A scalable cache design for I-structures in multithreaded architectures

I-Structures were originally proposed to handle producer-consumer parallelism in data-driven execution models. Although they provide fine-grain synchronization and non-strict execution capability, they do not exploit data locality, usually a key factor in performance improvement. In this paper, we propose a novel cache design for I-Structures in a multithreaded multiprocessor. It can exploit both temporal and spatial locality without any of the associated cache coherence costs. A highly scalable method for storing the deferred requests is employed, which further facilitates the processing of deferred requests in a parallel and distributed fashion