[FFmpeg-devel] [PATCH 1/2] lavfi/transpose: support slice threading

[Paul B Mahol]

On 8/15/13, Michael Niedermayer <michaelni at gmx.at> wrote:
> On Wed, Aug 14, 2013 at 09:39:32PM +0000, Paul B Mahol wrote:
>> Signed-off-by: Paul B Mahol <onemda at gmail.com>
>> ---
>>  libavfilter/vf_transpose.c | 72
>> ++++++++++++++++++++++++++++++----------------
>>  1 file changed, 47 insertions(+), 25 deletions(-)
>>
>> diff --git a/libavfilter/vf_transpose.c b/libavfilter/vf_transpose.c
>> index 3ee9c6d..82f68e5 100644
>> --- a/libavfilter/vf_transpose.c
>> +++ b/libavfilter/vf_transpose.c
>> @@ -133,31 +133,19 @@ static AVFrame *get_video_buffer(AVFilterLink
>> *inlink, int w, int h)
>>          ff_default_get_video_buffer(inlink, w, h);
>>  }
>>
>> -static int filter_frame(AVFilterLink *inlink, AVFrame *in)
>> +typedef struct ThreadData {
>> +    AVFrame *in, *out;
>> +} ThreadData;
>> +
>> +static int filter_slice(AVFilterContext *ctx, void *arg, int jobnr,
>> +                        int nb_jobs)
>>  {
>> -    TransContext *trans = inlink->dst->priv;
>> -    AVFilterLink *outlink = inlink->dst->outputs[0];
>> -    AVFrame *out;
>> +    TransContext *trans = ctx->priv;
>> +    ThreadData *td = arg;
>> +    AVFrame *out = td->out;
>> +    AVFrame *in = td->in;
>>      int plane;
>>
>> -    if (trans->passthrough)
>> -        return ff_filter_frame(outlink, in);
>> -
>> -    out = ff_get_video_buffer(outlink, outlink->w, outlink->h);
>> -    if (!out) {
>> -        av_frame_free(&in);
>> -        return AVERROR(ENOMEM);
>> -    }
>> -
>> -    out->pts = in->pts;
>> -
>> -    if (in->sample_aspect_ratio.num == 0) {
>> -        out->sample_aspect_ratio = in->sample_aspect_ratio;
>> -    } else {
>> -        out->sample_aspect_ratio.num = in->sample_aspect_ratio.den;
>> -        out->sample_aspect_ratio.den = in->sample_aspect_ratio.num;
>> -    }
>> -
>>      for (plane = 0; out->data[plane]; plane++) {
>>          int hsub = plane == 1 || plane == 2 ? trans->hsub : 0;
>>          int vsub = plane == 1 || plane == 2 ? trans->vsub : 0;
>> @@ -165,12 +153,14 @@ static int filter_frame(AVFilterLink *inlink,
>> AVFrame *in)
>>          int inh  = in->height  >> vsub;
>>          int outw = FF_CEIL_RSHIFT(out->width,  hsub);
>>          int outh = FF_CEIL_RSHIFT(out->height, vsub);
>> +        int start = (outh *  jobnr   ) / nb_jobs;
>> +        int end   = (outh * (jobnr+1)) / nb_jobs;
>
> squares should be faster than long thin rectangles
> (this should be also true for the single thread case)

Sorry this does not make any sense to me.
If you got idea how to do it better than either go and do it or say
exactly what should be done and why.