1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-02 03:06:28 +02:00
FFmpeg/libavcodec/riscv/vorbisdsp_rvv.S
Rémi Denis-Courmont a28aa0475d lavc/vorbisdsp: unroll RISC-V V inverse_coupling
This increases the group multiplier as per T-Head C910 benchmarks:

inverse_coupling_c: 4597.0
inverse_coupling_rvv_i32: 1312.7 (m1)
inverse_coupling_rvv_i32: 1116.7 (m2)
inverse_coupling_rvv_i32: 732.2  (m4)
inverse_coupling_rvv_i32: 898.0  (m8)
2023-07-16 23:24:00 +03:00

44 lines
1.4 KiB
ArmAsm

/*
* 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 "libavutil/riscv/asm.S"
func ff_vorbis_inverse_coupling_rvv, zve32f
fmv.w.x ft0, zero
1:
vsetvli t0, a2, e32, m4, ta, ma
vle32.v v16, (a1)
sub a2, a2, t0
vle32.v v24, (a0)
vfmax.vf v8, v16, ft0
vfmin.vf v16, v16, ft0
vfsgnj.vv v8, v8, v24
vfsgnj.vv v16, v16, v24
vfsub.vv v8, v24, v8
vfsub.vv v24, v24, v16
vse32.v v8, (a1)
sh2add a1, t0, a1
vse32.v v24, (a0)
sh2add a0, t0, a0
bnez a2, 1b
ret
endfunc