Re: [Gems-users] tracer output file mismatch for same benchmark

[Dan Gibson <degibson@xxxxxxxx>]

They should not be the same. Changing timing changes execution paths. See Alameldeen and Wood http://www.cs.wisc.edu/multifacet/papers/ieeemicro03_variability.pdf.

Regards,
Dan

On Wed, Apr 21, 2010 at 1:09 PM, lopamudra chatterjee <lopamudralopa@xxxxxxxxxxxxxx> wrote:

Hi,

I am running the same benchmark on 2 configuration where L1 to L2 mapping is different. But ruby0.output-tracer-file gives a different sequence of processors and addresses for the two runs. Is n't this supposed to be same? Then to compare performance should I run both using the same cache file?

Regards,
Lopamudra


_______________________________________________
Gems-users mailing list
Gems-users@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/gems-users
Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/" to your search.

-- 
http://www.cs.wisc.edu/~gibson [esc]:wq!