Browse > Article

Efficient Hardware Support: The Lock Mechanism without Retry  

Kim Mee-Kyung (상명대학교 소프트웨어학부)
Hong Chul-Eui (상명대학교 소프트웨어학부)
Abstract
A lock mechanism is essential for synchronization on the multiprocessor systems. The conventional queuing lock has two bus traffics that are the initial and retry of the lock-read. %is paper proposes the new locking protocol, called WPV (Waiting Processor Variable) lock mechanism, which has only one lock-read bus traffic command. The WPV mechanism accesses the shared data in the initial lock-read phase that is held in the pipelined protocol until the shared data is transferred. The nv mechanism also uses the cache state lock mechanism to reduce the locking overhead and guarantees the FIFO lock operations in the multiple lock contentions. In this paper, we also derive the analytical model of WPV lock mechanism as well as conventional memory and cache queuing lock mechanisms. The simulation results on the WPV lock mechanism show that about 50% of access time is reduced comparing with the conventional queuing lock mechanism.
Keywords
병렬 시스템 동기화;잠금기법;해석적 모델링;합성부하 모델 시뮬레이션;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Moon, E., Thang, S., Jhon, C., 'Analysis of the Relation of Synchronization Algorithm and Parallel Programs in Shared-Memory Multiprocessor Systems', Proceedings of High Performance Computing Symposium, 2000
2 An Do Ki, Byung Kwan Park, 'Highly Pipelined Bus : HiPi-Bus,' Proceedings JTC-CSCC'91, 1991
3 Cho, H., 'Cache coherency and concurrency control in a multisystem data sharing', IEICE Transactions on Information & Systems, Vol. E82-D. No. 6, 1999 pp. 1042-1050
4 Nikolopoulos, D., Papatheodorou, S., 'Fast Synchronization on Scalable Cache Coherent Multiprocessors using Hybrid', Proceedings of the 14th International Parallel & Distributed Processing, 2000 pp. 711-719
5 Tauri, T., Nakagawa, T., Ido, N., 'Evaluation of the Lock Mechanism in a Snooping Cache', Proceedings of International Conference on Supercomputing, 1992
6 Stenstrom, P., 'A Survey of Cache Coherence Schemes for Multiprocessors', IEEE Computer, June 1990 pp. 12-24
7 Moon, E., Thang, S., Jhon, C., 'Adjacency preferred hardware synchronization method for CC-NUMA systems', Proceedings of International Conference on Electronics, Informations and Communications. 1998
8 Yamamura, S., Hirai, A., Yamamoto, M, 'Speeding Up Kernel Scheduler by Reducing Cache Misses', Proceedings of the Freenix Track 2002 USENIX Annual Technical Conference, 2002, pp. 275-285
9 Thiebaut, D., 'On fractal dimension of computer programs and its application to the prediction of cache miss ratio', IEEE Trans. on Computers, Vol. 38. No. 7, 1989, pp.1012-1026   DOI   ScienceOn