Hi,
While looking through the code in branchpred.c, I came across the following
snippet:
// G-share constraints: METASIZE, BIMODSIZE, 1, L2SIZE, log2(L2SIZE),
(HISTORYXOR = true), BTBSETS, BTBWAYS, RASSIZE
struct BranchPredictorImplementation: public CombinedPredictor<65536,
65536, 1, 65536, 16, 1, 1024, 4, 1024> {
BranchPredictorImplementation(W8 coreid, W8
threadid):CombinedPredictor<65536, 65536, 1, 65536, 16, 1, 1024, 4, 1024>
(coreid, threadid){}
};
Now, depending on the simulation system configuration, the value of L1 and
L2 sizes will vary. However, the initialization of CombinedPredictor object
receives hardcoded value for these sizes. Don't we have to update this
value for the particular cache size we use ? Or is this intentional ? If
yes, can you please share some thoughts on it ?
Thanks!
--
Regards,
Ankita
_______________________________________________
http://www.marss86.org
Marss86-Devel mailing list
[email protected]
https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
