Callisto: revisiting parallel runtime systems for multicore architectures
Tim Harris, Oracle Labs
Bio: Tim Harris is a researcher at Oracle Labs where his interests include parallel programming, operating systems, and architecture support for programming language runtime systems. His other recent work has focused on the implementation of software transactional memory for multi-core computers, and the design of programming language features based on it. He is a co-author of the Morgan Claypool book Transactional Memory.
Tim has a BA and PhD in computer science from Cambridge University Computer Laboratory. He was on the faculty at the Computer Laboratory from 2000-2004 where he led the department’s research on concurrent data structures and contributed to the Xen virtual machine monitor project. He was at Microsoft Research from 2004, and then joined Oracle Labs in 2012.
Down the Tubes: Sacrificing cores to build fast and heavily pipelined network stacks
Herbert Bos, VU Amsterdam
Abstract: There are two main ways to build fast network stacks. Either you keep as much of the code processing the same data on the same core (core affinity), or you spread the processing across multiple cores that together form a pipeline through which you push the data. For over a decade now, my group at VU has focused on the pipeline model—trying to marry high-performance and reliability. In this talk, I will give a brief overview of these research efforts, highlighting interesting results, issues, and lessons learned.
Bio: Herbert Bos is Professor of Systems and Network Security at VU University Amsterdam. He obtained his Ph.D. degree from Cambridge University Computer Laboratory and joined VU in 2004 to work on operating systems and I/O architectures. In recent years, he has drifted into systems security and has a lot of fun developing new defensive mechanisms, new techniques to analyze malware, and better ways to detect vulnerabilities.