Speaker: Dr. Jay Lofstead

Date: Friday, September 29, 2023, 2:15 – 3:15pm

Location: 307 James Love Building

Abstract: Scientific observations and simulations generate enormous data volumes that must be explored to gain new insights into physics phenomena. Two mature tool generations have been proposed with each offering different capabilities to aid scientists in their analysis tasks. A third generation is currently being explored that offers deep, custom tagging and advanced querying against tags and data. While each tool generation continues to offer value as new generations are created, the third-generation tools offer deep functionality that can be significantly helpful for scientists. This talk will explore this field as well as a proposed fourth generation tool being researched currently that will further aid complex analysis tasks for scientists. The work requires deeper understanding of data management tools, such as databases, indexing and data reduction techniques, including lossy compression, and advanced derived quantity querying capabilities. Accelerating these advanced operations without exploding data volumes is a challenging task that can offer tremendous benefits.

Links and comments: Jay Lofstead is a Principal Member of Technical Staff at Sandia National Laboratories. His research interests focus around large scale data management and trusting scientific computing. In particular, he works on storage, IO, metadata, workflows, reproducibility, software engineering, machine learning, and operating system-level support for any of these topics. Broadly across these topics, he is also deeply interested in ethics related to these topics and computing in general and how to drive inclusivity across the computation-related science domains. Dr. Lofstead received his Ph.D. in Computer Science from the Georgia Institute of Technology in 2010.