Changeset 3294 for trunk/DOC/TexFiles/Chapters/Chap_MISC.tex

Timestamp:

2012-01-28T17:44:18+01:00 (12 years ago)

Author:

rblod

Message:

Merge of 3.4beta into the trunk

File:

• trunk/DOC/TexFiles/Chapters/Chap_MISC.tex (modified) (1 diff, 1 prop)

trunk/DOC/TexFiles/Chapters/Chap_MISC.tex

@@ -253 +253 @@
 Note this implementation may be sensitive to the optimization level. 
 
+\subsection{MPP scalability}
+\label{MISC_mppsca}
+
+The default method of communicating values across the north-fold in distributed memory applications
+(\key{mpp\_mpi}) uses a \textsc{MPI\_ALLGATHER} function to exchange values from each processing
+region in the northern row with every other processing region in the northern row. This enables a
+global width array containing the top 4 rows to be collated on every northern row processor and then
+folded with a simple algorithm. Although conceptually simple, this "All to All" communication will
+hamper performance scalability for large numbers of northern row processors. From version 3.4
+onwards an alternative method is available which only performs direct "Peer to Peer" communications
+between each processor and its immediate "neighbours" across the fold line. This is achieved by
+using the default \textsc{MPI\_ALLGATHER} method during initialisation to help identify the "active"
+neighbours. Stored lists of these neighbours are then used in all subsequent north-fold exchanges to
+restrict exchanges to those between associated regions. The collated global width array for each
+region is thus only partially filled but is guaranteed to be set at all the locations actually
+required by each individual for the fold operation. This alternative method should give identical
+results to the default \textsc{ALLGATHER} method and is recommended for large values of \np{jpni}.
+The new method is activated by setting \np{ln\_nnogather} to be true ({\bf nammpp}). The
+reproducibility of results using the two methods should be confirmed for each new, non-reference
+configuration.
 
 % ================================================================