CFD Online Logo CFD Online URL
www.cfd-online.com
[Sponsors]
Home > Forums > Software User Forums > ANSYS > FLUENT

Fluent core number specification - 2 computers

Register Blogs Community New Posts Updated Threads Search

Reply
 
LinkBack Thread Tools Search this Thread Display Modes
Old   June 6, 2018, 04:46
Default Fluent core number specification - 2 computers
  #1
Senior Member
 
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13
Jiricbeng is on a distinguished road
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.
Jiricbeng is offline   Reply With Quote

Old   June 6, 2018, 09:22
Default
  #2
Senior Member
 
Lucky
Join Date: Apr 2011
Location: Orlando, FL USA
Posts: 5,676
Rep Power: 66
LuckyTran has a spectacular aura aboutLuckyTran has a spectacular aura aboutLuckyTran has a spectacular aura about
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.
LuckyTran is offline   Reply With Quote

Old   June 7, 2018, 02:45
Default
  #3
Senior Member
 
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13
Jiricbeng is on a distinguished road
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.
Jiricbeng is offline   Reply With Quote

Old   June 18, 2018, 10:47
Default
  #4
Senior Member
 
Jiri
Join Date: Mar 2014
Posts: 218
Rep Power: 13
Jiricbeng is on a distinguished road
Any ideas please?
Jiricbeng is offline   Reply With Quote

Old   June 18, 2018, 11:42
Default
  #5
Senior Member
 
Lucky
Join Date: Apr 2011
Location: Orlando, FL USA
Posts: 5,676
Rep Power: 66
LuckyTran has a spectacular aura aboutLuckyTran has a spectacular aura aboutLuckyTran has a spectacular aura about
Also in the little bar but instead of

Code:
computerA computerB
you should write
Code:
computerA computerA computerA computerA computerB comuterB computerB computerB computerB
This tells Fluent the priority it should assign the processes to. Note that order matters. In this example it will use up all 4 on computerA before it assigns any to computerB. If you want to stripe it across two machines (which is a bad idea but a good example nonetheless) and alternate ABABABABB then you would write something like:
Code:
computerA computerB computerA computerB computerA comuterB computerA computerB computerB
LuckyTran is offline   Reply With Quote

Reply


Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are On
Refbacks are On


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


All times are GMT -4. The time now is 15:55.