Two Techniques to Enhance the Performance of Memory Consistency Models

Two Techniques to Enhance the Performance of Memory Consistency Models (1991)

Cached

Download Links

[www-flash.stanford.edu]
[casaturn.kaist.ac.kr]

Other Repositories/Bibliography

DBLP

by Kourosh Gharachorloo , Anoop Gupta , John Hennessy

Venue:	In Proceedings of the 1991 International Conference on Parallel Processing
Citations:	123 - 5 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Two Techniques to Enhance the Performance of Memory Consistency Models	SVM HeaderParse 0.1
AUTHOR NAME	Kourosh Gharachorloo	SVM HeaderParse 0.1
AUTHOR AFFIL	Computer Systems Laboratory; Stanford University, CA	SVM HeaderParse 0.2
AUTHOR ADDR	94305	SVM HeaderParse 0.1
AUTHOR NAME	Anoop Gupta	SVM HeaderParse 0.1
AUTHOR AFFIL	Computer Systems Laboratory; Stanford University, CA	SVM HeaderParse 0.2
AUTHOR ADDR	94305	SVM HeaderParse 0.1
AUTHOR NAME	John Hennessy	SVM HeaderParse 0.1
AUTHOR AFFIL	Computer Systems Laboratory; Stanford University, CA	SVM HeaderParse 0.2
AUTHOR ADDR	94305	SVM HeaderParse 0.1
ABSTRACT	The memory consistency model supported by a multiprocessor directly affects its performance. Thus, several attempts have been made to relax the consistency models to allow for more buffering and pipelining of memory accesses. Unfortunately, the potential increase in performance afforded by relaxing the consistency model is accompanied by a more complex programming model. This paper introduces two general implementation techniques that provide higher performance for all the models. The first technique involves prefetching values for accesses that are delayed due to consistency model constraints. The second technique employs speculative execution to allow the processor to proceed even though the consistency model requires the memory accesses to be delayed. When combined, the above techniques alleviate the limitations imposed by a consistency model on buffering and pipelining of memory accesses, thus significantly reducing the impact of the memory consistency model on performance. 1 Intro...	user correction - Legacy Corrections
YEAR	1991	INFERENCE
VENUE	In Proceedings of the 1991 International Conference on Parallel Processing	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	355--364	INFERENCE
CITATIONS	25 found	ParsCit 1.0