Representative hardware implementations of the distributed shared memory (DSM) concept are comparatively evaluated in this study-two NUMA (Dash and SCI) and two COMA (KSR1 and DDM) architectures. Analysis was oriented towards the comparison of approaches, rather than their implementations. For that purpose, a hierarchical two-level cluster-based system with a uniform bus-based cluster structure on the first level is assumed. The DSM mechanisms of four approaches were simulated on the second level. A simulation methodology based on synthetic address traces was applied. The comparison was carried out for a large variety and a broad range of system-oriented, application-oriented and technology-oriented parameters. The results have shown the somewhat better efficiency of COMA protocols (because of the dynamic migration of responsibility for shared data) and the large impact of the available interconnection network bandwidth on system scalability (an almost linear speedup is achieved with ring-based systems).<<ETX>>
[1]
David B. Gustavson.
The Scalable Coherent Interface and related standards projects
,
1992,
IEEE Micro.
[2]
Richard E. Kessler,et al.
An analysis of distributed shared memory algorithms
,
1989,
[1989] Proceedings. The 9th International Conference on Distributed Computing Systems.
[3]
Anoop Gupta,et al.
The Stanford Dash multiprocessor
,
1992,
Computer.
[4]
Bill Nitzberg,et al.
Distributed shared memory: a survey of issues and algorithms
,
1991,
Computer.
[5]
James K. Archibald,et al.
Cache coherence protocols: evaluation using a multiprocessor simulation model
,
1986,
TOCS.
[6]
Erik Hagersten,et al.
DDM - A Cache-Only Memory Architecture
,
1992,
Computer.
[7]
Anoop Gupta,et al.
Comparative performance evaluation of cache-coherent NUMA and COMA architectures
,
1992,
ISCA '92.
[8]
Michael Stumm,et al.
Algorithms implementing distributed shared memory
,
1990,
Computer.