Skip to main content
  • 447 Accesses

Abstract

In this chapter, the RISPP approach is benchmarked. The benchmark results for the individual parts of the run-time system and prototyping results for the RISPP architecture are already presented in Chap. 4 and in Sect. 5.5, respectively. The first section provides benchmarks for the entire RISPP approach for different architectural parameters. In addition, the RISPP approach is compared with state-of-the-art approaches.

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

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and 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
Hardcover Book
USD 109.99
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

Notes

  1. 1.

    A Virtex-II 3000 and 6000 were used to develop the first RISPP prototypes; however, this thesis only presents the results for the final prototype that uses a Virtex-4 LX 160.

  2. 2.

    The smallest run-time reconfigurable element – a frame – spans the full FPGA height for Virtex-II devices.

  3. 3.

    The LUTs have six inputs instead of four (Virtex-II and Virtex-4) and a frame spans 20 CLBs (16 for Virtex-4).

  4. 4.

    Please note that the SI implementations for Molen were selected optimally, considering how the reconfigurable fabric should be shared among the SIs (that are demanded in the computational blocks of the benchmark application) and considering the actual SI execution frequencies, but not considering “when” and “how often” Molen might reconfigure the SIs. When provided with nine ACs, a Molen compiler may decide to use only eight of them; however, still Molen’s performance does not improve beyond six ACs, whereas RISPP achieves noticeably better performance when equipped with more ACs, providing up to 1.94× speedup in comparison to Molen’s fastest execution time.

  5. 5.

    Please note that specific benchmark results for the individual components of the RISPP run-time system and the RISPP architecture prototype are presented in Chap. 4 and Sect. 5.5, respectively.

  6. 6.

    Actually, their nonreconfigurable counterparts used by the ASIPs.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Lars Bauer .

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer Science+Business Media, LLC

About this chapter

Cite this chapter

Bauer, L., Henkel, J. (2011). Benchmarks and Comparisons. In: Run-time Adaptation for Reconfigurable Embedded Processors. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-7412-9_6

Download citation

  • DOI: https://doi.org/10.1007/978-1-4419-7412-9_6

  • Published:

  • Publisher Name: Springer, New York, NY

  • Print ISBN: 978-1-4419-7411-2

  • Online ISBN: 978-1-4419-7412-9

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics