skip to main content
10.1145/2018323.2018349acmconferencesArticle/Chapter ViewAbstractPublication PageshpgConference Proceedingsconference-collections
research-article

Precision selection for energy-efficient pixel shaders

Published:05 August 2011Publication History

ABSTRACT

In this work, we seek to realize energy savings in modern pixel shaders by reducing the precision of their arithmetic. We explore three schemes for controlling this reduction. The first is a static analysis technique, which analyzes shader programs to choose precision with guaranteed error bounds. This approach may be too conservative in practice since it cannot take advantage of run-time information, so we also examine two methods that take the actual data values into account - a programmer-directed approach and a closed-loop error-tracking approach, both of which can lead to higher savings. To use this last method, we developed several heuristics to control how the precisions will change over time. We simulate several series of frames from commercial applications to evaluate the performance of these different schemes. The average savings found by the static and dynamic approaches are 31%, 70%, and 62% in the pixel shader's arithmetic, respectively, which could result in as much as a 10--20% savings of the GPU's energy as a whole.

References

  1. Akeley, K., and Su, J. 2006. Minimum triangle separation for correct z-buffer occlusion. In 21st ACM SIGGRAPH/EUROGRAPHICS Symposium on Graphics Hardware, ACM, New York, NY, USA, GH '06, 27--30. Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. AMD, 2008. Rendermonkey 1.82. http://developer.amd.com/archive/gpu/rendermonkey/pages/default.aspx, Dec.Google ScholarGoogle Scholar
  3. ATTILA, 2011. Traces - AttilaWiki. http://attila.ac.upc.edu/traceList/, Accessed: April 2011.Google ScholarGoogle Scholar
  4. Baker, P., 2011. Metaballs II. http://www.paulsprojects.net/metaballs2/metaballs2.html, Apr.Google ScholarGoogle Scholar
  5. Callaway, T., and Swartzlander, E. E., J. 1997. Power-delay characteristics of CMOS multipliers. In 13th IEEE Symposium on Computer Arithmetic, 1997, 26--32. Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. Chittamuru, J., Burleson, W., and Euh, J. 2003. Dynamic wordlength variation for low-power 3D graphics texture mapping. In 2003 IEEE Workshop on Signal Processing Systems, SIPS '03, 251--256.Google ScholarGoogle Scholar
  7. del Barrio, V., Gonzalez, C., Roca, J., Fernandez, A., and Espasa, R. 2006. ATTILA: a cycle-level execution-driven simulator for modern GPU architectures. In 2006 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS '06, 231--241.Google ScholarGoogle Scholar
  8. EA Black Box, 2008. Need for Speed: Undercover. http://undercover.needforspeed.com/home.action, Nov.Google ScholarGoogle Scholar
  9. Hao, X., and Varshney, A. 2001. Variable-precision rendering. In 2001 Symposium on Interactive 3D Graphics, ACM, New York, NY, USA, I3D '01, 149--158. Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. Huang, Z., and Ercegovac, M. 2002. Two-dimensional signal gating for low-power array multiplier design. In IEEE International Symposium on Circuits and Systems, ISCAS '02, 489--492.Google ScholarGoogle Scholar
  11. id, 2005. Doom 3. http://idsoftware.com/games/doom/doom3/index.php, Apr.Google ScholarGoogle Scholar
  12. Lee, Y., Park, J., and Chung, K. 2007. Design of low power MAC operator with dual precision mode. In 13th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA '07, 309--318. Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. Lee, Y., Jung, H., and Chung, K. 2009. Low power MAC design with variable precision support. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Science 92-A, 7, 1623--1632.Google ScholarGoogle Scholar
  14. Liu, Y., and Furber, S. 2004. The design of a low power asynchronous multiplier. In 2004 International Symposium on Low Power Electronics and Design, ISLPED '04, 301--306. Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. Microsoft, 2011. PIX. http://msdn.microsoft.com/en-us/library/ee417062(v=VS.85).aspx, Apr.Google ScholarGoogle Scholar
  16. NVIDIA Corporation, 2010. NVIDIA Direct3D SDK 10 Code Samples. http://developer.download.nvidia.com/SDK/10.5/direct3d/samples.html, Jun.Google ScholarGoogle Scholar
  17. Pool, J., Lastra, A., and Singh, M. 2008. Energy-precision tradeoffs in mobile graphics processing units. In 2008 IEEE International Conference on Computer Design, ICCD '08, 60--67.Google ScholarGoogle Scholar
  18. Pool, J., Lastra, A., and Singh, M. 2010. An energy model for graphics processing units. In 2010 IEEE International Conference on Computer Design, ICCD '10, 409--416.Google ScholarGoogle Scholar
  19. Pool, J., Lastra, A., and Singh, M. 2011. Power-gated arithmetic circuits for energy-precision tradeoffs in mobile graphics processing units. Journal of Low Power Electronics 7, 2 (April), 148--162.Google ScholarGoogle ScholarCross RefCross Ref
  20. Tong, J., Nagle, D., and Rutenbar, R. 2000. Reducing power by optimizing the necessary precision/range of floating-point arithmetic. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 8, 3 (jun), 273--286. Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. Valve, 2005. Half-Life 2: Lost Coast. http://store.steampowered.com/app/340, Oct.Google ScholarGoogle Scholar
  22. Wilkinson, J. H. 1959. Rounding errors in algebraic processes. In 1959 International Conference on Information Processing, 44--53.Google ScholarGoogle Scholar

Index Terms

  1. Precision selection for energy-efficient pixel shaders

    Recommendations

    Comments

    Login options

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

    Sign in
    • Published in

      cover image ACM Conferences
      HPG '11: Proceedings of the ACM SIGGRAPH Symposium on High Performance Graphics
      August 2011
      185 pages
      ISBN:9781450308960
      DOI:10.1145/2018323

      Copyright © 2011 ACM

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 5 August 2011

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article

      Acceptance Rates

      Overall Acceptance Rate15of44submissions,34%

      Upcoming Conference

      HPG '24
      High-Performance Graphics
      July 26 - 28, 2024
      Denver , CO , USA

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader