SGI UV2000 / Venus (Outdated)¶
This page is deprecated! The SGI UV2000 (Venus) is a former system!
The SGI UV2000 is a shared memory system based on Intel Sandy Bridge processors. It is operated by the Linux operating system SLES 11 SP 3 with a kernel version 3.x.
|Number of CPU sockets
|Physical cores per sockets
|Total number of cores
From our experience, most parallel applications benefit from using the additional hardware hyperthreads.
Venus uses the same home filesystem as all our other HPC installations.
For computations, please use
Login to the System¶
Login to the system is available via ssh at
The RSA fingerprints of the Phase 2 Login nodes are:
The installation of the Message Passing Interface on Venus (SGI MPT) supports the MPI 2.2 standard
man mpi ). There is no command like
mpicc, instead you just have to use the "serial"
ifort) and append
-lmpi to the linker command line.
% icc -o myprog -g -O2 -xHost myprog.c -lmpi
- C++ programmers: You need to link with both libraries:
- Fortran programmers: The MPI module is only provided for the Intel
compiler and does not work with
Please follow the following guidelines to run your parallel program using the batch system on Venus.
Applications on an HPC system can not be run on the login node. They have to be submitted to compute nodes with dedicated resources for the user's job. Normally a job can be submitted with these data:
- number of CPU cores,
- requested CPU cores have to belong on one node (OpenMP programs) or can distributed (MPI),
- memory per process,
- maximum wall clock time (after reaching this limit the process is killed automatically),
- files for redirection of output and error messages,
- executable and command line parameters.
The batch system on Venus is Slurm. Please see general information on Slurm.
Submission of Parallel Jobs¶
The MPI library running on the UV is provided by SGI and highly optimized for the ccNUMA architecture of this machine.
On Venus, you can only submit jobs with a core number which is a multiple of 8 (a whole CPU chip and 128 GB RAM). Parallel jobs can be started like this:
srun -n 16 a.out
Please note: There are different MPI libraries on Venus than on other ZIH systems, so you have to compile the binaries specifically for their target.
- The large main memory on the system allows users to create RAM disks within their own jobs.