-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3622/#review8924
-----------------------------------------------------------


Interesting. This seems a problem worth correcting, but I fail to see how this 
change accomplishes it.  What prevents the notification from happening?  
Presumably there is some state being modified, but it is entirely unclear what 
or where.  Have you looked into that?

- Curtis Dunham


On Sept. 1, 2016, 12:10 p.m., Taehoon Kim wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3622/
> -----------------------------------------------------------
> 
> (Updated Sept. 1, 2016, 12:10 p.m.)
> 
> 
> Review request for Default.
> 
> 
> Repository: gem5
> 
> 
> Description
> -------
> 
> This diff fixes incorrect prefetch notification.
> 
> If we set the option on_miss in BasePrefetch.py, prefetch should generated at 
> MSHR misses.
> However, prefetch controller doesn't generate prefetch request.
> 
> I just change the order of notify() in cache.cc
> 
> 
> Diffs
> -----
> 
>   src/mem/cache/cache.cc a51ae096ca25 
> 
> Diff: http://reviews.gem5.org/r/3622/diff/
> 
> 
> Testing
> -------
> 
> 
> Thanks,
> 
> Taehoon Kim
> 
>

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

Reply via email to