> On May 20, 2012, 7:54 a.m., Ali Saidi wrote:
> > src/mem/cache/cache_impl.hh, line 1267
> > <http://reviews.gem5.org/r/1207/diff/1/?file=26556#file26556line1267>
> >
> >     Seems fine for the normal case, but if you hookde two caches up 
> > directly, would this break?
> >     
> >
> 
> Andreas Hansson wrote:
>     Very valid point. Would that even work today? I am tempted to bet 
> against...but perhaps that's just me being overly cynical.
>     
>     As a very minor side note, there are quite a few limitations already in 
> what connectivity is allowed, e.g. two buses cannot be directly connected.
> 
> Ali Saidi wrote:
>     I'm fairly certain that it would work, or at least it did at one point in 
> time.

Ok, in that case we can keep the check. I'll discard the patch. If we want that 
case to work we should probably add a regression.


- Andreas


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/1207/#review2736
-----------------------------------------------------------


On May 18, 2012, 9:12 a.m., Andreas Hansson wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/1207/
> -----------------------------------------------------------
> 
> (Updated May 18, 2012, 9:12 a.m.)
> 
> 
> Review request for Default.
> 
> 
> Description
> -------
> 
> Cache: Remove redundant check for uncacheable snoops
> 
> This patch removes the check for uncacheable requests in the cache
> snoop timing/atomic access methods. This check is now taken care of by
> the bus, and there is no need to perform it also in the caches.
> 
> 
> Diffs
> -----
> 
>   src/mem/cache/cache_impl.hh 7100059f7bfd 
> 
> Diff: http://reviews.gem5.org/r/1207/diff/
> 
> 
> Testing
> -------
> 
> util/regress all passing (disregarding t1000 and eio)
> 
> 
> Thanks,
> 
> Andreas Hansson
> 
>

_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to