The HPC Asia 2009 keynote speech, given by Dr. Peter Arzberger, gives us deep understanding into Dr. Arzberger’s vision for the successful integration of HPC with cross-cultural and international collaboration. He also describes the beginnings of the PRAGMA institute he started several years and currently chairs along with its organizational structure. Dr. Arzberger’s goes on to give us his insight into how to better educate students of science so that they will be better prepared to do research in the global science community.
Part1| Part2 | Part3 | Part4 | Part5 | Part6 | Part7 | Part8 [PDF Download] [Video]
Part 2: HPC Technology Trends
Of course, another huge technology trend are these that we’ve experienced over the last many years, these exponential trends in the amount of computing that we can do and the amount of data that we can store and how we can move this data and interact with each other with this data. And, more recently, of course, there’s been a lot of talk about how we virtualize the machines and also work in a cloud setting. What’s interesting in this cloud setting is that there is actually now a business model that we can use. It doesn’t solve all problems. But it is an interesting model to look at.
What I want to do for the next couple five days to really focus on the area of translational medicine and talk about some of the IT challenges there as they relate to some of the key issues. In this area, we really are focused on three major driving issues. One is the heart and how can we better use patient data in modeling the heart and so that we can try to understand how a particular operation procedure will work on that particular individual patient. Another area is virtual screening or how can we improve the process by which we identify the possible targets to address those infectious diseases. And the third area which I’ll spend a little bit more time on is how do we take advantage of these new technologies that produce really high resolution for a particular electro microscopsy and begin to see inside the cell in areas that are very critical.
We envision very much a pipeline of activities, and you’ll see this several times throughout my talk. We really begin with the data; we have to define the data in certain ways. We begin to model the data and we begin to simulate and understand through that simulation how it affects the biology of the heart, how we can improve drugs for diseases, and how we can gain understanding by using these technologies.
So, just two slides show one particular example. Now, this particular example you can see the microscope that allows you to produce the image. What we’re looking at here is a cardiac cell. Inside the cardiac cell there are structures called T-tubules which is where the calcium will migrate inside the cell. What you don’t see here is the sophisticated mathematics and the computing that went into making this reconstruction. But what you do see are some mathematical tools that allow you to do the segmentation and the meshing. Now this is mathematical meshing. It is not visualization meshing.
The challenge in the HPC arena is that it’s a very difficult activity. Right now just with one T-tubules model that can show the correct geometry. That’s really a major issue. What we’d love to be able to do is model 200~300 of these that you would actually see in a real cell. The reason that we’re interested in this is that there is an association between the spatial derangement of these things and the mechanical actions of the heart. We’re trying to understand what these minor structures have to do with these major structures. And so again, it’s a really wonderful example of where HPC and mathematics come together to actually give us some insights into a new frontier in biology.
Another area where we can begin to see how IT can affect important societal things is this cultural heritage. If you look at these particular images, what you really see is a wealth of history of our society depicted here. On the left, you see the picture as we see it today. On the right, you see the same picture under ultraviolet fluorescents. You can see where there have been touches made to that picture. If we look at types of technologies of frequencies, you begin to see different aspects of what has happened to the original painting over time. And you can begin to construct the history of that painting-- and what has changed and so on. And looking at this painting over tiled display walls (TDW), you can get an up close and personal look at the various images. But it’s not just the construction of the history as Professor Serachini, whom I borrowed these slides from, said, rather, it’s really the notion of moving from the understanding of history to the preservation of that piece of art and being able to create, through synthesis of data, almost like a health chart of each of the artifacts which we can study. And that’s another new area of HPC.