Re: [Algorithms] lights/shadows rendering architecture

[Megan F. <sha...@gm...>]

A stall happens when operations can't be parallelized, I thought - and
in this case, you can't parallel writing to the buffer and using it,
since it has to finish rendering before it can be read from in the
lighting operations.

(this sort of thing blew my original cloud scheme out of the water -
too many prior-render-dependant renders in a row)

On 9/21/05, Joris Mans <jor...@te...> wrote:
> > That means you'll have a pipeline doing:
> >
> > -Render shadowbuffer A
> > *stall*
> > -Use shadowbuffer A
> > -Render shadowbuffer B
> > *stall*
> > -Use shadowbuffer B
> > -Render shadowbuffer C
> > *stall*
> > -Use shadowbuffer C
> > etc.
> >
>
> Why would the system stall between rendering to shadowbuffer A and using
> it? Its not like the GPU renders a shadowbuffer which the CPU has to use
> afterwards. I presume it all gets batched up in the command queue of the
> GPU, and since there is only 1 GPU the shadowbuffer will be rendered
> before the commands using it will be issued, so no stall, right?
>
>
> Joris
>
>
>
> -------------------------------------------------------
> SF.Net email is sponsored by:
> Tame your development challenges with Apache's Geronimo App Server.
> Download it for free - -and be entered to win a 42" plasma tv or your ver=
y
> own Sony(tm)PSP.  Click here to play: http://sourceforge.net/geronimo.php
> _______________________________________________
> GDAlgorithms-list mailing list
> GDA...@li...
> https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list
> Archives:
> http://sourceforge.net/mailarchive/forum.php?forum_id=3D6188
>


--
-Megan Fox
Lead Developer, Elium Project
http://www.elium.tk