Abstract | ||
---|---|---|
The purpose of this work is to reduce the power consumption of dedicated circuits for the real-time implementation of Coordinate Rotational Digital Computer (CORDIC) algorithms in Machine Learning. In this paper, we embrace the use of approximate computing techniques to improve energy efficiency by tuning the accuracy of computation for reducing the power consumption. Achieved results show that employing Lower Part Or (LOA) adder into CORDIC circuit reduces the power consumption by 21% with respect to state of the art. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICECS46596.2019.8964758 | 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS) |
Keywords | Field | DocType |
CORDIC,Low Power circuits,Energy Efficient techniques | Adder,Computer science,Efficient energy use,Digital computer,Field-programmable gate array,Electronic engineering,CORDIC,Electronic circuit,Computer engineering,Power consumption,Computation | Conference |
ISBN | Citations | PageRank |
978-1-7281-0997-8 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mario Osta | 1 | 1 | 1.39 |
Ali Ibrahim | 2 | 71 | 12.23 |
M. Valle | 3 | 97 | 19.19 |