mirror of https://github.com/FFmpeg/FFmpeg.git
flac_decorrelate_ms_16_c: 457.2 flac_decorrelate_ms_16_rvv_i32: 203.0 flac_decorrelate_ms_32_c: 457.2 flac_decorrelate_ms_32_rvv_i32: 203.5 flac_decorrelate_rs_16_c: 456.2 flac_decorrelate_rs_16_rvv_i32: 207.0 flac_decorrelate_rs_32_c: 456.2 flac_decorrelate_rs_32_rvv_i32: 210.5release/7.0
parent
be1675035f
commit
636ae0e0bc
5 changed files with 173 additions and 0 deletions
@ -0,0 +1,55 @@ |
||||
/*
|
||||
* 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 "libavcodec/flacdsp.h" |
||||
|
||||
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_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); |
||||
|
||||
av_cold void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt, |
||||
int channels) |
||||
{ |
||||
#if HAVE_RVV && (__riscv_xlen >= 64) |
||||
int flags = av_get_cpu_flags(); |
||||
|
||||
if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) { |
||||
switch (fmt) { |
||||
case AV_SAMPLE_FMT_S16: |
||||
c->decorrelate[1] = ff_flac_decorrelate_ls_16_rvv; |
||||
c->decorrelate[2] = ff_flac_decorrelate_rs_16_rvv; |
||||
break; |
||||
case AV_SAMPLE_FMT_S32: |
||||
c->decorrelate[1] = ff_flac_decorrelate_ls_32_rvv; |
||||
c->decorrelate[2] = ff_flac_decorrelate_rs_32_rvv; |
||||
break; |
||||
} |
||||
} |
||||
#endif |
||||
} |
@ -0,0 +1,113 @@ |
||||
/* |
||||
* 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 "libavutil/riscv/asm.S" |
||||
|
||||
#if (__riscv_xlen == 64) |
||||
func ff_flac_decorrelate_ls_16_rvv, zve32x |
||||
ld a0, (a0) |
||||
ld a2, 8(a1) |
||||
ld a1, (a1) |
||||
1: |
||||
vsetvli t0, a3, e32, m8, ta, ma |
||||
vle32.v v0, (a1) |
||||
sub a3, a3, t0 |
||||
vle32.v v8, (a2) |
||||
sh2add a1, t0, a1 |
||||
vsll.vx v0, v0, a4 |
||||
sh2add a2, t0, a2 |
||||
vsll.vx v8, v8, a4 |
||||
vsub.vv v8, v0, v8 |
||||
vsetvli zero, zero, e16, m4, ta, ma |
||||
vncvt.x.x.w v16, v0 |
||||
vncvt.x.x.w v20, v8 |
||||
vsseg2e16.v v16, (a0) |
||||
sh2add a0, t0, a0 |
||||
bnez a3, 1b |
||||
|
||||
ret |
||||
endfunc |
||||
|
||||
func ff_flac_decorrelate_rs_16_rvv, zve32x |
||||
ld a0, (a0) |
||||
ld a2, 8(a1) |
||||
ld a1, (a1) |
||||
1: |
||||
vsetvli t0, a3, e32, m8, ta, ma |
||||
vle32.v v0, (a1) |
||||
sub a3, a3, t0 |
||||
vle32.v v8, (a2) |
||||
sh2add a1, t0, a1 |
||||
vsll.vx v0, v0, a4 |
||||
sh2add a2, t0, a2 |
||||
vsll.vx v8, v8, a4 |
||||
vadd.vv v0, v0, v8 |
||||
vsetvli zero, zero, e16, m4, ta, ma |
||||
vncvt.x.x.w v16, v0 |
||||
vncvt.x.x.w v20, v8 |
||||
vsseg2e16.v v16, (a0) |
||||
sh2add a0, t0, a0 |
||||
bnez a3, 1b |
||||
|
||||
ret |
||||
endfunc |
||||
|
||||
func ff_flac_decorrelate_ls_32_rvv, zve32x |
||||
ld a0, (a0) |
||||
ld a2, 8(a1) |
||||
ld a1, (a1) |
||||
1: |
||||
vsetvli t0, a3, e32, m4, ta, ma |
||||
vle32.v v0, (a1) |
||||
sub a3, a3, t0 |
||||
vle32.v v4, (a2) |
||||
sh2add a1, t0, a1 |
||||
vsll.vx v0, v0, a4 |
||||
sh2add a2, t0, a2 |
||||
vsll.vx v4, v4, a4 |
||||
vsub.vv v4, v0, v4 |
||||
vsseg2e32.v v0, (a0) |
||||
sh3add a0, t0, a0 |
||||
bnez a3, 1b |
||||
|
||||
ret |
||||
endfunc |
||||
|
||||
func ff_flac_decorrelate_rs_32_rvv, zve32x |
||||
ld a0, (a0) |
||||
ld a2, 8(a1) |
||||
ld a1, (a1) |
||||
1: |
||||
vsetvli t0, a3, e32, m4, ta, ma |
||||
vle32.v v0, (a1) |
||||
sub a3, a3, t0 |
||||
vle32.v v4, (a2) |
||||
sh2add a1, t0, a1 |
||||
vsll.vx v0, v0, a4 |
||||
sh2add a2, t0, a2 |
||||
vsll.vx v4, v4, a4 |
||||
vadd.vv v0, v0, v4 |
||||
vsseg2e32.v v0, (a0) |
||||
sh3add a0, t0, a0 |
||||
bnez a3, 1b |
||||
|
||||
ret |
||||
endfunc |
||||
#endif |
Loading…
Reference in new issue