Date: | Wed, 19 Aug 2009 13:14:55 -0700 |
---|---|
From: | Niket Agarwal <niketa@xxxxxxxxxxxxx> |
Subject: | Re: [Gems-users] latency parameters in MOESI_SMP_directory protocol |
So if all the network latencies are added separately from the directory latency, why the default parameter is quite high for DIRECTORY_LATENCY which is 80 cycles? I was thinking that's because of the location of the directory as you said which is assumed to be in memory. Apart from going to off-chip to access memory to access the directory, there is also the latency to access the directory structure which contains list of sharers. Thus the 80 cycles. Also, other than parameters how do we really make sure that the directory is stored in memory or in the cache? In SLICC, the directory look up happens in the _mem file. This ensures that directory structure is in memory. On the other hand, MEMORY_RESPONSE_LATENCY_MINUS_2 is set to 158 in the default parameters. Shouldn't that be set to something close to 80, since they are referring to same structure?
This is the latency to access the DRAM to get the actual data and is different than the directory structure. Accordingly, what would be realistic parameters for a 16-core CMP? Sorry for the long set of questions, again I appreciate any input for clarification. This depends on your assumptions and configurations. You can look at related papers to what you are trying to model to get the best estimates.
|
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] latency parameters in MOESI_SMP_directory protocol, Edward Lee |
---|---|
Next by Date: | [Gems-users] some questions about MOESI_CMP_directory, shanshuchang |
Previous by Thread: | Re: [Gems-users] latency parameters in MOESI_SMP_directory protocol, Edward Lee |
Next by Thread: | [Gems-users] NUCA in gems-2.1, jin ouyang |
Indexes: | [Date] [Thread] |