PDL Talk Series
August 5, 2021
TIME: 12:00 noon - to approximately 1:00 pm EDT
PLACE: Virtual - a zoom link will be emailed closer to the seminar
SPEAKER: Charles McGuffey, Assistant Professor, Reed College
Modernizing Models and Management of the Memory Hierarchy for Non-Volatile Memory
Non-volatile memory technologies (NVMs) are a new family of technologies that combine near memory level performance with near storage level cost density. The result is a new type of memory hierarchy layer that exists and performs somewhere between the two. These new technologies offer many opportunities for performance improvement, but in order to take advantage of these system design needs to account for their adapted for their particular characteristics.
In this talk, we focus on how to design memory management and caching systems for NVMs. Our work is broken into three major categories targeting different primary performance metrics.
- We study how to design algorithms and memory management to achieve fault tolerance with low cost and efficient recovery using NVMs.
- We design an extension the traditional model of caching to account for data writes in order to improve NVM device lifetime and energy consumption.
- We investigate how to improve throughput in caches by taking advantage of granularity change in the memory hierarchy.
Throughout our work we rely on a blend of theoretical and practical approaches. We provide models for processor faults, cache writebacks, cache-storage communication, and trace complexity that isolate the targeted effects from orthogonal complications. For each model, we show worst case theoretical bounds for our algorithms along with proofs that explain how the benefits are derived. We then take our results and provide empirical evaluations to show their effectiveness in practice. We believe that our ideas and approach provide a solid foundational study on memory hierarchy design in the era of non-volatile memories.
BIO: Charles McGuffey is an Assistant Professor at Reed College. He works on computer systems and algorithm design, attempting to improve both the theory and practice of computer systems by looking at the interaction between hardware and software. His work looks to gain practical insight into understudied and emerging aspects of computer design to improve resulting performance. In addition to research, Charles is happy to talk about new or different ways of thinking about computer science or how to apply it. Charles joined Reed in the fall of 2021, upon the completion of his Ph.D. in computer science at Carnegie Mellon University. He also holds bachelors degrees in both computer engineering and computer science from Clarkson University.
CONTACTS
Director, Parallel Data Lab
VOICE: (412) 268-1297
Executive Director, Parallel Data Lab
VOICE: (412) 268-5485
PDL Administrative Manager
VOICE: (412) 268-6716