From: Jon M. Taylor <taylorj@gaia.ecs.csus.edu>
  To  : ggi-develop@eskimo.com
  Date: Tue, 3 Aug 1999 16:37:58 -0700 (PDT)

Re: Matrox GGI accellerator

On Tue, 3 Aug 1999, Rodolphe Ortalo wrote:

> Jos Hulzink wrote:
> 
> > I'm just wondering by myself how big a pingpongbuffer must me for optimal
> > speed. You don't want a sync to take ages, just because there was a huge
> > buffer still waiting to be filled completely that still needs to be
> > executed.
> 
> I guess only experimental figures will tell us. It's a pity we don't
> have a full running thing yet. Furthermore, I suspect that a precise
> application may exhibit a specific optimum. 

	I suspect the same.  Most modern 3D games want to spew primitives at
the hardware as fast as possible and in a continuous stream.  2D GUIs will
probably be quite 'bursty', and thus it will be necessary either to have the
userspace code be able to explicitly request flushing of a partially-filled
buffer or to have a cooperation between the interrupt handlers of the KGI
driver and the ping-pong page fault mechanism.  For example, if userspace
ever manages to outrun the hardware itself, it will probably be necessary to
have a fifo-watermark interrupt handler which either puts the userspace code
to sleep until the overload condition is resolved.

Jon

---
'Cloning and the reprogramming of DNA is the first serious step in 
becoming one with God.'
	- Scientist G. Richard Seed