Date: | Thu, 15 Apr 2010 13:00:41 -0500 |
---|---|
From: | Tony Nowatzki <tjn@xxxxxxxxxxx> |
Subject: | [Gems-users] L1 v.s. L2 cache miss in MESI_CMP_filter_directory protocol |
Hi, Does anyone know the relationship among L2_cache_total_misses, L1D_cache_total_misses, and L1I_cache_total_misses ?I ran several benchmarks in MESI_CMP_filter_directory, and observed that L2_cache_total_misses is close to (L1D_cache_total_misses + L1I_cache_total_misses). I suppose L2 cache miss should be a lot smaller than L1D_cache_total_misses + L1I_cache_total_misses. Thanks, Tony |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Very high cache miss overhead, Mark Samuelson |
---|---|
Next by Date: | [Gems-users] L2 sharing in CMP, sparsh mittal ISU |
Previous by Thread: | Re: [Gems-users] Very high cache miss overhead, Mark Samuelson |
Next by Thread: | Re: [Gems-users] Very high cache miss overhead, Byn Choi |
Indexes: | [Date] [Thread] |