[Cbc] Parallel computations with CBC

["Büsing, Henrik"]

That is also what I was thinking. I am having only very few branches.
Probably, I still have to find a model where I am getting enough branches to
see the parallelization. 

 

Thank you!
Henrik

 

 

-- 

Dipl.-Math. Henrik Büsing

Jülich Supercomputing Centre

Institute for Advanced Simulation

 

Forschungszentrum Jülich

Wilhelm-Johnen-Straße

52425 Jülich, Germany

 

Phone:  +49-2461-61-9884

Fax:    +49-2461-61-6656

E-Mail: H.Buesing at fz-juelich.de

WWW:    http://www.fz-juelich.de/ias/jsc

----------------------------------------------------------------------------
---------

----------------------------------------------------------------------------
---------

Forschungszentrum Juelich GmbH

52425 Juelich

Sitz der Gesellschaft: Juelich

Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498

Vorsitzender des Aufsichtsrats: MinDir Volker Rieke

Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender),

Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,

Prof. Dr. Sebastian M. Schmidt

----------------------------------------------------------------------------
---------

----------------------------------------------------------------------------
---------

 

Von: Tobias Stengel [mailto:Tobias.Stengel at locom.de] 
Gesendet: Donnerstag, 19. September 2019 13:01
An: Büsing, Henrik <h.buesing at fz-juelich.de>; cbc at list.coin-or.org
Betreff: AW: Parllel computations with CBC

 

Are you sure that CBC is already branching when look for the CPU
utilization?

Processing of the root node i.e. solving the root relaxation is single
threaded and can take quite some time depending on the model.

 

 

  _____  

Von: Cbc [cbc-bounces at coin-or.org]" im Auftrag von ""Büsing, Henrik"
[h.buesing at fz-juelich.de]
Gesendet: Donnerstag, 19. September 2019 11:21
An: cbc at list.coin-or.org <mailto:cbc at list.coin-or.org> 
Betreff: [Cbc] Parllel computations with CBC

Dear all, 

 

I am trying to run CBC in parallel. I did a 

 

../coinbrew fetch Cbc

../coinbrew build Cbc --enable-cbc-parallel
--prefix=/work/user/METIS/Cbc/build/build_parallel/ --test

 

and then run

 

cbc -threads 16 -import model.mps –solve

 

Cbc responds with 

 

“threads was changed from 0 to 16”

 

but I do not see any CPU utilization on more than one core. 

 

Any ideas on how I could check, I did everything right? 

Thank you for your help!
Henrik Büsing

 

 

-- 

Dipl.-Math. Henrik Büsing

Jülich Supercomputing Centre

Institute for Advanced Simulation

 

Forschungszentrum Jülich

Wilhelm-Johnen-Straße

52425 Jülich, Germany

 

Phone:  +49-2461-61-9884

Fax:    +49-2461-61-6656

E-Mail: H.Buesing at fz-juelich.de <mailto:H.Buesing at fz-juelich.de> 

WWW:    http://www.fz-juelich.de/ias/jsc

----------------------------------------------------------------------------
---------

----------------------------------------------------------------------------
---------

Forschungszentrum Juelich GmbH

52425 Juelich

Sitz der Gesellschaft: Juelich

Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498

Vorsitzender des Aufsichtsrats: MinDir Volker Rieke

Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender),

Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,

Prof. Dr. Sebastian M. Schmidt

----------------------------------------------------------------------------
---------

----------------------------------------------------------------------------
---------

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://list.coin-or.org/pipermail/cbc/attachments/20190919/f397b6e5/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 6327 bytes
Desc: not available
URL: <http://list.coin-or.org/pipermail/cbc/attachments/20190919/f397b6e5/attachment-0001.p7s>