Hi all,

I am trying to study the performance impact of off-chip bandwidth
contention on CMP. Currently, I only use the number of L2 misses,
because the L2 miss goes off-chip. But I have no clear idea about how
to relate the off-chip bandwidth limitations with L2 misses. Are
memdepunit.memDep.conflictingLoads and
memdepunit.memDep.conflictingStores good metrics to use?

Thanks

Meng-Ju
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users

Reply via email to