83cd80d10a
* commit '12004a9a7f20e44f4da2ee6c372d5e1794c8d6c5': audiodsp/x86: yasmify vector_clipf_sse audiodsp: reorder arguments for vector_clipf Merged the version from Libav after a discussion with James Almer on IRC: 19:22 <ubitux> jamrial: opinion on 12004a9a7f20e44f4da2ee6c372d5e1794c8d6c5? 19:23 <ubitux> it was apparently yasmified differently 19:23 <ubitux> (it depends on the previous commit arg shuffle) 19:24 <ubitux> i don't see the magic movsxdifnidn in your port btw 19:24 <ubitux> it's a port from 1d36defe94c7d7ebf995d4dbb4f878d06272f9c6 19:25 <jamrial> seems better thanks to said arg shuffle 19:25 <jamrial> the loop is the same, but init is simpler 19:25 <jamrial> probably worth merging 19:25 <ubitux> OK 19:25 <ubitux> thanks 19:26 <jamrial> curious they didn't make len ptrdiff_t after the previous bunch of commits, heh 19:26 <ubitux> yeah indeed Both commits are merged at the same time to prevent a conflict with our existing yasmified ff_vector_clipf_sse. Merged-by: Clément Bœsch <u@pkh.me>
64 lines
2.2 KiB
ArmAsm
64 lines
2.2 KiB
ArmAsm
/*
|
|
* ARM NEON optimised audio functions
|
|
* Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
|
|
*
|
|
* 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/arm/asm.S"
|
|
|
|
function ff_vector_clipf_neon, export=1
|
|
VFP vdup.32 q1, d0[1]
|
|
VFP vdup.32 q0, d0[0]
|
|
NOVFP vdup.32 q0, r3
|
|
NOVFP vld1.32 {d2[],d3[]}, [sp]
|
|
vld1.f32 {q2},[r1,:128]!
|
|
vmin.f32 q10, q2, q1
|
|
vld1.f32 {q3},[r1,:128]!
|
|
vmin.f32 q11, q3, q1
|
|
1: vmax.f32 q8, q10, q0
|
|
vmax.f32 q9, q11, q0
|
|
subs r2, r2, #8
|
|
beq 2f
|
|
vld1.f32 {q2},[r1,:128]!
|
|
vmin.f32 q10, q2, q1
|
|
vld1.f32 {q3},[r1,:128]!
|
|
vmin.f32 q11, q3, q1
|
|
vst1.f32 {q8},[r0,:128]!
|
|
vst1.f32 {q9},[r0,:128]!
|
|
b 1b
|
|
2: vst1.f32 {q8},[r0,:128]!
|
|
vst1.f32 {q9},[r0,:128]!
|
|
bx lr
|
|
endfunc
|
|
|
|
function ff_vector_clip_int32_neon, export=1
|
|
vdup.32 q0, r2
|
|
vdup.32 q1, r3
|
|
ldr r2, [sp]
|
|
1:
|
|
vld1.32 {q2-q3}, [r1,:128]!
|
|
vmin.s32 q2, q2, q1
|
|
vmin.s32 q3, q3, q1
|
|
vmax.s32 q2, q2, q0
|
|
vmax.s32 q3, q3, q0
|
|
vst1.32 {q2-q3}, [r0,:128]!
|
|
subs r2, r2, #8
|
|
bgt 1b
|
|
bx lr
|
|
endfunc
|