I am currently an Application Performance Specialist atLawrence Berkeley National Lab (LBL) in the National Energy Research Scientific Computing Center (NERSC), the Deputy Working Group Coordinator for the Run, Event, and Detector Responses Working Group in the Geant4 Collaboration, and the Deputy Coordinator of the Geant4 R&D Task Force.
My current focus is heterogeneous high-performance computing (HPC) using C/C++, Python, and CUDA and tools such as Docker, multithreading, and MPI. Additionally, I provide a header-only variadic instrumented performance analysis library "timemory" that provides compile time and runtime hooks to a variety of performance metrics including timers, memory usage, hardware counters, resource usage, profiling markers (e.g. NVTX), and automated roofline generation in Python, C, and C++ projects running on the CPU and/or GPU .
I received a PhD, M.S. and B.S. in Nuclear Engineering from Texas A&M University in 2017, 2013, and 2011, respectively.