Return to: U of M Home
The key aspect of research activities that is common to the research topics is the very large scale computing via the new parallel algorithms. Traditionally, a significant effort is expended to speed up the computational times through the optimization of codes for specific computing architectures, which can be termed software implementation research. However, it is impossible to achieve significant utilization of high-performance computers employing todays and/or next generation simulation codes based on yesterdays unscalable paradigms. It has been realized that very large scale computing via the high performance computing is the only key to unlocking many of the complex problems facing modern science and engineering. The parallel processing technique, which concurrently utilizes anywhere from a few to a few thousand processors, has been recognized as the key technology for dealing with large-scale simulations in a reasonable computation time for many Department of Defense and Department of Energy initiatives.
Publications, Conference Proceedings & Presentations
A-Scalability of an Integrated Computational Technology and Framework for Non-linear Structural Dynamics - Part II: Implementation Aspects and Parallel Performance Results, International Journal for Numerical Methods in Engineering, 58, 2295--2323, 2003.
Recent Advances Enabling Scalable Computations via Optimal Algorithms for Structural Dynamics, WCCM 5th World Congress on Computational Mechanics, Vienna University of Technology, Vienna, Austria, July 7--12, 2002.
Absolute Scalability of Space/Time Domain Decomposition in Computational Structural Dynamics for Virtual Modeling and Testing Applications, DoD Success story, 2002. (with A. Mark and R. Namburu)
Total Scalability and Space/Time Domain Decomposition for Computational Structural Dynamics, From Terabytes to Insights-Supercomputing 2002, November 18--22, Baltimore MD.
A General Framework and Integrated Methodology Towards Scalable Heterogeneous Computations for Structural Dynamics on Massively Parallel Platforms, 42nd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, Seattle, Washington, April 13--19, 2001.
Parallel Computations via a Single Analysis Code of a Unified family of Generalized Integration Operators [GInO] for Non-linear Structural Dynamics, 41st AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, Atlanta, Georgia, April 3--6, 2000.
Highly Scalable Parallel Computational Models for Large Scale RTM Process Modeling Simulations, Part 2: Parallel Formulation Theory and Implementation, Numerical Heat Transfer: Fundamentals, 36, 286--308, 1999. (with A. Mark)
Highly Scalable Parallel Computational Models for Large Scale RTM Process Modeling Simulations, Part 3: Validation and Performance Results, Numerical Heat Transfer: Fundamentals, 36, 351--386,1999. (with A. Mark)
Computational Techniques and Parallel Software Development for Large Scale Composite Manufacturing Process Simulations, DoD HPC Users' Group Conference, Monterey, CA, 7-10 June 1999. (with R. Mohan and D. Shires)
Computational Strategies and Approaches for Integrated Modeling Technology on High Performance Computing Platforms: Process Modeling Simulations, 21st Army Science Conference - Science & Technology for Army After Next, 199--204, 1998. (with A. Mark and R. Mohan)
High Performance Computing on a Symmetric Multiprocessor (SMP) Environment for RTM Process Modeling of Large Complex Structural Geometries, Special issue on large-scale analysis, design and intelligent synthesis environments, Advances in Engineering Software, 29, 399-408, 1998. (with M. Baddourah and A. Mark)
R. Kanapady, K. K. Tamma, M. Baddourah and A. Mark, High Performance Computing on a Symmetric Multiprocessor (SMP) Environment for RTM Process Modeling of Large Complex Structural Geometries, 4th National Symposium on Large Scale Analysis and Design on High Performance Computers and Workstations, Williamsburg, VA, October 15 - 17, 1997. (with M. Baddourah and A. Mark)