As we prepare for the 25th anniversary of the International Supercomputing Conference (ISC’10), we once again tracked down one of our favorite commentators, Wolfgang Gentzsch, for some inside perspective.
insideHPC: ISC is celebrating its twenty-fifth anniversary. How many of the ISC conferences have you attended?
Wolfgang Gentzsch: I’ve been fortunate to have attended all the ISC conferences since the first event. It seems hard to believe that it has been 25 years.
insideHPC: What are some of the most significant changes you have seen with the ISC conference over those years?
Wolfgang Gentzsch: Watching the growth of the conference has been just amazing. And, not only did ISC grow from about 150 attendees in 1986 to almost 2,000 today, the unique, genial atmosphere that this conference has become known for managed to survive that growth.
Looking back over the years, some of us certainly miss the unforgettable wine tours to the Mannheim hinterland in the Summer time, but of course, today that would just not be practical. Can you imagine trying to load 2,000 participants into 40 buses for a winery tour?
insideHPC: What do you think will be some of the hottest topics being discussed at ISC’10?
Wolfgang Gentzsch: HPC in the context of Multicore, Green IT, Cloud Computing and, certainly, the organizer of this conference for the past 25 years, Hans Meuer himself. And, purely from the networking standpoint, what are all my HPC friends doing this year?
insideHPC: While the ISC conference is on a much different scale than the ACM/IEEE SC conference, it is seen by many as being just as important — and in many ways — even more important for HPC companies looking to do business in Europe. How would you describe ISC to a company that is new to HPC?
Wolfgang Gentzsch: In such a fast changing area such as HPC, it makes a lot of sense to me to have two supercomputing conferences per year, every 6 months, one in the US and one in Europe. Change happens fast in this community — and once a year is just not enough to keep up with all the advancements. While the annual SC conference attracts a growing number of international attendees, there will always be some number of HPC professionals in Europe who just can’t do the travel to the annual US event. ISC brings a good balance and affords the vendors an opportunity to get close to their European customers.
ISC attracts various levels of decision makers in research, government and industry. So, for any HPC vendor, new or established, ISC is a great venue for meeting existing and future customers.
insideHPC: What advice do you have for first time attendees coming to ISC’10?
Wolfgang Gentzsch: Before you come to ISC, look at the rich online program. There is something of interest for everyone. My advice would be to make a detailed plan for the talks you wish to attend, the booths you would like to visit, the people you want to meet, and of course the parties where you can relax and network with your colleagues. Without some forethought and planning, the show can be overwhelming.
insideHPC: Tell us a little more about your role at DEISA — and can you explain the role of DEISA to our readers?
Wolfgang Gentzsch: DEISA is the Distributed European Infrastructure for Supercomputing Applications, providing access to HPC resources for individuals and teams of researchers, supporting them with solutions for solving their grand challenge big science applications. Hundreds of researchers in Europe and around the world have so far benefited from this Grid of HPC resources residing at 12 of the largest HPC centers in Europe. DEISA has now been in production for 5 years. My main role in DEISA is to work with the dissemination team, to spread the message widely, and to invite scientists and researchers to make use of this precious e-infrastructure.
insideHPC: Stepping back to take a much larger view of the global HPC community, what is your perspective on the HPC business climate for 2010 — and how does it compare to 2009?
Wolfgang Gentzsch: I would sum up the climate for 2010 as “evolution everywhere.” At one end (the smallest scale) we have increasing cores on the chip for lower power consumption, and at the other end (the large scale) we see the trend to consider Cloud services even for HPC applications. And in general, continuous commoditization with more user-friendly access, and more sectors using simulations on HPC systems.
So, how does this compare to the climate for 2009? I’d say it’s like a battery that’s been recharged and running at full speed. The activity level is exciting and HPC is experiencing renewed vigor and growth.
insideHPC: This brings up an interesting question. Some critics say we are putting way too much hype on Cloud services, and that it is really just a new label for Grid computing. What is your perspective on this?
Wolfgang Gentzsch: Cloud Computing is the result of a natural evolution of our community’s work on distributed computing. 10 years ago, when we talked about Grid Computing, our goal indeed was what Cloud Computing promises today: remote, secure, dependable, consistent, pervasive, and inexpensive access to computing, as just another (new) utility. That’s Cloud today. Grid remained more in the realm of the scientists, with their complex workflows which a Grid can accommodate, and with their needs to adjust (and match) applications and resources. And still, a Cloud can be a service node in a Grid, whenever a scientific workflow component is suitable for the simpler architecture of a Cloud.
Finally, in my opinion, Clouds will serve a useful purpose in a number of areas, but I don’t see Clouds, at least not in the midterm, for those environments where you need the highest performance computing while requiring low latency and powerful interconnect architectures for tightly coupled algorithms.
insideHPC: What do you see as the key enablers to us being able to really advance scientific discovery, and what are the key barriers?
Wolfgang Gentzsch: From my perspective, the most important key enablers will be easy access for every scientist to any HPC system, along with supporting interdisciplinary collaboration in virtual organizations.
A key barrier is that we still do not have enough scientists and engineers, compared with the challenges we face. Unfortunately, programs designed to attract many more students early on to science education is a topic still strongly neglected by many governments. I have some hope now with great technologies such as Web 2.0 and Cloud Computing, that we can start bringing science simulations and other content to our children and students, making it easy for them to access, and delivering programs in an “edutaining” way, such as what is being demonstrated already on the Web, for example, with the GridwiseTech e-School prototype and other projects.
insideHPC: Looking out to the next 3-5 years, how will HPC make a difference in our lives?
Wolfgang Gentzsch: HPC already makes a profound difference. Today, we are enjoying many amenities to make our lives easier, such as the advancements in travel, living, health, leisure, and knowledge.
Many advanced products and technologies have been designed on HPC systems, and HPC systems have allowed us to gain deeper insight into the secrets of nature. I have no doubt that this progress will continue and even accelerate in the coming years.
However, for HPC enthusiasts, this means: no hope for early retirement.
Wolfgang Gentzsch is currently Advisor to the EU funded project DEISA, a member of the Board of Directors of the OGF Open Grid Forum standards organization, and a senior consultant to HPC, Grid, and Cloud companies and governments. Before that he directed the German D-Grid Initiative and was an adjunct professor of computer science at Duke University in Durham and at NC State in Raleigh, and visiting scientist at the RENCI Renaissance Computing Institute at UNC Chapel Hill, North Carolina; Vice Chair of the EU e-Infrastructure Reflection Group e-IRG; and a member of the US President’s Council of Advisors for Science and Technology, PCAST.