Hi all,
It seems that Gem5 has implemented "blocking" cache coherency protocol under 
Ruby memory system.
Does anyone have experience of analyzing performance difference between 
"blocking" protocol and "nonblocking" protocol? Did anyone try to modify the 
protocol to "nonblocking"?
Can you share your experience?
Thanks.

Kwoyuan
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to