On Tue, 10 Aug 1999, David Brownlee wrote:
> On Tue, 10 Aug 1999, Matt Thomas wrote:

> > An rtVAX was a "modified (read broken)" 78032 (uVAX II CPU) which could run
> > VAXELN but not ULTRIX or VMS (due to a change in how user PTEs are mapped).
> > NetBSD/vax probably doesn't run on it but it could be changed to do so.
> > But I doubt it's work the effort.

> 	Didn't it have the single level MMU with a max 4MB of RAM?
> 	Could it make a good base for anyone looking to port to the
> 	uVaxI?

According to the VARM:

  The rtVAX is a variant of the VAX Architecture. An rtVAX processor
  implements the per-process page tables in physical memory.  All other
  VAX processors implement the per-process page tables in virtual memory.
  Therefore, translation of of process-space addresses is different on an
  rtVAX than described in Chapter 4. *

  [...]

  * Chapter 4 being "Memory Management".

So it sounds like it's some particular restrictions on how it handles
memory management.  I'm not sure how much additional work would be
required to special case the processor in order to keep all the process
page tables in "core".

Anyone with real time programming experience know why this particular
characteristic imposed on the rtVAX would be desireable for real time
requirements?

-brian.
---
Brian "JARAI" Chase | http://world.std.com/~bdc/ | VAXZilla LIVES!!!