Date: | Mon, 21 May 2007 16:31:42 -0700 (PDT) |
---|---|
From: | James Wang <jameswang99@xxxxxxxxx> |
Subject: | [Gems-users] Timing Issue For LogTM |
Hi All: I would like to understand how LogTM times its abort and how I could vary that. From my understanding of the code, there are two parts to the time of LogTM abort. One is the abort delay in the protocol, which is also checked in $GEMS/ruby/system/Sequencer.C code. Another part, I think, is to set in the $GEMS/ruby/config/rubyconfig.default RESTART_DELAY: 1000. Is there anything else that relates to the restart of the transaction in LogTM? Thanks in advance for any reply! Regards James |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Simics unstalled with processor binding, Cong Wang |
---|---|
Next by Date: | [Gems-users] Ruby Cache Features, pana |
Previous by Thread: | Re: [Gems-users] Support for Partial Abort in LogTM, Kevin Moore |
Next by Thread: | [Gems-users] TLB misses, Ruby and Simics, mehmetderin . harmanci |
Indexes: | [Date] [Thread] |