Statistical analysis and modeling for error composition in approximate computation circuits

Wei Ting J. Chan, Andrew B. Kahng, Seokhyeong Kang, Rakesh Kumar, John M Sartori

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Scopus citations

Abstract

Aggressive requirements for low power and high performance in VLSI designs have led to increased interest in approximate computation. Approximate hardware modules can achieve improved energy efficiency compared to accurate hardware modules. While a number of previous works have proposed hardware modules for approximate arithmetic, these works focus on solitary approximate arithmetic operations. To utilize the benefit of approximate hardware modules, CAD tools should be able to quickly and accurately estimate the output quality of composed approximate designs. A previous work [10] proposes an interval-based approach for evaluating the output quality of certain approximate arithmetic designs. However, their approach uses sampled error distributions to store the characterization data of hardware, and its accuracy is limited by the number of intervals used during characterization. In this work, we propose an approach for output quality estimation of approximate designs that is based on a lookup table technique that characterizes the statistical properties of approximate hardwares and a regression-based technique for composing statistics to formulate output quality. These two techniques improve the speed and accuracy for several error metrics over a set of multiply-accumulator testcases. Compared to the interval-based modeling approach of [10], our approach for estimating output quality of approximate designs is 3.75x more accurate for comparable runtime on the testcases and achieves 8.4x runtime reduction for the error composition flow. We also demonstrate that our approach is applicable to general testcases.

Original languageEnglish (US)
Title of host publication2013 IEEE 31st International Conference on Computer Design, ICCD 2013
PublisherIEEE Computer Society
Pages47-53
Number of pages7
ISBN (Print)9781479929870
DOIs
StatePublished - Jan 1 2013
Event2013 IEEE 31st International Conference on Computer Design, ICCD 2013 - Asheville, NC, United States
Duration: Oct 6 2013Oct 9 2013

Publication series

Name2013 IEEE 31st International Conference on Computer Design, ICCD 2013

Other

Other2013 IEEE 31st International Conference on Computer Design, ICCD 2013
CountryUnited States
CityAsheville, NC
Period10/6/1310/9/13

    Fingerprint

Keywords

  • Approximate computation
  • error modeling

Cite this

Chan, W. T. J., Kahng, A. B., Kang, S., Kumar, R., & Sartori, J. M. (2013). Statistical analysis and modeling for error composition in approximate computation circuits. In 2013 IEEE 31st International Conference on Computer Design, ICCD 2013 (pp. 47-53). [6657024] (2013 IEEE 31st International Conference on Computer Design, ICCD 2013). IEEE Computer Society. https://doi.org/10.1109/ICCD.2013.6657024