AHPCRC Projects: Advanced Algorithms


Fluid dynamics calculations	Matrix solution methods	Global minimum location

Optimization algorithms	Fast multipole method	Hybrid parameter optimization methods

Advanced Algorithms for High Performance Computing

Image archive

High performance computing applications solve millions of mathematical equations to simulate and predict real-world phenomena. In order to balance the need for accuracy and detail with the economical use of time and computer resources, mathematical methods must be developed to find the fastest route to the most accurate results. Algorithmic capabilities developed for AHPCRC point the way toward wider application as commercially available computers become increasingly powerful.

Projects and People
1–7: High Performance Optimization Library Walter Murray (Stanford) Michael Saunders (Stanford)
4–5: PFMMPACK Parallel Fast Multipole Method Library Eric Darve (Stanford) (project duration: 2007–2009)
4–6: Hybrid Schemes for Parameter Estimation Problems Miguel Argáez (UTEP) Leticia Velázquez (UTEP)
More projects: