Server memory management is an evolving and challenging area. With growing memory capacity installed per machine and increasing memory DIMM costs, data center planners are facing with huge increase in memory TCO. A plausible direction is to categorize memory accesses by required service level objective (SLO) with the end goal to map lower SLO request to cheaper but low quality memory resource, while using expensive, highest quality memory resource for most critical application request. I work in Linux server memory management to categorize memory access transparent to the user space.

Dr. Ghazal Tashakor is a scientific staff member affiliated with multiple institutes and universities in Germany and Spain. She obtained her Ph.D. in High-Performance Computing (HPC) and advanced simulation from the Autonomous University of Barcelona in 2019. Her ongoing research endeavors primarily focus on conducting large-scale computer simulations. Additionally, she serves as a core developer in distributed and parallel architecture patterns, ranging from grid computing to data visualization/monitoring, with a specific emphasis on Big Data and advanced hierarchical models. She collaborates with various research centers in Germany, including Fraunhofer and Jülich Supercomputer Centre.

I am an Assistant Professor in the Department of Computer Science at George Mason University. My research interest mainly falls in system reliability and GPU architecture, including the reliable operation of GPUs, non-conventional sensors, autonomous driving systems, and neural networks.

Dana Vantrease specializes in hw and sw solutions for custom AI silicon. She has worked on such systems at Amazon Web Services (Inferentia, Trainium), Qualcomm (NPU), and MatX.