2023-11-12 19:56:32 +00:00
|
|
|
/*
|
|
|
|
|
* 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_scalarproduct_and_madd_int16_rvv, zve32x
|
|
|
|
|
vsetvli t0, zero, e32, m8, ta, ma
|
|
|
|
|
vmv.v.x v0, zero
|
|
|
|
|
1:
|
|
|
|
|
vsetvli t0, a3, e16, m4, tu, ma
|
|
|
|
|
vle16.v v8, (a0)
|
|
|
|
|
sub a3, a3, t0
|
|
|
|
|
vle16.v v16, (a1)
|
|
|
|
|
sh1add a1, t0, a1
|
|
|
|
|
vwmacc.vv v0, v8, v16
|
|
|
|
|
vle16.v v24, (a2)
|
|
|
|
|
sh1add a2, t0, a2
|
|
|
|
|
vmacc.vx v8, a4, v24
|
|
|
|
|
vse16.v v8, (a0)
|
|
|
|
|
sh1add a0, t0, a0
|
|
|
|
|
bnez a3, 1b
|
|
|
|
|
|
|
|
|
|
vsetvli t0, zero, e32, m8, ta, ma
|
|
|
|
|
vmv.s.x v8, zero
|
|
|
|
|
vredsum.vs v0, v0, v8
|
|
|
|
|
vmv.x.s a0, v0
|
|
|
|
|
ret
|
|
|
|
|
endfunc
|
2023-11-12 20:12:53 +00:00
|
|
|
|
|
|
|
|
func ff_scalarproduct_and_madd_int32_rvv, zve32x
|
|
|
|
|
vsetvli t0, zero, e32, m8, ta, ma
|
|
|
|
|
vmv.v.x v0, zero
|
|
|
|
|
1:
|
|
|
|
|
vsetvli t0, a3, e32, m8, tu, ma
|
|
|
|
|
vle16.v v8, (a0)
|
|
|
|
|
sub a3, a3, t0
|
|
|
|
|
vsext.vf2 v24, v8
|
|
|
|
|
vle32.v v16, (a1)
|
|
|
|
|
sh2add a1, t0, a1
|
|
|
|
|
vmacc.vv v0, v16, v24
|
|
|
|
|
vsetvli zero, zero, e16, m4, ta, ma
|
|
|
|
|
vle16.v v24, (a2)
|
|
|
|
|
sh1add a2, t0, a2
|
|
|
|
|
vmacc.vx v8, a4, v24
|
|
|
|
|
vse16.v v8, (a0)
|
|
|
|
|
sh1add a0, t0, a0
|
|
|
|
|
bnez a3, 1b
|
|
|
|
|
|
|
|
|
|
vsetvli t0, zero, e32, m8, ta, ma
|
|
|
|
|
vmv.s.x v8, zero
|
|
|
|
|
vredsum.vs v0, v0, v8
|
|
|
|
|
vmv.x.s a0, v0
|
|
|
|
|
ret
|
|
|
|
|
endfunc
|
