[gem5-users] Does a write request to cache block subsequent ones?

[Chen Meng via gem5-users]

Hi,

I am curious about the process of writing to classical cache.

I have found some parameters related, like `fillLatency`, `forwardLatency`, 
`dataLatency` and `lookupLatency` in BaseCache.  However none of these ones 
impact the subsequent requests.   For instance, `fillLatency` only relates to 
the status of destination cache line.

The scheduling of request to next level cache is based on a fixed latency 
(`forwardLatency` and payload-specific delay).  This means the process of 
sending a request is irrelevant to the status of write congestion.

Is it true the current model in gem5 will handle the request from CPU-side 
without any blocking?  If not, where is the impact of writing latency to the 
write operations revealed in the current model? Thanks!

Regards,
Meng

_______________________________________________
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