Seminar: On the Julia Language for High-Productivity and High-Performance Scientific Computing
William Godoy
Senior Computer Scientist
Computer Science and Mathematics Division
Oak Ridge National Laboratory (ORNL)
Friday, October 3
2:30 - 3:45 PM
Classroom Building, Room 260
Abstract
Julia is both a high-performance and high-productivity programming language for scientific computing. As an open-source project that originated from MIT, it is known for its speed, rivaling statically-typed languages like C and Fortran, while offering the ease of use and expressiveness of dynamically-typed languages like Python and R. This oxymoronic combination addresses the "two-language problem," where developers often use a high-level language (e.g. Python) for prototyping and then rewriting performance-critical parts in a lower-level language (e.g. C++). This talk presents an overview of our research and community efforts in exploring the Julia language for the scientific mission of the U.S. Department of Energy (DOE). Specifically, we present our efforts on the following: (1) building an accessible performance-portable CPU/GPU library, i.e., "write once, run anywhere," called JACC; (2) deploying and disseminating Julia to the scientific masses; and (3) advancing Julia research - including best paper awards - and its incorporation to the experimental and computational facilities at DOE's Oak Ridge National Laboratory. Julia aspires to make more accessible the future landscape of heterogeneous, AI-driven, and energy-aware computing by leveraging existing investments outside DOE in LLVM and commercial applications of the language.
Biography
William Godoy is a senior computer scientist in the Computer Science and Mathematics Division at Oak Ridge National Laboratory (ORNL). His interests are in high-performance computing, parallel programming systems, scientific software and workflows. At ORNL, he contributed to the Exascale Computing Project applications - QMCPACK - and software technologies portfolios – ADIOS2, Julia/LLVM, and projects impacting ORNL’s computing and neutron science facilities. Godoy currently works across research projects funded by the US Department of Energy Advanced Scientific Computing Research (ASCR) program co leading project on AI for HPC Software, High-productivity HPC programming, and future supercomputing research. Prior to ORNL, he was a staff member at Intel Corporation and a postdoctoral fellow at NASA Langley Research Center. Godoy received PhD and MSc degrees from the University at Buffalo, The State University of New York, and a BSc from the National Engineering University (UNI) Lima, Peru, in mechanical engineering. He is a senior member of the IEEE, and a member of ACM, ASME serving in several venues and technical committees and has contributed to more than 50 papers in computational and computer science peer-reviewed venues.