-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/1311/#review3128
-----------------------------------------------------------



configs/common/Options.py
<http://reviews.gem5.org/r/1311/#comment3286>

    My instinct is to see if we can get by with a single option here, e.g., if 
--switch-freq had no default, then setting it would imply --repeat-switch and 
we wouldn't need --repeat-switch as an explicit option.
    
    I see that the current method is consistent with -s/-w, but if we're 
worried about consistency, I'd be in favor of "fixing" -s/-w instead of 
introducing two new options here.
    
    Thoughts?
    



configs/common/Simulation.py
<http://reviews.gem5.org/r/1311/#comment3288>

    It looks like some of this added code duplicates code above... can we get 
away with reusing the switch_cpus list instead of creating a new 
repeat_switch_cpus list?


- Steve Reinhardt


On July 17, 2012, 5:32 p.m., Anthony Gutierrez wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/1311/
> -----------------------------------------------------------
> 
> (Updated July 17, 2012, 5:32 p.m.)
> 
> 
> Review request for Default.
> 
> 
> Description
> -------
> 
> Changeset 9121:2877a0a82b1e
> ---------------------------
> configs: add option for repeatedly switching back-and-forth between cpu types.
> 
> this patch adds a --repeat-switch option that will enable repeat core
> switching at a user defined period (set with --switch-freq option).
> currently, a switch can only occur between like CPU types. inorder CPU
> switching is not supported.
> 
> *note*
> this patch simply allows a config that will perform repeat switching, it
> does not fix drain/switchout functionality. if you run with repeat switching
> you will hit assertion failures and/or your workload with hang or die.
> 
> 
> Diffs
> -----
> 
>   configs/common/Options.py 48eeef8a0997fd97ede789b5a32c03bf846022f1 
>   configs/common/Simulation.py 48eeef8a0997fd97ede789b5a32c03bf846022f1 
> 
> Diff: http://reviews.gem5.org/r/1311/diff/
> 
> 
> Testing
> -------
> 
> The options added to this config play nicely with the other options.
> Ran with repeat switching on with various other options. Simulation
> started and ran successfully while switching until an assertion failed
> or the workload kernel panicked or hung due to drain/switchout bugs.
> 
> 
> Thanks,
> 
> Anthony Gutierrez
> 
>

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

Reply via email to