Changes between Version 15 and Version 16 of ParallelismPerformances


Ignore:
Timestamp:
2012-11-23T10:58:02+01:00 (11 years ago)
Author:
dsolyga
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • ParallelismPerformances

    v15 v16  
    186186 * NCC forcing files : 32 processors 
    187187 * CRUNCEP : ~128 processors (evaluation as CRUNCEP has 4 times more points than NCC)  
    188 Summary : ORCHIDEE should be used on more than 128 processors for the moment. I you increase the number of processors, you could lose time because of MPI communications and the multiple 
     188 * Other forcing files : use a linear relationship to evaluate your number of processors. If you have 45000 points you could use 32*3 = 96 processors.  
     189 
     190__Summary__ : ORCHIDEE should be used on more than 128 processors for the moment. I you increase the number of processors, you could lose time because of MPI communications and the multiple 
    189191writring of output files.[[BR]] 
    190192To know how the parallelization has been improved, you could read the following report [wiki:ParallelVersion here] (in french sorry!). In this report, the optimal number of