How to check performance of your HPC cluster? Post: 302643935

Sponsored Content

Special Forums UNIX and Linux Applications High Performance Computing How to check performance of your HPC cluster? Post 302643935 by otheus on Monday 21st of May 2012 04:02:26 AM

05-21-2012

Registered User

"Understanding" isn't so important. At the end of the results, there is a number labeled "GLOPS". It looks like this:

Code:

WR00L2C2        8192    16     1     1             327.60          1.119e+00

The first column expresses some of the options used in the options (HPL.dat) file. The next two columns express the size in dimensions. The last column -- the one you want -- is the number of Gigaflops measured for that run. It's in scientific notation, meaning:

Code:

1.119 x 10^(00)  = 1.119 GFlops

If the output were 3.42e-01, then you'd have:

Code:

3.42 x 10^(-01) = 0.342 GFlops = 342 MFlops

Do you understand now?

---------- Post updated at 10:02 AM ---------- Previous update was at 09:34 AM ----------

As to how to configure this to run on multiple nodes, you have to (1) configure HPL.dat to run on mxn processors, where m and n are close together; so if you have a cluster containing 12 cores, optimal is normally m=3 and n=4. That's not always the case, but it typically is. (2) You must configure your MPI environment so that it runs on that many processors. How you do #2 depends on your MPICH software and setup. If you have a batch system like PBS or SGE, that further complicates the matter, as you need to queue the job with that number of processors. Sometimes with queuing engines, you can't easily dictate which nodes the job will run on. So if you have 6 nodes each with 4 cores, it might not be possible to say "run this on 3 nodes using all cores on each one". (But normally it's possible to say "run it on 3 nodes using 1 core on each one".)

These 2 Users Gave Thanks to otheus For This Post:

otheus

View Public Profile for otheus

Find all posts by otheus

8 More Discussions You Might Find Interesting

1. Solaris

Performance check without a counterpart

Hi, is it possible to check out the speed limits of a box without a remote peer for netio and stuff? I transferred 1 Terrabyte last night, which is not really much and need to find the bottleneck. The remote server is soon going to retire, yet I need to copy the 8T to the new machine. This...

2. Shell Programming and Scripting

how to check all the applications are in cluster using shell script

Hi I have an application running in four different node.The server is tomcat.Each node in each tomcat server.How do i check whether all the nodes are in cluster using shell script. any command to check this would be of great use.:)

3. Shell Programming and Scripting

Monitoring script to check if cm cluster is up or not.

hi guys have this little problem, need some help from script gurus. basically I'm running hpux cmviewcl command, cmviewcl command will produce db1pkg up running enabled box1 my script PSV='box1' STAT='up' check_db1pkg() { # assign cmviewcl output...

4. UNIX for Dummies Questions & Answers

How to check if the server is on a Cluster

Hi im connecting to a datacenter remotely. is there a command to know if the server is on a cluster? i want to know the command to use in these OS(hp-ux,solaris,linux) Thanks

5. Linux

Cluster check

I am working on a Linux server and want to check the cluster status. I dont know how many server is in cluster and what is the command to check. could you please help me to get the cluster status?

6. AIX

How to check if a filesystem is part of a cluster

Hello, - How do I know if a filesystem is part of a cluster? - Or do I have to check if the vg related to the fs is part of a cluster instead? if so, how do I check it? - I would also need to check if there are vxfs type inside aix machines and if there are, how do I know if that type of...

7. Red Hat