fmtconvert_neon.S 2.71 KB
Newer Older
1 2 3 4 5
/*
 * ARM NEON optimised Format Conversion Utils
 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
 * Copyright (c) 2015 Janne Grunau  <janne-libav@jannau.net>
 *
6
 * This file is part of FFmpeg.
7
 *
8
 * FFmpeg is free software; you can redistribute it and/or
9 10 11 12
 * 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.
 *
13
 * FFmpeg is distributed in the hope that it will be useful,
14 15 16 17 18
 * 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
19
 * License along with FFmpeg; if not, write to the Free Software
20 21 22 23 24 25 26 27 28 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 64 65 66 67 68 69 70 71 72 73 74 75 76
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "config.h"
#include "libavutil/aarch64/asm.S"

function ff_int32_to_float_fmul_scalar_neon, export=1
        ld1             {v1.4s,v2.4s}, [x1], #32
        scvtf           v1.4s,  v1.4s
        scvtf           v2.4s,  v2.4s
1:
        subs            w2,  w2,  #8
        fmul            v3.4s,  v1.4s,  v0.s[0]
        fmul            v4.4s,  v2.4s,  v0.s[0]
        b.le            2f
        ld1             {v1.4s,v2.4s}, [x1], #32
        st1             {v3.4s,v4.4s}, [x0], #32
        scvtf           v1.4s,  v1.4s
        scvtf           v2.4s,  v2.4s
        b               1b
2:
        st1             {v3.4s,v4.4s}, [x0]
        ret
endfunc

function ff_int32_to_float_fmul_array8_neon, export=1
        lsr             w4,  w4,  #3
        subs            w5,  w4,  #1
        b.eq            1f
2:
        ld1             {v0.4s,v1.4s}, [x2], #32
        ld1             {v2.4s,v3.4s}, [x2], #32
        scvtf           v0.4s,  v0.4s
        scvtf           v1.4s,  v1.4s
        ld1             {v16.2s},  [x3], #8
        scvtf           v2.4s,  v2.4s
        scvtf           v3.4s,  v3.4s
        fmul            v4.4s,  v0.4s,  v16.s[0]
        fmul            v5.4s,  v1.4s,  v16.s[0]
        fmul            v6.4s,  v2.4s,  v16.s[1]
        fmul            v7.4s,  v3.4s,  v16.s[1]
        st1             {v4.4s,v5.4s}, [x1], #32
        st1             {v6.4s,v7.4s}, [x1], #32
        subs            w5,  w5,  #2
        b.gt            2b
        b.eq            1f
        ret
1:
        ld1             {v0.4s,v1.4s}, [x2]
        ld1             {v16.s}[0],  [x3]
        scvtf           v0.4s,  v0.4s
        scvtf           v1.4s,  v1.4s
        fmul            v4.4s,  v0.4s,  v16.s[0]
        fmul            v5.4s,  v1.4s,  v16.s[0]
        st1             {v4.4s,v5.4s}, [x1]
        ret
endfunc