ffmpeg/libavcodec/riscv/huffyuvdsp_rvv.S
Rémi Denis-Courmont 90a779bed6 lavc/huffyuvdsp: basic R-V V add_hfyu_left_pred_bgr32
Better performance can probably be achieved with a more intricate
unrolled loop, but this is a start:

add_hfyu_left_pred_bgr32_c: 15084.0
add_hfyu_left_pred_bgr32_rvv_i32: 10280.2

This would actually be cleaner with the RISC-V P extension, but that is
not ratified yet (I think?) and usually not supported if V is supported.
2023-11-15 16:51:07 +02:00

54 lines
1.5 KiB
ArmAsm

/*
* 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"
func ff_add_int16_rvv, zve32x
1:
vsetvli t0, a3, e16, m8, ta, ma
vle16.v v16, (a0)
sub a3, a3, t0
vle16.v v24, (a1)
sh1add a1, t0, a1
vadd.vv v16, v16, v24
vand.vx v16, v16, a2
vse16.v v16, (a0)
sh1add a0, t0, a0
bnez a3, 1b
ret
endfunc
func ff_add_hfyu_left_pred_bgr32_rvv, zve32x
vsetivli zero, 4, e8, m1, ta, ma
vle8.v v8, (a3)
sh2add a2, a2, a1
1:
vle8.v v0, (a1)
vadd.vv v8, v8, v0
addi a1, a1, 4
vse8.v v8, (a0)
addi a0, a0, 4
bne a2, a1, 1b
vse8.v v8, (a3)
ret
endfunc