Thanks Steve for the reply. Things seem to be working fine for 8 cpus but with 
more than this I have an assertion failure.

Assertion `target->pkt->cmd == MemCmd::ReadResp from cache_impl.hh (809, 
m5-beta5, cache patches applied).

This is happening in handleResponse() after satisfying cpuSide request. The 
packet is inValidate but the cmd is not ReadResp.

Do u have any idea?


---- Original message ----
>Date: Fri, 29 May 2009 15:29:26 -0700
>From: Steve Reinhardt <[email protected]>  
>Subject: Re: [m5-users] More than 4 cpus in FS mode  
>To: M5 users mailing list <[email protected]>
>
>   Glad it worked... thanks for following up.  That
>   I/O bridge doesn't exist in SE mode so that's why
>   this only shows up with Linux.  Hard to say about
>   real systems... in some cases because a real system
>   design has a hard limit on the number of cores then
>   it is practical to simply design buffering in for
>   the worst case and not worry about specific flow
>   control problems.
>

_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users

Reply via email to