1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-02 03:06:28 +02:00
FFmpeg/libavcodec/riscv/vp9_mc_rvi.S
sunyuechi b82d9f55d1 lavc/vp9dsp: R-V mc copy
C908:
vp9_put4_8bpp_c: 0.7
vp9_put4_8bpp_rvi: 0.5
vp9_put8_8bpp_c: 2.5
vp9_put8_8bpp_rvi: 0.5
vp9_put16_8bpp_c: 16.7
vp9_put16_8bpp_rvi: 1.5
vp9_put32_8bpp_c: 37.2
vp9_put32_8bpp_rvi: 5.7
vp9_put64_8bpp_c: 107.5
vp9_put64_8bpp_rvi: 21.7

Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>
2024-05-15 19:52:28 +03:00

106 lines
2.7 KiB
ArmAsm

/*
* Copyright (c) 2024 Institue of Software Chinese Academy of Sciences (ISCAS).
*
* 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_copy64_rvi
1:
addi a4, a4, -1
ld t0, (a2)
ld t1, 8(a2)
ld t2, 16(a2)
ld t3, 24(a2)
ld t4, 32(a2)
ld t5, 40(a2)
ld t6, 48(a2)
ld a7, 56(a2)
sd t0, (a0)
sd t1, 8(a0)
sd t2, 16(a0)
sd t3, 24(a0)
sd t4, 32(a0)
sd t5, 40(a0)
sd t6, 48(a0)
sd a7, 56(a0)
add a2, a2, a3
add a0, a0, a1
bnez a4, 1b
ret
endfunc
func ff_copy32_rvi
1:
addi a4, a4, -1
ld t0, (a2)
ld t1, 8(a2)
ld t2, 16(a2)
ld t3, 24(a2)
sd t0, (a0)
sd t1, 8(a0)
sd t2, 16(a0)
sd t3, 24(a0)
add a2, a2, a3
add a0, a0, a1
bnez a4, 1b
ret
endfunc
func ff_copy16_rvi
1:
addi a4, a4, -1
ld t0, (a2)
ld t1, 8(a2)
sd t0, (a0)
sd t1, 8(a0)
add a2, a2, a3
add a0, a0, a1
bnez a4, 1b
ret
endfunc
func ff_copy8_rvi
1:
addi a4, a4, -1
ld t0, (a2)
sd t0, (a0)
add a2, a2, a3
add a0, a0, a1
bnez a4, 1b
ret
endfunc
#endif
func ff_copy4_rvi
1:
addi a4, a4, -1
lw t0, (a2)
sw t0, (a0)
add a2, a2, a3
add a0, a0, a1
bnez a4, 1b
ret
endfunc