mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-23 07:42:51 +00:00
61e5ca4ded
This cannot beat the Zbb implementation, and it is unlikely that a real meaningful CPU design would support V and not Zbb. The best loop rewrite that I could come up with (4 shifts, 2 ands, 3 ors) is still ~40% slower than Zbb. A proper faster vector implementation should be feasible with the cryptographic vector extensions, but that is a story for another time.
39 lines
1.2 KiB
ArmAsm
39 lines
1.2 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 "config.h"
|
|
#include "libavutil/riscv/asm.S"
|
|
|
|
func ff_bswap16_buf_rvv, zve32x
|
|
1:
|
|
vsetvli t0, a2, e16, m8, ta, ma
|
|
vle16.v v8, (a1)
|
|
sub a2, a2, t0
|
|
vsll.vi v16, v8, 8
|
|
sh1add a1, t0, a1
|
|
vsrl.vi v24, v8, 8
|
|
vor.vv v8, v16, v24
|
|
vse16.v v8, (a0)
|
|
sh1add a0, t0, a0
|
|
bnez a2, 1b
|
|
|
|
ret
|
|
endfunc
|