Avi Purkayastha

Sr. Scientist


Avi Purkayastha joined the Computational Science Center at NREL in 2010 as a senior scientist in high performance computing, where he is working on enabling and advancing large-scale NREL application domain codes on HPC systems. Previously, he was in private industry at a systems startup company, SiCortex Inc., where he worked for two years on application development, porting, optimization, and application benchmarking for the MIPS64-based parallel cluster system, as well as technical marketing and sales of the product.

Before his experience in the startup commercial world, Dr. Purkayastha was a research scientist at the Texas Advanced Computing Center, affiliated with the University of Texas at Austin, from 2001 to 2007. There he was principal in HPC applications and user support, as well as in research and development in large-scale scientific applications and different HPC systems and technologies.

While at Northern Illinois University, he worked with Drs. Biswa Datta and Chris Bischof of Argonne National Laboratory to design, develop, and implement a parallel algorithm for control systems.

Research Interests

HPC systems and applications

Modeling and simulations across multiple domains in different scales and fidelity

Software support, optimization, and engineering

Data science and artificial intelligence/machine learning


Ph.D., Applied Mathematics, Northern Illinois University

M.S., Mechanical Engineering - Thermal Fluids, Colorado School of Mines

Python, data science, and artificial intelligence/machine learning certificates

Professional Experience

Principal Applications Engineer, SiCortex (2007–2009)

Research Scientist, Texas Advanced Computing Center - University of Texas Austin (2001–2007)

Visiting Professor Computational Science / Research Scientist, Mississippi State University (1998–2000)

Associate Professor, University of Puerto Rico (1993–2000)

Research Assistant, Northern Illinois University (1985–1992)

Featured Work

An FEM-MLMC Algorithm for a Moving Shutter Diffraction in Time Stochastic Model, Discrete and Continuous Dynamical Systems (2019)

Holistic Approaches to HPC Power & Workflow Management, 9th International Green and Sustainable Computing Conference (2018)

Development of FAST.Farm: A New Multi-Physics Engineering Tool for Wind-Farm Design and AnalysisProceedings of the AIAA SciTech Forum: 35th Wind Energy Symposium (2017)

An Analysis of Application Power and Schedule Composition in a High Performance Computing Environment, NREL Technical Report (2016)

Legendre Spectral Finite Elements for Reissner–Mindlin Composite Plates, Finite Elements in Analysis and Design (2015)