The Scalable Coherent Interface: scaling to high-performance systems

James, D.V.

doi:10.1109/cmpcon.1994.282943

Cited by 12 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-First, the model could be enlarged to cover the full set cache coherence protocol and all of the processor/cache options defined in the SCI Standard. Furthermore, the extensions of the SCI cache coherence protocol currently under development (for an overview see [10]) could be included in the model. -Second, in the current version of our model, the processor/cache options have to be enabled/disabled by hand and they are identical for all nodes.…”

Section: Future Workmentioning

confidence: 99%

Automatic verification of the SCI cache coherence protocol

Stern

Dill

1995

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper describes an ongoing effort to verify the cache coherence protocol of the IEEE/ANSI Standard for Scalable Coherent Interface using the Murky verification system. A model of the typical set protocol was constructed in the Mur~ description language. This model was augmented with a specification of properties necessary for cache coherence. The Mur~ verification system automatically checks if all reachable states in the model satisfy the given specification. Although verification is still under way, we have already found several errors in the C-code defining the protocol. Finally, we elucidate the experiences gained in the verification project.

show abstract

Section: Future Workmentioning

confidence: 99%

Automatic verification of the SCI cache coherence protocol

Stern

Dill

1995

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…This protocol is an IEEE standard (Std 1596(Std -1992. "The SCI coherence protocols are based on a distributed directories scheme [21].…”

Section: Introductionmentioning

confidence: 99%

Enhancements to the scalable coherent interface cache protocol

Safranek¹

2000

View full text Add to dashboard Cite

The first extension is a simplification to the SCI protocol in the area of prepending to a sharing list. Depending if the cache line is marked "Fresh" or "Gone", the flow of events is distinctly different. The guaranteed forward progress extension is a simplification to the SCI protocol in this area; making the act of prepending to an existing sharing list independent of whether the line is in the "Fresh" or "Gone" state. In addition, this extension eliminates the need for SCI command, as well as distributes the resource requirements of supplying data of a shared line equally among all nodes of the sharing list.The second extension addresses the time to purge (or invalidate) an SCI sharing list. This extension provides a realizable solution that allows the node being invalidated to acknowledge the request prior to the completion of the invalidation while maintaining the memory consistency model of the processors of the system. The resulting cache protocol was developed and implemented for Sequent Computer System Inc. NUMA-Q system. The cache protocol was run on systems ranging from eight to sixty four processors and provided between 7% and 20% reduction in time to invalidate an SCI sharing list.

show abstract

“…However, for data-acquisition purposes, commercially available SCI products are very rare, and for high-end applications nothing is provided since this market segment is too small. A lot of research remains to be done in this field [8][9][10][11][12]17]. In this paper, the performances of two SCI tests stands are reported that show the principal suitability of SCI for data-acquisition systems in future fusion reactor experiments.…”

Section: Introductionmentioning

confidence: 99%