 3)];
Te = Tc - Td;
Tg = Tc + Td;
}
ro[WS(os, 2)] = T3 - T6;
io[WS(os, 2)] = Tf - Tg;
ro[0] = T3 + T6;
io[0] = Tf + Tg;
io[WS(os, 1)] = T9 - Ta;
ro[WS(os, 1)] = Tb + Te;
io[WS(os, 3)] = Ta + T9;
ro[WS(os, 3)] = Tb - Te;
}
}
}
static const kdft_desc desc = { 4, "n1_4", { 16, 0, 0, 0 }, &GENUS, 0, 0, 0, 0 };
void X(codelet_n1_4) (planner *p) { X(kdft_register) (p, n1_4, &desc);
}
#else
/* Generated by: ../../../genfft/gen_notw.native -compact -variables 4 -pipeline-latency 4 -n 4 -name n1_4 -include dft/scalar/n.h */
/*
* This function contains 16 FP additions, 0 FP multiplications,
* (or, 16 additions, 0 multiplications, 0 fused multiply/add),
* 13 stack variables, 0 constants, and 16 memory accesses
*/
#include "dft/scalar/n.h"
static void n1_4(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs)
{
{
INT i;
for (i = v; i > 0; i = i - 1, ri = ri + ivs, ii = ii + ivs, ro = ro + ovs, io = io + ovs, MAKE_VOLATILE_STRIDE(16, is), MAKE_VOLATILE_STRIDE(16, os)) {
E T3, Tb, T9, Tf, T6, Ta, Te, Tg;
{
E T1, T2, T7, T8;
T1 = ri[0];
T2 = ri[WS(is, 2)];
T3 = T1 + T2;
Tb = T1 - T2;
T7 = ii[0];
T8 = ii[WS(is, 2)];
T9 = T7 - T8;
Tf = T7 + T8;
}
{
E T4, T5, Tc, Td;
T4 = ri[WS(is, 1)];
T5 = ri[WS(is, 3)];
T6 = T4 + T5;
Ta = T4 - T5;
Tc = ii[WS(is, 1)];
Td = ii[WS(is, 3)];
Te = Tc - Td;
Tg = Tc + Td;
}
ro[WS(os, 2)] = T3 - T6;
io[WS(os, 2)] = Tf - Tg;
ro[0] = T3 + T6;
io[0] = Tf + Tg;
io[WS(os, 1)] = T9 - Ta;
ro[WS(os, 1)] = Tb + Te;
io[WS(os, 3)] = Ta + T9;
ro[WS(os, 3)] = Tb - Te;
}
}
}
static const kdft_desc desc = { 4, "n1_4", { 16, 0, 0, 0 }, &GENUS, 0, 0, 0, 0 };
void X(codelet_n1_4) (planner *p) { X(kdft_register) (p, n1_4, &desc);
}
#endif