RE: do_ri failure in cache flushing routines

[G H <giles67@yahoo.com>]

I've not had much response to this question so I would like to rephrase it :

 

Can anyone think of any possible scenario where do_ri could occur in blast_icache32() ??

 

Is this possibly a cache synchronisation problem ??

 

TIA

 

>While testing out an amd au1500 based board I have been getting " do_ri " exceptions >that always occur in the cache flushing routines. More often than not in >blast_icache_32().

 

>So far this has mainly happened after running the board for days on end while running >multiple telnet sessions to it. It has sometimes ( quite rarely ) happened after a few >hours to a day of multiple telnet session use.

__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com