/******************************************************************************
* rvv_merge.S: RISC-V Vector mean
******************************************************************************
* Copyright (C) 2022 Rémi Denis-Courmont
*
* This program 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.
*
* This program 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 this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301, USA.
*****************************************************************************/
#include "macros.S"
.option arch, +b, +v
func merge8_rvv
lpad 0
csrwi vxrm, 0
1:
vsetvli t0, a3, e8, m8, ta, ma
vle8.v v16, (a1)
add a1, a1, t0
vle8.v v24, (a2)
add a2, a2, t0
vaaddu.vv v16, v16, v24
sub a3, a3, t0
vse8.v v16, (a0)
add a0, a0, t0
bnez a3, 1b
ret
endfunc
func merge16_rvv
lpad 0
csrwi vxrm, 0
srli a3, a3, 1
1:
vsetvli t0, a3, e16, m8, ta, ma
vle16.v v16, (a1)
sh1add a1, t0, a1
vle16.v v24, (a2)
sh1add a2, t0, a2
vaaddu.vv v16, v16, v24
sub a3, a3, t0
vse16.v v16, (a0)
sh1add a0, t0, a0
bnez a3, 1b
ret
endfunc
¤ Dauer der Verarbeitung: 0.3 Sekunden
¤
*© Formatika GbR, Deutschland
|
|