article

Free access

An empirical evaluation of two memory-efficient directory methods

Authors:

Brian W. O'Krafka,

A. Richard NewtonAuthors Info & Claims

ACM SIGARCH Computer Architecture News, Volume 18, Issue 2SI

Pages 138 - 147

https://doi.org/10.1145/325096.325130

Published: 01 May 1990 Publication History

Abstract

This paper presents an empirical evaluation of two memory-efficient directory methods for maintaining coherent caches in large shared memory multiprocessors. Both directory methods are modifications of a scheme proposed by Censier and Feautrier [5] that does not rely on a specific interconnection network and can be readily distributed across interleaved main memory. The schemes considered here overcome the large amount of memory required for tags in the original scheme in two different ways. In the first scheme each main memory block is sectored into sub-blocks for which the large tag overhead is shared. In the second scheme a limited number of large tags are stored in an associative cache and shared among a much larger number of main memory blocks. Simulations show that in terms of access time and network traffic both directory methods provide significant performance improvements over a memory system in which shared-writeable data is not cached. The large block sizes required for the sectored scheme, however, promotes sufficient false sharing that its performance is markedly worse than using a tag cache.

References

[1]

A. Agarwal et al. An evaluation of directory schemes for cache coherence. In Proceedings of the Internarional Symposium on Computer Architecfure, pages 280-289, May 1988.

Digital Library

[2]

J. Archibald and J-L. Baer. An economical solution to the cache coherence problem. In Proceedings of the Internadonal Symposium on Computer Architecture, pages 355-362,1984.

Digital Library

[3]

T. Axelrod et at. A simulator for MIMD performance prediction: AppIication to the S-l MkIIa mnltiprocessor. Parallel Computing. 1:237-274. 1984.

[4]

M. Carlmn. private communication.

[5]

L. M. Censier and P. Feaunier. A new solution to coherence problems in multicache systems. IEEE Transactions on Computers, C-27(12):1 11% 1118, Dec. 1978.

[6]

S. Devadas and A. R. Newton. Topological optimization of multiple level array logic. IEEE Transacrions on Computer-Aided Design, Nov. 1987.

Digital Library

[7]

S. J. Eggers andR. H. Katz. A characterization of sharing inparallelprograms and its application to coherency protocol evaluation. In Proceedings of he International Symposium on Computer Architecfure, pages 373-383, June 1988.

Digital Library

[8]

M. J. Flynn. Some computer organizations and their effectiveness. IEEE Transactions on Computers, C-21(9):948-960, Sept. 1972.

Digital Library

[9]

D. Gajski et al. Cedar-a large scale multiprocessor. In Proceedings of thelnlemational Conference on Parallel Processing, pages 514-529. August 1983.

[10]

J. R. Goodman and P. J. Woest The Wisconsin Multicube: A new largescale cache-coherent multiprocessor. In Proceedings ofthe International Symposium on Computer Architecture, pages 422-433, May 1988.

Digital Library

[11]

Goulieb et al. The NYU Ultracomputer-designing an MIMD shared memory parallel computer. IEEE Transactions on Cotnpurers, C- 32(2):175-189, Feb. 1983.

[12]

M. D. Hill and A. J. Smith. Experimental evaluation of on-chip microprocessor cache memories. In Proceedings of the Internarional Symposium on Compuier Architecture, pages 158-166, June 1984.

Digital Library

[13]

E. A. Lee and D. G. Messerschmitt. Static scheduling of synchronous data flow programs for digital signal processing. IEEE Transactions on Computers, C-36(1):24-35, Jan. 1987.

Digital Library

[14]

H. T. Ma et al. Logic verification algorithms and their parallel implementation. In Proceedings of the Design Automarion Conference, PP. 283-290, July 1987.

Digital Library

[15]

G. F. Pfister et al. The IBM research parallel processor prototype (RP3): Introduction and archhecture. In Proceedings of rhe International Symposium on Computer Architecrure, June 198.5.

Digital Library

[16]

C. Scheurich and M. Dubois. Correct memory operation of cache-based multiprocessors. In Proceedings of the International Symposium on Computer Architecture, pages 234-243, June 1987.

Digital Library

[17]

J. T. Schwartz. Ultracomputers. ACM Transactions on Programming Languages andsysfems, 2(4):48&521,Oct. 1980.

Digital Library

[18]

H. J. Siegel. Interconnection Nehvorkr for Large-Scale Parallel Processing. Lexington Books, 1985.

Digital Library

[19]

A. J. Smifh. Cache memories. ComputingSurveys, 14(3):473-530, Sept. 1982.

Digital Library

[20]

H. S. Stone. High-Performance Computer Architecture. Addison- Wesley Publishing Company, 1987.

Digital Library

[21]

A. W. Wilson Jr. Hierarchical cache/bus architecture for shared memory multiprocessors. In Proceerlings of the International Symposium on Computer Architecture, pages 244-252, June 1987.

Digital Library

Cited By

Soltaniyeh MKadayif IOzturk O(2018)Classifying Data Blocks at Subpage Granularity With an On-Chip Page Table to Improve Coherence in Tiled CMPsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2017.272928037:4(806-819)Online publication date: 1-Apr-2018
https://dl.acm.org/doi/10.1109/TCAD.2017.2729280
Valls JRos ASahuquillo JGómez M(2015)PS directoryThe Journal of Supercomputing10.1007/s11227-014-1332-571:8(2847-2876)Online publication date: 1-Aug-2015
https://dl.acm.org/doi/10.1007/s11227-014-1332-5
Shi XSu FPeir J(2014)Directory Lookaside Table: Enabling scalable, low-conflict, many-core cache coherence directory2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)10.1109/PADSW.2014.7097798(111-118)Online publication date: Dec-2014
https://doi.org/10.1109/PADSW.2014.7097798
Show More Cited By

Index Terms

An empirical evaluation of two memory-efficient directory methods
1. Hardware
  1. Hardware validation
  2. Integrated circuits
    1. Semiconductor memory

Recommendations

An evaluation of directory schemes for cache coherence
Special Issue: Proceedings of the 15th annual international symposium on Computer Architecture

The problem of cache coherence in shared-memory multiprocessors has been addressed using two basic approaches: directory schemes and snoopy cache schemes. Directory schemes have been given less attention in the past several years, while snoopy cache ...
An empirical evaluation of two memory-efficient directory methods
ISCA '90: Proceedings of the 17th annual international symposium on Computer Architecture

This paper presents an empirical evaluation of two memory-efficient directory methods for maintaining coherent caches in large shared memory multiprocessors. Both directory methods are modifications of a scheme proposed by Censier and Feautrier [5] that ...
Scalable directory architecture for distributed shared memory chip multiprocessors

Traditional Directory-based cache coherence protocol is far from optimal for large-scale cache coherent shared memory multiprocessors due to the increasing latency to access directories stored in DRAM memory. Instead of keeping directories in main ...

Comments

Information & Contributors

Information

Published In

cover image ACM SIGARCH Computer Architecture News

ACM SIGARCH Computer Architecture News Volume 18, Issue 2SI

Special Issue: Proceedings of the 17th annual international symposium on Computer Architecture

June 1990

356 pages

ISSN:0163-5964

DOI:10.1145/325096

Issue’s Table of Contents

ISCA '90: Proceedings of the 17th annual international symposium on Computer Architecture
May 1990
378 pages
ISBN:0897913663
DOI:10.1145/325164
Chairmen:
Jean-Loup Baer,
Larry Snyder,
James Goodman

Copyright © 1990 Authors.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 May 1990

Published in SIGARCH Volume 18, Issue 2SI

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

71
Total Citations
View Citations
552
Total Downloads

Downloads (Last 12 months)110
Downloads (Last 6 weeks)14

Reflects downloads up to 07 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Soltaniyeh MKadayif IOzturk O(2018)Classifying Data Blocks at Subpage Granularity With an On-Chip Page Table to Improve Coherence in Tiled CMPsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2017.272928037:4(806-819)Online publication date: 1-Apr-2018
https://dl.acm.org/doi/10.1109/TCAD.2017.2729280
Valls JRos ASahuquillo JGómez M(2015)PS directoryThe Journal of Supercomputing10.1007/s11227-014-1332-571:8(2847-2876)Online publication date: 1-Aug-2015
https://dl.acm.org/doi/10.1007/s11227-014-1332-5
Shi XSu FPeir J(2014)Directory Lookaside Table: Enabling scalable, low-conflict, many-core cache coherence directory2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)10.1109/PADSW.2014.7097798(111-118)Online publication date: Dec-2014
https://doi.org/10.1109/PADSW.2014.7097798
(1995)ReferencesScalable Shared-Memory Multiprocessing10.1016/B978-1-55860-315-8.50017-8(317-331)Online publication date: 1995
https://doi.org/10.1016/B978-1-55860-315-8.50017-8
Lilja DYew P(1991)Combining hardware and software cache coherence strategiesProceedings of the 5th international conference on Supercomputing10.1145/109025.109093(274-283)Online publication date: 1-Jun-1991
https://dl.acm.org/doi/10.1145/109025.109093
Chaudhuri MMartínez JDuato JJohn L(2021)Zero inclusion victimProceedings of the 48th Annual International Symposium on Computer Architecture10.1109/ISCA52012.2021.00015(71-84)Online publication date: 14-Jun-2021
https://dl.acm.org/doi/10.1109/ISCA52012.2021.00015
Chaudhuri M(2021)Zero Directory Eviction Victim: Unbounded Coherence Directory and Core Cache Isolation2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA)10.1109/HPCA51647.2021.00032(277-290)Online publication date: Feb-2021
https://doi.org/10.1109/HPCA51647.2021.00032
Shukla SChaudhuri M(2017)Tiny Directory: Efficient Shared Memory in Many-Core Systems with Ultra-Low-Overhead Coherence Tracking2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)10.1109/HPCA.2017.24(205-216)Online publication date: Feb-2017
https://doi.org/10.1109/HPCA.2017.24
Fang LLiu PHu QHuang MJiang GFensch CO'Boyle MSeznec ABodin F(2013)Building expressive, area-efficient coherence directoriesProceedings of the 22nd international conference on Parallel architectures and compilation techniques10.5555/2523721.2523762(299-308)Online publication date: 7-Oct-2013
https://dl.acm.org/doi/10.5555/2523721.2523762
Ros AKaxiras SYew PCho SDeRose LLilja D(2012)Complexity-effective multicore coherenceProceedings of the 21st international conference on Parallel architectures and compilation techniques10.1145/2370816.2370853(241-252)Online publication date: 19-Sep-2012
https://dl.acm.org/doi/10.1145/2370816.2370853
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents