Changes between Version 14 and Version 15 of ParallelismPerformances

Timestamp:

2012-11-23T10:53:55+01:00 (11 years ago)

Author:

dsolyga

Comment:

--

ParallelismPerformances

@@ -164 +164 @@
 
 
-=== Methodology (22/11/2012) ===
+=== Patch Evaluation ===
 
 In order to study both the influence of the IO patches and the Load balance file, I make a survey using the following setup :
@@ -183 +183 @@
 Notice that the patch is significant for a high number of processors (>16). For 32 and 48 processors, the gain is about 60% (it seems that it is the optimal for NCC).
 After 48, the gain diminished. [[BR]]
+''' Recommendations  : '''
+ * NCC forcing files : 32 processors
+ * CRUNCEP : ~128 processors (evaluation as CRUNCEP has 4 times more points than NCC) 
+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
+writring of output files.[[BR]]
+To 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
+processors was evaluated to 6!