Date: | Thu, 19 Mar 2009 11:15:50 -0500 |
---|---|
From: | Dan Gibson <degibson@xxxxxxxx> |
Subject: | Re: [Gems-users] Coherence misses |
You are using a broadcast protocol. Simply because a request is observed does not imply a state transitions. For instance, in S state, an OTHER_GETS doesn't need to change coherence state. What you should look for is the data from the cache's - Transitions - section of the stats file. It will look something like this: OM Load 0 <-- OM Ifetch 0 <-- OM Store 0 <-- OM L1_Replacement 0 <-- OM Own_GETX 0 <-- OM Fwd_GETX 0 <-- OM Fwd_GETS 0 <-- OM Ack 0 <-- OM All_acks 0 <-- The format is: [CurrentState] [messageType] [count] <-- You are looking for all the transitions that indicate a coherence miss, like: S Other_GETX 45 <-- or M Other_GETS 191 <-- I also notice that some of your instruction fetch stats appear to be zero. Is this intentional on your part? If not, verify you invoke Simics with the -stall flag, that you issue 'instruction-fetch-mode instruction-fetch-trace' and 'istc-disable' to simics before loading Ruby. Regards, Dan
On Thu, Mar 19, 2009 at 10:52 AM, Edward Lee <edwl202@xxxxxxxxx> wrote: Thanks Dan for your reply. I assume you are referring to "Chip Stats" section. I thought about that I was a little confused.
-- http://www.cs.wisc.edu/~gibson [esc]:wq! |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Coherence misses, Edward Lee |
---|---|
Next by Date: | Re: [Gems-users] Coherence misses, Edward Lee |
Previous by Thread: | Re: [Gems-users] Coherence misses, Edward Lee |
Next by Thread: | Re: [Gems-users] Coherence misses, Edward Lee |
Indexes: | [Date] [Thread] |