Peta-scale computers are monstrous (literally speaking) compared to the workstations or clusters most scientists use when developing models, methods and codes. Yet, several applications that sustain a petaflop/s under production condition on general-purpose supercomputers have emerged within months of the existence of systems that could sustain a petaflop/s on the Linpack benchmark. In this presentation we will review the developments that lead to the much faster than expected advent of "sustained petaflop/s computing". The experience of integrated teams that unify domain knowledge, applied mathematics and computer science, as well as the challenge to develop applications to solve models of complex systems call for a nimble programming environment. We will discuss the use of generic libraries and the concept of just in time abstraction that enable several of today's sustained petaflop/s applications.
Thomas Schulthess received his PhD in Physics in 1994 from the ETH Zurich. After postdoctoral fellowships at Lawrence Livermore National Laboratory and Oak Ridge National Laboratory (ORNL) he became a research staff member of ORNL's Computer Science and Mathematics Division in 1999 where he served as group leader of the Computational Materials Science Group from 2002 to 2008. He was appointed to ORNL's Nanoscience Research Center, the Center for Nanophase Materials Sciences, in 2005 where he led the Nanomaterials Theory Institute until 2008. Since October 2008, Thomas holds a chair in computational physics at ETH Zurich and directs the National Supercomputing Center of Switzerland (CSCS) in Manno. Thomas' research interests are in condensed matter, nano- and materials sciences, as well as the development of extreme scale computing to solve important problems in these fields. He led the teams that developed DCA++, the first application to sustain a petaflop/s under production conditions in November 2008 and is used to study models of high-temperature superconductivity, and WL-LSMS, an application to study magnetic nanostructured materials. The DCA++ and WL-LSMS development teams received the Grodon Bell Prizes for Peak Performance at SC08 and SC09, respectively.