Date: | Thu, 28 Aug 2008 10:41:44 -0500 |
---|---|
From: | "Mike Marty" <mike.marty@xxxxxxxxx> |
Subject: | Re: [Gems-users] Redundant states in MOESI_SMP_directory cache implementation |
The distinction between the states really isn't necessary. The difference between M and E is whether or not the data is dirty with respect to memory. This is tracked by the Dirty bit. If you look at the replacement logic, the Dirty bit is checked to determine whether or not the data should be sent on a replacement (replacement from the E state is non-silent).
Thus the protocol could have been written without the E state as you point out, because is would be equivalent to the M state with the dirty bit cleared. Thus the E state is indeed redundant. --Mike On Thu, Aug 28, 2008 at 10:27 AM, Morten Sleth Rasmussen <msr@xxxxxxxxxx> wrote: Hi, |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | [Gems-users] Redundant states in MOESI_SMP_directory cache implementation, Morten Sleth Rasmussen |
---|---|
Next by Date: | [Gems-users] Wattch SIGSEGV on Opal init, Fred A Bower |
Previous by Thread: | [Gems-users] Redundant states in MOESI_SMP_directory cache implementation, Morten Sleth Rasmussen |
Next by Thread: | [Gems-users] Regarding Supervier Mode bit in Simics 3 and gems 2.1, sjafri |
Indexes: | [Date] [Thread] |