I am an application performance specialist, engaging with scientists to help them optimize their software for large-scale high-performance computing (HPC) environments. I am passionate about helping science teams tackle the problem of deploying their existing algorithms on emergent, highly heterogeneous hardware.
My interests also include new high-productivity HPC programming models for distributed programs and hardware accelerators; developing cross-facility workflows; and applying novel simulation techniques to broad range of complex systems, as well as inverse problems.
Before coming to NERSC, I worked as a postdoc on developing fluid-structure interaction codes for fluctuating hydrodynamics and active matter simulations. This work was conducted at the Technical University of Berlin, and later the Center for Computational Sciences and Engineering (at LBL).
I lead the NESAP for Data project. NESAP for Data addresses data-intensive science pipelines that process massive datasets from experimental and observational science (EOS) facilities like synchrotron light sources, telescopes, microscopes, particle accelerators, or genome sequencers.
I am a liaison for the ExaFEL project. This project aims to perform near real-time reconstruction of x-ray scattering data using NERSC's systems. X-ray scattering experiments pose a novel use case for cross-facility HPC workflows: near-complete data analysis is needed to effectively use limited beamtime. This brings with it new challenges for HPC: how to move data between experiment and NERSC, and analyze this data in mere minutes. In this project I am helping scientists optimize their codes to make efficient use of emerging Exascale hardware -- and future NERSC systems.
Antypas, KB and Bard, DJ and Blaschke, JP and Canon, RS and Enders, B and Shankar, M and Somnath, S and Stansberry, D and Uram, TD and Wilkinson, SR, "Enabling discovery data science through cross-facility workflows", Institute of Electrical and Electronics Engineers (IEEE), December 2021, 3671-3680, doi: 10.1109/bigdata52589.2021.9671421
Weiqun Zhang, Ann Almgren, Vince Beckner, John Bell, Johannes Blaschke, Cy Chan, Marcus Day, Brian Friesen, Kevin Gott, Daniel Graves, Max P. Katz, Andrew Myers, Tan Nguyen, Andrew Nonaka, Michele Rosso, Samuel Williams, Michael Zingale, "AMReX: a framework for block-structured adaptive mesh refinement", Journal of Open Source Software, 2019, 4(37):1370, doi: 10.21105/joss.01370
JOSS Article for Citation of AMReX:
AMReX is a C++ software framework that supports the development of block-structured adaptive mesh refinement (AMR) algorithms for solving systems of partial differential equations (PDEs) with complex boundary conditions on current and emerging architec- tures.