The University of WashingtoneScience 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/

TheoryExperimentObservation

TheoryExperimentObservation

TheoryExperiment

Observation

TheoryExperimentObservation

ComputationalScience

Protein interactions in striated muscles

Tom Daniel lab

QCD to study interactions of

nuclei

David Kaplan lab

GasStars

Dark Matter

Study of dark matter

Tom Quinn lab

TheoryExperimentObservation

ComputationalScience

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 dataper 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 Tom Ackerman,

Atmospheric Sciences Ginger Armbrust,

Oceanography Tom Daniel, Biology David Goodlett, Medicinal

Chemistry Terry Gray, UW

Technology Ron Johnson, CTO David Kaplan, Physics Richard Karpen, Arts &

Sciences

Ed Lazowska, CSE and eScience Institute Interim Director

Mary Lidstrom (chair), Vice Provost for Research

Matt O’Donnell, Engineering Tom Quinn, Astronomy Chance Reschke, eScience

Institute Technical Coordinator

Mani Soma, EE and Office of the VP for Research

Werner Stuetzle, Arts & Sciences

Peter Tarczy-Hornoch, Biomedical & Health Informatics

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• Data management specifically, technology in general

3. Computing power and high-bandwidth network access4. Data collection and analysis5. Communication and collaboration technologies6. Shared laboratories and pricing

Activities

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