Jonathan Madsen is a Senior Member of Technical Staff at AMD in the Research division and a member of the ISO C++ Standards Committee. His research interest include performance analysis for heterogeneous architectures, specifically source code instrumentation, dynamic instrumentation, compiler instrumentation, sampling, and the development of APIs which streamline the implementation of tools utilizing these techniques. Additional interests include performance portability frameworks for heterogeneous architectures, such as Kokkos, and the evolution the C++ language.
Jonathan received his PhD in Nuclear Engineering from Texas A&M University in 2017 and formerly worked at Lawrence Berkeley National Laboratory as a postdoctoral fellow and as a NERSC staff member in the Application Performance group. During his time at NERSC, he developed a C++-based toolkit called timemory which lead to the development of a variety of tools and APIs for analyzing the performance of applications written in C, C++, Fortran, Python, CUDA, and HIP.
Parallel Programming Languages and Models