[Users] benchmarks

[Erik Schnetter]

Yes it should. Next Monday?

-erik

On Dec 2, 2013, at 14:57 , Steven R. Brandt <sbrandt at cct.lsu.edu> wrote:

> I don't recall ever having an ET call where this was discussed. Should it be scheduled?
> 
> Cheers,
> Steve
> 
> On 10/23/2013 11:23 AM, Erik Schnetter wrote:
>> I believe these benchmark parameter files are wildly out of date and should be removed.
>> 
>> These days, we auto-generate benchmark files based on the target system to ensure that the benchmark parameters are scaled correctly. I have some script in Simfactory that do this. There is a low-level interface to the scripts where you (unfortunately) need to set many parameters (nodes, cores, processes, threads, SMT threads, memory to be used, CPU time to be used, etc.), and a high-level interface where you (unfortunately) basically cannot set anything since these are all chosen automatically... I should give an overview in person; would next Monday during the ET call make sense?
>> 
>> -erik
>> 
>> On 2013-10-23, at 11:40 , Roland Haas 
>> <roland.haas at physics.gatech.edu>
>>  wrote:
>> 
>> 
>>> Signed PGP part
>>> Hello Steve,
>>> 
>>> here the ones I know of:
>>> 
>>> 
>>>> BenchIO
>>>> 
>>>> BSSN_MoL
>>>> 
>>> this is the CCATIE code. AEI private and not to be used anymore as far
>>> as I know (superseded by MacLachlan).
>>> 
>>> 
>>>> FlexIO IOFlexIO
>>>> 
>>> Old IO libraries. Used only with PUGH.
>>> 
>>> 
>>>> whisky_init_data
>>>> 
>>> this is now GRHydro_InitData
>>> 
>>> 
>>>> whisky
>>>> 
>>> this is now GRHydro
>>> 
>>> 
>>>> whisky_rnsid
>>>> 
>>> this uses a private version of RNSID (original RNSID stand alone code
>>> by Nick Stergioulas then extended). Rumour (and me talking to Nick
>>> when I met him accidentally in Germany) has it that a new public
>>> version of RNSID that contains (most of?) these features is being
>>> prepared. Frank would know I think.
>>> 
>>> 
>>>> Are these out of date? Are there better files to use for
>>>> benchmarking?
>>>> 
>>> Mostly they are out of data I'd say. For benchmarking I'd use the tov
>>> and vacuum files from the xirel project. Alternatively I think Erik
>>> send around some of his benchmarking files a while ago.
>>> 
>>> Yours,
>>> Roland
>>> 
>>> --
>>> My email is as private as my paper mail. I therefore support encrypting
>>> and signing email messages. Get my PGP key from 
>>> http://keys.gnupg.net
>>> .
>>> 
>>> _______________________________________________
>>> Users mailing list
>>> 
>>> Users at einsteintoolkit.org
>>> http://lists.einsteintoolkit.org/mailman/listinfo/users
>> 
>> 
>> _______________________________________________
>> Users mailing list
>> 
>> Users at einsteintoolkit.org
>> http://lists.einsteintoolkit.org/mailman/listinfo/users
> 
> _______________________________________________
> Users mailing list
> Users at einsteintoolkit.org
> http://lists.einsteintoolkit.org/mailman/listinfo/users

-- 
Erik Schnetter <schnetter at cct.lsu.edu>
http://www.perimeterinstitute.ca/personal/eschnetter/

My email is as private as my paper mail. I therefore support encrypting
and signing email messages. Get my PGP key from http://pgp.mit.edu/.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 203 bytes
Desc: Message signed with OpenPGP using GPGMail
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20131202/10aab7d3/attachment.bin