1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-18 03:19:31 +02:00
FFmpeg/libavcodec/riscv/audiodsp_rvv.S
Rémi Denis-Courmont 3575ee2ea3 lavc/audiodsp: unroll RISC-V clip functions
audiodsp.vector_clip_int32_c: 17500.7
audiodsp.vector_clip_int32_rvv_i32: 8404.7  (m1)
audiodsp.vector_clip_int32_rvv_i32: 2689.9  (m8)

audiodsp.vector_clipf_c: 33679.7
audiodsp.vector_clipf_rvf: 7019.7
audiodsp.vector_clipf_rvv_f32: 8328.0       (m1)
audiodsp.vector_clipf_rvv_f32: 2209.4       (m8)
2023-10-02 18:07:54 +03:00

74 lines
2.0 KiB
ArmAsm

/*
* Copyright © 2022 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_int16_rvv, zve32x
vsetvli t0, zero, e32, m8, ta, ma
vmv.v.x v8, zero
vmv.s.x v0, zero
1:
vsetvli t0, a2, e16, m4, tu, ma
vle16.v v16, (a0)
sub a2, a2, t0
vle16.v v24, (a1)
sh1add a0, t0, a0
vwmacc.vv v8, v16, v24
sh1add a1, t0, a1
bnez a2, 1b
vsetvli t0, zero, e32, m8, ta, ma
vredsum.vs v0, v8, v0
vmv.x.s a0, v0
ret
endfunc
func ff_vector_clip_int32_rvv, zve32x
1:
vsetvli t0, a4, e32, m8, ta, ma
vle32.v v8, (a1)
sub a4, a4, t0
vmax.vx v8, v8, a2
sh2add a1, t0, a1
vmin.vx v8, v8, a3
vse32.v v8, (a0)
sh2add a0, t0, a0
bnez a4, 1b
ret
endfunc
func ff_vector_clipf_rvv, zve32f
NOHWF fmv.w.x fa0, a3
NOHWF fmv.w.x fa1, a4
1:
vsetvli t0, a2, e32, m8, ta, ma
vle32.v v8, (a1)
sub a2, a2, t0
vfmax.vf v8, v8, fa0
sh2add a1, t0, a1
vfmin.vf v8, v8, fa1
vse32.v v8, (a0)
sh2add a0, t0, a0
bnez a2, 1b
ret
endfunc