Download No Slide Title

The University of Washington
eScience Institute
This afternoon:
 Phyllis Wise, Provost
 Ed Lazowska, Computer Science &
Engineering
 Dan Fay, Microsoft Research
 Martin Savage, Physics
 David Baker, Biochemistry
 Andy Connolly, Astronomy
eScience: Computational Science
for the 21st Century
Ed Lazowska
Bill & Melinda Gates Chair in
Computer Science & Engineering
Interim Director, eScience Institute
November 2008
http://eScience.washington.edu/
Theory
Experiment
Observation
Theory
Experiment
Observation
Theory
Experiment
Observation
Theory
Experiment
Observation
Computational
Science
Protein interactions
in striated muscles
Tom Daniel lab
QCD to study
interactions of
nuclei
David Kaplan lab
Gas
Stars
Study of dark matter
Dark Matter
Tom Quinn lab
Theory
Experiment
Observation
Computational
Science
eScience
eScience is driven by data
 Massive volumes of data from sensors and networks
of sensors
Apache Point telescope,
SDSS
15TB of data
(15,000,000,000,000 bytes)
Large Synoptic Survey
Telescope (LSST)
30TB/day,
60PB in its 10-year
lifetime
Large Hadron Collider
700MB of data
per second,
60TB/day, 20PB/year
Illumina Genome
Analyzer
~1TB/day
Regional Scale Nodes of the
NSF Ocean Observatories
Initiative
2000 km of fiber optic cable
on the seafloor, connecting
thousands of chemical,
physical, and biological
sensors
The Web
20+ billion web pages
x 20KB = 400+TB
One computer can
read 30-35 MB/sec
from disk => 4 months
just to read the web
Point-of-sale terminals
eScience is about the analysis of data
 The automated or semi-automated extraction of
knowledge from massive volumes of data
There’s simply too much of it to look at
The technologies of eScience
 Sensors and sensor networks
 Databases
 Data mining
 Machine learning
 Data visualization
 Cluster computing
at enormous scale
eScience will be pervasive
 Computational science has been transformational, but
to some extent it has been a niche
As an institution (e.g., a university), you didn’t need to
employ it broadly in order to be competitive
 eScience capabilities must be broadly available and
broadly practiced
If not, the institution will simply cease to be competitive
The University of Washington
eScience Institute
 Mission
Help position the University of Washington at the forefront
of research both in modern eScience techniques and
technologies, and in the fields that depend upon these
techniques and technologies
 Strategy
Increase the sharing of expertise and facilities
Bootstrap a cadre of Research Scientists
Add faculty in key fields
Make the entire University more effective
 Launched July 1 with $1 million in permanent funding
from the Washington State Legislature
Sought, and need, $2 million
Steering Committee
 Appointed by Provost
Phyllis Wise
Ed Lazowska, CSE and eScience
Institute Interim Director
Mary Lidstrom (chair), Vice
Tom Ackerman,
Provost for Research
Atmospheric Sciences
Matt O’Donnell, Engineering
Ginger Armbrust,
Tom Quinn, Astronomy
Oceanography
Chance Reschke, eScience
Tom Daniel, Biology
Institute Technical Coordinator
David Goodlett, Medicinal
Mani Soma, EE and Office of
Chemistry
the VP for Research
Terry Gray, UW Technology
Werner Stuetzle, Arts &
Ron Johnson, CTO
Sciences
David Kaplan, Physics
Peter Tarczy-Hornoch,
Richard Karpen, Arts &
Biomedical & Health
Sciences
Informatics
Activities
 Direction-setting interviews with UW research
leaders regarding technology needs
 124 interviews thus far
 Top researchers of all ages in all fields
 Technology needs, in priority order
1. Data management facilities
•
Storage, backup, security
2. Shared expertise
•
3.
4.
5.
6.
Data management specifically, technology in general
Computing power and high-bandwidth network access
Data collection and analysis
Communication and collaboration technologies
Shared laboratories and pricing
 Initial staffing
Research Scientist recruited for cluster computing
Chance Reschke
Research Scientist being recruited for data management
Consulting model developed
Jeff Gardner as “TeraGrid Champion”
Data management consultancy under development
Overall coordination coming on-board
Erik Lundberg
First faculty search underway
Werner Stuetzle chairing search committee
 Laying the groundwork for broadly shared facilities
Data center space coordination and planning
UW Tower scheduled to come online in late 2009
~600KW for research computing
EPIC
Intelligent use of the research allocation in UW Tower
Coordinated, cost-effective compute and storage solutions for
the UW eScience community
 Active exploration of alternative approaches to
facilities
Amazon Web Services
Google/IBM cloud
Microsoft Dryad and Azure
 Participation in proposal preparation
Moore Foundation Sequencing Center
NSF Data Net - The GRADD Collaboration
NSF Track 2d (with PNNL, PSC, CMU)
 Community building
Web site for general information
http://eScience.washington.edu/
SIG for eScience technical staff
http://staff.washington.edu/reschke/escience-sig/SIG.pdf
Monthly technical “brown bag lunch”
Regular discussions with research groups across campus
regarding their eScience needs
We can help you (some currently,
better shortly) with …
 Facilities
 Proposals
 Data management issues
See posters
Email info@escience.washington.edu