NESAP Postdocs - 2018
Since introducing the NERSC Exascale Scientific Applications Program (NESAP) in 2015, NERSC has hired more than a dozen postdoctoral fellows and placed them with NESAP code optimization teams. The postdocs are working in multidisciplinary teams composed of computer scientists, applied mathematicians, domain scientists and performance optimization experts that are helping NERSC users transition codes to the Cori system.
Here’s a look at the current roster of NESAP postdocs:
Bill Arndt joined NERSC as a postdoctoral fellow in early 2016 and is working to modify the HMMER algorithm to run on Cori. HMMER is a biological sequence search tool that is frequently used by researchers at the Joint Genome Institute to annotate new genome sequences. After obtaining his Ph.D. in computer science from the University of South Carolina-Columbia, Arndt spent almost two years at the Howard Hughes Medical Institute where he worked on data processing scripts that support HMMER.org.
Rahulkumar Gayatri got his Ph.D. in the area of parallel programming models from Barcelona Supercomputing Center in March 2015 under the supervision of Dr Rosa Maria Badia and Eduard Ayguade. His thesis work was on synchronization of multiple threads on a multi-core processor. Later he worked in the HPC group at Wipro Infotech where he provided parallel programming solutions to clients. Currently he is working on the SW4 and performance portability projects.
Kevin Gott joined NERSC as a NESAP postdoc in July 2016. His current project is the profiling tool ProfVis, a full-scale profiling collection, visualization and post-processing tool being developed by CCSE with Ann Almgren. It is being used to profile the exa-scale computing project AMReX, an adaptive mesh refinement framework used in a wide variety of scientific applications. His other NESAP projects include surface tension modeling with ALE-AMR for use in modeling extreme ultraviolet lithography with Alice Koniges and the implementation of a thread-multiple MPI/OpenMP force calculation in the real-space DFT solver PARSEC, maintained by the Center for Computational Materials led by Dr. J.R. Chelikowsky at The University of Texas at Austin. He received his Ph.D. in Mechanical Engineering from the Pennsylvania State University, where his dissertation focused on the development of a combination CFD-DSMC solver for simulating physical vapor deposition. His research interests include fluid mechanics, physics, code development and optimization.
Jonathan Madsen earned his PhD from Texas A&M University in Nuclear Engineering in December 2017 under the supervision of Dr. Ryan G. McClarren. He has been a member of the Geant4 collaboration since 2011 and is currently a member of the Run, Event, and Detector Responses Working Group with a focus on scoring and multithreading. His doctoral research focused on applying the concepts of compressed sensing to Monte Carlo scoring arrays in an effort to reduce memory allocation and reduce computation time through statistical de-noising during the reconstruction of the solution. As part of the NESAP program, Madsen is working on applications developed by the Cosmic Microwave Background group at Berkeley Lab led by Julian Borrill.
Laurie Stephey, a NESAP for Data postdoc, is working with the DESI (Dark Energy Spectroscopic Instrument) project to help make their large-scale data processing run efficiently at NERSC. This can be especially challenging since much of the DESI code is written in python, a very popular language that is convenient for developers but not traditionally used in HPC. She is employing strategies like MPI using mpi4py and Just-In-Time compilation using numba to make the DESI simulation tools run faster. In 2009, Laurie earned her B.A. in Physics from Rollins College in Orlando, Florida. In 2017, she earned her Ph.D. from the University of Wisconsin-Madison studying edge physics in the HSX and W7-X stellarators. Many of Laurie's colleagues in plasma physics are NERSC users, so she has been familiar with NERSC for several years. Laurie is excited about the frontiers in HPC for scientific applications, and is glad to be working on these research questions at NERSC.
Zahra Ronaghi joined NERSC as the first NESAP for Data postdoc in January 2017, working with Doga Gursoy at Argonne National Lab on performance optimization of TomoPy, a tomographic reconstruction code that is used by DOE light sources. She is also working with the Application Performance Group at NERSC on exploring performance portability of BoxLib/AMReX, an adaptive mesh refinement framework used in a variety of scientific codes. Zahra graduated from Clemson University with a Ph.D. in biomedical engineering and received her B.S. and M.S. degrees in electrical engineering. Her Ph.D. research focused on medical imaging and brining high performance computing through high-speed network to the clinic for processing real-time surgical data.
Yunsong Wang joined NERSC as a NESAP for Data postdoctoral fellow in January 2018. He is working with Paolo Calafiura's group at Berkeley Lab on performance optimization of Geant4 and Athena, two Monte Carlo particle transport codes used for the ATLAS experiment at CERN. Yunsong received his Ph.D. in high performance computing from Maison de la Simulation of CEA Saclay and École Polytechnique in December 2017, where his research focused on accelerating Monte Carlo neutron transport simulations by using emerging many-core systems.
- Taylor Barnes: MOLSSI (NSF)
- Brian Friesen: NERSC
- Tuomas Koskela: University of Helsinki
- Mathieu Lobet: CES
- Tareq Malas: Intel
- Andrey Ovsyannikov: Intel