Search Documentation

Oakley, Owens, Ruby

ParMETIS (Parallel Graph Partitioning and Fill-reducing Matrix Ordering) is an MPI-based parallel library that implements a variety of algorithms for partitioning unstructured graphs, meshes, and for computing fill-reducing orderings of sparse matrices. ParMETIS extends the functionality provided by METIS and includes routines that are especially suited for parallel AMR computations and large scale numerical simulations. The algorithms implemented in ParMETIS are based on the parallel multilevel k-way graph-partitioning, adaptive repartitioning, and parallel multi-constrained partitioning schemes developed in Karypis lab.

METIS (Serial Graph Partitioning and Fill-reducing Matrix Ordering) is a set of serial programs for partitioning graphs, partitioning finite element meshes, and producing fill reducing orderings for sparse matrices. The algorithms implemented in METIS are based on the multilevel recursive-bisection, multilevel k-way, and multi-constraint partitioning schemes developed in Karypis lab.

Glenn, Oakley, Ruby

Connections to OSC

In order for users to access OSC resources through the web your firewall rules should allow for connections to the following IP ranges.  Otherwise, users may be blocked or denied access to our services.

  • 192.148.248.0/24
  • 192.148.247.0/24
  • 192.157.5.0/25

The followingg TCP ports should be opened:

  • 80 (HTTP)
  • 443 (HTTPS)
  • 22 (SSH)

The following domain should be allowed:

Oakley

SuiteSparse is a suite of sparse matrix algorithms, including: UMFPACK(multifrontal LU factorization), CHOLMOD(supernodal Cholesky, with CUDA acceleration), SPQR(multifrontal QR) and many other packages.

Ruby

OSC is refreshing the software stack on Ruby on September 15, 2015 (during the scheduled downtime). During the software refresh, some default versions are updated to be more up-to-date. Information about the old and new default versions, as well as all available versions of each software package will be included on the corresponding OSC software webpage. See https://www.osc.edu/supercomputing/software-list.

Glenn, Oakley, Ruby

OSC timely installs new software versions on OSC systems, and periodically do coordinated software refresh (update the default versions to be more up-to-date and remove some versions that are quite out of date) on OSC systems. While we encourage everyone to use up-to-date software, the old defaults will still be available till the next software refresh, in case some users prefer to use the old defaults.

Oakley

OSC is refreshing the software stack on Oakley on September 15, 2015 (during the scheduled downtime); something we have not done since Oakley entered service in 2012. During the software refresh, some default versions are updated to be more up-to-date and some older versions are removed. Information about the old and new default versions, as well as all available versions of each software package will be included on the corresponding OSC software webpage.

Ruby

Full Node Charging Policy

Oakley

Memory Limit:

It is strongly suggested to consider the memory use to the available per-core memory when users request OSC resources for their jobs. On Oakley, it equates to 4GB/core and 48GB/node.

Glenn

Memory Limit:

It is strongly suggested to consider the memory use to the available per-core memory when users request OSC resources for their jobs. On Glenn, it equates to 3GB/core and 24GB/node.

Oakley, Owens, Ruby

Introduction

Pages