HP-MPI Version 2.2.5 for Linux Release Note

HP-MPI V2.2.5 for Linux Release Note
What’s in This Version
13
An abbreviated example would be:
MPI_IC_SUFFIXES="VAPI_MAIN:VAPI_CISCO"
MPI_ICLIB_VAPI__VAPI_MAIN="libmtl_common.so:libmpga.so:libmosal.so:libvapi.so
"MPI_ICMOD_VAPI__VAPI_MAIN ="^mod_vapi :||:^mod_vip "
MPI_ICLIB_VAPI__VAPI_CISCO="libpthread.so:libmosal.so:libvapi.so
"MPI_ICMOD_VAPI__VAPI_CISCO="^mod_vapi :||:^mod_vip "
When HP-MPI checks for VAPI availability, it will first try to dlopen the four libraries given in
the MPI_ICLIB_VAPI__VAPI_MAIN variable, and see if the modules listed in
MPI_ICMOD_VAPI__VAPI_MAIN are loaded. If that fails, it will then try the library and modules
listed in MPI_ICMOD_VAPI__VAPI_CISCO. The values in the variables are split into a list of
items based on the ":" character or the tab character. This makes the settings shown in
hpmpi.conf somewhat more readable than the above example, because there the list entries
are tab separated instead of ":" separated as above.
MPI-2 name publishing support HP-MPI now supports the MPI-2 dynamic process
functionality MPI_Publish_name, MPI_Unpublish_name, MPI_Lookup_name, with the
restriction that a separate nameserver must be started up on a server.
The service can be started as:
% $MPI_ROOT/bin/nameserver
and it will print out an IP and port. Then when running mpirun, the extra option
-nameserver with an IP address and port must be provided:
% $MPI_ROOT/bin/mpirun -spawn -nameserver <IP:port> ...
The scope over which names are published and retrieved consists of all mpiruns which are
started using the same IP:port for the nameserver.
IB partitioning support HP-MPI supports IB partitioning via Mellanox VAPI and open
fabric Verbs API.
By default, HP-MPI will search the unique full membership partition key from the port
partition key table used. If no such pkey is found, an error is issued. If multiple pkeys are
found, all such pkeys are printed and an error message is issued.
If the environment variable MPI_IB_PKEY has been set to a value, either in hex or decimal, the
value is treated as the pkey, and the pkey table is searched for the same pkey. If the pkey is
not found, an error message is issued.
When a rank selects a pkey to use, a check is made to make sure all ranks are using the same
pkey. If ranks are not using the same pkey, and error message is issued.