Table of Contents
-
KEYNOTE:
Jay Boisseau,
Texas Advanced Computing Center
-
PLENARY:
Henry Neeman,
University of Oklahoma
-
PLENARY:
Stephen Wheat,
Intel Corp
-
PLENARY:
Robert Whitten Jr.,
National Center for Computational Sciences,
Oak Ridge National Laboratory
-
PLENARY:
Tommy Toles,
Advanced Micro Devices
-
Joshua Alexander,
University of Oklahoma
-
Amy Apon,
University of Arkansas
-
Keith Ball,
EverGrid Inc
-
Keith Brewster,
University of Oklahoma
-
Robert Ferdinand,
East Central University
-
Chris Franklin,
University of Oklahoma
-
Paul Gray,
University of Northern Iowa
-
Mohammed A. Kalkhan,
Colorado State University
-
Randy Kolar,
University of Oklahoma
-
Scott Lathrop,
TeraGrid
-
Box Leangsuksun,
Lousiana Tech University
-
Xiaolin (Andy) Li,
Oklahoma State University
-
John Matrow,
Wichita State University
-
Greg Monaco,
Great Plains Network
-
Charlie Peck,
Earlham College
-
Jeff Pummill,
University of Arkansas
-
Horst Severini,
University of Oklahoma
-
Gordon K. Springer,
University of Missouri
-
Dan Stanzione,
Arizona State University
-
Ravi K. Vadapalli,
Texas Tech University
KEYNOTE
Slides:
PDF
Talk Abstract
The
Texas
Advanced Computing Center
(TACC)
at
The
University of Texas at Austin.
has experienced tremendous growth in
infrastructure,
services,
and R&D activities
over the past six years.
These achievements include
deploying new, world-class HPC systems.
One year ago,
TACC deployed
the
largest cluster for academic research
in the world,
and TACC is repeating that feat now
with a
10x
more powerful system.
The rapid growth in scale of these systems
has provided valuable experience
and interesting insights
for deploying large-scale systems --
and how the requirements and issues
are changing rapidly now
due to quad-core processors,
larger switches,
and
new science drivers.
Biography
John
R. ("Jay") Boisseau
is the director of the
Texas
Advanced Computing Center
(TACC)
at
The
University of Texas at Austin.
Since he assumed this position in June 2001,
TACC has rapidly grown
into one of
the leading advanced computing centers
in the world,
by developing and deploying powerful
High Performance Computing,
remote visualization,
data storage,
and
grid computing technologies
for researchers.
Boisseau participates and guides
the overall resources and services,
research and development,
and education and outreach programs
of the center,
and serves as the principal investigator for
TACC's two largest awards:
the
National
Science Foundation
TeraGrid
institutional lead,
and the
NSF
Leadership-Class
System Acquisition
("Track 2")
petascale computing system
to be deployed at TACC in late 2007.
His specific activities include
performance characteristics of
high-end computing systems and microprocessors,
and
the development of
grid technologies and portals
for computational science.
His newest interest is
the application of HPC and grid technologies
to computational biology and biomedicine.
Boisseau started his training at the
University
of Virginia,
where he received a bachelors degree in
astronomy and physics in 1986,
while working in
various scientific computing positions.
He continued his education at the
The
University of Texas at Austin,
where he received
his masters in astronomy in 1990,
then took a position at the
Arctic
Region Supercomputing Center
in 1994,
while conducting computational research on
Type IA explosion mechanisms,
which he completed in 1996.
He then moved to the
San Diego
Supercomputer Center,
where he eventually founded
and became the Associate Director of
the
Scientific Computing Department,
initiating and leading
several major activities of the center
in HPC and grid computing.
OTHER
PLENARY SPEAKERS
Director
OU
Supercomputing Center for Education
& Research (OSCER)
University
of Oklahoma
Topic:
"OSCER State of the Center Address"
Slides:
PowerPoint
PDF
Talk Abstract
The
OU
Supercomputing Center for
Education & Research
(OSCER)
celebrated its 6th anniversary
on August 31 2007.
In this report,
we examine
what OSCER is,
how OSCER began,
and where OSCER is going.
Biography
Dr.
Henry Neeman
is the
Director of the
OU
Supercomputing Center for Education &
Research,
an adjunct assistant professor in the
School of
Computer Science
and a research scientist at the
Center for
Analysis & Prediction of Storms,
all at the
University of
Oklahoma.
He received his BS in computer science
and his BA in statistics
with a minor in mathematics
from the
State
University of New York at Buffalo
in 1987,
his MS in CS from the
University of
Illinois at Urbana-Champaign
in 1990
and his PhD in CS from UIUC in 1996.
Prior to coming to OU,
Dr. Neeman was a postdoctoral research
associate at the
National
Center for Supercomputing Applications
at UIUC,
and before that served as
a graduate research assistant
both at NCSA
and at the
Center for
Supercomputing Research &
Development.
In addition to his own teaching and research,
Dr. Neeman collaborates with
dozens of research groups,
applying High Performance Computing techniques
in fields such as
numerical weather prediction,
bioinformatics and genomics,
data mining,
high energy physics,
astronomy,
nanotechnology,
petroleum reservoir management,
river basin modeling
and engineering optimization.
He serves as an ad hoc advisor
to student researchers
in many of these fields.
Dr. Neeman's research interests include
high performance computing,
scientific computing,
parallel and distributed computing,
structured adaptive mesh refinement
and
scientific visualization.
Senior Director, High Performance Computing
Intel
Topic:
"Exa, Zeta, Yotta: Not Just Goofy Words"
Slides:
PDF
Video:
Quicktime
Talk Abstract: coming soon
Biography
Dr. Stephen Wheat is
the Senior Director of
Intel's
High Performance Computing
Platform Organization.
He is responsible for
the development of
Intel's HPC strategy
and the pursuit of that strategy
through
platform architecture,
software,
tools,
sales and marketing,
and
eco-system development and collaborations.
Dr. Wheat has a wide breadth of experience
that gives him a unique perspective
in understanding large scale HPC deployments.
He was the Advanced Development manager
for the Storage Components Division,
the manager of
the RAID Products Development group,
the manager of
the Workstation Products Group
software and validation groups,
and manager of
the systems software group
within
the Supercomputing Systems Division (SSD).
At SSD,
he was a Product Line Architect
and was
the systems software architect for
the ASCI Red system.
Before joining Intel in 1995,
Dr. Wheat worked at
Sandia
National Laboratories,
performing leading research in
distributed systems software,
where he created and led
the SUNMOS and PUMA/Cougar programs.
Dr. Wheat is a
Gordon
Bell Prize
winner
and has been awarded Intel's prestigious
Achievement Award.
He has a patent in Dynamic Load Balancing
in HPC systems.
Dr. Wheat holds a Ph.D. in Computer Science
and has several publications on
the subjects of
load balancing,
inter-process communication,
and
parallel I/O in large-scale HPC systems.
Outside of Intel,
he is a commercial multi-engine pilot
and
a certified multi-engine flight instructor.
National
Center for Computational Sciences
Oak Ridge
National Laboratory
Topic:
"The National Center for
Computational Sciences: An Introduction"
Slides: available after the Symposium
Video:
Quicktime
Talk Abstract
The
National
Center for Computational Sciences
(NCCS)
was founded in 1992 to advance
the state of the art in
high performance computing,
by bringing
a new generation of parallel computers
out of the laboratory and
into the hands of the scientists
who could most use them.
It is a managed activity of
the
Advanced
Scientific Computing Research
program of the
Department of
Energy
Office of
Science
(DOE-SC)
and is located at
Oak Ridge
National Laboratory.
Biography
Robert M. Whitten Jr.
is a member of the
User Assistance and Outreach Group
of the
National
Center for Computational Sciences
at
Oak Ridge
National Laboratory.
The User Assistance and Outreach Group
is tasked with providing
technical support to researchers that use
the leadership class computing resources
of the NCCS.
Robert holds degrees in Computer Science from
East Tennessee
State University.
Business Development Executive
Advanced
Micro Devices
Topic:
"Future of Supercomputing:
The Computational Element"
Slides:
PDF
Talk Abstract
This talk will address
the key trends in computation
that the industry will be facing
over the next few years.
Common challenges and innovative approaches
will be discussed,
as the audience will get a
"behind the scenes" look
at what goes into
the design of next generation platforms.
Historic architectures
will be compared with
today's leading edge designs,
to showcase the improvements made
to pave the way for future scaling.
Biography
Tommy Toles has a BSEE
from Texas A&M University.
Early in his career,
he worked as a hardware design engineer
for both
Bell Helicopter
and
the Tandy Corporation.
Over the past 15 years,
Tommy has served AMD in several areas,
including technology marketing and sales.
Currently,
he serves as a Business Development Executive,
assisting IT managers
in planning for new technologies
and
obtaining maximum value
from existing technology.
He has been involved with
several large clusters
across both academic and
commercial organizations.
Tommy is married with 3 children,
lives in Austin TX,
and enjoys waterskiing at dawn
several mornings each week.
OTHER PLENARY SPEAKERS
TO BE ANNOUNCED
BREAKOUT
SPEAKERS
IT Support Specialist
OU Information
Technology
University
of Oklahoma
Topic:
"Implementing Linux-enabled Condor in
Multiple Windows PC Labs"
(with
Chris Franklin
and
Horst Severini)
Slides:
PDF
PowerPoint
Poster
Talk Abstract
At the
University
of Oklahoma
(OU),
Information
Technology
is completing a rollout of Condor,
a free opportunistic grid
middleware system,
across 775 desktop PCs in IT labs
all over campus.
OU's approach,
developed in cooperation with the
Research
Computing Facility
at the
University
of Nebraska Lincoln,
provides the full suite of Condor features,
including
automatic checkpointing,
suspension and migration as well as
I/O over the network
to disk on the originating machine.
These features are normally limited
to Unix/Linux installations,
but OU's approach allows them on
PCs running Windows as
the native operating system,
by leveraging
coLinux
as a mechanism for providing Linux as
a virtualized background service.
With these desktop PCs otherwise idle
approximately 80% of the time,
the Condor deployment is allowing OU
to get 5 times as much value
out of its desktop hardware.
Biography
Joshua Alexander is a
Computer Engineering
undergraduate at the
University
of Oklahoma.
He currently works with the Customer Services
division of
OU
Information Technology,
and also serves as
an undergraduate researcher
for the
OU
Supercomputing Center for Education &
Research (OSCER).
His current project for OSCER
involves both the OU IT
Condor
pool
and development of software tools
for deploying Condor at other institutions.
Associate Professor
Department of
Computer Science &
Computer Engineering
University of
Arkansas
Topic:
"Roundtable:
The Great Plains Network's
Grid Computing & Middleware Initiative"
(with
Greg Monaco
and
Gordon Springer)
Slides:
PDF
(Bill Spollen)
Roundtable Abstract
This roundtable focuses on
recent developments in collaborative middleware
among the
Great
Plains Network
participants
and an exploration of directions
for the coming year.
The roundtable will feature
a demonstration of
resources
developed at the
University
of Missouri,
discussion of a
project
to use
Shibboleth
as a means of managing identities
for a Wiki
(e.g.,
GPN
Wiki),
participation in the
University of Oklahoma
Condor
project,
and,
finally,
Globus
grid issues
(extending access to GPN globus-based grid
to other users and institutions).
Biography
Dr. Amy
Apon
holds a Ph.D. from
Vanderbilt
University
in
performance analysis of
parallel and distributed systems.
Her current research focus on
cluster and grid computing,
including
scheduling in grid systems,
management of
large-scale data-intensive applications,
and
authorization and authentication architectures.
She also teaches courses in the area of
cluster and grid computing
and
is collaborating with
Louisiana
State University
to teach a course in
high-performance computing
that explores new course delivery methods
using high-definition video broadcast
over
Access
Grid
and
new high-speed fiber optical networks
in
Louisiana
(LONI)
and
Arkansas
(AREON).
As the Principal Investigator of
a
National
Science Foundation
Major
Research Instrumentation
grant,
she plays a key role in,
directing
high
performance computing
activities on the
University
of Arkansas
campus.
Systems Engineer
EverGrid Inc
Topic:
"User-Friendly Checkpointing and
Stateful Preemption in HPC Environments
Using Evergrid Availability Services"
Slides:
PowerPoint
Talk Abstract
As high-performance computing (HPC) workloads
increase in complexity and size,
the HPC systems that support them
must scale accordingly.
As the size of workloads increase,
the Mean Time Between Failure (MTBF)
of the system components
(CPUs, memory, and disks)
will become shorter than
expected application runtimes.
Next generation systems
must be designed to handle failures
without
interrupting the workloads on the system
or
crippling the efficiency of the resource.
To handle fault-tolerance
in the HPC environment,
Evergrid
Inc
provides a transparent,
fault-tolerant framework
that can periodically save
the state of an application
and
correctly restore/restart the application
if a failure occurs.
This solution,
Availability
Services
(AVS),
is provided as a user-level shared library
that is dynamically loaded
with an HPC application at runtime.
It supports
integration with popular scheduling systems
such as
LSF
and
PBS
to provide automatic handling
of checkpoint and restart.
AVS
provides stateful preemption of HPC workloads,
enabling true fair-share scheduling policies
for large shared HPC clusters.
Biography
Keith is a Systems Engineer at
Evergrid
Software
in Blacksburg VA,
working next door to
Virginia
Tech's
System X
supercomputer.
Keith received a PhD in physics at the
University
of Chicago,
performing
statistical and molecular dynamics studies
of potential energy landscapes
of small atomic clusters.
After postdoctoral positions at
Darmstadt
Technical University
in Germany
and at
University
of California, San Francisco
on the computational prediction
of protein folds,
he worked for several years
in bioinformatics and computational chemistry
at biotechnology companies in California.
Keith is presently applying
his computational and scientific background
to help integrate checkpointing solutions
into large-scale distributed HPC applications
and systems.
Senior Research Scientist
Center for
Analysis & Prediction of Storms
University of
Oklahoma
Topic:
"High Resolution Assimilation of
Radar Data for
Thunderstorm Forecasting on OSCER"
Slides:
PowerPoint
Movie
Talk Abstract
Recently,
a network of four X-band radars
was deployed in southwestern Oklahoma
by the
Center
for Adaptive Sensing of the Atmosphere
(CASA).
CAPS has developed a system
to assimilate reflectivity data
from the CASA radars,
along with NEXRAD,
mesonet,
satellite
and
conventional data,
at 1-km grid resolution
using ADAS and incremental analysis
updating in
the ARPS numerical weather prediction model.
Four 6-hour forecasts were made
using various combinations of these data
for each event day during
the Spring of 2007.
These forecasts were run in near-real time --
a pair of 6-hour forecasts took 8 hours
using 150 nodes on topdawg,
a cluster of Pentium4 Xeon EM64T
Linux computers at the
OU
Supercomputing Center for Education &
Research
(OSCER).
Additional forecasts were made later
utilizing the radial velocity
data in ADAS.
Forecasts that accurately depicted
the development of storms,
and even small-scale rotation
within the storms,
were successfully made.
Biography
Keith Brewster is a Senior Research Scientist
at the
Center
for Analysis and Prediction of Storms
at the
University
of Oklahoma
and an Adjunct Associate
Professor in the
OU School of
Meteorology.
His research involves
data assimilation of
advanced observing systems,
including data from
Doppler
radars,
satellites,
wind profilers,
aircraft
and
surface mesonet systems.
He earned an M.S. and Ph.D. in Meteorology
from the
University
of Oklahoma
and a B.S. from the
University
of Utah.
Associate Professor
Department
of Mathematics
East
Central University
Topic:
"Solution and Parameter Estimation
in Groundwater Model"
Slides:
PDF
Talk Abstract
The model presented take the form of
a coupled system of
two nonlinear PDEs
describing the dynamics of
contaminated groundwater
flowing through fissures (cracks)
in a rock matrix,
leading to the contaminant
traveling and diffusing along
the length of the fissure
and also into the surrounding rock matrix.
A finite difference scheme is used
to approximate the model solution,
and the scheme is further used
to estimate model parameters
using an inverse method.
Both solution and parameter approximation
use large amounts of computation.
Biography
Robert Ferdinand obtained his PhD
in Applied Mathematics
from the
University
of Louisiana
in 1999.
His areas of interest include
mathematical modeling of
physical and biological processes,
in which
numerical schemes are
used to computationally approximate
model solutions:
for example,
the inverse method is applied to
numerically estimate model parameters,
which
involves substantial computing.
His theoretical work involves
perturbation techniques to investigate
long-term behavior of model solutions.
IT Systems Administrator
OU Information
Technology
University
of Oklahoma
Topic:
"Implementing Linux-enabled Condor in
Multiple Windows PC Labs"
(with
Joshua Alexander
and
Horst Severini)
Slides:
PDF
PowerPoint
Poster
Talk Abstract
At the
University
of Oklahoma
(OU),
Information
Technology
is completing a rollout of Condor,
a free opportunistic grid
middleware system,
across 775 desktop PCs in IT labs
all over campus.
OU's approach,
developed in cooperation with the
Research
Computing Facility
at the
University
of Nebraska Lincoln,
provides the full suite of Condor features,
including
automatic checkpointing,
suspension and migration as well as
I/O over the network
to disk on the originating machine.
These features are normally limited
to Unix/Linux installations,
but OU's approach allows them on
PCs running Windows as
the native operating system,
by leveraging
coLinux
as a mechanism for providing Linux as
a virtualized background service.
With these desktop PCs otherwise idle
approximately 80% of the time,
the Condor deployment is allowing OU
to get 5 times as much value
out of its desktop hardware.
Biography
Chris Franklin
is a senior in the
School of
Computer Science
at the
University
of Oklahoma.
He has worked for
OU
Information Technology
for three years,
and is currently part of a team of 3 people
responsible for the administration of
approximately 800 lab PCs,
among other systems.
Associate Professor
Department of
Computer Science
University of
Northern Iowa
Topic:
"High Performance Computing in a
Small College Environment:
Tools, Techniques, and Resources"
(with Charlie Peck)
Slides:
PDF
Talk Abstract
Providing computational resources
and software tools
to faculty and students
in a small college environment
is different, in fundamental ways,
from doing so for large R1 and
similar institutions.
The types of demands,
e.g. research and teaching,
the human and technical resources available,
and the support requirements
are just some things
that change significantly with scale.
Unfortunately,
most of the available
best-practice and similar information
is more appropriate
for large sites than small ones.
Yet educating students and faculty
about HPC
in small college environments
is of the utmost importance,
given the continuing shortage
of computationally-aware STEM people
in that space.
Paul and Charlie draw on
many years of experience
spent supporting HPC hardware and software
in small college environments
to describe
the tools, techniques, and resources
appropriate for that context.
A question and answer session will follow.
Biography
Paul Gray is an Associate Professor of
Computer
Science
at the
University
of Northern Iowa.
He is the chair of the
SC
(SuperComputing) Conference
Education Program
and instructs summer workshops on
parallel computing education with the
Supercomputing Education program
efforts.
His current efforts combine the
Open
Science Grid
and
TeraGrid
with educational endeavors that revolve around
LittleFe
bringing aspects of grid computing into
the high school and undergraduate curriculum.
Research Scientist / Faculty
Biometrics, Geospatial information,
Spatial Statistics
Natural
Resource Ecology Laboratory
Colorado
State University
Topic:
"GODM:
Creating a Cyberinfrastructure to
Involve Volunteer Groups in
Citizen Science"
Slides: available after the Symposium
Talk Abstract
The vision of our research team is to
empower citizen scientists
(e.g., students, educators,
volunteer organizations,
private stakeholders, and the public)
in using an existing cyberinfrastructure
(i.e., the Global Organism Detection and
Monitoring system (GODM))
to digitally collect, input, integrate, and
analyze data on
the distribution of harmful non-native plants
and animals.
Specifically, the goals are to:
(1) promote the sharing of data on
harmful non-native plants and animals
using our publicly
available cyberinfrastructure;
(2) provide cyberinfrastructure tools
to help citizen scientists
accurately collect and efficiently
disseminate data on non-native species;
(3) provide mapping and
decision support services to
less technologically advanced groups to
analyze and map
the current and future
distributions of invaders;
(4) educate citizen scientists on
the utility of cyberinfrastructure to
empower them to advance
science and conservation and management
practices at local to global scales;
and
(5) foster a shift from a
reactive to a proactive
prevention, control, and containment strategy
for new invaders.
To meet these goals,
the collaborative research team will:
interview citizen scientists
to determine appropriate enhancements to
existing cyberinfrastructure tools;
identify
thresholds to ensure
high quality data collection;
implement
identified enhancements to
existing cyberinfrastructure tools;
and
develop educational materials
to distribute to both early adopters
and eventual end users
of the GODM cyberinfrastructure.
Biography
Dr. Mohammed A. Kalkhan is a Research Scientist - Faculty at the Natural Resource Ecology Laboratory (NREL) and as an Affiliate Faculty in the Department of Forest, Rangeland, and Watershed Stewardship, faculty member and advisor for Interdisciplinary Graduate Certificate in Geospatial Science, and Department of Earth Resources, (currently the Department of Geosciences) at Colorado State University (CSU). Dr. Kalkhan received his BSc in Forestry from College of Agriculture and Forestry (1973) and Masters degree in Forest Mensuration from the University of Mosul, Iraq (1980), and his PhD in Forest Biometrics- Remote Sensing Applications from the Department of Forest Sciences at Colorado State University in 1994. From 1975 to 1982, he was Lecturer at Department of Forestry, College of Agriculture and Forestry, University of Mosul, Iraq. In 1994, he joined the Natural Resource Ecology Laboratory. He has served on a number of Program Planning Committees including: Monitoring Science and Technology Symposium - Unifying Knowledge for Sustainability in the Western Hemisphere, Sponsored by the USDA Forest Service and EPA; NASA-USGS Invasive Species Tasks (Present); USGS-NPS Mapping, NASA, USDA- Agriculture Research Service (ARS) on a research program to develop predictive spatial models and maps for Leafy spurge at Theodore Roosevelt National Park, North Dakota using hyperspectral imaging from NASA EO-1 Hyperion (Space), NASA AVIRIS (High altitude aircraft), ARS (CASI- Low altitude aircraft); and The First Conference on Fire, Fuels, Treatments and Ecological Restoration: Proper Place, Appropriate Time. Member of Consortium for Advancing the Monitoring of Ecosystem Sustainability in the America (CAMESA). Dr. Kalkhan also serves as a member of graduate student committees (9 graduated and currently working with 7 students) at CSU.
Dr. Kalkhan's research activities include Biometrics (natural resource applications), landscape (structure-analysis-modeling), remote sensing, GIS, biodiversity assessment, ecological modeling, wetland ecosystems, spatial statistics, sampling methods and designs, determination of uncertainty, mapping accuracy assessment, agricultural ecology (cropping, health monitoring, assessment, precision farming, water resources, soils), fire ecology-characteristics-behavior and modeling, environmental, and health- clinical studies. These activities can be used and related to landscape issues and relate to local and regional land use and land cover, wetlands, fire ecology and other natural resource characteristics. His research interests involve the integration of field data, GIS, and remote sensing with geospatial statistics to understand landscape parameters through the use of a complex model with thematic mapping approaches for wildfire, wetland, invasive species, and plant diversity studies. These studies are aimed at developing a better understanding of landscape-scale ecosystems at any level and to develop better tools for ecological forecasting. His research is funded by NASA, NSF, USGS, NPS, BOR, BLM, USDA Forest Service and other national organizations. Examples of his current research projects include the newly funded NASA and NPS project on integrated geospatial information and spatial statistics for modeling and mapping invasive species in the western USA (i.e. tamarisk or salt cedar, Russian olive, leafy spurge, etc.), and fuel variability and invasive species characteristics within the Rocky Mountain region (Cerro Grande, Hayman and High Meadow, Rocky Mountain National Park, Grand Teton Nation Park, and wetlands of costal area of Texas, and others). The research challenges are to develop a new tool based on geospatial information and mathematics-statistics to forecast landscape characteristics. Dr. Kalkhan has also been active in the academic community in the past and present, co-teaching courses in spatial statistics modeling-mapping of natural resources, sampling designs, biometrics, remote sensing-GIS, forest measurements, and other.
Associate Professor
School of
Civil Engineering &
Environmental Science
University of
Oklahoma
Topic:
"Hurricane Storm Surge Modeling
for Southern Louisiana"
Talk Abstract: coming soon
Coastal Louisiana is characterized by
low-lying topography
and
an intricate network of
sounds,
estuaries,
bays,
marshes,
lakes,
rivers
and
inlets
that permit widespread inundation
during hurricanes,
such as that witnessed
during the 2005 hurricane season with
Katrina and Rita.
A basin to channel scale implementation of
the
ADCIRC
hydrodynamic model
has been developed
that simulates
hurricane storm surge,
tides
and
river flow
in this complex region.
This is accomplished by defining
a domain and computational resolution
appropriate for the relevant processes,
specifying realistic boundary conditions,
and implementing
accurate,
robust,
and highly parallel unstructured grid
numerical algorithms.
The model domain incorporates
the Western North Atlantic,
the Gulf of Mexico
and
the Caribbean Sea,
so that interactions between
basins and the shelf
are explicitly modeled,
and boundary conditions
for tidal and hurricane processes
are specified at the open boundary,
which is located in deep water.
Selective refinement of
the unstructured grid
enables high resolution of
the complex overland region
for modeling localized scales of flow,
while minimizing simulation time,
so that the model can also be used
in forecast mode.
The current computational grid
resolves features down to 60 meters
and
contains 2.17 million nodes,
each with 3 degrees of freedom.
ADCIRC applies
a finite element-based solution to
the generalized wave continuity form of
the governing shallow water equations.
The model algorithms
must be robust and stable
to accommodate the energetic flows
that are generated during a hurricane,
especially in the narrow inlets and channels
connecting water bodies and/or floodplains.
Validation of the model is achieved through
hindcasts of historical hurricanes.
Currently,
the validated model is being used by
the USACE,
FEMA,
and
the State of Louisiana
for preparing post-Katrina IPET reports,
levee design,
and coastal restoration studies.
Biography: coming soon
Director
of
Education,
Outreach & Training
TeraGrid
Topic:
"Advancing Scientific Discovery
through TeraGrid"
Slides:
PowerPoint
Talk Abstract
TeraGrid
is an open scientific discovery infrastructure
combining
leadership class resources
at nine partner sites
to create an integrated,
persistent computational resource.
Using high-performance network connections,
the TeraGrid integrates
high-performance computers,
data resources and tools,
and high-end experimental facilities
around the country.
You will learn how TeraGrid's resources,
including
more than 250 teraflops of
computing capability
and
more than 30 petabytes of
online and archival data storage,
is advancing scientific discovery.
Biography
Scott Lathrop
has been involved in
high performance computing and communications
activities since 1986,
and has been actively involved in
engaging local, regional and national
research and education communities
since that time.
Lathrop is the Director of
Education,
Outreach & Training
(EOT)
for the
TeraGrid
Project.
The TeraGrid project is funded by the
National
Science Foundation
to provide
an open and extensible partnership of
researchers,
computational experts,
and
resource providers
that together provide
a comprehensive cyberinfrastructure
to enable discovery in science and engineering.
Lathrop coordinates the EOT activities
among the Resource Provider sites
involved in the TeraGrid project.
He is also a member of the
Advancement Team
that is helping to lead the
Engaging
People in Cyberinfrastructure
(EPIC)
project,
funded by NSF,
among more than twenty organizations
involved in EOT activities around the country.
Lathrop is the
SC07
Education Program
chair,
the premier international conference
on
high performance computing,
networking,
storage and analysis.
Lathrop is co-PI on the NSF funded
Computational
Science Education Reference Desk
(CSERD),
a
Pathways
project of the
National
Science Digital Library
(NSDL)
program.
Associate Professor
of
Computer
Science
SWEPCO Endowed Professor
Louisiana Tech
University
Topic:
"Resiliency in HPC"
Slides: available after the Symposium
Talk Abstract
High Performance Computing
is an essential enabling technology
not only for scientific advancements
but also for
economic and business driving forces,
especially in today's digital world.
Time to market,
time to insight
and
time to discovery
are prime objectives in
HPC and grid adoption and utilization.
In addition,
a recent introduction of
dual-core and multi-core processor products
will propel adoption of HPC
in mainstream environments.
Experts have predicted that
personal supercomputers
will soon be available on the desktop.
Nevertheless,
there are many challenges
in a wide spectrum of obstacles,
such as mismatches in
the technological advancements of
hardware and software components,
programmability,
system reliability and robustness,
especially in very large scale systems.
In this talk,
Box will present his
current research and development in HPC,
especially his effort towards
resiliency in
High Performance Computing environments.
Biography
Dr.
Chokchai "Box" Leangsuksun
is the
SWEPCO Endowed Professor,
an associate professor
in
Computer
Science
and the
Center for
Entrepreneurship and Information Technology
(CEnIT)
at
Louisiana
Tech University.
He received his Ph.D. and M.S.
in computer science from
Kent State
University
(Kent OH)
in 1989 and 1995 respectively.
His research interests include:
-
Highly Reliable and
High Performance Computing
-
Intelligent component based
Software Engineering
-
Service-Oriented Architecture,
Service engineering and management
-
High Performance Scientific computing
& Bioinformatics
Prior joining Louisiana Tech University
in early 2002,
Box was a member of
Technical Staff,
Lucent Technologies-Bell Labs Innovation,
from 1995-2002,
and was responsible in
many key research and development roles
in various strategic products.
Within a short academic time span,
Box has established
his name and research recognitions
by founding and co-chairing
a high availability and performance workshop,
serving as program committee in
various international conferences/workshops,
releasing open source software,
writing articles featured in
major technical journals/magazines,
and giving presentations
at highly-regarded conferences.
He has also collaborated with
various research groups and
national and industrial labs,
including
Oak Ridge National Laboratory,
Ames Laboratory,
Lawrence Livermore National Laboratory,
National Center for Supercomputing
Applications,
LAM/MPI,
Dell,
Intel,
and
Ericsson
etc.
In September 2003,
he received an outstanding teaching award
from the
College of Engineering and Science,
Louisiana Tech University.
Assistant Professor
Computer
Science Department
Oklahoma
State University
Topic:
"P2P Desktop Grid for
Hybrid Sensor Grid Systems"
Talk Abstract
With rapid progress on
grid computing and sensor networks,
now is the right time
to envision an ultimate
pervasive grid environment
integrating both grids and sensornets
seamlessly.
We are working on a peer-to-peer approach
to enable such an integrated system.
This talk will sketch a roadmap towards
a hybrid sensor grid system,
including three subsystems:
AgentGrid,
AgentBroker,
and
TinyAgent.
Biography
Dr. Li has been an assistant professor
in the
Department
of Computer Science
at
Oklahoma
State University
since 2005.
His research interests include
Distributed Systems
(Autonomic, Grid, P2P, and HPC),
Computer Networks,
and
Software Engineering.
He is director of the
Scalable
Software Systems Laboratory
(S3Lab).
His research has been sponsored by
National
Science Foundation
(NSF),
Department
of Homeland Security
(DHS),
AirSprite
Technologies,
and OSU.
He has been a visiting scholar in
Department
of Computer Sciences
of the
University
of Texas at Austin,
an alumnus of
IBM
Extreme Blue,
a research staff at
Center for Wireless Communication
(now the
Institute
for Infocomm Research,
I2R),
and a research scholar at the
National
University of Singapore
(NUS).
He received his Ph.D. degrees from
Rutgers
University
and NUS.
Director
High
Performance Computing Center
Wichita
State University
Topic:
"Internet2 and Benefits to
State Education Networks"
Slides:
PPT1
PPT2
PPT3
Talk Abstract
Internet2 is
a research-only network
among the 207 largest universities
tasked with developing
the next generation Internet protocols,
security,
applications,
etc.
The Internet2 K20 Initiative
brings together
Internet2 member institutions,
primary and secondary schools,
colleges and
universities,
libraries,
and
museums
to extend new
technologies,
applications,
middleware,
and
content
to all educational sectors,
as quickly and connectedly as possible.
Biography
John Matrow has a
B.S. in Computer Science from
Central
Missouri State University
and
a M.S. in Computer Science from
Iowa
State University.
He has
worked for the State of Iowa,
and spent 20 years at
LSI Logic Storage Systems,
formerly Symbios Logic,
nee NCR Microelectronics Division,
both in
IT and product development.
Since 2000,
John has been System
Administrator/Trainer and now Director of
the
High
Performance Computing Center
at
Wichita
State University,
and has been actively involved in
raising the level of research
with regard to
high performance computing
and
high performance networking
(Internet2).
John also teaches night courses in
database for the
Computer Science
and
MIS
departments.
Executive Director
Great
Plains Network
Topic:
"Roundtable:
The Great Plains Network's
Grid Computing & Middleware Initiative"
(with
Amy Apon
and
Gordon Springer)
Slides:
PDF
(Bill Spollen)
Roundtable Abstract
This roundtable focuses on
recent developments in collaborative middleware
among the
Great
Plains Network
participants
and an exploration of directions
for the coming year.
The roundtable will feature
a demonstration of
resources
developed at the
University
of Missouri,
discussion of a
project
to use
Shibboleth
as a means of managing identities
for a Wiki
(e.g.,
GPN
Wiki),
participation in the
University of Oklahoma
Condor
project,
and,
finally,
Globus
grid issues
(extending access to GPN globus-based grid
to other users and institutions).
Biography
Dr.
Greg Monaco
has held several positions with the
Great
Plains Network
since August 2000, when he joined GPN.
He began as Research Collaboration Coordinator,
and then was promoted to
Director for Research and Education.
Greg is currently the
Executive Director of GPN.
His resume can be found
here.
Associate Professor
Department
of Computer Science
Earlham
College
Topic:
"High Performance Computing in a
Small College Environment:
Tools, Techniques, and Resources"
(with Paul Gray)
Slides:
PDF
Talk Abstract
Providing computational resources
and software tools
to faculty and students
in a small college environment
is different, in fundamental ways,
from doing so for large R1 and
similar institutions.
The types of demands,
e.g. research and teaching,
the human and technical resources available,
and the support requirements
are just some things
that change significantly with scale.
Unfortunately,
most of the available
best-practice and similar information
is more appropriate
for large sites than small ones.
Yet educating students and faculty
about HPC
in small college environments
is of the utmost importance,
given the continuing shortage
of computationally-aware STEM people
in that space.
Paul and Charlie draw on
many years of experience
spent supporting HPC hardware and software
in small college environments
to describe
the tools, techniques, and resources
appropriate for that context.
A question and answer session will follow.
Biography
Charlie teaches computer science at
Earlham
College
in Richmond IN.
He is also the nominal leader of Earlham's
Cluster
Computing Group.
His research interests include
parallel and distributed computing,
computational science,
and
education.
Working with colleagues,
Charles is co-PI for the
LittleFe
project.
During the summer,
he often teaches
parallel and distributed computing workshops
for
undergraduate science faculty
under the auspices of the
National
Computational Science Institute
and the
SC
(SuperComputing) Conference
Education Program.
Senior Linux Cluster Administrator
High
Performance Computing
at the
University
of Arkansas
Topic:
"Birds of a Feather Meeting:
Linux Cluster Administration for
High Performance Computing"
BoF Abstract
This BoF,
dedicated specifically to
administration of HPC systems,
is hopefully the first of many.
As HPC systems are
rapidly becoming more prevalent,
there is an immediate need
to adapt administrative support
to the unique needs of HPC users.
Topics of discussion will include,
but not be limited to,
building, installing, and configuring
Linux clusters,
as well as meeting the needs of
both individual users and
the user community as a whole.
Biography
Jeff Pummill is
the Senior Linux Cluster Administrator for
the University of Arkansas.
Prior to his position at the UofA,
he spent 13 years in the fields of
mechanical design and structural analysis,
while also maintaining
a large number of Unix workstations and
a small Linux cluster
used for Finite Element Analysis.
His current
areas of interest include
hardware architectures, resource managers,
compilers, and benchmarking tools.
Research Scientist
Department
of Physics & Astronomy
University
of Oklahoma
Topic:
"Implementing Linux-enabled Condor in
Multiple Windows PC Labs"
(with
Joshua Alexander
and
Chris Franklin)
Slides:
PDF
PowerPoint
Poster
Talk Abstract
At the
University
of Oklahoma
(OU),
Information
Technology
is completing a rollout of Condor,
a free opportunistic grid
middleware system,
across 775 desktop PCs in IT labs
all over campus.
OU's approach,
developed in cooperation with the
Research
Computing Facility
at the
University
of Nebraska Lincoln,
provides the full suite of Condor features,
including
automatic checkpointing,
suspension and migration as well as
I/O over the network
to disk on the originating machine.
These features are normally limited
to Unix/Linux installations,
but OU's approach allows them on
PCs running Windows as
the native operating system,
by leveraging
coLinux
as a mechanism for providing Linux as
a virtualized background service.
With these desktop PCs otherwise idle
approximately 80% of the time,
the Condor deployment is allowing OU
to get 5 times as much value
out of its desktop hardware.
Biography
Horst
Severini
got his Vordiplom (BS equivalent) in Physics at
the
University
of Wuerzburg
in Germany in 1988,
then went on to earn a Master of Science
in Physics in 1990
and
a Ph.D. in Particle Physics in 1997,
both at the
State
University of New York at Albany.
He is currently a Research Scientist in
the
High
Energy Physics group
at the
University
of Oklahoma,
and also the Grid Computing Coordinator at the
Oklahoma
Center for High Energy Physics
(OCHEP),
and the Associate Director for
Remote and Heterogeneous Computing at
OU
Supercomputing Center for
Education & Research
(OSCER).
Associate Professor,
Department
of Computer Science
Director,
Research
Support Computing
Scientific Director,
UM
Bioinformatics Consortium
University
of Missouri-Columbia
Topic:
"Roundtable:
The Great Plains Network's
Grid Computing & Middleware Initiative"
(with
Amy Apon
and
Greg Monaco)
Slides:
PDF
(Bill Spollen)
Roundtable Abstract
This roundtable focuses on
recent developments in collaborative middleware
among the
Great
Plains Network
participants
and an exploration of directions
for the coming year.
The roundtable will feature
a demonstration of
resources
developed at the
University
of Missouri,
discussion of a
project
to use
Shibboleth
as a means of managing identities
for a Wiki
(e.g.,
GPN
Wiki),
participation in the
University of Oklahoma
Condor
project,
and,
finally,
Globus
grid issues
(extending access to GPN globus-based grid
to other users and institutions).
Biography
Gordon K. Springer teaches primarily
operating systems and computer networking
to upper level undergraduate and
graduate students.
He is responsible for directing
the installation and maintenance of
high-performance computing and
networking resources
for the Columbia campus research community.
In addition,
he oversees the infrastructure
that serves
the life science community
for the 4-campus UM System.
From a research perspective,
Dr. Springer has recently been working on
developing middleware solutions for
collaborations across multiple institutions
to facilitate authentication and authorization
in Virtual Organizations,
especially in the
Great
Plains Network
(GPN).
Director
High
Performance Computing Initiative
Arizona
State University
Topic:
"Towards a Sustainable Business Model
for Campus HPC"
Slides:
PDF
Talk Abstract
The primary challenges of deploying
Supercomputing,
large scale storage,
and other forms of cyberinfrastructure
at a university are rarely technical.
Building
the political and financial infrastructure
to support high performance computing
is just as important,
and often more difficult,
than the technical issues.
This talk will provide
an overview of these issues,
provide as an example
the model used at Arizona State
to address them,
and start a discussion of
other possible models
for running an HPC operation
that a university can and will support.
Biography
Dr. Dan Stanzione,
Director of the
High Performance Computing Initiative (HPCI)
at Arizona State University,
joined the
Ira A. Fulton School of Engineering
in 2004.
Prior to ASU,
he served as an AAAS Science Policy Fellow
in the Division of Graduate Education
at the National Science Foundation.
Stanzione began his career at
Clemson University,
where he earned his doctoral and master degrees
in computer engineering
as well as his bachelor of science in
electrical engineering.
He then directed
the supercomputing laboratory at Clemson
and also served as
an assistant research professor
of electrical and computer engineering.
Dr. Stanzione's research focuses on
parallel programming,
scientific computing,
Beowulf clusters,
scheduling in computational grids,
alternative architectures for
computational grids,
reconfigurable/adaptive computing,
and
algorithms for high performance bioinformatics.
Also an advocate of engineering education,
he facilitates student research
through the HPCI
and teaches
specialized computation engineering courses.
Research Scientist
High
Performance Computing Center
Texas
Tech University
Topic:
"Grid Computing: What's in It for Me?"
Slides: available after the Symposium
Talk Abstract
Grid computing
is an emerging "collaborative"
computing paradigm
to extend institution/organization specific
high performance computing capabilities
greatly beyond local resources.
Strategic application areas
such as
bioscience and medicine,
energy exploration
and
environmental modeling
involve strong interdisciplinary components
and
often require collaborations and
computational capabilities
beyond institutional limitations.
The institution/organization specific
high performance computing center
is the building block for
the grid computing environment
that spans over
several administrative/campus domains.
In this talk,
I will discuss how
grid computing environment
can be an excellent paradigm for
a win-win situation for many systems
such as
the resource providers,
application developers,
users,
industries
and
campus administration.
As an example,
our efforts through TIGRE project 1
in creating a higher educational grid
to extend the scope of
aforementioned strategic application areas
will be outlined.
1
Texas Internet Grid for Research and Education
(TIGRE)
Project Document
and the
TIGRE
Portal
Biography: coming soon
OTHER BREAKOUT SPEAKERS
TO BE ANNOUNCED
