On 12/4/05, Attila Kinali <[EMAIL PROTECTED]> wrote:
> On Sat, 26 Nov 2005 13:14:31 -0500
> Timothy Miller <[EMAIL PROTECTED]> wrote:
>
> > The first thing we can do is carefull tune the DMA command packet set.
> >  There are, of course, limitations on this, because we need to keep
> > the hardware simple, but there are likely many things we can do to
> > squeeze out a little more performance.  For instance, X and Y
> > coordinates are usually 16 bits, but sometimes, we don't need numbers
> > that big.  In those cases, we can use the extra bits to squeeze in
> > some other parameter(s).  The same is true for absolute addresses.
>
> Just a little note here: Please avoid such stuffings unless
> there is really an advantage in using them. Because with
> every different DMA command packet format you make the life
> for a driver writer harder and it makes the code harder to
> understand and thus harder to maintain.

I'll write the macros for them so they don't have to worry about it.  :)

Plus, they can add the more specialized ones as a later optimization,
after they get the basic stuff working.

> I know, hardware should here command what sofware should
> do, but we should optimize over both sides.

The objective is to identify where it is worthwhile to optimize and do
it in a reasonable way.  Besides, writing drivers is challenging
anyhow.  Doing something as mundane as making an alternative compacted
form of a packet won't really be over the heads of the driver
developers.

_______________________________________________
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