Need advice: Mobile ATI card with 'shared' memory - EXA performance?

[Francesco Biscani]

On Thursday 08 December 2005 02:05, Dan wrote:
> Greetings.
>
> I'm on the verge of buying a Turion ( mobile Athlon 64 ) notebook. As
> far as I can tell, there are NO ATI cards for the Turion with dedicated
> RAM. The only cards worth talking about with dedicated RAM are nVidia
> cards. I'd prefer to use an ATI if possible.
>
> While this will be primarily a purchase for coding work, I'd also like
> to use EXA. I've been using it on my Powerbook, and I'm quite impressed
> so far. I know that one of the big issues at the moment with EXA is
> memory consumption, and that people are recommending using a card with
> stacks of memory for EXA with lots of windows open. Where does this put
> users who have cards that share video RAM with the motherboard? Is it
> going to be horrible performance, as if I'd run out of dedicated RAM, or
> will EXA be able to use shared RAM at a respectable pace?
>
> Dan

Hello,

I'm using an HP notebook right now, with a Radeon IGP 345 with shared memory. 
You can have up to 128MB of shared memory, but right now I'm using 64M. EXA 
performance is ok, I can drag around transparent full-size (1024x768) windows 
without hiccups.

The big slowdowns come when you run out of video memory, and you can realize 
it by monitoring X memory usage with xrestop. When the total size of pixmap 
buffers approximates your video RAM size you notice great slowdowns, 
expecially when switching desktops. With my actual setup (64M+1024x768 at 16bit) 
this seldom happens (I dare to say it never happens). If you go up to 32bit 
color depth you can trigger the "slow" behaviour much more easily (just open 
up many windows). In this case I guess going up to 128MB of RAM could help, 
even if I have not tried yet (and I need to purchase another 512M stick of 
system ram to go there ;) )

My (ignorant and based upon only experience) conclusion is that in this 
specific case the bottleneck is not RAM speed.

HTH.

  Francesco

-- 
Dr. Francesco Biscani
Dipartimento di Astronomia
Università di Padova
biscani at pd.astro.it