Hi, I am currently using M5 running uniprocessor workload. I find that there is some unwanted coherence overhead in L2 cache (ReadExReq is always a miss). Because my current work does not require any coherence, is there any way to bypass the coherence protocol?
_______________________________________________ m5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
