Ken Powell Appointed Interim AVP for Research

Professor Kenneth G. Powell will serve as interim Associate Vice President for Research – Research Cyberinfrastructure in the Office of the Vice President for Research (OVPR), beginning September 1, 2012. As interim Associate VP, he will oversee the operations of the Office of Research Cyberinfrastructure (ORCI).

Dr. Kenneth Powell

Prof. Powell will succeed Prof. Daniel Atkins, who will be returning to the faculty to pursue research on cyber-enabled learning. During his tenure as Associate VP, Prof. Atkins established ORCI as a platform of technological and human support for advanced, integrated computation and information resources in the service of research and learning. Prof. Powell’s appointment in OVPR will continue until the AVP position is permanently filled through a process now underway with a search committee headed by Prof. James Penner-Hahn.

An active user of advanced research computing resources, Prof. Powell is Arthur F. Thurnau Professor of Aerospace Engineering and Director of the Center for Advanced Computing in the College of Engineering. At ORCI, he has been Director for Research Services and Computing and Information Resources for Research as a Utility Service (CIRRUS), which lays the foundation for the expansion of U-M’s research cyberinfrastructure capabilities.

Prof. Powell earned his S.B. in mathematics and aeronautics in 1982, his S.M. in aeronautics in 1984 and his Sc.D. in aeronautics in 1987, all from the Massachusetts Institute of Technology. He joined the University of Michigan as an assistant professor in 1987, was promoted to associate professor in 1993 and to professor in 2000. Prof. Powell was appointed as the Arthur F. Thurnau Professor in 2002 and served as the interim Chair of Aerospace Engineering from 2010-2011. He has an outstanding history of honors and awards, as well as service on numerous U-M committees, throughout his career.

Keynote Speakers Announced for CI Days

CI Days 2012, to be held November 7 and 8, will feature keynote speakers Dr. Ian Foster from the Argonne National Lab, and Dr. Chris Johnson from the University of Utah.

Dr. Foster is director of the Computation Institute, a joint institute of the University of Chicago and Argonne National Laboratory. He is also an Argonne Senior Scientist and Distinguished Fellow and the Arthur Holly Compton Distinguished Service Professor of Computer Science.

Dr. Johnson is the founding director of the Scientific Computing and Imaging (SCI) Institute at the University of Utah where he is a Distinguished Professor of Computer Science and holds faculty appointments in the Departments of Physics and Bioengineering. His research interests are in the areas of scientific computing and scientific visualization.

LSA 352 Cyberscience Course Now Available on Open.Michigan

Open.Michigan is a University of Michigan initiative that enables faculty, students, and others to share their educational resources and research with the global learning community.

LSA Honors 352 – Cyberscience and the Fourth Paradigm, taught by Prof. Gus Edvard, invites students to explore the social and technical development of computing for the sciences, from the ENIAC through the top-500 list of supercomputers and on to Amazon’s EC2.

Through a selection of readings, discussions with invited guests, and first-hand experimentation, students in the course will learn about an assortment of technologies that underlie modern scientific inquiry, investigate their use by U-M cyber-scientists, and gain an appreciation of the fiscal, political and social challenges imposed by this growing area of scholarship.
 

 

HPCWire.com Report – The View from Argonne

June 21, 2012- The US Department of Energy (DOE) will be the most likely recipient of the initial crop exascale supercomputers in the country. That would certainly come as no surprise, since  according the latest TOP500 rankings, the top three US machines all live at DOE labs – Sequoia at Lawrence Livermore, Mira at Argonne, and Jaguar at Oak Ridge. Read the full article.

MICHR Mentoring Forum: Mentoring Effective Team Scientists – July 10

How do you assemble an effective research team? If you want to get funded these days leadership in team science is critical. Funding innovation is about more than knowledge and ideas. Collaborating with investigators from different backgrounds and career stages requires new language, organizational and group skills, and familiarity with collaborative tools and technologies.

Join us on July 10, 2012, from 7:30 AM – 12:30 PM at Palmer Commons, and get started in your training, or come to hear the latest. Two outstanding leaders in team science and positive leadership will speak to you and your mentee about the praxis of team science. Expect some highly engaged small group experience.

Register NOW! Breakfast at 7:30 a.m. Program starts promptly at 8 a.m. at Palmer Commons. Boxed lunch.

SPEAKERS:
Kim Cameron, PhD, MA, MS Associate Dean, Executive Education

William Russell Kelly
Professor of Management and Organizations Ross School of Business
And Professor of Higher Education
School of Education University of Michigan

Title: The Science of High Performing Teams: Enabling Positively Deviant Team Performance

Holly Falk-Krzesinski, Ph.D. Research Assistant Professor and Director, Research Team Support & Development (RTS&D) Clinical and Translational Sciences (NUCATS) Institute Northwestern University, Chicago

Preliminary Title: The Science of Team Science

Extreme Scaling Workshop in Chicago – July 15-16

The National Center for Supercomputing Applications’ Blue Waters and the Extreme Science and Engineering Discovery Environment (XSEDE) projects are hosting the annual Extreme Scaling Workshop on July 15-16, 2012, in Chicago.

Petascale systems provide computational science teams with effective, scalable, sustained computing platforms. The research community expects these systems to provide sustained petascale performance on a broad range of science and engineering applications and algorithms, from applications that are compute-intensive to those that are data- and memory-intensive.

The workshop will address algorithmic and applications challenges and solutions in large-scale computing systems with limited memory and I/O bandwidth. The presentations and discussions are intended to assist the computational science and engineering community in making effective use of petascale through extreme-scale systems, across the spectrum of local campus-scale systems to national systems.

Workshop Audience
Scientists, engineers, and high-performance technologists from colleges, universities, laboratories, industry, HPC centers, and other organizations conducting related work are encouraged to attend. Workshop participants will address the issues and will help identify current activities and future needs in order to help the overall computational science community make effective use of petascale through extreme-scale systems, and across the spectrum of local systems through national/international systems.

The continued growth in the number of cores per chip and accelerator-based hybrid systems requires expanded application-driven requirements for new computational models and methods, improved parallel programming algorithms, software development for parallel and distributed systems and application flexibility. Similarly, memory bandwidth limitations and increased challenges of data movement require significantly greater effort in fundamental approaches to application methods.

Achieving the full potential of these new systems, with all their advanced technology components, requires additional effort on the part of the science teams. Fortunately, these efforts are completely aligned with what science teams have to do in order to use almost any system over the next decade.

Workshop Agenda
The workshop begins at noon on Sunday, July 15, and ends at 5 p.m. on Monday, July 16. The event includes a keynote on Sunday afternoon, along with a series of 90-minute sessions that include two presentations and a discussion of the issues raised in the presentations. After the workshop, proceedings—including the papers, presentations, and a summary of the discussions—will be made available via the ACM Digital Library.

The list of talks and presenters is posted on the workshop website: www.xsede.org/web/xscale/agenda.

Workshop Registration
A workshop fee of $125 helps cover the cost of meals, including lunch and dinner on Sunday, and breakfast and lunch on Monday, along with breaks each day. Register before July 15 for the best rates.

Housing
The workshop and accommodations are at the Radisson Hotel Chicago O’Hare, 1450 E. Touhy Ave., Des Plaines, IL, at a nightly room rate of $100 plus taxes. All costs associated with housing and travel are the responsibility of the participants. Use this link to make hotel reservations and receive the conference rate: http://www.radisson.com/extremescalingworkshop.

This workshop is being offered in cooperation with ACM SIGHPC, sighpc.org.

Contact
For more information, contact Scott Lathrop, NCSA, at lathrop@illinois.edu.

TEDxPurdueU Talk on nanoHUB by Gerhard Klimeck

The theme of TEDxPurdueU 2012 was “…innovation.” The speakers selected were Purdue students, alumni, and faculty whose stories shed unique light on various aspects of the creative process from idea conception to reality. Gerhard Klimeck spoke on Mythbusting Scientific Knowledge Transfer with nanoHUB.org at this event in March, 2012.

Gerhard Klimeck is the Director of nanoHUB/NCN (Network for Computational Nanotechnology) and a Professor of Electrical and Computer Engineering at Purdue University.

The NCN provides on-line simulation resources to the Nanotechnology Community at large through its nanoHUB. nanoHUB provides the capability to perform on-line simulation through a web browser without the installation of any software. nanoHUB served over 10,800 simulation users and over 195,000 users in 2011 alone.

Gerhard’s research interest is the modeling of nanoelectronic devices, genetic algorithm based optimization, and image processing.

Gerhard is also Faculty-Part-Time Principal member at the Jet Propulsion Laboratory in the Applied Cluster Computing Technologies Group.


Visitors Get First Look at U-M’s New Modular Data Center

The University of Michigan’s new Modular Data Center (MDC) was filled to capacity and humming on June 14 – with nearly 250 visitors and VIPs from across campus, as well as the state of Michigan. The occasion was the ribbon-cutting ceremony for U-M’s latest and most ecologically friendly data center.

The day began with brief remarks by U-M’s AVP and Chief Information Officer, Laura Patterson; AVP for Research Computing, Dan Atkins; Chief Financial Officer Tim Slottow; and Director of Communications Systems and Data Centers, Andy Palms. Atkins, who reminded that audience that his academic career has spanned most of the modern computer age, gave a brief history lesson to remind us how far computing has come. With the help of Andy Caird, Atkins showed part of the IIiac II computer, designed and built at the University of Illinois in the early 1960’s when he was a graduate student there.

Andy Caird, director of high-performance computing at U-M, shows the Illiac II component during Atkins' speech.

“This massive plug-in component stores only two 4-bit numbers and adds them together — that’s all it does,” said Atkins. “The entire machine was at least eight times larger than the Modular Data Center, and required hundreds of these frames plugged into 12-foot high racks. In contrast, this MDC can hold tens of thousands of enormously more powerful computers and used in parallel offer computing at least 10 trillion times more powerful than Illiac 2.” He went on to highlight the importance of the MDC to the expansion of research computing at U-M. The MDC is the future home of Flux, the university’s shared HPC research computing cluster.

Andy Palms points to the louvers and exhaust fans of the Modular Data Center. Photo courtesy of Terra Molengraff

Visitors took tours of the structure – roughly the size of a double-wide trailer – led by Andy Palms and Dick Boyd, director of telecommunications operations, who described the MDC’s airflow technology. “Rather than running what amounts to a very expensive air conditioner all year long, the MDC allows us to essentially open the windows during the colder months, and limit air conditioning to the few months in the summer when we really need it,” said Palms.

View of the upper ventilation area in the Modular Data Center

U-M received positive press coverage for being the first university in the country to employ this new kind of sustainable data center. The following list is a sample of the coverage.

June 15, University Record – Photo and caption

June 14, IT Business Edge – University of Michigan’s EcoPOD goes doublewide

June 14, Data Center Knowledge – Michigan Unveils First HP EcoPOD Modular Data Center

June 13, Concentrate Media – U-M’s energy-saving Modular Data Center cools down computing costs

June 7, ZD Net – University of Michigan thinks green with modular data center

June 1, Data Center Dynamics – University of Michigan Deploys HP EcoPod for HPC

May 31, Geek Zone Technology Community – University of Michigan takes important strides in research and sustainable computing

May 30, Voice and Data – University of Michigan Reveals Eco-friendly Data Center

May 30, Marc Hamilton’s Blog – University of Michigan’s New EcoPOD Opening Soon

May 29, CBS Detroit – U-M takes important strides in research and sustainable computing

May 21, University Record – U-M to unveil new eco-friendly data center

 

Flux Users Lunch – June 27

You are invited to drop in any time between noon and 1:30 on Wednesday, June 27 for a Flux Users Group lunch. We’ll be in Room 1180 in the Duderstadt Center, and lunch will be provided by the Office of Research Cyberinfrastructure (ORCI).

Flux operators and support staff will be available for your questions. Join us to:

  • Connect with other users doing similar work.
  • Learn about new and upcoming Flux services.
  • Share your experiences with Flux and help us improve our service.

Who should come? Any current Flux user, or anyone interested in learning more using Flux in the future.

Please RSVP by Thursday, June 21 to help us adequately plan for lunch. We look forward to seeing you there.

Virtual School for CS and Engineering Starts in July

Graduate and doctoral students from all disciplines can gain valuable skills in computational science — including programming for many-core processors and heterogeneous systems and leveraging cloud resources — during hands-on summer school schools offered by the Virtual School for Computational Science and Engineering (VSCSE).

The VSCSE helps students use emerging petascale computing resources to address real problems in a wide range of science and engineering disciplines.

The summer schools for 2012 are:

  • Programming Heterogeneous Parallel Computing Systems (July 10-13 2012) [GPGPU]
  • Science Cloud Summer School (July 30 – Aug 3 2012)
  • Proven Algorithmic Techniques for Many-Core Processors (Aug 13-17 2012)

These schools will be delivered to sites nationwide using high-definition videoconferencing technologies, allowing students to participate from convenient locations across the country where they will be able to:

  • work with a cohort of fellow computational scientists,
  • have access to local experts, and
  • interact in real time with school instructors.

Registration for each school is $100.

For more information, go to: www.vscse.org/summerschool/2012/ or contact:
Scott Lathrop (lathrop@illinois.edu)
Blue Waters Technical Program Manager for Education XSEDE
Director of Education and Outreach
217-714-2517

Register now at: hub.vscse.org/

Host Sites:

Programming Heterogeneous Parallel Computing Systems (July 10-13 2012)

  • U Illinois Urbana-Champaign/National Center for Supercomputing Applications
  • Harvard U, Cambridge MA
  • Louisiana State U, Center for Computation & Technology, Baton Rouge LA
  • Pittsburgh Supercomputing Center, Pittsburgh PA
  • Princeton U, Princeton Inst for Computational Science & Engineering, NJ
  • Rutgers U, Piscataway NJ
  • U California Los Angeles
  • U Michigan, Ann Arbor
  • U Oklahoma, Norman
  • U South Carolina, Columbia
  • U Tennessee Knoxville
  • U Utah, Salt Lake City UT

Science Cloud Summer School (July 30 – Aug 3 2012)

  • Indiana U, Bloomington
  • Louisiana State U, Center for Computation & Technology, Baton Rouge
  • Michigan State U, Institute for Cyber Enabled Research, East Lansing
  • Pennsylvania State U, State College
  • Princeton U, Princeton NJ
  • Rutgers U, Piscataway NJ
  • U California Los Angeles
  • U Michigan, Ann Arbor
  • U Wisconsin Milwaukee

Proven Algorithmic Techniques for Many-core Processors (Aug 13-17 2012)

  • U Illinois Urbana-Champaign, National Center for Supercomputing Applications
  • Harvard U, Cambridge MA
  • Michigan State U, Institute for Cyber Enabled Research, East Lansing
  • Pittsburgh Supercomputing Center, Pittsburgh PA
  • Pennsylvania State U, State College
  • Rutgers U, Piscataway NJ
  • U California Los Angeles
  • U Oklahoma, Norman
  • U South Carolina, Columbia
  • U Tennessee Knoxville
  • U Utah, Salt Lake City
  • Vanderbilt U, Nashville TN