Several users have noticed poor latency with Open MPI when using the
new Mellanox ConnectX HCA hardware. Open MPI was getting about 1.9us
latency with 0 byte ping-pong benchmarks (e.g., NetPIPE or
osu_latency). This has been fixed in OMPI v1.2.4.
Short version:
--
Open MPI v1
Dear Reuti and Harvey,
I just tried by setting control_slaves to TRUE and it works!
Thank you very much,
Vittorio
On Oct 17, 2007, at 7:48 PM, Reuti wrote:
Hi,
Am 17.10.2007 um 18:49 schrieb Vittorio Zaccaria:
I am just trying to run a very simple application using mpirun in
an SGE 6 e
Can you send a short test program that shows this problem, perchance?
On Oct 3, 2007, at 1:41 PM, Daniel Rozenbaum wrote:
Hi again,
I'm trying to debug the problem I posted on several times recently;
I thought I'd try asking a more focused question:
I have the following sequence in the cl
This looks like a compiler issue, to me. It is probably worth asking
your Intel compiler support people as to why this happens.
I tried with both icc 9.1 and 10.0 and am able to replicate your
findings:
it works fine without -fast, but claims that it can't find mpi_f90
when you use -fast:
On Oct 17, 2007, at 12:35 PM, Jim Kusznir wrote:
checking if Fortran 90 compiler supports LOGICAL... yes
checking size of Fortran 90 LOGICAL... ./configure: line 34070: 7262
Segmentation fault ./conftest 1>&5 2>&1
configure: error: Could not determine size of LOGICAL
Awesome! It looks l
Hi,
Am 17.10.2007 um 18:49 schrieb Vittorio Zaccaria:
I am just trying to run a very simple application using mpirun in
an SGE 6 environment.
The job is called 'example' and it is submitted to the SGE
environment with the
following command:
> qsub -pe parallel 2 example
where 'parallel'
Hello,
I am just trying to run a very simple application using mpirun in
an SGE 6 environment.
The job is called 'example' and it is submitted to the SGE
environment with the
following command:
> qsub -pe parallel 2 example
where 'parallel' is a working parallel environment.
'example' is
Hello:
I'm trying to rebuild the CentOS OpenMPI rpm (to add torque support)
on my x86_64 cluster. I was able to build 64-bit binaries fine, but
CentOS wants the 32-bit libs and -devel portions installed as well for
full compatability. In this area, I'm running into trouble.
When I try and build
The CM PML only support networks that do matching in hardware. In
Open MPI temrs, the CM PML require one of the MTL (instead of the BTL
for all others PML). For a full list of supported networks, one can
list the content of the ompi/mca/mtl directory (right now: Myrinet,
Portals and QSLogic
Hi,
I am trying to use the cm component from pml, but when I execute the
command: "mpirun -np 2 --mca pml cm ompi_test", I get the error message
that "No available pml components were found". I did a ompi_info to see if
the cm component exist, and it does. The output of ">ompi_info | grep cm"
Hi all,
I'm using OpenMPI 1.2.2 with Intel compilers (icc, ifort)
But I found mpicc and mpif90 cannot work with Intel -fast optimisation.
[ywan@frontend01 hello]$ mpif90 -fast -o hello -i-dynamic hello.f90
IPO: performing
11 matches
Mail list logo