Publication Details
Automated Synthesis of Commutative Approximate Arithmetic Operators
approximate circuit design, cartesian genetic programming, approximate arithmetic
circuits
Approximate computing, leveraging the inherent resilience to errors, emerges as
a promising strategy for reducing power consumption in digital systems. The
primary objective of this paper is to introduce an efficient method based on
Cartesian Genetic Programming for designing approximate arithmetic circuits with
commutative property. Specifically, this work focuses on the design of 8-bit
approximate multipliers and 32-bit approximate adders, both serving as
foundational components for hardware accelerators in neural networks. We have
identified that while the design of commutative approximate adders poses no
issues for evolution, the design of commutative approximate multipliers
represents a challenging problem causing the commonly used CGP stuck at highly
sub-optimal solutions. In response to this challenge, we propose a novel
application-specific mutation operator. This operator significantly enhances the
efficiency of the search process, enabling the discovery of solutions that were
previously unreachable. The achieved results revealed that imposing the
requirement for a commutative property does not substantially compromise the
quality-error trade-offs of the obtained approximate circuits, making the
resulting Pareto front comparable to that of unconstrained designs.
@inproceedings{BUT189460,
author="Zdeněk {Vašíček}",
title="Automated Synthesis of Commutative Approximate Arithmetic Operators",
booktitle="2024 IEEE Congress on Evolutionary Computation, CEC 2024 - Proceedings",
year="2024",
pages="1--8",
publisher="IEEE Computer Society",
address="Yokohama",
doi="10.1109/CEC60901.2024.10612202",
isbn="979-8-3503-0836-5"
}