On Wed, 23 Jan 2008 12:16:40 -0700
James Richard Tyrer <[EMAIL PROTECTED]> wrote:


> >> This would appear to be a motion compensation issue.  IIUC, TI went
> >> to hardware motion compensation for the TMS320DM6467.
> > 
> > Where do you see hardware motion compensation?
> 
>       http://focus.ti.com/lit/ml/sprn249/sprn249.pdf


Ok. i didnt read the marketing blah.
 
> > The TMS320DM6467 looks to me just like a VLIW DSP combined with an
> > ARM chip and a lot of peripherial stuff. No fancy decoder unit.
> 
> Read more!  It also includes
> 
>       Dual Programmable High-Definition Video Image Co-Processor
>       (HDVICP) Engines
> 
>       Video Data Conversion Engine (VDCE)
>               Horizontal and Vertical Downscaling
>               Chroma Conversion (4:2:2↔4:2:0)


Yes, but what does it do exactly? and how is it programmed?
These are the interesting questions. There is no real information
out there. The best thing i could find on the web was a video
on youtube!
Though, i actually dont want to know as i might be tainted
by that knowledge.

> > BTW: What is a hardware motion compensation for you? I ask because 
> > the process of motion compensation is something that looks always
> > very similar, no matter how much you do in hardware.
> > 
> Hardware motion compensation would be motion compensation done (or 
> partially done) by hardware dedicated to that use only.

Uhm.. i dont want to be picky, but do you count a general purpose
CPU as an hardware motion compensation unit, if it is dedicated
for that use only?

                                Attila Kinali

-- 
Linux ist... wenn man einfache Dinge auch mit einer kryptischen
post-fix Sprache loesen kann
                        -- Daniel Hottinger
_______________________________________________
Open-hardware mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-hardware

Reply via email to