Visit additional Tabor Communication Publications
November 06, 2009
Wilfred "Wilf" Pinfold is this year's general chair for SC09, the 22nd annual event in the Supercomputing series. He is also the director of Extreme Scale Programs at Intel. In this Q&A, Wilf shares his thoughts on organizing the conference, explains this year's big themes (hint: sustainability plays a big part) and gives his opinions on the state of the industry and how that reflects on the conference.
HPCwire: Wilf, you've been involved in SC for some time, but this year you're the general chair. What's it like being the lead organizer for a 10,000-plus attendee conference?
Wilfred Robert Pinfold: I have played roles in the technical program, exhibits, and communications and have been a participant since 1989. Each year the conference has grown and matured, and each year, the new conference chair has taken the best from the previous year and built on it. This history provides a substantial knowledge base and culture that you learn to trust and rely on.
As the general chair for a year, there are two decisions that stand out as the most critical. The first is selecting the committee. These people not only need to be passionate and competent in what you are asking them to do, but they must also be willing and able to commit substantial amounts of their time over the 2 to 3 year planning cycle. Through a combination of good judgment and luck, I have an extraordinary committee. The second is deciding what to keep unchanged and what to change or build on. I have found that anything you change takes an order of magnitude more time and effort than the things the community has done well before. However, in a subject as dynamic as high performance computing, change is a critical element. So, each year the chair must decide what changes to take on.
HPCwire: What are the big themes for SC09 and why were they singled out?
Pinfold: We chose to structure much of this year's content around three thrust areas. These thrust areas were selected as areas in which high performance computing has had, is having, and will have a very substantial impact on society. The intention is to make high performance computing more accessible by making its impact on our lives more tangible.
Starting with the Tuesday opening address -- the future opportunity of the 3D Internet will be introduced by Justin Rattner. The 3D Internet is about users immersing themselves in data from scientific instruments (telescopes, spacecraft, topographic imaging systems) or from extreme data sources (the internet, genomic data, financial markets).
On Wednesday the plenary speaker will be Leroy Hood, a leader in systems biology who will explore bio-computing, an area of intense current research and development. We will look at the promise this field offers in discovering treatments for many chronic diseases including cancer, diabetes and Alzheimer's.
On Thursday the keynote will address sustainability, an area where the high performance computing community has already dramatically impacted public policy with weather modeling and the scientific foundations for alternative energy in fusion, hydroelectric and wind power. Al Gore will discuss the importance of highly accurate climate and pollution models in making good public policy decisions. Following these plenary sessions the technical program and exhibits will dig more deeply into these concepts. I am excited by the opportunity these thrust areas give us in reaching a wider audience.
HPCwire: This year, there is a design competition for the "Data Center of the Future," which fits in nicely with the sustainability theme. Can you tell us what that competition entails?
Pinfold: The "Data Center of the Future" is one of the new concepts we introduced this year and it has already gone through some change. The competition has been replaced with a booth, tutorial, panel and two Birds of a Feather sessions. The booth will showcase technologies from UCAR/NCAR, LBNL, University of Illinois, ORNL, Barcelona Supercomputing Center, Swiss National Supercomputing Center and the Tokyo Institute of Technology. The tutorial will address "Power and Thermal Management in Datacenters"; the panel will discuss "Energy Efficient Datacenters: How Lean and Green Do We Need to Be?"; and the BoFs will look into the "Green500" and the "Energy Efficient HPC Working Group." These forums better address the breadth of this topic.
HPCwire: The SC crowd seems to get a little younger each year. What's on tap for students and other newcomers to the community?
Pinfold: We have an excellent student program this year. Student volunteers will have the opportunity to learn about, and discuss, the latest technologies in exchange for helping make the conference a success. We will provide them face-to-face networking opportunities with potential employers exhibiting at SC09 and a Mentor/Protégé Program to match each participant (protégé) with a mentor who has attended SC before and who is willing to share their experiences.
HPCwire: For the keynote address, SC seems to vacillate between more conventional speakers from within the industry and thought leaders from without. This year's selection of Al Gore is clearly in the latter category. What went into his selection and was he difficult to book?
Pinfold: Portland helped us select sustainability as one of our thrust areas for 2009. The city itself and the local community are very well attuned to sustainable practices. We assembled a list of the top speakers in sustainability technology thought leadership. VP Al Gore was top on this list. Al Gore will speak on "Computing Solutions For a Changing World." There are additional complexities to scheduling a high-profile speaker but starting early and having very competent planners made it relatively seamless.
HPCwire: Putting yourself in the role of attendee, what do you think are some of the can't-miss sessions, presentations, or events this year?
Pinfold: That is hard. We go out of our way to make sure there is something for everyone. To help guide attendees this year we have set up three thrust areas Sustainability, Bio-computing and 3D Internet. These areas help provide a context for how the technologies HPC, networking, storage and analytics work to provide value in key areas of scientific endeavor. By using the SC Your Way section of the conference Web site, attendees can tailor their schedule based on topics and keywords of interest -- so it gets much easier each year to build a personal schedule that will help each attendee get the most out of the conference. I hope this will help guide attendees to the can't-miss material in their fields.
HPCwire: It's been a tough year for the industry, which has seen a lot of consolidation and scaling back. How is this affecting the exhibitor presence?
Pinfold: As you probably know we sell the majority of our booth space at a booth selection event at the conference the year before the event. The industry mainstays all signed up and several expanded their presence. New exhibitors tended to hold back waiting to see if they would be in a position to sign up. In just the past month, we have had an extraordinary surge of companies signing up for booth space. We will have a sold-out tradeshow floor at the event.
HPCwire: A lot of organizations are cutting event travel in these lean times. Do you think the attendance will drop off this year, hold steady, or increase?
Pinfold: We saw a significant increase in attendance in 2008 despite the economic downturn. This year we planned conservatively for an attendance between 2007 and 2008 levels. So we see it as holding steady and possibly increasing. Current registration numbers are following this trend. Exhibits were slow but late demand has been high and if this holds true for registration, we may actually set a new record.
I can only speculate why SC has been able to retain attendance when so many events have been hurt by travel budget cuts. If I were to guess it is that SC is mission critical for many in the community. It is an excellent place to do business with such a large part of the HPC community in attendance. For thousands of HPC professionals, if they can only attend one event each year, this is going to be the event they will select.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 15, 2013 |
Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 09, 2013 |
The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
May 08, 2013 |
For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.