Skip to main content

A Scalable and Adaptive Directory Scheme for Hardware Distributed Shared Memory

  • Conference paper
Advances in Computer Systems Architecture (ACSAC 2004)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 3189))

Included in the following conference series:

  • 358 Accesses

Abstract

In hardware distributed shared memory in the style of CC-NUMA, directory information that specifies locations of sharing processors is used for cache coherence. Structure of the directories affects the size of hardware, time required for coherence transaction, and network traffic. In this paper, we propose and evaluate a new scalable directory scheme, ”adaptive hierarchical coarse directory”, that exploits hierarchy in the system and exhibits appropriate values in terms of the above three items. The directory has tolerance to many copies of a memory block scattered in a large-scale parallel system. This characteristic makes it easy for operating systems to allocate parallel threads in multitasking/multiuser environment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Tanaka, K., Matsumoto, T., Hiraki, K.: Lightweight Hardware Distributed Shared Memory Supported by Generalized Combining. In: Proc. of 5th International Symposium on High-Performance Computer Architecture (HPCA), January 1999, pp. 90–99 (1999)

    Google Scholar 

  2. Tanaka, K., Matsumoto, T., Hiraki, K.: On Scalability Issue of Directory Schemes of Hardware Distributed Shared memory. In: 9th Workshop on Scalable Shared Memory Multiprocessors (SSMM) (June 2000)

    Google Scholar 

  3. Censier, L.M., Feautrier, P.: A New Solution to Coherence Problems in Multicache Systems. IEEE Transactions on Computers C-27(12), 1112–1118 (1978)

    Article  MATH  Google Scholar 

  4. Chaiken, D., Kubiatowicz, J., Agarwal, A.: LimitLESS Directories: A Scalable Cache Coherence Scheme. In: Proc. of 4th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS–IV), April 1991, pp. 224–234 (1991)

    Google Scholar 

  5. James, D., Laundrie, A.T., Gjessing, S., Sohi, G.S.: Distibuted–Directory Scheme: Scalable Coherent Interface. Computer 23(6), 74–77 (1990)

    Article  Google Scholar 

  6. Thapar, M., Delagi, B.: Distributed–Directory Scheme: Stanford Distributed Directory Protocol. Computer 23(6), 78–80 (1990)

    Article  Google Scholar 

  7. Hagersten, E., Landin, A., Haridi, S.: DDM–A Cache-Only Memory Architecture. Computer 25(9), 44–54 (1992)

    Article  Google Scholar 

  8. Agarwal, A., Simoni, R., Hennessy, J., Horowitz, M.: An Evaluation of Directory Schemes for Cache Coherence. In: Proc. of 15th International Symposium on Computer Architecture (ISCA), June 1988, pp. 280–289 (1988)

    Google Scholar 

  9. Matsumoto, T., Hiraki, K.: A Shared Memory Architecture for Massively Parallel Computer Systems. IEICE Japan SIG Reports 92(173), 47–55 (1992) (In Japanese)

    Google Scholar 

  10. Matsumoto, T., Nishimura, K., Kudoh, T., Hiraki, K., Amano, H., Tanaka, H.: Distributed Shared Memory Architecture for JUMP-1: a General-Purpose MPP Prototype. In: Proc. of International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN), June 1996, pp. 131–137 (1996)

    Google Scholar 

  11. Sunada, D., Glasco, D., Flynn, M.: ABSS v2.0: a SPARC Simulator. In: Proc. of the 8th Workshop on Synthesis And System Integration of Mixed Technologies (SASIMI 1998) (October 1998)

    Google Scholar 

  12. Woo, S.C., Ohara, M., Torrie, E., Singh, J.P., Gupta, A.: The SPLASH-2 Programs: Characterization and Methodological Considerations. In: Proc. of 22th International Symposium on Computer Architecture (ISCA), June 1995, pp. 24–36 (1995)

    Google Scholar 

  13. Gupta, A., Weber, W., Mowry, T.: Reducing Memory and Traffic Requirements for Scalable Directory-Based Cache Coherence Schemes. In: Proc. of International Conference on Parallel Processing (ICPP), August 1990, pp. I-312–321 (1990)

    Google Scholar 

  14. Choi, J.H., Park, K.H.: Segment Directory Enhancing the Limited Directory Cache Coherence Schemes. In: Proc. of 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing (IPPS/SPDP), April 1999, pp. 258–267 (1999)

    Google Scholar 

  15. Acacio, M.E., Gonzalez, J., Carcia, J.M., Duato, J.: A New Scalable Directory Architecture for Large-Scale Multiprocessors. In: Proc. of 7th International Symposium on High-Performance Computer Architecture (HPCA), January 2001, pp. 97–106 (2001)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Tanaka, K., Hagiwara, T. (2004). A Scalable and Adaptive Directory Scheme for Hardware Distributed Shared Memory. In: Yew, PC., Xue, J. (eds) Advances in Computer Systems Architecture. ACSAC 2004. Lecture Notes in Computer Science, vol 3189. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30102-8_45

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30102-8_45

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23003-8

  • Online ISBN: 978-3-540-30102-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics