From: becka@rz.uni-duesseldorf.de
  To  : ggi-develop@eskimo.com
  Date: Thu, 19 Aug 1999 11:02:39 +0200 (MET DST)

Re: VC Switching

> more efficient on Intel's 4MB pages (although latency might be too high
> there) 

No. As said, latency can be in the order of a memcpy of the queued command.

> or on architectures like the alpha(?) which can change their page sizes.

AFAIK the Alpha has a fixed page size of 8192k. BUt maybe it's just Linux 
using it that way.

> no way to trigger an interrupt by writing to a particular memory location...? 

*grin* - with a little hardware - no problem :-). That would actually be 
very useful for the scheme I described to avoid the problem of when to 
look again, when the accel runs dry.

A graphics card with a programmable Interrupt-on-Memaccess generator would 
be useful, there :-).

CU, ANdy

-- 
Andreas Beck              |  Email :  <Andreas.Beck@ggi-project.org>