Approximate computing survey, Part I: terminology and software & hardware approximation techniques

V Leon, MA Hanif, G Armeniakos, X Jiao… - arXiv preprint arXiv …, 2023 - arxiv.org
The rapid growth of demanding applications in domains applying multimedia processing
and machine learning has marked a new era for edge and cloud computing. These …

Simplified compressor and encoder designs for low-cost approximate radix-4 booth multiplier

G Park, J Kung, Y Lee - … Transactions on Circuits and Systems II …, 2022 - ieeexplore.ieee.org
In this brief, we present a novel design methodology of cost-effective approximate radix-4
Booth multipliers, which can significantly reduce the power consumption of error-resilient …

[HTML][HTML] High-performance, energy-efficient, and memory-efficient FIR filter architecture utilizing 8x8 approximate multipliers for wireless sensor network in the Internet …

DV Kumar, MA Majid - Memories-Materials, Devices, Circuits and …, 2022 - Elsevier
IoT uses wireless sensor networks (WSN) to deploy many sensors to track environmental
and physical parameters. The WSN measurements are frequently contaminated and altered …

FPGA acceleration of deep reinforcement learning using on-chip replay management

Y Meng, C Zhang, V Prasanna - Proceedings of the 19th ACM …, 2022 - dl.acm.org
A major bottleneck in parallelizing deep reinforcement learning (DRL) is in the high latency
to perform various operations used to update the Prioritized Replay Buffer on CPU. The low …

Max-dnn: Multi-level arithmetic approximation for energy-efficient DNN hardware accelerators

V Leon, G Makris, S Xydis, K Pekmestzi… - 2022 IEEE 13th Latin …, 2022 - ieeexplore.ieee.org
Nowadays, the rapid growth of Deep Neural Network (DNN) architectures has established
them as the defacto approach for providing advanced Machine Learning tasks with excellent …

From Circuits to SoC Processors: Arithmetic Approximation Techniques & Embedded Computing Methodologies for DSP Acceleration

V Leon - arXiv preprint arXiv:2302.12194, 2023 - arxiv.org
The computing industry is forced to find alternative design approaches and computing
platforms to sustain increased power efficiency, while providing sufficient performance …

Design Space Exploration on High-Order QAM Demodulation Circuits: Algorithms, Arithmetic and Approximation Techniques

I Stratakos, V Leon, G Armeniakos, G Lentaris… - Electronics, 2021 - mdpi.com
Every new generation of wireless communication standard aims to improve the overall
performance and quality of service (QoS), compared to the previous generations. Increased …

A survey on FPGA-based accelerator for ML models

F Yan, A Koch, O Sinnen - arXiv preprint arXiv:2412.15666, 2024 - arxiv.org
This paper thoroughly surveys machine learning (ML) algorithms acceleration in hardware
accelerators, focusing on Field-Programmable Gate Arrays (FPGAs). It reviews 287 out of …

Design Automation and Quantitative Analysis of Approximate Arithmetic Circuits

ME Elbtity, MH Amin, H Hassan, R Zand - Authorea Preprints, 2024 - techrxiv.org
This paper addresses the growing interest in approximate computing circuits, recognized as
promising alternatives for accelerating hardware for applications such as machine learning …

Enabling an Isolated and Energy-Aware Deployment of Computationally Intensive Kernels on Multi-tenant Environments

A Kokkinis, A Nanos, K Siozios - International Conference on Embedded …, 2023 - Springer
Nowadays, hardware acceleration can be used as a service for maximizing the applications'
performance and achieve significant speedup in time-critical scenarios. FPGA devices …