|
[Sponsors] |
Fluent core number specification - 2 computers |
|
LinkBack | Thread Tools | Search this Thread | Display Modes |
June 6, 2018, 04:46 |
Fluent core number specification - 2 computers
|
#1 |
Senior Member
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13 |
Hello,
Fluent allows to distribute an analysis to several computers and you can set total core number. Then Fluent distributes the number of cores per each computer on its own. Is there any way to specify the number of cores for each computer individually? For example, computer A - 4 cores and computer B - 5 cores. In CFX you can do that easily in solver setup, but I cant figure out how to do that in Fluent. Thank you very much. |
|
June 6, 2018, 09:22 |
|
#2 |
Senior Member
Lucky
Join Date: Apr 2011
Location: Orlando, FL USA
Posts: 5,676
Rep Power: 66 |
Yes. Probably the easiest way is to specify the hostnames and put computer A 4 times and computer B 5 times. Find this screen in the GUI when you launch Fluent. Then use the distributed memory on a cluster option and you have two options. Write the machine names directly into the little bar or specify a file that has these machine names. If you launch from a text window, it's probably easier to specify the machine file.
Solver setup... sounds like you are using workbench. Can't help you there. |
|
June 7, 2018, 02:45 |
|
#3 |
Senior Member
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13 |
Thank you for your reply. Yes I managed to use the distributed memory, I write the machine names directly into the little bar, it works. But Fluent divides the total core number on its own.
So, could you please explain in more detail what you mean "put computer A 4 times and computer B 5 times". Where shall I "put" computer A and B ? Is it somewhere in the window when I launch Fluent in GUI ? PS: Solver setup - in CFX I meant the CFX window which pops up when you start CFX solver, not necessarily in workbench. Thank you verry much for your reply. |
|
June 18, 2018, 10:47 |
|
#4 |
Senior Member
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13 |
Any ideas please?
|
|
June 18, 2018, 11:42 |
|
#5 |
Senior Member
Lucky
Join Date: Apr 2011
Location: Orlando, FL USA
Posts: 5,676
Rep Power: 66 |
Also in the little bar but instead of
Code:
computerA computerB Code:
computerA computerA computerA computerA computerB comuterB computerB computerB computerB Code:
computerA computerB computerA computerB computerA comuterB computerA computerB computerB |
|
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Decomposing meshes | Tobi | OpenFOAM Pre-Processing | 22 | February 24, 2023 09:23 |
Cluster ID's not contiguous in compute-nodes domain. ??? | Shogan | FLUENT | 1 | May 28, 2014 15:03 |
Stable boundaries | marcoymarc | CFX | 33 | March 13, 2013 06:39 |
DecomposePar unequal number of shared faces | maka | OpenFOAM Pre-Processing | 6 | August 12, 2010 09:01 |
[blockMesh] BlockMeshmergePatchPairs | hjasak | OpenFOAM Meshing & Mesh Conversion | 11 | August 15, 2008 07:36 |