Re: Gtk performance issues from a user's point of view

[Tero Huttunen <tero huttunen tut fi>]

On Sun, 2006-10-01 at 08:51 -0700, Carl Worth wrote:
> On Sun, 01 Oct 2006 09:56:56 +0300, Tero Huttunen wrote:
> > It seems, that Gtk is drawing everything with non-accelerated path,
> > whereas Qt and Xt seem to be good at accelerating things. Now, Gtk could
> > be drawing everything through Render (including solid-fills), however,
> > it probably isn't.
> 
> Do you mean that your red drawing hack shows non-Render solid fills,
> but not Render-based solid fills?

Yes. Non-Render solid fills are red, Render-based are unaffected.

> What evidence do you have that GTK+ probably isn't drawing through
> Render?

I thought it wouldn't do solid fills through Render. However, I did a
new hack, by modifying R200SubsequentCPUtoScreenTexture to return
immediately. Result:

http://www.students.tut.fi/~huttune2/accel2.png

Clearly Qt can accelerate some of the Render-operations, since some of
the text is missing, however, Gtk doesn't seem to accelerate anything.
What other functions should I test?

> From its beginning, cairo has always preferred to draw things with
> Render whenever possible, so since GTK+ started drawing with cairo it
> definitely should be drawing as much as possible with cairo.
> 
> With a GTK+/cairo stack things like solid fills should be going
> through Render and should be hitting accelerated paths for that. If
> not, then there are performance bugs that I would be very interested
> in hearing more details about so that we can fix them.
> 
> -Carl

-- 
Tero Huttunen