mirror of
https://github.com/tildearrow/furnace.git
synced 2024-11-30 16:33:01 +00:00
102 lines
3.4 KiB
C
102 lines
3.4 KiB
C
/*
|
|
* 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 10:45:12 EDT 2021 */
|
|
|
|
#include "dft/codelet-dft.h"
|
|
|
|
#if defined(ARCH_PREFERS_FMA) || defined(ISA_EXTENSION_PREFERS_FMA)
|
|
|
|
/* Generated by: ../../../genfft/gen_notw_c.native -fma -simd -compact -variables 4 -pipeline-latency 8 -n 2 -name n2fv_2 -with-ostride 2 -include dft/simd/n2f.h -store-multiple 2 */
|
|
|
|
/*
|
|
* This function contains 2 FP additions, 0 FP multiplications,
|
|
* (or, 2 additions, 0 multiplications, 0 fused multiply/add),
|
|
* 7 stack variables, 0 constants, and 5 memory accesses
|
|
*/
|
|
#include "dft/simd/n2f.h"
|
|
|
|
static void n2fv_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs)
|
|
{
|
|
{
|
|
INT i;
|
|
const R *xi;
|
|
R *xo;
|
|
xi = ri;
|
|
xo = ro;
|
|
for (i = v; i > 0; i = i - VL, xi = xi + (VL * ivs), xo = xo + (VL * ovs), MAKE_VOLATILE_STRIDE(4, is), MAKE_VOLATILE_STRIDE(4, os)) {
|
|
V T1, T2, T3, T4;
|
|
T1 = LD(&(xi[0]), ivs, &(xi[0]));
|
|
T2 = LD(&(xi[WS(is, 1)]), ivs, &(xi[WS(is, 1)]));
|
|
T3 = VSUB(T1, T2);
|
|
STM2(&(xo[2]), T3, ovs, &(xo[2]));
|
|
T4 = VADD(T1, T2);
|
|
STM2(&(xo[0]), T4, ovs, &(xo[0]));
|
|
STN2(&(xo[0]), T4, T3, ovs);
|
|
}
|
|
}
|
|
VLEAVE();
|
|
}
|
|
|
|
static const kdft_desc desc = { 2, XSIMD_STRING("n2fv_2"), { 2, 0, 0, 0 }, &GENUS, 0, 2, 0, 0 };
|
|
|
|
void XSIMD(codelet_n2fv_2) (planner *p) { X(kdft_register) (p, n2fv_2, &desc);
|
|
}
|
|
|
|
#else
|
|
|
|
/* Generated by: ../../../genfft/gen_notw_c.native -simd -compact -variables 4 -pipeline-latency 8 -n 2 -name n2fv_2 -with-ostride 2 -include dft/simd/n2f.h -store-multiple 2 */
|
|
|
|
/*
|
|
* This function contains 2 FP additions, 0 FP multiplications,
|
|
* (or, 2 additions, 0 multiplications, 0 fused multiply/add),
|
|
* 7 stack variables, 0 constants, and 5 memory accesses
|
|
*/
|
|
#include "dft/simd/n2f.h"
|
|
|
|
static void n2fv_2(const R *ri, const R *ii, R *ro, R *io, stride is, stride os, INT v, INT ivs, INT ovs)
|
|
{
|
|
{
|
|
INT i;
|
|
const R *xi;
|
|
R *xo;
|
|
xi = ri;
|
|
xo = ro;
|
|
for (i = v; i > 0; i = i - VL, xi = xi + (VL * ivs), xo = xo + (VL * ovs), MAKE_VOLATILE_STRIDE(4, is), MAKE_VOLATILE_STRIDE(4, os)) {
|
|
V T1, T2, T3, T4;
|
|
T1 = LD(&(xi[0]), ivs, &(xi[0]));
|
|
T2 = LD(&(xi[WS(is, 1)]), ivs, &(xi[WS(is, 1)]));
|
|
T3 = VSUB(T1, T2);
|
|
STM2(&(xo[2]), T3, ovs, &(xo[2]));
|
|
T4 = VADD(T1, T2);
|
|
STM2(&(xo[0]), T4, ovs, &(xo[0]));
|
|
STN2(&(xo[0]), T4, T3, ovs);
|
|
}
|
|
}
|
|
VLEAVE();
|
|
}
|
|
|
|
static const kdft_desc desc = { 2, XSIMD_STRING("n2fv_2"), { 2, 0, 0, 0 }, &GENUS, 0, 2, 0, 0 };
|
|
|
|
void XSIMD(codelet_n2fv_2) (planner *p) { X(kdft_register) (p, n2fv_2, &desc);
|
|
}
|
|
|
|
#endif
|