“Scalable Algorithms and Hybrid Parallelization Strategies for Multivariate Integration with ParAdapt and CUDA” by Omofolakunmi (Fola) Olagbemi, doctoral candidate at Western Michigan University’s Computer Science Department

The evaluation of numerical integrals finds applications in fields such as High Energy Physics, Bayesian Statistics, Stochastic Geometry, Molecular Modeling and Medical Physics. The erratic behavior of some integrands due to singularities, peaks, or ridges in the integration region suggests the need for reliable algorithms and software that not only provide an estimation of the integral with a level of accuracy acceptable to the user, but also perform this task in a timely manner. We developed ParAdapt, a numerical integration software based on a classic global adaptive strategy, which employs Graphical Processing Units (GPUs) in providing integral evaluations. Specifically, ParAdapt applies adaptive region partitioning strategies developed for efficient integration and mapping to GPUs. The resulting methods render the framework of the classic global adaptive scheme suitable for general functions in moderate dimensions, say 10 to 25. The algorithms presented have been determined to be scalable as evidenced by speedup values in the double and triple digits up to very large numbers of subdivisions. An analysis of the various partitioning and parallelization strategies is given.

Short Bio: Fola is a doctoral candidate at Western Michigan University’s Computer Science Department, looking forward to graduating at the end of the Fall 2019 semester. During her time as a graduate student, Fola has taught several classes in Java (both Labs and Lectures), at both the introductory and more advanced levels. In the current (Fall 2019) semester, in addition to a Java Lab, she is teaching an introductory course in Web Technologies (including topics like HTML, CSS, JavaScript and PHP).
Prior to coming to the United States to pursue a PhD degree, Fola worked for some years at PricewaterhouseCoopers in Nigeria, working with teams to provide assurance services to the firm’s clients.
Her research areas include: high performance computing, applying GPUs and CUDA to scientific computations including the estimation of multivariate numerical integrals from diverse fields such as Bayesian Statistics and High Energy Physics.
Fola obtained her Bachelors in Computer Science from University of Lagos, Lagos, Nigeria, and her M.S. degree in Computer Science from the University of Massachusetts at Boston.