Hello Jason:
   Resource stall, you mean there is only one bank, but we use resource stall 
to implement interleaving bank?
    I want to config multi banks of L0 and L1 to improve the parallelism of 
cache,and  the number of banks can point by defined L0_bank_number arguments in 
.py scripy,if I want to do this, should I implement "real" banking?
    If I want to implement "real" banking, I should add L0_select_number_bits 
refer to L1_select_number_bits?I have been added L0_select_number_bits, but L1 
becomes shared cache, no more private for one cpu. Maybe the reason is that I 
connect L0 to ruby network.
    As I know, bank interleaving is a basic multi banks cache solution. But I 
don't know how to define bank index,and how to find data when config multi 
banks?  For example,  how a set associate cache bank stores data? A bank store 
a complete cache line or just a few bytes? If the cache line is 8 bytes and the 
private L0 is divided into four banks, does each bank store only 2 bytes of 
data?
   I wonder whether multi-bank L0 and L1 cache will affect the MESI Coherence 
Protocol ?
I fell doubt about the details, Looking forward to your reply.
_______________________________________________
gem5-users mailing list -- gem5-users@gem5.org
To unsubscribe send an email to gem5-users-le...@gem5.org
%(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s

Reply via email to