Date: | Tue, 12 Aug 2008 20:02:56 -0500 |
---|---|
From: | Philip Garcia <pcgarcia@xxxxxxxx> |
Subject: | [Gems-users] Are direct-mapped caches disabled for a reason? |
I was playing with some settings in Ruby today (in GEMS 2.1), and it
seems that direct mapped caches are disallowed by an assert statement
on line 42 of system/PseudoLRUPolicy.h (failed assertion 'num_sets > 0
&& assoc > 1 && assoc <= (Index) sizeof(uint64)*4' at fn
PseudoLRUPolicy::PseudoLRUPolicy(Index, Index) in system/
PseudoLRUPolicy.h:42). While I can change this assert so that it says
assoc>=1, is there any reason why this was in effect? Things seem to
run properly without it, but I don't really know for sure.
thanks, Phil |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Opal's sim-step command, Berkin Ozisikyilmaz |
---|---|
Next by Date: | Re: [Gems-users] Are direct-mapped caches disabled for a reason?, Dan Gibson |
Previous by Thread: | Re: [Gems-users] about the simulation result, Dan Gibson |
Next by Thread: | Re: [Gems-users] Are direct-mapped caches disabled for a reason?, Dan Gibson |
Indexes: | [Date] [Thread] |