Read-Copy-Update (RCU) is a technique for letting multiple readers safely access a data structure while a writer concurrently modifies it. It is used heavily in the Linux kernel in situations where fast reads are important and writes are infrequent. Optimized implementations rely only on the weaker memory orderings provided by modern hardware, avoiding the need for expensive synchronization instructions (such as memory barriers) as much as possible.
Using GPS, a recently developed program logic for the C11 weak memory model, we verify an implementation of RCU for a singly-linked list assuming “release-acquire” semantics. This is, to our knowledge, the first formal proof of an RCU implementation in a weak-memory setting.
Mon 15 Jun
|14:00 - 14:25|
Ilya SergeyIMDEA Software Institute, Aleksandar NanevskiIMDEA Software Institute, Anindya BanerjeeIMDEA Software InstituteLink to publication Media Attached
|14:25 - 14:50|
|14:50 - 15:15|
Peter GammieNICTA, Tony HoskingAustralian National University, Data61, and Purdue University, Kai EngelhardtUNSW and NICTALink to publication Media Attached
|15:15 - 15:40|