[petsc-users] KSPSolve doesn't seem to scale. (Must be doing something wrong...)

[William Coirier]

Matt:

So if we use the ex5 from SNES, use default ksp/pc and size the problem big enough via the M,N, it should scale?

Just checking...
________________________________
From: Matthew Knepley [knepley at gmail.com]
Sent: Saturday, March 15, 2014 9:15 AM
To: William Coirier
Cc: Karl Rupp; petsc-users at mcs.anl.gov
Subject: Re: [petsc-users] KSPSolve doesn't seem to scale. (Must be doing something wrong...)

On Sat, Mar 15, 2014 at 9:08 AM, William Coirier <William.Coirier at kratosdefense.com<mailto:William.Coirier at kratosdefense.com>> wrote:
Thanks Karl. We'll check this out on different architectures. I appreciate your help!

Related to all of this, is there an example code in the distribution that might be recommended to use for testing machines for scalabiilty? Perhaps an example from the KSP?

SNES ex5 is a very simple code and easy to see what is happening on the architecture. I use it to start. You
can increase the grid size using -da_grid_x M -da_grid_y N.

   Matt

Thanks again...

Bill C.
________________________________________
From: Karl Rupp [rupp at iue.tuwien.ac.at<mailto:rupp at iue.tuwien.ac.at>]
Sent: Saturday, March 15, 2014 4:01 AM
To: William Coirier
Cc: petsc-users at mcs.anl.gov<mailto:petsc-users at mcs.anl.gov>
Subject: Re: [petsc-users] KSPSolve doesn't seem to scale. (Must be doing something wrong...)

Hi William,

I couldn't find something really suspicious in the logs, so the lack of
scalability may be due to hardware limitations. Did you run all MPI
processes on the same machine? How many CPU sockets? If it is a
single-socket machine, chances are good that you saturate the memory
channels pretty well with one process already. With higher process
counts the cache per process is reduced, thus reducing cache reuse. This
is the only reasonable explanation why the execution time for VecMDot
goes up from e.g. 7 seconds for one and two processes to about 24 for
four and eight processes.

I suggest you try to run the same code across multiple machines if
possible, you should see better scalability there. Also, for
benchmarking purposes try to replace the ILU preconditioner with e.g.
Jacobi, this should give you better scalability (provided that the
solver still converges, of course...)

Best regards,
Karli


On 03/14/2014 10:45 PM, William Coirier wrote:
> I've written a parallel, finite-volume, transient thermal conduction solver using PETSc primitives, and so far things have been going great. Comparisons to theory for a simple problem (transient conduction in a semi-infinite slab) looks good, but I'm not getting very good parallel scaling behavior with the KSP solver. Whether I use the default KSP/PC or other sensible combinations, the time spent in KSPSolve seems to not scale well at all.
>
> I seem to have loaded up the problem well enough. The PETSc logging/profiling has been really useful for reworking various code segments, and right now, the bottleneck is KSPSolve, and I can't seem to figure out how to get it to scale properly.
>
> I'm attaching output produced with -log_summary, -info, -ksp_view and -pc_view all specified on the command line for 1, 2, 4 and 8 processes.
>
> If you guys have any suggestions, I'd definitely like to hear them! And I apologize in advance if I've done something stupid. All the documentation has been really helpful.
>
> Thanks in advance...
>
> Bill Coirier
>
>   --------------------------------------------------------------------------------------------------------------------
>
> ***NOTICE*** This e-mail and/or the attached documents may contain technical data within the definition of the International Traffic in Arms Regulations and/or Export Administration Regulations, and are subject to the export control laws of the U.S. Government. Transfer of this data by any means to a foreign person, whether in the United States or abroad, without an export license or other approval from the U.S. Department of State or Commerce, as applicable, is prohibited. No portion of this e-mail or its attachment(s) may be reproduced without written consent of Kratos Defense & Security Solutions, Inc. Any views expressed in this message are those of the individual sender, except where the message states otherwise and the sender is authorized to state them to be the views of any such entity. The information contained in this message and or attachments is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you
 are not the intended recipient or believe that you may have received this document in error, please notify the sender and delete this e-mail and any attachments immediately.
>


 --------------------------------------------------------------------------------------------------------------------

***NOTICE*** This e-mail and/or the attached documents may contain technical data within the definition of the International Traffic in Arms Regulations and/or Export Administration Regulations, and are subject to the export control laws of the U.S. Government. Transfer of this data by any means to a foreign person, whether in the United States or abroad, without an export license or other approval from the U.S. Department of State or Commerce, as applicable, is prohibited. No portion of this e-mail or its attachment(s) may be reproduced without written consent of Kratos Defense & Security Solutions, Inc. Any views expressed in this message are those of the individual sender, except where the message states otherwise and the sender is authorized to state them to be the views of any such entity. The information contained in this message and or attachments is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you are not the intended recipient or believe that you may have received this document in error, please notify the sender and delete this e-mail and any attachments immediately.



--
What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.
-- Norbert Wiener

 --------------------------------------------------------------------------------------------------------------------

***NOTICE*** This e-mail and/or the attached documents may contain technical data within the definition of the International Traffic in Arms Regulations and/or Export Administration Regulations, and are subject to the export control laws of the U.S. Government. Transfer of this data by any means to a foreign person, whether in the United States or abroad, without an export license or other approval from the U.S. Department of State or Commerce, as applicable, is prohibited. No portion of this e-mail or its attachment(s) may be reproduced without written consent of Kratos Defense & Security Solutions, Inc. Any views expressed in this message are those of the individual sender, except where the message states otherwise and the sender is authorized to state them to be the views of any such entity. The information contained in this message and or attachments is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you are not the intended recipient or believe that you may have received this document in error, please notify the sender and delete this e-mail and any attachments immediately.