CERN Computing Colloquium

The SABUL Application Library for High Performance Data Transport: How to Move Very Large Data Sets Over Very Long Distances Using Today's Network Inf

by Robert Grossman (University of Illinois at Chicago and Open Data Partners)

Europe/Zurich
500/1-001 - Main Auditorium (CERN)

500/1-001 - Main Auditorium

CERN

400
Show room on map
Description
In this talk we describe the SABUL application level library for high performance data transport. SABUL combines a UDP data channel with a TCP control channel. SABUL uses the TCP control channel to provide reliable data transport. SABUL also employs a rate control and congestion control algorithm so that it is friendly to both TCP and other SABUL streams. In this talk we describe both experimental and simulation studies using SABUL.
SABUL has been used to move geoscience data between Chicago and Amsterdam at over 950 Mb/s (limited only by the 1 Gb/s NIC). A striped version of SABUL was used at iGrid 02 to move data between two three-node clusters located in Chicago and Amsterdam at over 2.8 G/bs. The SABUL library is being developed as an open source project at Source Forge and is available for deployment in applications today.

Biography
Robert Grossman - Biographical Sketch. Robert Grossman is the Director of the Laboratory for Advanced Computing (LAC) and the National Center for Data Mining (NCDM) at the University of Illinois at Chicago (UIC). The Lab and Center perform research, sponsor standards, manage an international data mining testbed, and engage in outreach activities in the areas of data mining and data intensive computing.
Robert Grossman became a faculty member at the University of Illinois at Chicago in 1988 and is a Professor of Mathematics, Statistics, and Computer Science UIC. He currently holds a part time appointment at UIC.
Grossman is the spokesperson for the Data Mining Group (DMG), an industry consortium responsible for the Predictive Model Markup Language (PMML), an XML language for data mining and predictive modeling, and the Web Services for Data Mining and Exploration (WSDMX) Standard.
Robert Grossman is also the Founder and President of Open Data Partners LLC. Prior to working at Open Data, he was the Founder of Magnify, Inc. where he is currently the Chairman.
He has published over 100 papers in refereed journals and proceedings on data mining, internet technologies, high performance computing, high performance networking, applications of data mining to database marketing and financial risk applications, and related areas. He has also edited six books.