|
[Sponsors] |
November 6, 2007, 22:09 |
I evaluated parallel performan
|
#1 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
I evaluated parallel performance of simpleFoam using 1.24 Mill model on intel 2-processor machine (2.8 GHz, 3.5GB Memory, Feisty-Fawn Ubuntu OS). Here are numbers:
...................... ExecutionTime ...... ClockTime Single CPU:........... 28114 s ....... 28119 s 2-CPUs: .............. . 25712 s ...... 25765 s It does not look very good. Is model too small to see the real difference? I had used openMPI for parallel runs. I used the same simpleFoam executable for both simulations. Does a parallel executable need to be compiled differently for openMPI? thanks -- Rajneesh |
|
November 6, 2007, 23:28 |
it is a little strange that it
|
#2 |
New Member
mou
Join Date: Mar 2009
Posts: 20
Rep Power: 17 |
it is a little strange that it took a long time near 8 hour for one iteration. I test simpleFoam for 2,5 mill and it took 210 s. I think your memory is not enough for your problem and it use paging or swaping to do that. paging cause it take to long. you can test it. when you see "top" list, after a while your memory become near 100% and after that you can see ksawpd is added to the top list.
|
|
November 6, 2007, 23:37 |
Mou,
Time is for 300 iterat
|
#3 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
Mou,
Time is for 300 iterations. Sorry, should have mentioned in the post. |
|
November 7, 2007, 06:39 |
I observed the same with OpenM
|
#4 |
Senior Member
Thomas Jung
Join Date: Mar 2009
Posts: 102
Rep Power: 17 |
I observed the same with OpenMPI and OpenFOAM 1.4.1- almost no speedup, where before, with mpich and OpenFOAM1.4, I had linear speedup up to 4 processors.
I did not dare to post this because I thought I would have made a mistake - but if Rajneesh observes the same? Still investigating, however... Thomas |
|
November 7, 2007, 21:53 |
Rajneesh:
Q1) Is this a dua
|
#5 |
Senior Member
Srinath Madhavan (a.k.a pUl|)
Join Date: Mar 2009
Location: Edmonton, AB, Canada
Posts: 703
Rep Power: 21 |
Rajneesh:
Q1) Is this a dual-core or a dual-cpu or a hyperthreaded machine? If this is a dual-core or a hyperthreaded offering, then I am not surprised in the least. These configurations at best give you 1.2 speedup for 2 processes. This is because the memory bandwidth (which is the biggest bottleneck for CFD) is shared between the cores. Q2) When the parallel run is in progress did you check the online 'top' monitor which reports memory and CPU usage. Were both processes using 99% CPU all the time? |
|
November 7, 2007, 23:03 |
Srinath,
I am quite positiv
|
#6 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
Srinath,
I am quite positive that it is a dual-core (not dual CPU machine. (Its a HP pavilion media center PC, about 2 year old). So then these results are to be expected. CPU % was fluctuating between 99-100 for both CPUs all the time. Memory usage was only ~1.2GB (out of 3.5GB total). My concern was if I had to create parallel executable by compiling (wmake_ing) with some openMPI specific options. Looks like default executable is appropriate for both the serial and parallel runs. -- Rajneesh |
|
November 7, 2007, 23:39 |
My concern was if I had to cre
|
#7 |
Senior Member
Srinath Madhavan (a.k.a pUl|)
Join Date: Mar 2009
Location: Edmonton, AB, Canada
Posts: 703
Rep Power: 21 |
My concern was if I had to create parallel executable by compiling (wmake_ing) with some openMPI specific options. Looks like default executable is appropriate for both the serial and parallel runs.
That's because abstraction in OpenFOAM is so cool. They have a single Pstream library that needs to be modified if one chooses to use a different MPI offering. I've noticed that one also needs to rebuild the parallel utilities (decomposePar, reconstructPar et al.) if they change MPI libraries. And of course all solvers are compiled in such a way that they work without any rebuilds for both serial and parallel modes. |
|
November 26, 2007, 01:15 |
I re-ran the same case on netw
|
#8 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
I re-ran the same case on network of a Laptop and Desktop. Laptop has Centos Linux while the Desktop has Ubuntu.OpenMPI is used for parallel run. Here are numbers for 300 iterations.
.................................. ............ ExecutionTime ...... ClockTime Single CPU (desktop):.................... 28114 s ........ 28119 s 2 CPU (desktop + Laptop) ............ 14049 s ........ 14052 s Numbers are actually even better than linear speedup! -- Rajneesh |
|
November 26, 2007, 05:08 |
What interconnect did you use?
|
#9 |
Senior Member
Srinath Madhavan (a.k.a pUl|)
Join Date: Mar 2009
Location: Edmonton, AB, Canada
Posts: 703
Rep Power: 21 |
What interconnect did you use?
|
|
November 26, 2007, 05:09 |
Also, speedup makes sense only
|
#10 |
Senior Member
Srinath Madhavan (a.k.a pUl|)
Join Date: Mar 2009
Location: Edmonton, AB, Canada
Posts: 703
Rep Power: 21 |
Also, speedup makes sense only if the Desktop and Laptop feature the exact same processor.
|
|
November 26, 2007, 13:32 |
I had Laptop and Desktop conne
|
#11 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
I had Laptop and Desktop connected through a Belkin router. I can get exact specs but its ~5 year old.
Should'nt time for parallel run be atmost twice (for this setup of 2 CPUS) of the serial run time on the slowest of the two machines for linear speedup? |
|
November 26, 2007, 13:33 |
I should have written half ins
|
#12 |
New Member
Rajneesh
Join Date: Mar 2009
Posts: 28
Rep Power: 17 |
I should have written half instead of twice in the previous post.
|
|
November 26, 2007, 14:05 |
Well, if the machines are not
|
#13 |
Senior Member
Srinath Madhavan (a.k.a pUl|)
Join Date: Mar 2009
Location: Edmonton, AB, Canada
Posts: 703
Rep Power: 21 |
Well, if the machines are not the same speed, you can of course do the speedup calculation using the lowest serial time. That would project the worst possible scenario and thus a more definite speedup estimate.
|
|
November 27, 2007, 02:28 |
It would great if you could al
|
#14 |
Member
vof_user
Join Date: Mar 2009
Posts: 67
Rep Power: 17 |
It would great if you could all post briefly about setting up parallel run with OpenMPI on network of computers. I have struggled so far, with no success.
|
|
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Problem with openmpi | mighelone | OpenFOAM Running, Solving & CFD | 42 | July 18, 2012 15:26 |
SnappyHexMesh in parallel openmpi | wikstrom | OpenFOAM Bugs | 18 | November 26, 2008 06:55 |
Problems using local openmpi | stephan | OpenFOAM Installation | 1 | December 5, 2007 19:01 |
Cant run in parallel on two nodes using OpenMPI | CHristofer | Main CFD Forum | 0 | October 26, 2007 10:54 |
OpenFOAM 14 with OpenMPI 12 | fhy | OpenFOAM Installation | 0 | July 12, 2007 19:12 |