Open MPI unfortunately has to play some tricks with the malloc system when
using InfiniBand or the Cray interconnects. One other option is to set
the environment variable
OMPI_MCA_memory_linux_disable
to some non-zero value. That will disable the evil memory hooks, which
might help if PGI is
Jeff added a jdoc target in '~/ompi-java/ompi/mpi/java/java/Makefile.am'.
Javadoc is created in '~/ompi-java/ompi/mpi/java/java/doc'
I think javadoc could be created if you select '--enable-mpi-java',
and it could be copied in '~/ompi-install/share/javadoc'.
From: Ralph Castain
Subject: Re
The fix to build Java hasn't moved to 1.7 yet - waiting for Jeff to return from
vacation to review it.
Per your prior note about mpiexec hanging on Sparc, there is no reason why the
Java bindings would alter that situation. So the problem is the same, and I
won't create a new ticket for the jav
-bycore should still be available for backward compatibility, so I'll check
that one. I'll have to look to see what your binding pattern didn't work
https://svn.open-mpi.org/trac/ompi/ticket/4044
On Jan 1, 2014, at 1:48 AM, Siegmar Gross
wrote:
>
> Option "-bycore" isn't available any longe
This is clearly a problem with the allocator not picking up the rankfile nodes
- I'll have to take a look at it
https://svn.open-mpi.org/trac/ompi/ticket/4043
On Jan 1, 2014, at 1:48 AM, Siegmar Gross
wrote:
> Next I tried process binding.
>
> rf_linpc:
> -
> rank 0=linpc1 slot=0:0,1
Not sure I understand the problem here - are you saying that the proc ran, but
then mpiexec hangs instead of exiting?
On Jan 1, 2014, at 1:48 AM, Siegmar Gross
wrote:
> Nevertheless I have another problem with my small program.
>
> tyr small_prog 158 uname -p
> sparc
> tyr small_prog 159 ssh
We shouldn't just hang - that isn't right. Can you configure OMPI with
--enable-debug and then add "-mca plm_base_verbose 5 -mca state_base_verbose 5"
to your cmd line so we can see where it is hanging?
On Jan 1, 2014, at 1:48 AM, Siegmar Gross
wrote:
> In the past I could run a small progra
I believe that the Javadoc doesn't install by default - Jeff?
On Jan 1, 2014, at 1:48 AM, Siegmar Gross
wrote:
> "make install" didn't install the Javadoc documentation for the
> new Java interface. Is it necessary to install it in a separate
> step?
>
> tyr small_prog 118 ls -l /usr/local/ope
I'm going to split this apart so we can deal with these in a more manageable
fashion.
I have no ideas here as there isn't enough info - can you dig deeper to tell us
where the sigbus happens?
Meantime, I filed a ticket against it and we can capture your response there.
https://svn.open-mpi.org
Hi,
yesterday I installed openmpi-1.9a1r30100 on "Solaris 10 x86_64",
"Solaris 10 Sparc", and "openSUSE Linux 12.1 x86_64" with Sun C
5.12. First of all the good news: "configure", "make", "make
install", and "make check" completed without errors, i.e., "make
check" doesn't produce a "SIGBUS Error
10 matches
Mail list logo
