/*****************************************************************************
* amplify.S: RISC-V V software amplification
******************************************************************************
* 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 rvv_amplify_f32
lpad 0
srli a2, a2, 2
#if defined (__riscv_float_abi_soft)
fmv.w.x fa0, a3
#endif
1:
vsetvli t0, a2, e32, m8, ta, ma
vle32.v v16, (a1)
sh2add a1, t0, a1
vfmul.vf v16, v16, fa0
sub a2, a2, t0
vse32.v v16, (a0)
sh2add a0, t0, a0
bnez a2, 1b
ret
endfunc
func rvv_amplify_f64
lpad 0
srli a2, a2, 3
#if defined (__riscv_float_abi_soft) || defined (__riscv_float_abi_single)
fmv.d.x fa0, a3
#endif
1:
vsetvli t0, a2, e64, m8, ta, ma
vle64.v v16, (a1)
sh3add a1, t0, a1
vfmul.vf v16, v16, fa0
sub a2, a2, t0
vse64.v v16, (a0)
sh3add a0, t0, a0
bnez a2, 1b
ret
endfunc
func rvv_amplify_i16
lpad 0
srli a2, a2, 1
1:
vsetvli t0, a2, e16, m8, ta, ma
vle16.v v16, (a1)
sh1add a1, t0, a1
vmulhsu.vx v16, v16, a3
sub a2, a2, t0
vse16.v v16, (a0)
sh1add a0, t0, a0
bnez a2, 1b
ret
endfunc
func rvv_amplify_i32
lpad 0
srli a2, a2, 2
1:
vsetvli t0, a2, e32, m8, ta, ma
vle32.v v16, (a1)
sh2add a1, t0, a1
vmulhsu.vx v16, v16, a3
sub a2, a2, t0
vse32.v v16, (a0)
sh2add a0, t0, a0
bnez a2, 1b
ret
endfunc
func rvv_amplify_u8
lpad 0
1:
vsetvli t0, a2, e8, m8, ta, ma
vle8.v v16, (a1)
add a1, a1, t0
vmulhu.vx v16, v16, a3
sub a2, a2, t0
vse8.v v16, (a0)
add a0, a0, t0
bnez a2, 1b
ret
endfunc
¤ Dauer der Verarbeitung: 0.0 Sekunden
(vorverarbeitet am 2026-11-04)
¤
*© Formatika GbR, Deutschland
|
|