Peal:Probabilistic Error Analysis Methodology for Low-power Approximate Adders

Muhammad Kamran Ayub, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique

Research output: Contribution to journalArticlepeer-review

Abstract

Approximate computing has emerged as an efficient design approach for applications with inherent error resilience. Low-power approximate adders (LPAAs), for instance, IMPACT and InXA, are beingadvocated as building blocks for approximate computing hardware. For their practical adoption, the error caused by these units needs to be pre-evaluated and compared with maximum allowable error bounds for an application. To address this problem, we present PEAL, a Probabilistic error analysis methodology for Low-power Approximate Single and Multi-layered Adder Architectures, while consideringvariable probabilities for each bit of input operands for a given multi-bit adder design. PEAL is highly generic, linearly scalable, and applicable to any adder type. The analysis provides probability of success, which is accurate for single-layered adder architectures and provides a lower bound for multi-layered architectures. We have shown that state-of-the-art LPAAs can serve as effective building blocks of approximate computing only when the input probabilities are either very high (>0.8) or very low (<0.2). Interestingly, none of the state-of-the-art LPAA units, which to the best of our knowledge are the most widely adopted, has demonstrated effectiveness for mid-range probabilities (0.3-0.7). We have also analytically explained the cause of this usability limitation andproposed its solution. Moreover, we have proposed a method for estimating the Mean-squared Error ofdatapaths composed of LPAAs, to quantify the magnitude of error introduced in the output due to approximation of the adder units.

Original languageEnglish (US)
Article number1
JournalACM Journal on Emerging Technologies in Computing Systems
Volume17
Issue number1
DOIs
StatePublished - Dec 2020

Keywords

  • accuracy
  • adder
  • analysis
  • data path
  • error
  • error propagation
  • Low power
  • magnitude
  • methodology
  • multi-layered
  • performance
  • quality efficiency
  • scalability
  • statistics

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Peal:Probabilistic Error Analysis Methodology for Low-power Approximate Adders'. Together they form a unique fingerprint.

Cite this