Approximate computing: Difference between revisions

Revision as of 16:20, 30 October 2021

Revision as of 09:16, 18 November 2021

Line 1:

'''Approximate computing''' is an emerging paradigm for energy-efficient and/or high-performance design.<ref>J. Han and M. Orshansky, "[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.701.4955&rep=rep1&type=pdf Approximate computing: An emerging paradigm for energy-efficient design]", in the 18th IEEE European Test Symposium, pp. 1-6, 2013.</ref> It includes a plethora of computation techniques that return a possibly inaccurate result rather than a guaranteed accurate result, and that can be used for applications where an approximate result is sufficient for its purpose.<ref>A. Sampson, et al. "[http://dl.acm.org/citation.cfm?id=1993518 EnerJ: Approximate data types for safe and general low-power computation]", In ACM SIGPLAN Notices, vol. 46, no. 6, 2011.</ref> One example of such situation is for a search engine where no exact answer may exist for a certain search query and hence, many answers may be acceptable. Similarly, occasional dropping of some [[Frame (video)|frames]] in a video application can go undetected due to perceptual limitations of humans. Approximate computing is based on the observation that in many scenarios, although performing exact computation requires large amount of resources, allowing [[Approximation theory|bounded approximation]] can provide disproportionate gains in performance and energy, while still achieving acceptable result accuracy.<ref>{{clarifyCite journal|last=Mittal|first=Sparsh|date=January 2016-03-18|title=A Survey of Techniques for Approximate Computing|url=https://doi.org/10.1145/2893356|journal=ACM Computing Surveys|volume=48|issue=4|pages=62:1–62:33|doi=10.1145/2893356|issn=0360-0300}} </ref> For example, in [[k-means clustering|''k''-means clustering]] algorithm, allowing only 5% loss in classification accuracy can provide 50 times energy saving compared to the fully accurate classification.

The key requirement in approximate computing is that approximation can be introduced only in non-critical data, since approximating critical data (e.g., control operations) can lead to disastrous consequences, such as [[program crash]] or erroneous output.