[FLASH-USERS] FLASH Scaling Data

[Lynn Reid]

Well there are certainly published studies of FLASH-3 that I know of... see

   - Challenges of extreme computing using the FLASH code
   <http://adsabs.harvard.edu/full/2008ASPC..385..145D>; A Dubey, R Fisher,
   C Graziani, GC Jordan IV, DQ Lamb, LB Reid, P Rich, D Sheeler, D Townsley,
   K Weide; *Numerical Modeling of Space Plasma Flows, *Volume 385, Pages
   145

   - Pragmatic optimizations for better scientific utilization of large
   supercomputers
   <http://journals.sagepub.com/doi/abs/10.1177/1094342012464404>; Anshu
   Dubey, Alan C Calder, Christopher Daley, Robert T Fisher, Carlo Graziani,
   George C Jordan, Donald Q Lamb, Lynn B Reid, Dean M Townsley, Klaus
Weide; *International
   Journal of High Performance Computing Applications*, 27(3), pp 358-371
   - Evolution of FLASH, a multi-physics scientific simulation code for
   high-performance computing
   <http://journals.sagepub.com/doi/abs/10.1177/1094342013505656>;
   Anshu Dubey, Katie Antypas, Alan C Calder, Chris Daley, Bruce Fryxell, J
   Brad Gallagher, Donald Q Lamb, Dongwook Lee, Kevin Olson, Lynn B Reid, Paul
   Rich, Paul M Ricker, Katherine M Riley, Robert Rosner, Andrew Siegel, Noel
   T Taylor, Klaus Weide, Francis X Timmes, Natasha Vladimirova, John ZuHone,
   International Journal of High Performance Computing Applications, 28(2), pp
   223-235


You could also look for more recent publications at
http://flash.uchicago.edu/site/publications/flash_pubs.shtml


On 7 May 2018 at 11:04, Jason Galyardt <jason.galyardt at gmail.com> wrote:

> Hi all,
>
> I'm working on an proposal for a compute time allocation at a major
> cluster facility. The proposal guidelines request quantitative evidence
> concerning the parallel performance, stability, and scalability of FLASH.
> Network and I/O bandwidth benchmarks are also requested. I realize that
> there is quite a bit of variability in these performance metrics according
> to the particular simulation, physics included, solver used, etc. However,
> I have seen some old (FLASH 2 era) scalability studies; how extensible are
> such studies? Is it necessary to profile one's own simulation for such
> proposals? If so, are there any recommended profiling tools / procedures,
> aside from those included in FLASH?
>
> Thanks,
>
> Jason
>
> --------------
> Jason Galyardt, PhD
> University of Georgia
>



-- 
Lynn Reid
[image: Inline images 1]

-- 
----------------------------------------------------------------------------------------------------------------DISCLAIMER: 
This email, including any attachments, is intended only for use by the 
addressee(s) and may contain confidential and/or personal information and 
may also be the subject of legal privilege. If you are not the intended 
recipient, you must not disclose or use the information contained in it. In 
this case, please let me know by return email, delete the message 
permanently from your system and destroy any copies.

Before you take any 
action based upon advice and/or information contained in this email you 
should carefully consider the advice and information and consider obtaining 
relevant independent advice.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://flash.rochester.edu/pipermail/flash-users/attachments/20180507/fa9180d1/attachment.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 12194 bytes
Desc: not available
URL: <http://flash.rochester.edu/pipermail/flash-users/attachments/20180507/fa9180d1/attachment.png>