The LAM Team is pleased to release version 7.0.3.
What's a Supercomputing conference without a release from LAM/MPI? :-)
(if you're at SC, be sure to drop by and see us in the "Research in
Indiana" booth)
This is mainly a bug-fix release. The only new piece of functionality in
version 7.0.3 is improved support for very large clusters using the TCP
RPI. A long standing issue with lamd communication causing networking
issues has been resolved.
LAM tarballs, RH 8.0 i586 RPMs, and a Mac OS X 10.3 package is
available from the LAM/MPI main web site (and will be available on the
mirrors shortly): http://www.lam-mpi.org/.
A summary of the fixes are listed below:
- Minor fixes with bad printf() formats in the kenyad and blcr/crlam.
Thanks to Paul Hargrove for pointing these out to us.
- Workaround for libtool 1.5 bug with the Intel compiler (libtool
didn't think that icc supported -c and -o at the same time). Thanks
to Jon Bernard for bringing this to our attention.
- Changed LAM_CONFIGURE_* macros from -D command line arguments to
#define's to prevent problems with some compilers that don't like -D
values with embedded spaces. Thanks to Harshu for bringing this to
our attention.
- Changed search order for Fortran compilers to look for GNU g77
before f77 so that the default matches the defaults for the C and
C++ compilers. Thanks to Siegmar Gross for pointing this out.
- Removed LAM_NEED_SYS_SELECT_H, instead including sys/select.h any
time it is available.
- Updated SYS V semaphore and shmem tests to check for functionality.
Adds -lrt (Solaris) and -lcygipc (Cygwin) if needed.
- Added configure switch --with-fd-setsize to increase the size of an
FD_SET and increase the soft per-process file descriptor limit on
platforms that support such things. This should allow larger TCP
LAM jobs on platforms that support large FD_SET arrays. Be sure to
read the release notes for your platform before using this option.
- Fix issue with timeouts in the lamd's ACK code. It appears this was
due to a longstanding confusion as to whether TO_DLO_ACK was in
seconds or microseconds.
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
|
