CIT Training Course #476

#476

NIH Biowulf Supercluster for Scientific Applications


Description:
	The NIH Biowulf cluster is a Linux cluster designed and built at NIH which consists of over 3700 processors communicating over a fast network. The cluster is being used by NIH researchers for sequence analysis, phylogenetics and linkage analysis, computational chemistry, molecular modeling, proteomics and mass spectrometry analysis, mathematics, statistics, and structural biology. This hands-on class will give new users all the information they need to get started on the system. Information on the Biowulf cluster is now available.

Objectives:

This class is divided into 2 sessions:

Basic Session (9:30 - 12:00)
- introduction to the Biowulf Linux cluster, cluster concepts, accounts, logging in, storage options, interactive vs. batch jobs, how to set up and submit a simple batch job, batch queues, available software, and job monitoring.
Advanced Session (1:00 - 3:00)
- Followup to the basic session, for those users who will need to run molecular dynamics jobs, parallel programs, large-memory jobs, and/or require low-latency networks, or who will be developing their own code.
- Session will cover:
  - hardware & network configuration
  - types of nodes
  - selection of nodes using properties
  - system software
  - parallel programs
  - programming tools

Who should attend:
	NIH staff with a need or interest in high-performance scientific computing.

Instructor(s):
	Dr. Steven Fellini, Division of Computer System Services, CIT Dr. Susan Chacko, Division of Computer System Services, CIT

Sections Available:
-- Concluded --	476-09F	October 24	9:30 - 3:00	Building 12A, Room B51

NOTE: Although this course has already taken place, we'll put you on a waiting list for the next available session.

Course Listing