1/*
2 * Copyright (c) 2010 Mans Rullgard <mans@mansr.com>
3 *
4 * This file is part of FFmpeg.
5 *
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21#include "asm.S"
22
23function ff_dca_lfe_fir_neon, export=1
24        push            {r4-r6,lr}
25
26        add             r4,  r0,  r3,  lsl #2   @ out2
27        add             r5,  r2,  #256*4-16     @ cf1
28        sub             r1,  r1,  #12
29        cmp             r3,  #32
30        moveq           r6,  #256/32
31        movne           r6,  #256/64
32NOVFP   vldr            d0,  [sp, #16]          @ scale, bias
33        mov             lr,  #-16
341:
35        vmov.f32        q2,  #0.0               @ v0
36        vmov.f32        q3,  #0.0               @ v1
37        mov             r12, r6
382:
39        vld1.32         {q8},     [r2,:128]!    @ cf0
40        vld1.32         {q9},     [r5,:128], lr @ cf1
41        vld1.32         {q1},     [r1], lr      @ in
42        subs            r12, r12, #4
43        vrev64.32       q10, q8
44        vmla.f32        q3,  q1,  q9
45        vmla.f32        d4,  d2,  d21
46        vmla.f32        d5,  d3,  d20
47        bne             2b
48
49        add             r1,  r1,  r6,  lsl #2
50        subs            r3,  r3,  #1
51        vadd.f32        d4,  d4,  d5
52        vadd.f32        d6,  d6,  d7
53        vpadd.f32       d4,  d4,  d6
54        vdup.32         d5,  d0[1]
55        vmla.f32        d5,  d4,  d0[0]
56        vst1.32         {d5[0]},  [r0,:32]!
57        vst1.32         {d5[1]},  [r4,:32]!
58        bne             1b
59
60        pop             {r4-r6,pc}
61endfunc
62