Do you want to talk about a recent paper that you are excited about? Do you want to explain fundamental papers of your field to a wider audience? Do you want to (re-)discover important research works in computer science? Do you have this really cool paper you want to tell us about? Present the papers that you love, tell us about how you've implement them and use them, or simply listen and discuss!
We follow the Papers We Love Code of Conduct.
We keep a list of papers that we would like to talk about. Send us pull requests to add your own!
Sign-up: Please RSVP for meetings via Meetup
PWL Zürich returns from summer vacations with a compilers paper: Automatic Construction of Inlining Heuristics using Machine Learning by S. Kulkarni, J. Cavazos, C. Wimmer, D. Simon (2013) (pdf).
Method inlining is a very important but also dangerous compiler optimization: an inlining decision might lead to significant speedup or performance degradation and has to be constructed carefully. The paper compares various features and inlining techniques, in particular neuro-evolution. We will also discuss how having an idea about inlining traps and benefits might come useful in the "real-world", where not everybody is a compiler developer.…
PWL: Zürich is back! Animesh Trivedi is going to tell us about Raft!
This time around we are going to discuss the Raft distributed consensus algorithm from Diego Ongaro and John Ousterhout. The paper was originally published at USENIX ATC'14 and was awarded the best paper. Since then, the algorithm has been a part of teaching at many universities, has had many open-sourced implementations in multiple languages, and has found its way into production-level codes. This instantaneous acceptance into the systems building community raises an interesting question about what makes Raft so approachable than in comparison to others options, most notably Paxos? I will present my impressions of the paper and what makes it an interesting read.…
This time we are going to talk about an older paper. Published in 1998 by Matteo Frigo, Charles E. Leiserson, and Keith H. Randall, The implementation of the Cilk-5 multithreaded language (pdf) is about expressing parallel programs and building a run-time system that efficiently executes them. The paper is strongly motivated by theory, but also very practical. Many of the techniques and approaches used in the paper are (I think) still relevant today.
Presenter: Kornilios Kourtis <kkourt _at_ kkourt _dot_ io>…
I'm very excited for the first meetup of PWL: Zürich!
Andrea Lattuada will tell us all about Naiad: A Timely Dataflow System by Derek G. Murray, Frank McSherry, Rebecca Isaacs, Michael Isard, Paul Barham, and Martín Abadi.
This paper proposes a very powerful computational model for dataflow programming designed to minimise unnecessary synchronisation. The idea is to have a system that can be the foundation for various data-processing frameworks that can interoperate. There is an open-source implementation in rust (https://github.com/frankmcsherry/timely-dataflow) by one of the authors. It was awarded a best paper award at SOSP 2013.
Please RSVP, so that we have an idea of what to expect.