Intel® Clusters and HPC Technology

Issues with Intel MPI 4.0 Beta

I am testing out the beta for Intel MPI 4.0. I am having a problem where my application (WRF V3.0.1) is hanging in MPI_Finalize when a large number of cores are being used (>1024). The OS is Centos 5.3 and I am using OFED-1.4.1.

Is the the right place to ask questions about the beta? If not, where is?
If it is, what options do I have for debugging so that I can gather up the right information for Intel developers?


Installing the Intel Cluster Toolkit Compiler Edition on a GE + IB cluster


I have successfully installed the ICTCE on a simple GE cluster with
one switch and set of interfaces. What, if any, are the tricks and
complications when installing on a system with two networks (GE and
IB). I obviously wish the be able to run MPI over the IB network,
but would like to use and test either as I wish.

The installation guide offers no information on this question as far
as I can tell. The instructions ask you with construct the machines.LINUX
file using the hostname generated names for the compute nodes.

Hardware Performance Counters ; Power measurement

I have a 4-node Intel Nehalem cluster and a 512 core Intel Clovertown cluster. I am interested in looking for some tools to measure the power consumed by parallel applications. I know that we can use external devices to measure and log power consumption. I would like to know if someone around here has some experience with any particular tool-kit. I would greatly appreciate it if someone can point me in the right direction.

Using new unified installer for Cluster Tools 3.2.2 - Slow

I downloaded the new cluster toolkit 3.2.2.

Little 128 node cluster with master node.

The install scipt installs the rpms onto the master node.
Then it is taking quite awhile to 'Analyze node configuration'
Watching it's progress: It's taken 46 minutes to process 23 nodes.
I'm guessing the installer is attempting to discern network topology, or if any compute nodes share the install directory.
Though, when prompted by the installer, I selected 'non-shared' install, i.e. /opt/intel is local on each compute node.

Running mpi w/o mpiexec/mpirun

I can compile and run a mpi application using mpiexec without any difficulties.
What I want to do is to run a mpi application not in Terminal,I mean without using mpiexec or mpirun.
Is this doable? If it is, how can I setup mpd daemon and other necessary stuffs in source level?


static int run()
Subscribe to Intel® Clusters and HPC Technology