1
Grids and eScience

• Mark Hayes
• Technical Director - Cambridge eScience Centre

GEFD Summer School 2004
2
Outline of this talk

1. What is eScience?! (as opposed to just plain
   science.)
2. A brief history of the Internet
3. Some examples of succesful eScience
4. Environmental eScience
5. Where all this is heading

3
eScience - a definition
eScience is about global collaboration in key
areas of science and the next generation of
infrastructure that will enable it.
Dr.John Taylor, Director General of the Research
Councils 1998-2003
4
eScience - my definition
eScience is research into new ways of using the
Internet to do science.
5
In the beginning
The computer as a communication device
"The collection of people, hardware, and
software... will become a node in a
geographically distributed computer network.
Through the network... all the large computers
can communicate with one another. And through
them, all the members of the community can
communicate with other people, with programs,
with data, or with a selected combination of
those resources. J.C.R.Licklider, The Computer
as a Communication Device Science and
Technology, April 1968
The ARPAnet in 1970
6
A brief history of the Internet
1962 Paul Baran of RAND invents packet switched
networking 1968 Lickliders vision 1969
ARPAnet goes online 1973 Bob Kahn Vint Cerf
invent TCP/IP 1979 Usenet MUDs invented 1983
TCP/IP established as a standard 1987 number
of hosts gt 10,000 1989 number of hosts gt
100,000 1989 Tim Berners-Lee invents the World
Wide Web 1992 number of hosts gt 1,000,000
http//www.isoc.org/internet/history/
7
International connectivity - 1991
8
International connectivity - 1997
9

International bandwidth
From 3D geographic network displays - Cox et
al, ACM Sigmod Record - December 1996
10
What does the Internet look like?
http//www.cybergeography.org/
11
Using the Internet to do science

• Online publication of papers, pre-prints
• e.g. http//www.arxiv.org
  http//www.pubmedcentral.org/
• CPU cycle scavenging, e.g. SETI_at_home,
  climateprediction.net
• The Human Genome Project free access to data
• Sloan Digital Sky Survey online database of
  astronomical data
• http//www.sdss.org/

12
Early distributed computing
1.2 million CPU years so far...
Brute force attempt to crack strong encryption
Protein folding
13

SETI_at_home
The worlds most powerful distributed
super-computer
delivered 65 Teraflops/second yesterday (Earth
Simulator is 35 Tflop/s)
14
Its not just compute cycles...
An exponential growth in data from many areas of
science.
15
Human genome project1995-2003
5 institutions sequenced the bulk of the human
genome, depositing raw data in public FTP servers
within 24 hours of it being sequenced. 3 copies
of the data are mirrored in the UK, US
Japan. Annotating the data is an ongoing
world-wide collaborative effort. See e.g.
http//www.biodas.org/ http//www.ensembl.org/ F
or more on the human genome project http//www.sa
nger.ac.uk/HGP/overview.shtml http//www.genome.go
v/
16
Environmental eScience
http//www.climateprediction.net http//ndg.bad
c.rl.ac.uk/ (NERC DataGrid) http//www.earthsys
temgrid.org/
17
Where all this is heading
New science, carried out by virtual
organisations enabled by the internet. VO
distributed data, compute resources,
people Technology Globus - http//www.globus.o
rg/ Condor - http//www.cs.wisc.edu/cond
or/ Access Grid - http//www.accessgrid.org/
18
The Access Grid
High end video conferencing and collaboration
technology. O(100) nodes world wide.
...one of the most compelling glimpses into the
future Ive seen since I first saw NCSA Mosaic.
Larry Smarr
19
Real-time what if scenarios

• An explosion!
• A dangerous chemical escapes!
• Where is the pollutant headed?
• Who needs to be evacuated?

The gViz
project, Ken Brodlie et al, Leeds University
http//www.visualization.leeds.ac.uk/gViz/
http//www.allhands.org.uk/proceedings/papers/67.p
df
20
Coupled models

• flexibly couple together component models to
  form a unified Earth System Model (ESM),
• execute the resulting ESM across a computational
  Grid,
• share the distributed data produced by simulation
  runs, and
• provide high-level open access to the system,
  creating and supporting virtual organisations of
  Earth System modellers.

The GENIE
project, Paul Valdes et al
http//www.genie.ac.uk/
21
How you can get involved...

• NIEeS - http//www.niees.ac.uk/
• National eScience Centre (Edinburgh)
• http//www.nesc.ac.uk/
• Your local eScience Centre