mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-24 00:02:52 +00:00
90b1b9350c
Quite a bit faster than int32_to_float_fmul_array8_c calling
ff_int32_to_float_fmul_scalar_neon through FmtConvertContext.
Number of cycles per int32_to_float_fmul_array8 call while decoding
padded.dts on exynos5422:
before after change
cortex-a7: 1270 951 -25%
cortex-a15: 434 285 -34%
checkasm --bench cycle counts: cortex-a15 cortex-a7
int32_to_float_fmul_array8_c: 1730.4 4384.5
int32_to_float_fmul_array8_neon_c: 571.5 1694.3
int32_to_float_fmul_array8_neon: 374.0 1448.8
Interesting are the differences between
int32_to_float_fmul_array8_neon_c and int32_to_float_fmul_array8_neon.
The former is current behaviour of calling
ff_int32_to_float_fmul_scalar_neon repeatedly from the c function,
The raw numbers differ since checkasm uses different lengths than the
dca decoder.
56 lines
2.1 KiB
C
56 lines
2.1 KiB
C
/*
|
|
* ARM optimized Format Conversion Utils
|
|
*
|
|
* This file is part of Libav.
|
|
*
|
|
* Libav 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.
|
|
*
|
|
* Libav 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 Libav; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/arm/cpu.h"
|
|
#include "libavcodec/avcodec.h"
|
|
#include "libavcodec/fmtconvert.h"
|
|
|
|
void ff_int32_to_float_fmul_array8_neon(FmtConvertContext *c, float *dst,
|
|
const int32_t *src, const float *mul,
|
|
int len);
|
|
void ff_int32_to_float_fmul_scalar_neon(float *dst, const int32_t *src,
|
|
float mul, int len);
|
|
|
|
void ff_int32_to_float_fmul_scalar_vfp(float *dst, const int32_t *src,
|
|
float mul, int len);
|
|
void ff_int32_to_float_fmul_array8_vfp(FmtConvertContext *c, float *dst,
|
|
const int32_t *src, const float *mul,
|
|
int len);
|
|
|
|
av_cold void ff_fmt_convert_init_arm(FmtConvertContext *c, AVCodecContext *avctx)
|
|
{
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
if (have_vfp_vm(cpu_flags)) {
|
|
if (!have_vfpv3(cpu_flags)) {
|
|
c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_vfp;
|
|
c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_vfp;
|
|
}
|
|
}
|
|
|
|
if (have_neon(cpu_flags)) {
|
|
c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_neon;
|
|
c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_neon;
|
|
}
|
|
}
|