Kiloprocessor Extensions to SCI
作者： S. Kaxiras
关键词: Workstation 、 Scalability 、 Computer science 、 Application software 、 Distributed computing 、 Scalable Coherent Interface 、 Cache coherence 、 Parallel computing 、 Concurrent computing
摘要: To expand the Scalable Coherent Interface's (SCI) capabilities so it can be used to efficiently handle sharing in systems of hundreds or even thousands processors, SCI working group is developing Kiloprocessor Extensions SCI. We describe proposed GLOW and STEM kiloprocessor extensions These two sets provide with scalable reads writes widely-shared data. This kind datum represents one main obstacles scalability for many cache coherence protocols. The are intended complex networks interconnected rings, (e.g., large workstations). based on building k-ary trees that map well underlying topology. In contrast where not applicable topologies centralized switches). defines algorithms build maintain binary trees. show latencies grow only logarithmically number nodes sharing, linearly, therefore validating as a good solution efficient wide Previous work showed same STEM.
sci-hub.st 参考文章(12)
Ross Evan Johnson, Extending the scalable coherent interface for large-scale shared-memory multiprocessors University of Wisconsin at Madison. ,(1993)
James R Goodman, Ross E Johnson, Interconnect Topologies With Point-To-Point Rings University of Wisconsin-Madison Department of Computer Sciences. ,(1991)
Gottlieb, Grishman, Kruskal, McAuliffe, Rudolph, Snir, The NYU Ultracomputer—Designing an MIMD Shared Memory Parallel Computer IEEE Transactions on Computers. ,vol. 32, pp. 175- 189 ,(1983) , 10.1109/TC.1983.1676201
Yeong-Chang Maa, Dhiraj K. Pradhan, Dominique Thiebaut, Two economical directory schemes for large-scale cache coherent multiprocessors ACM Sigarch Computer Architecture News. ,vol. 19, pp. 10- ,(1991) , 10.1145/379189.379198
Steven K. Reinhardt, Mark D. Hill, James R. Larus, Alvin R. Lebeck, James C. Lewis, David A. Wood, The Wisconsin Wind Tunnel: virtual prototyping of parallel computers measurement and modeling of computer systems. ,vol. 21, pp. 48- 60 ,(1993) , 10.1145/166955.166979
Alain Kägi, Nagi Aboulenein, Douglas C. Burger, James R. Goodman, Techniques for reducing overheads of shared-memory multiprocessing Proceedings of the 9th international conference on Supercomputing - ICS '95. pp. 11- 20 ,(1995) , 10.1145/224538.224540
Gregory F. Pfister, V. Alan Norton, “Hot spot” contention and combining in multistage interconnection networks IEEE Transactions on Computers. ,vol. 34, pp. 943- 948 ,(1985) , 10.1109/TC.1985.6312198
D. Lenoski, J. Laudon, K. Gharachorloo, W.-D. Weber, A. Gupta, J. Hennessy, M. Horowitz, M.S. Lam, The Stanford Dash multiprocessor IEEE Computer. ,vol. 25, pp. 583- 599 ,(1992) , 10.1109/2.121510
Håkan Nilsson, Per Stenström, The Scalable Tree Protocol-a cache coherence approach for large-scale multiprocessors international parallel and distributed processing symposium. pp. 498- 506 ,(1992) , 10.1109/SPDP.1992.242703
Steven L. Scott, James R. Goodman, Mary K. Vernon, Performance of the SCI ring Proceedings of the 19th annual international symposium on Computer architecture - ISCA '92. ,vol. 20, pp. 403- 414 ,(1992) , 10.1145/139669.140404