87b128d5ef
Profiling results for overall audio decode and the mlp_filter_channel(_arm)
function in particular are as follows:
Before After
Mean StdDev Mean StdDev Confidence Change
6:2 total 380.4 22.0 370.8 17.0 87.4% +2.6% (insignificant)
6:2 function 60.7 7.2 36.6 8.1 100.0% +65.8%
8:2 total 357.0 17.5 343.2 19.0 97.8% +4.0% (insignificant)
8:2 function 60.3 8.8 37.3 3.8 100.0% +61.8%
6:6 total 717.2 23.2 658.4 15.7 100.0% +8.9%
6:6 function 140.4 12.9 81.5 9.2 100.0% +72.4%
8:8 total 981.9 16.2 896.2 24.5 100.0% +9.6%
8:8 function 193.4 15.0 103.3 11.5 100.0% +87.2%
Experiments with adding preload instructions to this function yielded no
useful benefit, so these have not been included.
The assembly version has also been tested with a fuzz tester to ensure that
any combinations of inputs not exercised by my available test streams still
generate mathematically identical results to the C version.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
68 lines
2.2 KiB
C
68 lines
2.2 KiB
C
/*
|
|
* Copyright (c) 2007-2008 Ian Caulfield
|
|
* 2009 Ramiro Polla
|
|
*
|
|
* This file is part of FFmpeg.
|
|
*
|
|
* FFmpeg is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2.1 of the License, or (at your option) any later version.
|
|
*
|
|
* FFmpeg 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
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public
|
|
* License along with FFmpeg; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include "config.h"
|
|
#include "libavutil/attributes.h"
|
|
#include "mlpdsp.h"
|
|
#include "mlp.h"
|
|
|
|
static void mlp_filter_channel(int32_t *state, const int32_t *coeff,
|
|
int firorder, int iirorder,
|
|
unsigned int filter_shift, int32_t mask,
|
|
int blocksize, int32_t *sample_buffer)
|
|
{
|
|
int32_t *firbuf = state;
|
|
int32_t *iirbuf = state + MAX_BLOCKSIZE + MAX_FIR_ORDER;
|
|
const int32_t *fircoeff = coeff;
|
|
const int32_t *iircoeff = coeff + MAX_FIR_ORDER;
|
|
int i;
|
|
|
|
for (i = 0; i < blocksize; i++) {
|
|
int32_t residual = *sample_buffer;
|
|
unsigned int order;
|
|
int64_t accum = 0;
|
|
int32_t result;
|
|
|
|
for (order = 0; order < firorder; order++)
|
|
accum += (int64_t) firbuf[order] * fircoeff[order];
|
|
for (order = 0; order < iirorder; order++)
|
|
accum += (int64_t) iirbuf[order] * iircoeff[order];
|
|
|
|
accum = accum >> filter_shift;
|
|
result = (accum + residual) & mask;
|
|
|
|
*--firbuf = result;
|
|
*--iirbuf = result - accum;
|
|
|
|
*sample_buffer = result;
|
|
sample_buffer += MAX_CHANNELS;
|
|
}
|
|
}
|
|
|
|
av_cold void ff_mlpdsp_init(MLPDSPContext *c)
|
|
{
|
|
c->mlp_filter_channel = mlp_filter_channel;
|
|
if (ARCH_ARM)
|
|
ff_mlpdsp_init_arm(c);
|
|
if (ARCH_X86)
|
|
ff_mlpdsp_init_x86(c);
|
|
}
|