• DocumentCode
    703945
  • Title

    Axilog: Language support for approximate hardware design

  • Author

    Yazdanbakhsh, Amir ; Mahajan, Divya ; Thwaites, Bradley ; Jongse Park ; Nagendrakumar, Anandhavel ; Sethuraman, Sindhuja ; Ramkrishnan, Kartik ; Ravindran, Nishanthi ; Jariwala, Rudra ; Rahimi, Abbas ; Esmaeilzadeh, Hadi ; Bazargan, Kia

  • Author_Institution
    Georgia Inst. of Technol., Atlanta, GA, USA
  • fYear
    2015
  • fDate
    9-13 March 2015
  • Firstpage
    812
  • Lastpage
    817
  • Abstract
    Relaxing the traditional abstraction of “near-perfect” accuracy in hardware design can lead to significant gains in energy efficiency, area, and performance. To exploit this opportunity, there is a need for design abstractions that can systematically incorporate approximation in hardware design. We introduce Axilog, a set of language annotations, that provides the necessary syntax and semantics for approximate hardware design and reuse in Verilog. Axilog enables the designer to relax the accuracy requirements in certain parts of the design, while keeping the critical parts strictly precise. Axilog is coupled with a Relaxability Inference Analysis that automatically infers the relaxable gates and connections from the designer´s annotations. The analysis provides formal safety guarantees that approximation will only affect the parts that the designer intended to approximate, referred to as relaxable elements. Finally, the paper describes a synthesis flow that approximates only the relaxable elements. Axilog enables applying approximation in the synthesis process while abstracting away the details of approximate synthesis from the designer. We evaluate Axilog, its analysis, and the synthesis flow using a diverse set of benchmark designs. The results show that the intuitive nature of the language extensions coupled with the automated analysis enables safe approximation of designs even with thousands of lines of code. Applying our approximate synthesis flow to these designs yields, on average, 54% energy savings and 1.9× area reduction with 10% output quality loss.
  • Keywords
    hardware description languages; inference mechanisms; Axilog; Verilog; accuracy requirements; approximate hardware design; area reduction; automated analysis; benchmark designs; design abstractions; energy efficiency; energy savings; language annotations; language support; near-perfect accuracy; quality loss; relaxability inference analysis; semantics; syntax; synthesis flow; Approximation methods; Benchmark testing; Hardware; Logic gates; Semantics; Timing; Wires;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Design, Automation & Test in Europe Conference & Exhibition (DATE), 2015
  • Conference_Location
    Grenoble
  • Print_ISBN
    978-3-9815-3704-8
  • Type

    conf

  • Filename
    7092497