Approximate FPGA Implementation of CORDIC for Tactile Data Processing Using Speculative Adders

Abstract

Abstract-In most robotic and biomedical applications, the interest for real-time embedded systems with tactile ability has been growing. For example in prosthetics, a dedicated portable system is needed for developing wearable devices. The main challenges for such systems are low latency, low power consumption and reduced hardware complexity. In order to improve hardware efficiency and reduce power consumption, approximate computing techniques have been assessed. This strategy is suitable for error-tolerant applications involving a large amount of data to be processed, which perfectly fits tactile data processing. This paper presents the first case study of applying Inexact Speculative Adders (ISA) to the FPGA implementation of a Coordinate Rotation Digital Computer (CORDIC) module within the Machine Learning algorithm of a tactile data processing system. The design has been synthesized and implemented on a Xilinx ZYNQ-7000 ZC702 device. Preliminary results have shown dynamic power reduction up to 40 % and delay latency reduction up to 21 % compared to a conventional CORDIC module, at the cost of a negligible average relative error of 0.049 % for sine and 0.003 % for cosine computations.

Sharpness recognition based on synergy between bio-inspired nociceptors and tactile mechanoreceptors

“…FPGAs have broad applications in the neural network simulations 31 and motivate further exploration 32,33 . An approximate circuit technique was used to implement tactile data processing on FPGA for the e-skin applications 34 . Furthermore, the spiking neural network implemented on FPGA was proposed for bidirectional interaction with living neurons cultured in microelectrode array 35 .…”

Design of Approximate Circuits by Fabrication of False Timing Paths: The Carry Cut-Back Adder

“…This work has proven the considerable advantage of exploiting false timing paths on adder circuits. This novel approach could benefit larger arithmetic circuits, such as multipliers [29], as well as bigger datapaths, like CORDIC [30] and FPU [31]. Its extremely lightweight circuit implementation could help building highly-efficient configurable or precisionscalable hardware accelerators, with a better predictable and controllable impact on their functionality.…”

Sharpness Recognition Based on Synergy between Bio-inspired Nociceptors and Tactile Mechanoreceptors 

“…FPGAs have broad applications in the neural network simulations 31 and motivate further exploration 32,33 . An approximate circuit technique was used to implement tactile data processing on FPGA for the e-skin applications 34 . Furthermore, the spiking neural network implemented on FPGA was proposed for bi-directional interaction with living neurons cultured in microelectrode array 35 .…”