Skip to main content
SpringerLink
Log in

Eliminating Redundant Memory Operations at Function Calls

  • Chapter
  • First Online:
Recent Advances in Computer Science and Information Engineering

Part of the book series: Lecture Notes in Electrical Engineering ((LNEE,volume 128))

  • 137 Accesses

Abstract

Since fast technological improvements in processor design have outpaced that in memory design, memory wall has become a performance bottleneck for microprocessor applications. Unfortunately, existing compilers do excessively context saving at function calls, which increases chances to access memory and decreases overall performance. In this paper, an optimal compiler algorithm is proposed to make context saving more efficient by utilizing an extended call graph. The algorithm is measured on a set of DSP-kernel programs by integrating it into an existing compiler IMPACT. The experimental results show a decrease in memory accesses by an average of 49.35% and an improvement in performance by an average of 3.15%.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover 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

  • Aho, A.V., Sethi, R., Ullman, J.D.: Compilers, Principles, Techniques and Tools. Addision Wesley (1988)

    Google Scholar 

  • Benitez, M., Davidson, J.: A retargetable integrated code improver, Technical Report CS-93-64, Univ. of. Virginia, Dept. of Computer Sc. (November 1993)

    Google Scholar 

  • Zhang, Y., Lee, H.J.: Register allocation by systematic merge of register-reuse chains. Electronics Letters 36(1), 16–17 (2000)

    Article  MathSciNet  Google Scholar 

  • Davidson, J., Jinturkar, S.: Memory access coalescing: a technique for eliminating redundant memory accesses. In: Proceedings of PLDI (June 1994)

    Google Scholar 

  • Barik, R., Sarkar, V.: Inter-procedural load elimination for dynamic optimization of parallel programs. In: Proceedings of PACT, pp. 41–52 (2009)

    Google Scholar 

  • Frederick, C.: Minimizing register usage penalty at procedural calls. In: Proceedings of PLDI, pp. 85–94 (1988)

    Google Scholar 

  • Frederick, C., Hennessy, J.L.: The Priority-Based Coloring Approach to Register Allocation. ACM Transactions on Programming Languages and Systems 12(4), 501–536 (1990)

    Article  Google Scholar 

  • The IMPACT Research group, http://www.crhc.uiuc.edu/Impact

  • DSPstone, http://www.ert.rwth-aachen.de/Projekte/Tools/DSPSTONE/dspstone.html

Download references

Author information

Authors and Affiliations

  1. Digital System Integration Laboratory Institute of Acoustics, Chinese Academy of Sciences, Beijing, China

    Hongmei Wang, Tiejun Zhang, Donghui Wang & Chaohuan Hou

  2. Coordinate Centre of China, National Computer Network Emergency Response Technical Team, Beijing, China

    Lei Shi

Authors
  1. Hongmei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lei Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tiejun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Donghui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chaohuan Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. , College of Communication Engineering, Jilin University, Room 313, Building No.1, Changchun, Nanhu Avenue 5372, Jilin, 130012, China, People's Republic

    Zhihong Qian

  2. , Department of Electrical Engineering, The University of Mississippi, Anderson Hall 314, Mississippi, 38677, Mississippi, USA

    Lei Cao

  3. , Department of Electrical and Computer En, Naval Postgraduate School, Rm. 452 Spanagel Bldg. 232, Dyer Road 833, Monterey, 93943-5121, California, USA

    Weilian Su

  4. , Faculty of Computing, London Metropolitan University, Holloway Road 166-220, London, N7 8DB, United Kingdom

    Tingkai Wang

  5. , College of Software, Changchun University of Science and Tech, Changchun, Jilin, 130022, China, People's Republic

    Huamin Yang

Rights and permissions

Reprints and permissions

Copyright information

© 2012 Springer-Verlag GmbH Berlin Heidelberg

About this chapter

Cite this chapter

Wang, H., Shi, L., Zhang, T., Wang, D., Hou, C. (2012). Eliminating Redundant Memory Operations at Function Calls. In: Qian, Z., Cao, L., Su, W., Wang, T., Yang, H. (eds) Recent Advances in Computer Science and Information Engineering. Lecture Notes in Electrical Engineering, vol 128. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25792-6_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-25792-6_3

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-25791-9

  • Online ISBN: 978-3-642-25792-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation