That seems to have been my problem, figures it was something simple - I
just didn't know that option existed. Thanks!
-Addison
On 6/14/2012 12:32 PM, Furat Afram wrote:
Hi
MARSS uses the system frequency as corefreq by default.
Did you set the corefreq in your simconfig ? if not please set it up
and let us know if that solve the problem
-Furat
On Thu, Jun 14, 2012 at 9:24 AM, Addison Mayberry
<[email protected] <mailto:[email protected]>> wrote:
Greetings,
I'm taking some measurements on an image without using checkpoints
- I have it set up so that when the image is run and boots, it
immediately logs in to root, drops into simulation, and runs my
benchmark. I've noticed that, when I do this on different
machines, the total cycle count (as seen in stats.yaml and reading
the sim_cycle variable) over the course of simulation varies
fairly dramatically depending on which machine it's on. Since
cycles elapsed affects some of my measurements, I'd like to have
the experiment be repeatable across different machines, and have
some assurance that the cycle count I'm seeing is at least
relatively accurate, if possible. Is this variation expected, due
to the way MARSS is set up?
Thanks in advance.
Sincerely,
Addison
_______________________________________________
http://www.marss86.org
Marss86-Devel mailing list
[email protected]
<mailto:[email protected]>
https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
_______________________________________________
http://www.marss86.org
Marss86-Devel mailing list
[email protected]
https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
