I'm looking to validate the SPEC CPU 2000 benchmarks with M5 2.0b3
against someone else's validated results, and it looks like there
might be some in connection with the "Analysis of Hardware
Prefetching Across Virtual Page Boundaries" paper. Though I'm not
interested in the prefetching modification to the Alpha, it doesn't
matter that it's been implemented as per the simulated system
parameters in Table 1 (of the paper); I want to get some kind of
reasonable apples-to-apples comparison of my own environment with one
that's known to work.
Essentially I'm looking for results from the Michigan team, but I'm
happy to validate against another if someone has the results. I'd
like to see two things, basically:
The py file used for the simulation and the m5stats.txt output for
each of the benchmarks (or other output files, if you changed the
defaults).
If you used an earlier version of the simulator, it might be
interesting to see if the numbers change with a new validation run...
Thanks,
Dan
Daniel Alex Finkelstein
Ph.D. Candidate (CS)
Work: +1-718-260-3378
Mobile: +1-718-246-7421
Fax: +1-718-228-5328
Email: [EMAIL PROTECTED]
IM: steuben13 (Skype)
Polytechnic University
6 MetroTech Center
Brooklyn, NY 11201 USA
_______________________________________________
m5-users mailing list
m5-users@m5sim.org
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
