Vol.:(0123456789) The Journal of Supercomputing https://doi.org/10.1007/s11227-020-03325-8 1 3 A systematic literature review on hardware implementation of artifcial intelligence algorithms Manar Abu Talib 1  · Sohaib Majzoub 1  · Qassim Nasir 1  · Dina Jamal 1 © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Artifcial intelligence (AI) and machine learning (ML) tools play a signifcant role in the recent evolution of smart systems. AI solutions are pushing towards a sig- nifcant shift in many felds such as healthcare, autonomous airplanes and vehicles, security, marketing customer profling and other diverse areas. One of the main chal- lenges hindering the AI potential is the demand for high-performance computation resources. Recently, hardware accelerators are developed in order to provide the needed computational power for the AI and ML tools. In the literature, hardware accelerators are built using FPGAs, GPUs and ASICs to accelerate computationally intensive tasks. These accelerators provide high-performance hardware while pre- serving the required accuracy. In this work, we present a systematic literature review that focuses on exploring the available hardware accelerators for the AI and ML tools. More than 169 diferent research papers published between the years 2009 and 2019 are studied and analysed. Keywords Hardware accelerators · Artifcial intelligence · Machine learning · AI on hardware · Real-time AI 1 Introduction Artifcial intelligence (AI) and machine learning (ML) tools gained a signifcant popularity in the last decade due to the advances in computational systems in terms of power, area, and performance. A wide range of applications started utilizing AI algorithms to obtain superior results compared to traditional methods. Such applica- tions include image processing [1] such as face detection and recognition, banking and market analysis [2], robotic arms in the automated manufacturing industry [3], healthcare applications [4], efcient and smart transactions in database management [5], and security applications for face tracking and analysis [6]. Embedded vision * Qassim Nasir nasir@sharjah.ac.ae 1 University of Sharjah, Sharjah, United Arab Emirates