PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning
Authors:
- 5 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 853-858
Abstract
In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-performance digital design. Unlike prior methods, our approach designs solutions tabula rasa purely through learning with synthesis in the loop. We design a grid-based state-action representation and an RL environment for constructing legal prefix circuits. Deep Convolutional RL agents trained on this environment produce prefix adder circuits that Pareto-dominate existing baselines with up to 16.0% and 30.2% lower area for the same delay in the 32b and 64b settings respectively. We observe that agents trained with open-source synthesis tools and cell library can design adder circuits that achieve lower area and delay than commercial tool adders in an industrial cell library.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Human-level control through deep reinforcement learningNature, 2015
- Towards Optimal Performance-Area Trade-Off in Adders by Synthesis of Parallel Prefix StructuresIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2014
- Towards the automatic exploration of arithmetic-circuit architectures2006
- A depth-decreasing heuristic for combinational logic; or how to convert a ripple-carry adder into a carry-lookahead adder or anything in-between2002
- Q-learningMachine Learning, 1992
- Optimization by Simulated AnnealingScience, 1983
- A Regular Layout for Parallel AddersIEEE Transactions on Computers, 1982
- Parallel Prefix ComputationJournal of the ACM, 1980
- Conditional-Sum Addition LogicIEEE Transactions on Electronic Computers, 1960