virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-21 10:55:51 +02:00
Code Issues Releases Activity

lavc/alacdsp: RISC-V V decorrelate_stereo

Browse Source 
To avoid data dependencies, this does the following unroll, which
requires one extra but probably free addition:

    coeff = (b * left_weight) >> decorr_shift;
    b += a;
    a -= coeff;
    b -= coeff;
    swap(a, b);
This commit is contained in:
Rémi Denis-Courmont 2022-10-04 20:17:16 +03:00 committed by Lynne
parent 23411e6dcd
commit 64ab577954
5 changed files with 91 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libavcodec/alacdsp.c
View File

@ -58,7 +58,9 @@ av_cold void ff_alacdsp_init(ALACDSPContext *c)
c->append_extra_bits[0] =
c->append_extra_bits[1] = append_extra_bits;
#if ARCH_X86
#if ARCH_RISCV
ff_alacdsp_init_riscv(c);
#elif ARCH_X86
ff_alacdsp_init_x86(c);
#endif
}

1
libavcodec/alacdsp.h
View File

@ -29,6 +29,7 @@ typedef struct ALACDSPContext {
} ALACDSPContext;
void ff_alacdsp_init(ALACDSPContext *c);
void ff_alacdsp_init_riscv(ALACDSPContext *c);
void ff_alacdsp_init_x86(ALACDSPContext *c);
#endif /* AVCODEC_ALACDSP_H */

2
libavcodec/riscv/Makefile
View File

@ -1,5 +1,7 @@
OBJS-$(CONFIG_AAC_DECODER) += riscv/aacpsdsp_init.o
RVV-OBJS-$(CONFIG_AAC_DECODER) += riscv/aacpsdsp_rvv.o
OBJS-$(CONFIG_ALAC_DECODER) += riscv/alacdsp_init.o
RVV-OBJS-$(CONFIG_ALAC_DECODER) += riscv/alacdsp_rvv.o
OBJS-$(CONFIG_AUDIODSP) += riscv/audiodsp_init.o \
riscv/audiodsp_rvf.o
RVV-OBJS-$(CONFIG_AUDIODSP) += riscv/audiodsp_rvv.o

39
libavcodec/riscv/alacdsp_init.c Normal file
View File

@ -0,0 +1,39 @@
/*
* Copyright © 2022 Rémi Denis-Courmont.
*
* 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 <stdint.h>
#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "libavcodec/avcodec.h"
#include "libavcodec/alacdsp.h"
void ff_alac_decorrelate_stereo_rvv(int32_t *buffer[2], int nb_samples,
int decorr_shift, int decorr_left_weight);
av_cold void ff_alacdsp_init_riscv(ALACDSPContext *c)
{
#if HAVE_RVV && (__riscv_xlen == 64)
int flags = av_get_cpu_flags();
if (flags & AV_CPU_FLAG_RVV_I32)
c->decorrelate_stereo = ff_alac_decorrelate_stereo_rvv;
#endif
}

46
libavcodec/riscv/alacdsp_rvv.S Normal file
View File

@ -0,0 +1,46 @@
/*
* Copyright © 2022 Rémi Denis-Courmont.
*
* 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/riscv/asm.S"
#if (__riscv_xlen == 64)
func ff_alac_decorrelate_stereo_rvv, zve32x
ld a4, 8(a0)
ld a0, 0(a0)
1:
vsetvli t0, a1, e32, m1, ta, ma
vle32.v v24, (a4)
sub a1, a1, t0
vle32.v v16, (a0)
vmul.vx v8, v24, a3
vadd.vv v24, v24, v16
vsra.vx v8, v8, a2
vsub.vv v16, v16, v8
vsub.vv v24, v24, v8
vse32.v v16, (a4)
sh2add a4, t0, a4
vse32.v v24, (a0)
sh2add a0, t0, a0
bnez a1, 1b
ret
endfunc
#endif