I am running simulations with prefetching techniques to improve the cache miss rate.
I had ran two sets of simulation - one with no prefetching technique and one with GHB prefetching technqiue. I have observed the improvement in the cache miss rate but not in IPC ( Instructions per cycle). My question is when I saw the improvement in cache miss rate, why not I saw the much improvement in the IPC? Thereby overall system performance in not improved much. -- Ashutosh Jain
_______________________________________________ m5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
