In this slidecast, Xuehai Qian from the University of Illinois at Urbana-Champaign will present his paper on ScalableBulk: Scalable Cache Coherence for Atomic Blocks in a Lazy Environment. The slidecast will be live-streamed at 2:00pm Central Time on March 3.
Abstract: Recently-proposed architectures that continuously operate on atomic blocks of instructions (also called chunks) can boost the programmability and performance of shared-memory multiprocessing. However, they must support chunk operations very efficiently. In particular, in lazy conflict-detection environments, it is key that they provide scalable chunk commits. Unfortunately, current proposals typically fail to enable maximum overlap of conflict-free chunk commits. This paper presents a novel directory-based protocol that enables highly-overlapped, scalable chunk commits. The protocol, called ScalableBulk, builds on the previously-proposed BulkSC protocol. It introduces three general hardware primitives for scalable commit: preventing access to a set of directory entries, grouping directory modules, and initiating the commit optimistically. Our results with SPLASH-2 and PARSEC codes with up to 64 processors show that ScalableBulk enables highly-overlapped chunk commits and delivers scalable performance. Unlike previously proposed schemes, it removes practically all commit stalls.