> >>> The only solution is a hardware accelerator.  IIUC, TI does currently 
> >>> sell a DSP that will do it.  Specifically one of the TMS320C64x line 
> >>> that runs at at least 600MHz.
> >>>
> >> This appears to be new and designed for this specific purpose:
> >>
> >> http://www.ti.com/lit/gpn/tms320dm642
> >>
> >> There are others in that family:
> >>
> >> http://focus.ti.com/paramsearch/docs/parametricsearch.tsp?family=dsp&sectionId=2&tabId=1857&familyId=749
> > 
> > http://focus.ti.com/docs/prod/folders/print/tms320dm642.html
> > click on benchmarks, which is
> > http://www-s.ti.com/sc/techlit/sprt379
> > 
> > says that the TMS320DM6446 only does 720p for mpeg2 amd mpeg4, and only
> > 720x480 for H.264.  I don't see a bitrate listed.  The bitrate makes a
> > lot of difference.
> > 
> > Am I looking at the correct benchmark pdf for the fastest chip?
> > (I'm not sure what the difference is between the dm642 and the DM6446 ?)
> > Am I misreading something?  Or otherwise missing something?
> > 
> > If there is a faster version that can decode 1080p, it might be a very
> > good solution.
> 
> There are faster Ti DSPs.  Actually, that chip is faster than the one 
> benchmarked.
> 
> http://focus.ti.com/docs/prod/folders/print/tms320c6454.html
> 
> http://focus.ti.com/docs/prod/folders/print/tms320c6455.html
> 
> However, I can't seem to find any information on whether or not they 
> will do H.264 HiP 1080p.

If you can dig out the instructions/second for the TMS320DM6446 and
for the fastest chip, then we could estimate what the fastest chip
might do.  I'm not sure how accurate the estimate would be, and we
don't know what bitrate their benchmarks used.

> And, they appear to be too expensive.

The quantity discounts are significant.  And if the TI chip can
decode and display video by itself, we don't need an ASIC.  We
could get a useful, sale-able product out the door sooner.

There may be things the TI DSP isn't good at.  CAD?  Google earth?
So we might still need an ASIC for a future board.
_______________________________________________
Open-graphics mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-graphics
List service provided by Duskglow Consulting, LLC (www.duskglow.com)

Reply via email to