[FFmpeg-devel] [PATCH 1/5] libavutil: Add fixed_dsp

[Nedeljko Babic]

>> From: Nedeljko Babic <nbabic at mips.com>
>> 
>> Signed-off-by: Nedeljko Babic <nbabic at mips.com>
>> ---
>>  libavutil/Makefile    |   1 +
>>  libavutil/fixed_dsp.c |  96 +++++++++++++++++++++++++++++++++++++++
>>  libavutil/fixed_dsp.h | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++
>>  libavutil/version.h   |   2 +-
>>  4 files changed, 221 insertions(+), 1 deletion(-)
>>  create mode 100644 libavutil/fixed_dsp.c
>>  create mode 100644 libavutil/fixed_dsp.h
>> 
>> diff --git a/libavutil/Makefile b/libavutil/Makefile
>> index 9340ee4..bc32fc0 100644
>> --- a/libavutil/Makefile
>> +++ b/libavutil/Makefile
>> @@ -86,6 +86,7 @@ OBJS = adler32.o                                                        \
>>         file.o                                                           \
>>         file_open.o                                                      \
>>         float_dsp.o                                                      \
>> +       fixed_dsp.o                                                      \
>>         frame.o                                                          \
>>         hash.o                                                           \
>>         hmac.o                                                           \
>> diff --git a/libavutil/fixed_dsp.c b/libavutil/fixed_dsp.c
>> new file mode 100644
>> index 0000000..936f4f7
>> --- /dev/null
>> +++ b/libavutil/fixed_dsp.c
>> @@ -0,0 +1,96 @@
>> +/*
>> + * Copyright (c) 2012
>> + *      MIPS Technologies, Inc., California.
>> + *
>> + * Redistribution and use in source and binary forms, with or without
>> + * modification, are permitted provided that the following conditions
>> + * are met:
>> + * 1. Redistributions of source code must retain the above copyright
>> + *    notice, this list of conditions and the following disclaimer.
>> + * 2. Redistributions in binary form must reproduce the above copyright
>> + *    notice, this list of conditions and the following disclaimer in the
>> + *    documentation and/or other materials provided with the distribution.
>> + * 3. Neither the name of the MIPS Technologies, Inc., nor the names of its
>> + *    contributors may be used to endorse or promote products derived from
>> + *    this software without specific prior written permission.
>> + *
>> + * THIS SOFTWARE IS PROVIDED BY THE MIPS TECHNOLOGIES, INC. ``AS IS'' AND
>> + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
>> + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
>> + * ARE DISCLAIMED.  IN NO EVENT SHALL THE MIPS TECHNOLOGIES, INC. BE LIABLE
>> + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
>> + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
>> + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
>> + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
>> + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
>> + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
>> + * SUCH DAMAGE.
>> + *
>> + * Author:  Nedeljko Babic (nbabic at mips.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 "fixed_dsp.h"
>> +
>> +static void vector_fmul_window_fixed_scaled_c(int16_t *dst, const int32_t *src0,
>> +                                       const int32_t *src1, const int32_t *win,
>> +                                       int len, uint8_t bits)
>> +{
>> +    int32_t s0, s1, wi, wj, i,j, round;
>> +
>> +    dst += len;
>> +    win += len;
>> +    src0+= len;
>> +    round = bits? 1 << (bits-1) : 0;
>> +
>> +    for (i=-len, j=len-1; i<0; i++, j--) {
>> +        s0 = src0[i];
>> +        s1 = src1[j];
>> +        wi = win[i];
>> +        wj = win[j];
>> +        dst[i] = av_clip_int16_c(((((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31) + round) >> bits);
>> +        dst[j] = av_clip_int16_c(((((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31) + round) >> bits);
>> +    }
>> +}
>> +
>> +static void vector_fmul_window_fixed_c(int32_t *dst, const int32_t *src0,
>> +                                       const int32_t *src1, const int32_t *win,
>> +                                       int len)
>> +{
>> +    int32_t s0, s1, wi, wj, i, j;
>> +
>> +    dst += len;
>> +    win += len;
>> +    src0+= len;
>> +
>> +    for (i=-len, j=len-1; i<0; i++, j--) {
>> +        s0 = src0[i];
>> +        s1 = src1[j];
>> +        wi = win[i];
>> +        wj = win[j];
>> +        dst[i] = ((int64_t)s0*wj - (int64_t)s1*wi + 0x40000000) >> 31;
>> +        dst[j] = ((int64_t)s0*wi + (int64_t)s1*wj + 0x40000000) >> 31;
>> +    }
>> +}
>> +
>
>> +AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact)
>> +{
>> +    AVFixedDSPContext * fdsp = (AVFixedDSPContext*)av_malloc(sizeof(AVFixedDSPContext));
>> +    fdsp->vector_fmul_window_fixed_scaled = vector_fmul_window_fixed_scaled_c;
>> +    fdsp->vector_fmul_window_fixed = vector_fmul_window_fixed_c;
>> +}
>
>ffmpeg/libavutil/fixed_dsp.c:96:1: error: control reaches end of non-void function [-Werror=return-type]
>

Sorry. This will be fixed.

>
>> +
>> +static av_always_inline int fixed_sqrt(int x, int bits)
>> +{
>
>some documentation for this could be helpfull

Documentation will be added.

>also i suspect this can be implemented faster using different
>algorithms for larger bits

We will check this.

Thanks,
Nedeljko