[Mpi3-tools] New MPIT draft available / Question regarding Verbosity
schulzm at llnl.gov
Mon Feb 8 02:14:05 CST 2010
I uploaded a new draft of the MPIT proposal to
Changes since the last draft are marked with changebars and are
colored in green.
The latest draft contains changes based on comments from Kathryn
the MPI group at Sun/Oracle.
There is one open question that I would like to bring up for a general
as discussed in the WG earlier, we need some kind of verbosity
allows the MPI implementation to classify each variable according to
and general usage scenario. Jeff and I have been going forth and back
one for a while over email, but we can't come to a useful conclusion
would like wider feedback.
In general, we both think that we want 5 classes of verbosity (odd
than 3, but not too large).
The original proposal had the following classes
which was rejected by the forum (I think rightfully so) since it
doesn't really convey
any useful application level information.
The current proposal has:
with the idea that the first two classes are intended for general MPI
the third and fourth for performance experts and system administrators
wishing to tune the performance of MPI itself, while the fifth is for
implementors and would include debugging information.
Open MPI uses a similar idea of verbosity and defines the following
However, both Jeff and I don't like these classes, since they don't
any useful information either.
Jeff proposes something like
but this proposal misses good names for 2 and 4.
Any comments or suggestions (either extending one of the above or
new) would be very much appreciated.
Martin Schulz, schulzm at llnl.gov, http://people.llnl.gov/schulzm
CASC @ Lawrence Livermore National Laboratory, Livermore, USA
More information about the mpiwg-tools