Hi Dr Radice, Thanks for the reply. What is the general speed you get on Marconi KNL for GW150914 case (or for any other simulation)? 


Regards

.............................

Bhavesh Khamesra

Graduate Student

Centre of Relativistic Astrophysics

Georgia Institute of Technology

From: David Radice <david.e.pi.3.14@gmail.com>
Sent: Wednesday, May 3, 2017 2:54:51 PM
To: Khamesra, Bhavesh
Cc: users@einsteintoolkit.org
Subject: Re: [Users] Benchmarking
 
Bhavesh:

> 2. I was able to run GW150914 on development queue (68 cores) and the speeds on Stampede were around 12.9M while that on KNL goes around 2.4M. To understand the reason for such small speeds, I tried running this on higher number of cores on  Stampede (128) and it runs at speed of around 20.9M (tested the run for 12 hours). However, on doing the same in normal queue in KNL, the simulation crashes after a couple of iterations on KNL with some segmentation fault error. Also, before crashing, the speed on KNL is around 4.2M. I have attached the error file of the simulation.

FYI, I have seen the same with my code: it runs (very slowly) on a single KNL node, but it crashes immediately when running on more than 1 node. Curiously, I do not have the same problem on Marconi KNL, an Italian cluster with the same architecture/interconnect as Stampede KNL.

Best wishes,

David