Transcript Slide 1

The
eXtremeDigital (XD)
Program
Barry I. Schneider
Office of Cyberinfrastructure
National Science Foundation
email:[email protected]
 eXtreme
complex
XD Solicitation/XD Program
Digital Resources for Science and Engineering (NSF 08-571) – eXtremely
 High-Performance Computing and Storage Services
• aka Track 2 awardees and others become service providers (SP) for XD
 High-Performance Remote Visualization and Data Analysis Services
• 2 awards; 5 years; $3M/year
• proposals due November 4, 2008 – Two awards funded in 2009 – RDAV (NICS) & Longhorn (TACC)
 Integrating Services (5 years, $26M/year)
• Coordination and Management Service (CMS)
– 5 years; $12M/year
• Technology Audit and Insertion Service (TAIS)
– 5 years; $3M/year – Two awards funded in 2010 – Buffalo (TAS) and UIUC (TIS)
• Advanced User Support Service (AUSS)
– 5 years; $8M/year
• Training, Education and Outreach Service (TEOS)
– 5 years, $3M/year
 two phase proposal process for IS
• pre-proposals November 4, 2008
• final proposals due June 15, 2009 – Final project called XSEDE funded July, 2011
for five years with a possible additional five year extension
XD at a Glance
 Technical Audit Service develops lightweight tools (XDMoD) to enable
stakeholders to obtain information on the systems, performance, usage and
other characteristics of the XD resources – extremely valuable for data
collection – Aid users, system administrators and NSF Program Director
 Technical Insertion Service evaluates software and middleware and makes
recommendations for injection into project
 XSEDE provides the integrating services for the project: Coordination and
management, advanced user services and training, education and outreach
 XSEDE is a comprehensive set of advanced heterogeneous high-end
digital services, integrated into a general-purpose infrastructure.
 XSEDE is about increased user productivity, not just high end resources
 Increased productivity leads to more science at all levels
 Increased productivity is sometimes the difference between a feasible
project and an impractical one
Thanks to the XSEDE folks for permission to use
material from slides used at the US-EU Summer
School in computational science held at Lake Tahoe
in early August
4
The Vision



Enhance the productivity of scientists and
engineers by providing them with new and
innovative capabilities
Facilitate scientific discovery while enabling
transformational science/engineering and
innovative educational programs
Develop a more sustainable approach
to the national CI
XSEDE supports a breadth of research
From direct contact with user community as part of
requirements collections

Earthquake Science and Civil
Engineering

Brain science

Analysis of large cosmological
simulations

Molecular Dynamics

Nanotechnology

DNA sequencing

Plant Science


Storm modeling
Computational Molecular
Sciences

Epidemiology

Neutron Science

Particle Physics


Economic analysis of phone
network patterns
International Collaboration in
Cosmology and Plasma Physics
Sampling of much larger set. Many examples are new to TeraGrid/HPC.
Range from petascale to disjoint HTC, many are data driven. XSEDE will
support thousands of projects.
XSEDE’s Distinguishing Characteristics
Foundation for a national CI ecosystem – in sync with the
NSF CIF21 vision
 A comprehensive suite of advanced digital services
 Federated with other high-end facilities, other
providers of digital services here and abroad
and importantly campus-based resources
 Unprecedented integration of diverse digital resources
 Developing an innovative, open architecture making
possible the continuous addition of new technology
capabilities and services – Achieve Seamless
integration of resources at
all levels

XSEDE: An Infrastructure Designed for
Innovation & Evolution

An environment in which all resources, data and services relevant
to a researcher can be embedded and shared
 Campus bridging creating a single virtual system with interactive data
transfer and resource sharing capabilities
• “make my data accessible everywhere I want to be”
 Coordinated archival approach to ensure persistence of important
datasets beyond the lifetime of particular service providers – Still needs
fleshing out

An underlying infrastructure to support this
 Open architecture with judicious use of standards designed to evolve in a
non-disruptive way
 Interoperability of XSEDE with other Cis – OSG, PRACE, DEISA
NAREGI
XSEDE’s Distinguishing Characteristics Architecture
 XSEDE
is designed for innovation & evolution
 There is an architecture defined, but it is still evolving as a consequence of
the review process
• based on set of design principles
• rooted in the judicious use of standards and best practices
• clearly defined transition plan from TeraGrid to XSEDE
 Professional
systems engineering approach
 Responds to evolving needs of existing, emerging, and new communities
• incremental development/deployment model
 New requirements gathering processes
• ticket mining, focus groups, usability panels, shoulder surfing
 Ensure robustness and security while incorporating new and improved
technologies and services
 Process control, quality assurance, baseline management, stakeholder
involvement
How XSEDE describes the architecture
A
set of “views” examining the elephant from the perspectives of different
stakeholders
 Not (only) immensely detailed documentation!
 Different





stakeholders require different views, e.g.,
Service provider
System administrator
Power user
Occasional user
Gateway developer
 Tell
us what views you think
are important
–Security officer
–NSF program manager
–Campus CIO
–Trainer
–...
XSEDE’s Distinguishing Characteristics Governance
 World-class
leadership from CI centers with deep experience: partnership
led by NCSA, NICS, PSC, TACC and SDSC
PI:
John Towns,
Co-PIs: Jay Boisseau,
Patricia Kovatch,
Ralph Roskies,
Nancy Wilkins-Diehr,
NCSA/Univ of Illinois
TACC/Univ of Texas Austin
NICS/Univ of Tenn-Knoxville
PSC/CMU
SDSC/UC-San Diego
 Partners
who strongly complement these CI centers with expertise in
science, engineering, technology and education
Univ of Virginia
SURA
Indiana Univ
Univ of Chicago
Berkeley
Shodor
Ohio Supercomputing Center
Cornell
Purdue
Rice
NCAR
Jülich Supercomputing Centre
Engaging stakeholders
 Collection
of stakeholder needs:
 surveys, ticket mining, …
 focus groups, usability panels, …
 interviews, shoulder surfing, …
 Prioritization
of identified need and derived requirements
 User Requirements Evaluation and Prioritization (UREP) Working Group
• broad participation across architecture, deployment, operations, users, and service providers
 Assessing
plans and deployments
 through a variety of stakeholder-focused, facilitated workshops
• e.g., interactive ATAM sessions focused on identifying, quantifying, discussing tradeoffs
 Representation
in the management of XSEDE
 XSEDE Advisory Board
 User Advisory Committee
 Service Providers Forum