Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
We present a new run-time system, DOSA, that efficiently implements a shared object space abstraction underneath a typed programming language. The key insight behind DOSA is that the ability to unambiguously distinguish pointers from data at run-time enables efficient fine-grained sharing using VM support. Like earlier systems designed for fine-grained sharing, DOSA improves the performance of fine-grained applications by eliminating false sharing. In contrast to these earlier systems, DOSA's VM-based approach and read aggregation enable it to match a page-based system on coarse-grained applications. Furthermore, its architecture permits optimizations that are not possible in conventional fine-grained or coarse-grained DSM systems.
Lionel Emile Vincent Parreaux, Aleksander Slawomir Boruch-Gruszecki
Martin Odersky, Yichen Xu, Aleksander Slawomir Boruch-Gruszecki
James Richard Larus, Mathias Josef Payer, Edouard Bugnion, Evangelos Marios Kogias, Adrien Ghosn