The new Blugold Supercomputing Cluster is ready to be used for research applications and classroom activities. This is still in 'beta phase', meaning some of the utilities are still being tested. Therefore, please try your applications and share your results with the BGSC.Admins group. Please use your university id to login to the cluster. Jobs can be submitted using job-queuing programs 'condor' or 'torque'.

Blugold Super Computing Cluster
In order to facilitate students’ learning and discovery in all science and computationally related disciplines, a high performance supercomputer cluster with graphical processing units (GPUs) was proposed for the University campus. Morgan Leider (Chemistry Major), William C.‎ Cox (LTS), Marc McEllistrem (Material Science), Fred King (Chemistry), and Sudeep Bhattacharyay (Chemistry) worked together to develop the initial proposal requesting funding for 16 Nodes with two 6-core processors on each node running at around 3.5 GHz. (192 cores at 3.5 GHz). Additionally, 4 GPUs were also sought on the cluster for using CUDA or OpenCL enabled programs. Other faculty members contributed to the proposal include: Biology: Derek Gingerich; Chemistry: Patricia Cleary, Steven Drucker, Sanchita Hati, Christine Morales, Jim Phillips, and Fred King; Computer Science: Peter Bui, Christopher Johnson, and Daniel Stevenson; Geology: Phillip Ihinger; LTS: William Cox, Craig May, Thomas Paine, and Steve Ranis; Mathematics: Mohammed Aziz, Carolyn Otto, Mike Penkava, Alex Smith, and Ursula Whitcher; Material Science: Marc McEllistream; Physics: Paul Thomas; Thomas Bartholow and Alex Strom (students, Chemistry).  The contributing members agreed that Dr. Sudeep Bhattacharyay (Chemistry) will serve as the principal coordinator for this project.

The scientific computing approach is to gain understanding of physical and chemical systems, through the analysis of mathematical models and computer simulations. Therefore, computation is the key to expedite students’ learning and discovery in all science-related disciplines. With informational technology delivering higher amounts of information at a faster pace and electronic devices becoming smarter and friendlier in educating ourselves, high-performance computing is posed to be a central tool to enhance learning, research, and discovery. This Blugold Supercomputing Cluster initiative will help to integrate computational studies in many course curricula as well as promote campus-wide collaborations to advance faculty-student research endeavors.
The proposal was funded in 2012 and the project received enough funding ($149,852.00) to purchase 2 GPU nodes, 1 head node, and 8 computing nodes and software.

BGSC WIKI

https://www.uwec.edu/bgsc/

Hardware

One head node, eight computing nodes, and two GPU nodes with a total of 8 GPU cards

Each node is equipped with 20 units of E5-2670V2 processors (called cores)

Software

A partial list of software is given in the following section:

Department of Chemistry
Gaussian09- A computational chemistry computer program enabling electronic structure calculations at different levels of theory
Gamess- A computational chemistry software program to perform electronic structure calculations at different levels of theory
QCHEM- A general-purpose electronic structure package featuring a variety of established and new methods implemented using innovative algorithms that enable fast calculations of large systems on regular lab workstations using density functional and wave-function based approaches.
NAMD- A freeware molecular dynamics simulation package useful for protein dynamics simulations using molecular mechanics

Department of Computer Science
Python- A widely used general-purpose, high-level programming language.
GCC- A compiler system produced by the GNU Project supporting various programming languages.
PGI Compiler- PGI compilers incorporate global optimization, vectorization, software pipelining, and shared-memory parallelization capabilities targeting both Intel and AMD processors.
FFTW 1.3- C subroutine library for computing the discrete Fourier transform in one or more dimensions, of arbitrary input size, and of both real and complex data
Cuda- A parallel programming framework.
MPL- an advanced modeling system that allows the model developer to formulate complicated optimization models in a clear, concise, and efficient way.
Condor- a specialized workload management system for compute-intensive jobs.
Intel Fortran- Compilers generate code for IA-32 and Intel 64 processors and certain non-Intel but compatible processors.

Department of Biology
Phyml- a software that estimates maximum likelihood phylogenies from alignments of nucleotide or amino acid sequences

Department of Mathematics
Mathematica- A computational software program used in many scientific, engineering, mathematical and computing fields, based on symbolic mathematics.
Magma- A software assisting computations in algebra, number theory, algebraic geometry and algebraic combinatorics.

-------------------------

If you need to log in to the BGSC cluster, please read the following section

If you are working off-campus, you will need VPN. Please visit (http://www.uwec.edu/Help/drives/vpn.htm).

If you are using campus network, you will have to use 'putty' on a PC or an unix shell to login to the cluster.

In putty or the unix shell, type 'ssh bgsc.uwec.edu' enter your 'university id' and 'password' to login

Jobs can be submitted

You can submit jobs by using either 'condor' or 'torque'

See /data/scratch/ for example of scripts

Contact us:

BGSC.ADMINS