In this guest feature from Scientific Computing World, Georgia Institute of Technology’s David A. Bader discusses his upcoming ISC’13 session, Better Understanding Brains, Genomes & Life Using HPC Systems.
Supercomputing at ISC has traditionally focused on problems in areas such as the simulation space for physical phenomena. Manufacturing, weather simulations and molecular dynamics have all been popular topics, but an emerging trend is the examination of how we use high-end computing to solve some of the most important problems that affect the human condition.
Prompted by Hans Meuer, general chairman of ISC, we decided to put together a session that asks how supercomputing is enabling the study of life, and by this we mean answering questions such as how life evolves, how we go from genotype to phenotype, and how our brains function. At the moment, brain function, for example, remains a mystery but I do believe that we will begin to make progress in the next 10 to 20 years. It truly is an exciting time for life sciences research, and we have brought together three speakers that will explore three different axes of computational biology and genomics.
The first speaker, Dr BingQiang Wang, is head of High Performance Computing, BGI Research at the Beijing Genome Institute, and he will begin the session by talking about bioinformatics and how we take the massive scale sequencing of genomes and use that intensive architecture to do the problems related to aligning sequences at extreme scale. In addition, it will focus on giving tools to the analysts and accelerate computations using GPUs. Essentially, his is a Big Data talk on the first aspect of biology, the study of sequences.
Our second speaker, Dr Rossen Apostolov, comes from the KTH Royal Institute of Technology, Sweden, and is technical director of the EU-funded project ScalaLife. We thought that ScalaLife was a very interesting project to preview at ISC because it’s taking a lot of simulation aspects in life sciences and then bringing HPC to bear in tackling these problems. The project brings together multi-physics simulations between molecular dynamics, quantum mechanics, and discrete optimisation, and then uses these different computational disciplines to solve the simulation of life itself. This will be a fascinating talk because it’s going to connect these unique types of simulation into a unified framework, again supported by the EU, for the simulation of living organisms – an impossible task without the use of supercomputing resources.
The third presentation will be given by Prof. Dr Markus Diesmann, director of the Institute of Neuroscience and Medicine, Computational and Systems Neuroscience (INM-6) and the Institute for Advanced Simulation, Theoretical Neuroscience (IAS-6) at the Jülich Research Centre, and Professor for Computational Neuroscience at the Medical Faculty of RWTH Aachen University. His talk will focus on some of the most challenging simulations of the collection of neurons that make up the brain, and will fit in with the need for massive supercomputers that can do these full-scale simulations. Diesmann leads a European effort to develop the algorithms, the simulation technology, the validation for both the brain imaging and scanning, along with the computational methods to aid our understanding of how the brain works. This is so critical because if we knew how the brain functioned we’d be able to better help the population in dealing with some of issues that affect it.
By the end of the session we hope to have informed the international supercomputing community that biology and molecular science are hot topics for applications. The most important point is that it will be a two-way conversation, bringing these communities together and giving system designers and vendors a better idea of how to make supercomputing systems that will be more efficient for tackling these types of challenges.
The hallmark of all the problems we will be exploring is that their efficient solutions require high-end computing systems and Big Data platforms. We really need to bring together supercomputers and Big Data storage systems to tackle what I feel is the holy grail of computing: the understanding of life.
Better Understanding Brains, Genomes & Life Using HPC Systems
Wednesday, 19 June 2013
9am – 10.30am
Hall 2, CCL – Congress Center Leipzig
This story appears here as part of a cross-publishing agreement with Scientific Computing World.
UIUC researchers uncovered detail about the capsid structure by running the first all-atom simulation of HIV on the Blue Waters supercomputer. Powered by 3,000 NVIDIA Tesla K20X GPU accelerators – the highest performance, most efficient accelerators ever built – the Cray XK7 supercomputer gave researchers the computational performance to run the largest simulation ever published, involving 64 million atoms.
Over at the 
