1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-26 19:01:44 +02:00
FFmpeg/libavcodec/riscv/flacdsp_init.c
Rémi Denis-Courmont ca664f2254 lavc/flacdsp: R-V V LPC16 function
In this case, the inner loop computing the scalar product can be reduced
to just one multiplication and one sum even with 128-bit vectors. The
result is a lot simpler, but also brings more modest performance gains:

flac_lpc_16_13_c:       15241.0
flac_lpc_16_13_rvv_i32: 11230.0
flac_lpc_16_16_c:       17884.0
flac_lpc_16_16_rvv_i32: 12125.7
flac_lpc_16_29_c:       27847.7
flac_lpc_16_29_rvv_i32: 10494.0
flac_lpc_16_32_c:       30051.5
flac_lpc_16_32_rvv_i32: 10355.0
2023-11-18 22:06:57 +02:00

125 lines
5.2 KiB
C

/*
* Copyright © 2023 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/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/riscv/cpu.h"
#include "libavcodec/flacdsp.h"
void ff_flac_lpc16_rvv(int32_t *decoded, const int coeffs[32],
int pred_order, int qlevel, int len);
void ff_flac_lpc32_rvv(int32_t *decoded, const int coeffs[32],
int pred_order, int qlevel, int len);
void ff_flac_lpc32_rvv_simple(int32_t *decoded, const int coeffs[32],
int pred_order, int qlevel, int len);
void ff_flac_decorrelate_indep2_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep4_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep6_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep8_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_ls_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_rs_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_ms_16_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep2_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep4_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep6_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_indep8_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_ls_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_rs_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
void ff_flac_decorrelate_ms_32_rvv(uint8_t **out, int32_t **in,
int channels, int len, int shift);
av_cold void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt,
int channels)
{
#if HAVE_RVV
int flags = av_get_cpu_flags();
if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) {
int vlenb = ff_get_rv_vlenb();
if (vlenb >= 16) {
c->lpc16 = ff_flac_lpc16_rvv;
# if (__riscv_xlen >= 64)
if (vlenb > 16)
c->lpc32 = ff_flac_lpc32_rvv_simple;
else
c->lpc32 = ff_flac_lpc32_rvv;
}
switch (fmt) {
case AV_SAMPLE_FMT_S16:
switch (channels) {
case 2:
c->decorrelate[0] = ff_flac_decorrelate_indep2_16_rvv;
break;
case 4:
c->decorrelate[0] = ff_flac_decorrelate_indep4_16_rvv;
break;
case 6:
c->decorrelate[0] = ff_flac_decorrelate_indep6_16_rvv;
break;
case 8:
c->decorrelate[0] = ff_flac_decorrelate_indep8_16_rvv;
break;
}
c->decorrelate[1] = ff_flac_decorrelate_ls_16_rvv;
c->decorrelate[2] = ff_flac_decorrelate_rs_16_rvv;
c->decorrelate[3] = ff_flac_decorrelate_ms_16_rvv;
break;
case AV_SAMPLE_FMT_S32:
switch (channels) {
case 2:
c->decorrelate[0] = ff_flac_decorrelate_indep2_32_rvv;
break;
case 4:
c->decorrelate[0] = ff_flac_decorrelate_indep4_32_rvv;
break;
case 6:
c->decorrelate[0] = ff_flac_decorrelate_indep6_32_rvv;
break;
case 8:
c->decorrelate[0] = ff_flac_decorrelate_indep8_32_rvv;
break;
}
c->decorrelate[1] = ff_flac_decorrelate_ls_32_rvv;
c->decorrelate[2] = ff_flac_decorrelate_rs_32_rvv;
c->decorrelate[3] = ff_flac_decorrelate_ms_32_rvv;
break;
# endif
}
}
#endif
}