Managing Data-Objects in Dynamically Reconfigurable Caches

Springer Science and Business Media LLC - Tập 25 - Trang 232-245 - 2010
Xue-Jun Yang1, Jun-Jie Wu1, Kun Zeng1, Yu-Hua Tang1
1National Laboratory for Parallel and Distributed Processing, School of Computer, National University of Defense Technology, Changsha, China

Tóm tắt

The widening gap between processor and memory speeds makes cache an important issue in the computer system design. Compared with work set of programs, cache resource is often rare. Therefore, it is very important for a computer system to use cache efficiently. Toward a dynamically reconfigurable cache proposed recently, DOOC (Data-Object Oriented Cache), this paper proposes a quantitative framework for analyzing the cache requirement of data-objects, which includes cache capacity, block size, associativity and coherence protocol. And a kind of graph coloring algorithm dealing with the competition between data-objects in the DOOC is proposed as well. Finally, we apply our approaches to the compiler management of DOOC. We test our approaches on both a single-core platform and a four-core platform. Compared with the traditional caches, the DOOC in both platforms achieves an average reduction of 44.98% and 49.69% in miss rate respectively. And its performance is very close to the ideal optimal cache.

Tài liệu tham khảo

George L, Appel A W. Iterated register coalescing. ACM Trans. Program. Lang. Syst., 1996, 18(3): 300–324.

Wu J, Zhang B, Zhou H, Yang X. SimOpt: A high-efficient opt cache simulator. In Proc. China National Computer Conference, Xi’an, China, Sept. 26–28, 2008, p.50.

Juan T, Royo D, Navarro J J. Dynamic cache splitting. In Proc. the XV International Conference of the Chilean Computer Science Society, Arica, Chile, Oct. 1–3, 1995, pp.253–262.