audiodsp_neon.S 2.17 KB
Newer Older
1 2 3 4
/*
 * ARM NEON optimised audio functions
 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
 *
5
 * This file is part of FFmpeg.
6
 *
7
 * FFmpeg is free software; you can redistribute it and/or
8 9 10 11
 * 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.
 *
12
 * FFmpeg is distributed in the hope that it will be useful,
13 14 15 16 17
 * 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
18
 * License along with FFmpeg; if not, write to the Free Software
19 20 21 22 23 24 25 26
 * 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]
27 28
NOVFP   vdup.32         q0,  r3
NOVFP   vld1.32         {d2[],d3[]}, [sp]
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
        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