Skip to main content

About Me

·463 words·3 mins

I am an Assistant Computer Scientist at Argonne National Laboratory under Franck Cappello. My particular research interests are lossy compression, science data and evaluation for AI, distributed systems, and systems programming.

Some specific topics I have worked on include: AI for Science focusing on identifying, leveraging, and evaluating the semantic content of scientific datasets. Lossy compression for scientific data with an interest in interface design, optimization to preserve user qualities of interest, accelerator implementations, the use of compilers in compression pipelines, prediction and modeling of compression ratio performance. Data management including novel uses of checkpointing and lineages of data states beyond fault recovery to accelerate computation as applied to AI inference, model training, and other areas.

Academics #

You can find my full CV here.

I completed a postdoc at Argonne National Laboratory in October 2024 focusing on AI, lossy compression, and data management. I earned my PhD at Clemson University studying Computer Science in December 2021. I am previously worked with the Data Intensive Computing Environments (DICE) Lab and Fault Tolerant HPC Lab (FTHPC) studying error bounded lossy compression under my adviors Dr. Amy Apon, Dr. Jon C. Calhoun, and Dr. Franck Cappello.

My publications can be found on my Google Scholar page here.

Some highlights of my career include:

Outside Computer Science #

I am a Christian. I am an Eagle Scout. I recently started doing crossfit. I enjoy spending time outdoors; I especially enjoy biking and backpacking. I also enjoy playing strategic board games with friends.

Contact Me #

The best way to reach me is via email

Author
Robert Underwood
Robert is an Assistant Computer Scientist in the Mathematics and Computer Science Division at Argonne National Laboratory focusing on data and I/O for large-scale scientific applications including AI for Science using techniques of lossy compression, and data management. He currently co-leads the AuroraGPT Data Team with Ian Foster. In addition to AI, Robert’s library LibPressio, allows users to experiment and adopt advanced compressors quickly, has over 200 average unique monthly downloads, is used in over 17 institutions worldwide, and he is also a contributor to the R&D100 winning SZ family of compressors and other compression libraries. He regularly mentors students and is the early career ambassador for Argonne to the Joint Laboratory for Extreme Scale Computing.