FWIW, I get a bunch of valid-looking compiler warnings when running
"make check" in the test/datatype directory.
On Sep 3, 2009, at 7:42 PM, Ralph Castain wrote:
Hi folks
A recent commit to the trunk is apparently causing "make check" to
fail due to an assertion failure in an opal datatype t
- "David Robertson" wrote:
> Hi all,
Hiya,
> We use both the PGI and Intel compilers over an
> Infiniband cluster and I was trying to find a way
> to have both orteruns in the path (in separate
> directories) at the same time.
Not a solution, but what we do here is to arrange our
installs
What happens if $sysconfdir/openmpi-priv-mca-params.conf is missing ?
Can the file name ( openmpi-priv-mca-params.conf ) also be configurable ?
Rich
On 9/3/09 5:23 AM, "Nadia Derbey" wrote:
What: Define a way for the system administrator to prevent users from
overwriting the default s
Hi all,
We use both the PGI and Intel compilers over an Infiniband cluster and I
was trying to find a way to have both orteruns in the path (in separate
directories) at the same time. I decided to use the --program-suffix
option. However, all the symlinks in the resulting bin directory point
Hi folks
A recent commit to the trunk is apparently causing "make check" to
fail due to an assertion failure in an opal datatype test. I have
turned this test "off" until someone can fix it as it is preventing
the creation of a tarball.
Could someone knowledgeable in the datatype changes
