On 3/18/07, Dieter <[EMAIL PROTECTED]> wrote:


One way to parallelize a process is splitting it up into pieces
that can run independently in serial, then running it on a SMP
machine.  AMD's x2 chips are coming down in price, and x4 chips

There are some things, like raytracing, that are "embarrassingly
parallel", which are very easy to split up into numerous independent
subproblems.  But the majority of problems are not like this.
Parallelizing certain problems can be very challenging or impossible.

I get the impression that some of these video codecs require too much
global information.  For instance, where there is metadata that
indicates that a large portion of the image has undergone a simple
translation, you can't split up the problem into decoding different
slices of the image.  Each slice will need to know too much about
every other slice.

--
Timothy Normand Miller
http://www.cse.ohio-state.edu/~millerti
Favorite book:  The Design of Everyday Things, Donald A. Norman, ISBN
0-465-06710-7
_______________________________________________
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