Commit 4fdacf4c authored by Rostislav Pehlivanov's avatar Rostislav Pehlivanov

imdct15: remove the AArch64 assembly

Prep work for the next commit, which will add a new FFT algorithm
which makes the iMDCT over 3x faster than it is currently (standalone,
the FFT is with some framesizes over 10x faster).

The new FFT algorithm uses the already thouroughly SIMD'd power of two
FFT which already has SIMD for AArch64, so users of that platform will
still see an improvement.

The previous FFT+SIMD was barely 2.5x faster than the C versions on these
platforms.
Signed-off-by: 's avatarRostislav Pehlivanov <atomnuker@gmail.com>
parent 57ae94a3
......@@ -6,7 +6,6 @@ OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_init_aarch64.o
OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_init.o
OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_init_aarch64.o
OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_init_aarch64.o
OBJS-$(CONFIG_IMDCT15) += aarch64/imdct15_init.o
OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_init.o
OBJS-$(CONFIG_NEON_CLOBBER_TEST) += aarch64/neontest.o
OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp_init.o
......@@ -35,7 +34,6 @@ NEON-OBJS-$(CONFIG_H264PRED) += aarch64/h264pred_neon.o
NEON-OBJS-$(CONFIG_H264QPEL) += aarch64/h264qpel_neon.o \
aarch64/hpeldsp_neon.o
NEON-OBJS-$(CONFIG_HPELDSP) += aarch64/hpeldsp_neon.o
NEON-OBJS-$(CONFIG_IMDCT15) += aarch64/imdct15_neon.o
NEON-OBJS-$(CONFIG_MDCT) += aarch64/mdct_neon.o
NEON-OBJS-$(CONFIG_MPEGAUDIODSP) += aarch64/mpegaudiodsp_neon.o
......
/*
* 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 <stddef.h>
#include "libavutil/cpu.h"
#include "libavutil/aarch64/cpu.h"
#include "libavutil/internal.h"
#include "libavcodec/imdct15.h"
#include "asm-offsets.h"
AV_CHECK_OFFSET(IMDCT15Context, exptab, CELT_EXPTAB);
AV_CHECK_OFFSET(IMDCT15Context, fft_n, CELT_FFT_N);
AV_CHECK_OFFSET(IMDCT15Context, len2, CELT_LEN2);
AV_CHECK_OFFSET(IMDCT15Context, len4, CELT_LEN4);
AV_CHECK_OFFSET(IMDCT15Context, tmp, CELT_TMP);
AV_CHECK_OFFSET(IMDCT15Context, twiddle_exptab, CELT_TWIDDLE);
void ff_celt_imdct_half_neon(IMDCT15Context *s, float *dst, const float *src,
ptrdiff_t stride, float scale);
void ff_imdct15_init_aarch64(IMDCT15Context *s)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
s->imdct_half = ff_celt_imdct_half_neon;
}
}
This diff is collapsed.
......@@ -136,9 +136,6 @@ av_cold int ff_imdct15_init(IMDCT15Context **ps, int N)
s->imdct_half = imdct15_half;
if (ARCH_AARCH64)
ff_imdct15_init_aarch64(s);
*ps = s;
return 0;
......
......@@ -51,7 +51,4 @@ int ff_imdct15_init(IMDCT15Context **s, int N);
*/
void ff_imdct15_uninit(IMDCT15Context **s);
void ff_imdct15_init_aarch64(IMDCT15Context *s);
#endif /* AVCODEC_IMDCT15_H */
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment