Re: [Gems-users] Simics 2.2 vs Simics 3.0 statistics difference

[Dan Gibson <degibson@xxxxxxxx>]

In that case, you'll need to do several runs of whatever version you decide to use.

Regards,
Dan

On Thu, Mar 12, 2009 at 2:09 PM, Berkin Ozisikyilmaz <boz283@xxxxxxxxxxxxxxxxxxxx> wrote:

I tried changing the RANDOM_SEED. The results are significantly different.

Berkin

-----Original Message-----
From: gems-users-bounces@xxxxxxxxxxx [mailto:gems-users-bounces@xxxxxxxxxxx]
On Behalf Of Dan Gibson

Sent: 2009-03-10 08:18
To: Gems Users
Subject: Re: [Gems-users] Simics 2.2 vs Simics 3.0 statistics difference

List:
Has anyone else noticed similar problems that we can report to
Virtutech? Naturally, hard data is preferable -- we have always
noticed some changes in target behavior and performance from version
to version, though nearly always within 1%.

While we wait for 'list' to respond:
Try both versions with different RANDOM_SEED. This may not be a
version-dependent issue, but rather a general sensitivity to initial
conditions.

Regards,
Dan


On Mon, Mar 9, 2009 at 11:16 PM, Berkin Ozisikyilmaz
<boz283@xxxxxxxxxxxxxxxxxxxx> wrote:
> Hi,
>
> I haven't tried running with different RANDOM_SEED values.
> I would stick with simics 2.2 but my problem arises from the fact that my
> license is about to expire in a week, and I have more than a weeks
> simulations left, and Simics is no longer issuing Simics2 licenses.
> Switching to version 3 means in this case that I would have to rerun a
> couple of months worth of simulations. I have contacted them, and they
> pointed me to GEMS forum to see if anybody had similar observations. It
> seems that I would need to contact them.
>
> Berkin
>
> -----Original Message-----
> From: gems-users-bounces@xxxxxxxxxxx
[mailto:gems-users-bounces@xxxxxxxxxxx]
> On Behalf Of Dan Gibson
> Sent: 2009-03-10 00:00
> To: Gems Users
> Subject: Re: [Gems-users] Simics 2.2 vs Simics 3.0 statistics difference
>
> On Mon, Mar 9, 2009 at 9:40 PM, Berkin Ozisikyilmaz
> <boz283@xxxxxxxxxxxxxxxxxxxx> wrote:
>> ... since the combination of input parameters
>> that I feed the applications change and hence for each of those I would
> need
>> to create a checkpoint and it wouldn't be a feasible way to do.
>>
>
> ... or you can pick a Simics version and stick to it. It is well known
> that small variations in initial conditions can have huge impacts on
> parallel workloads. If your workload sees a lot of variance (aside:
> how much does does performance vary run to run with a different
> RANDOM_SEED and with the same Simics version?), you will have to run
> additional data points to reach an acceptable confidence margin.
>
> Regards,
> Dan
>
> --
> http://www.cs.wisc.edu/~gibson [esc]:wq!
> _______________________________________________
> 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.
>
>
> _______________________________________________
> 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!
_______________________________________________
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.


_______________________________________________
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!