You can waste tremendous amounts of time and talent trying to balance CPU
and GPU performance or you can just run it all on the GPU like a boss.
On Jul 25, 2017 6:58 PM, "Ryan Novosielski" <novosirj.rutgers.edu> wrote:
On Jul 25, 2017, at 12:03, Ross Walker <ross.rosswalker.co.uk<mailto:
ross.rosswalker.co.uk>> wrote:
Uh, no. These run fine (ie *reliable*) and when set up properly will
naturally run out of phase with eachother and maximise throughput. See e.g.
https://na01.safelinks.protection.outlook.com/?url=
http%3A%2F%2Fonlinelibrary.wiley.com%2Fdoi%2F10.1002%2Fjcc.24030%2Fabstract%
3Bjsessionid%3D3CD2B4EE326378381D60FCB0BD1B26A0.f02t02&data=02%7C01%
7Cnovosirj%40rutgers.edu%7C0297acc30daa4e3426c808d4d38fd3da%
7Cb92d2b234d35447093ff69aca6632ffe%7C1%7C0%7C636366062069482396&sdata=
zv6WgAM3l1XI30lIDH%2FkzjfYX%2FQ7eH276w4hRKcVvFA%3D&reserved=0
(or same on arxiv.
Mark
Only if you go to the trouble of placing threads properly and locking
things to the right cores and corresponding GPUs. This, and the complexity
in choosing hardware for Gromacs as illustrated by the plethora of options
and settings highlighted in that paper, is something that is generally way
beyond the average user and a pain in the butt to configure properly with
most queuing systems. So while it works in theory my experience is that
this is very difficult to achieve reliably in practice.
I realize we're drifting off topic, but recommendations on this subject
welcome (perhaps direct e-mail would be better). This is eventually going
to come up at our site.
--
____
|| \\UTGERS, |---------------------------*
O*---------------------------
||_// the State | Ryan Novosielski - novosirj.rutgers.edu
<mailto:novosirj.rutgers.edu>
|| \\ University | Sr. Technologist - 973/972.0922 (2x0922) ~*~ RBHS Campus
|| \\ of NJ | Office of Advanced Research Computing - MSB C630,
Newark
`'
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Tue Jul 25 2017 - 19:30:03 PDT
