Yo all
Per last week's discussions, I have created a set of new simplified
API's for the registry. These include:
1. orte_gpr.put_1 and orte_gpr.put_N: these allow you to put data on
the registry without having to define your own value structures. They
take a segment name, a NULL-terminated
This is one of the few topics that we didn't get to discuss last week.
I think there are two main parts -- an easy part and a hard part. :-)
Easy part: the processor affinity framework and its interface
Hard part: how and when this framework is invoked in Open MPI
Processor affinity framework
On Aug 2, 2005, at 10:23 AM, Torsten Hoefler wrote:
Hi all,
after having some off-list conversation about enabling thread support
for applications using Open MPI, I found several errors during
compilation (revision 6701 with --enable-mpi-threads):
* mutex.h:267
OMPI_SIZEOF_SIZE_T is not defined
Will re-add back to the nightlies -- the nightlies were initially
configured when threads were the default, so there are currently builds
that explicitly turn threads *off*. :-)
On Aug 2, 2005, at 11:26 AM, Brian Barrett wrote:
I'll take a look today. We should probably add the threaded bu
I'll take a look today. We should probably add the threaded builds
back into the nightly build tests...
Brian
On Aug 2, 2005, at 10:23 AM, Torsten Hoefler wrote:
Hi all,
after having some off-list conversation about enabling thread support
for applications using Open MPI, I found several er
Hi all,
after having some off-list conversation about enabling thread support
for applications using Open MPI, I found several errors during
compilation (revision 6701 with --enable-mpi-threads):
* mutex.h:267
OMPI_SIZEOF_SIZE_T is not defined
* orte_pointer_array.c:358
table is not defined
Coul