diff options
| author | Thomas Radke <tradke@aei.mpg.de> | 2005-05-26 11:42:00 +0000 |
|---|---|---|
| committer | Thomas Radke <tradke@aei.mpg.de> | 2005-05-26 11:42:00 +0000 |
| commit | 6a5fdd7e19335d54e102a6e5b7211fc920c94317 (patch) | |
| tree | 7bce2af36a1d658587a5957b673985ce739f425e /Carpet/CarpetLib/param.ccl | |
| parent | cbe3768986ffe1b8156427751d617f124f6fabfe (diff) | |
CarpetLib: clean-up of communication scheme for individual sends/recvs on single components
The default communication scheme in Carpet (which does an individual send/recv
operation for each component) comes with two parameters for fine tuning:
CarpetLib::use_lightweight_buffers
CarpetLib::combine_recv_send
the defaults of which are set to use a well-tested but also slower
communication pattern (as turned out during benchmark runs).
This patch cleans up the implementation of this communication scheme so that the
fastest communication pattern (combined posting of send/recv; use of lightweight
buffers) is now always used. The above parameters therefore became obsolete
and shouldn't be used anymore in parfiles.
darcs-hash:20050526114253-776a0-780933a1539a260d74da8b92522fa2f48c714964.gz
Diffstat (limited to 'Carpet/CarpetLib/param.ccl')
| -rw-r--r-- | Carpet/CarpetLib/param.ccl | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/Carpet/CarpetLib/param.ccl b/Carpet/CarpetLib/param.ccl index 4cd753401..6966e1282 100644 --- a/Carpet/CarpetLib/param.ccl +++ b/Carpet/CarpetLib/param.ccl @@ -37,11 +37,11 @@ BOOLEAN use_waitall "Use MPI_Waitall instead individual MPI_Wait/MPI_Waitsome st { } "yes" -BOOLEAN combine_recv_send "Combine MPI_Irecv and MPI_Isend calls" +BOOLEAN combine_recv_send "Combine MPI_Irecv and MPI_Isend calls -- DEPRECATED - DO NOT USE ANYMORE" { } "no" -BOOLEAN use_lightweight_buffers "Use lightweight communication buffers instead of data objects" +BOOLEAN use_lightweight_buffers "Use lightweight communication buffers instead of data objects -- DEPRECATED - DO NOT USE ANYMORE" { } "no" |