Hi,
In the default Caches.py, there are:
class L1Cache(BaseCache):
assoc = 2
block_size = 64
latency = '1ns'
mshrs = 10
tgts_per_mshr = 20
is_top_level = True
class L2Cache(BaseCache):
assoc = 8
block_size = 64
latency = '10ns'
mshrs = 20
tgts_per_mshr = 12
According to the description:
tgts_per_mshr = Param.Int("max number of accesses per MSHR")
So the L1 cache has 10 MSHR each can serve 20 accesses simultaneously.
The L2 on the other hand has 20 MSHR and each can serve 12 accesses
simultaneously.
Are these values realistic? Aren't they very large? I know I can
change them, but I want to know if they are realistic.
reagards
--
// Naderan *Mahmood;
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
