Description: In the phase II effort, Intelligent Automation Inc., (IAI) and University of Central Florida (UCF) propose to develop a comprehensive numerical test suite for benchmarking current and future high performance computing activities that will include: (1) dense and unsymmetrical matrix problems faced in space aviation and problems in thermally driven structural response and radiation exchange, (2) implicit solution algorithms with production models and benchmarks for indefinite matrices and pathological cases, (3) configurations scaling for large systems in shared, distributed and mixed memory conditions, (4) documentation for strengths, weaknesses, and limitations of the toolkits used together with recommendations and (5) precision and round-off studies on serial and parallel machines, comparison of solutions on serial and parallel hardware with study of wall clock performance with respect to the number of processors We successfully demonstrated in phase I that we can accurately and precisely benchmark run time solvers of dense complex matrices in hybrid-distributed memory architecture. We achieved highly scalable super-linear speed-up and scalability of the algorithm for large problem sizes. The tools developed in phase II will greatly improve the performance and efficiency to adapt the benchmarks to HPC systems different hardware architectures at NASA facilities and for non-NASA commercial applications.

Benefits: The bench marking suite developed for HPC under this topic is applicable to computations in aerospace, avionics, military and civilian use. These high performance applications include thermal and structural problems in industry, manufacturing sectors and military. Other applications include diagnostics, weather, nuclear simulations and health monitoring applications. IAI has tremendous experience of developing distributed applications and simulation platforms and commercializing them by packaging to field-ready units. We had successfully sold our developed distributed computing applications to established companies. Here again the developed technology from this contract will be packaged for different market segments with the goal of licensing our technology and possible collaboration efforts.

Our technical approach builds on our experience in cluster computing, distributed agents system, parallel model developments for High Performance Computing (HPC) and our teams expertise in these areas for problem selection. The benchmarking application will be directly useful for high performance computing applications for NASA. For NASA there is a vast potential need for benchmarking the solutions that could be applied to heat transfer problems in structures in avionics, diagnostic of structures in space exploration and exploration of structure formation, weather, nuclear simulations and problems in geology. Applications include testing requirements testing requirements for temperature contour of space shuttle, boundary layer Transition protuberance, heat shield problems computations and computation architectures where simulation modeling environments have solvers that run into hundreds of degrees of freedom. IAI has a long history of successfully developing distributed computing simulation applications for NASA. Our previously developed distributed agent simulation system has been embraced by NASA as the development platform for its simulator for the next generation air traffic control system.