RL-MUL: Multiplier Design Optimization with Deep Reinforcement Learning

arXiv:2404.00639v1 Announce Type: cross
Abstract: Multiplication is a fundamental operation in many applications, and multipliers are widely adopted in various circuits. However, optimizing multipliers is challenging and non-trivial due to the huge design space. In this paper, we propose RL-MUL, a multiplier design optimization framework based on reinforcement learning. Specifically, we utilize matrix and tensor representations for the compressor tree of a multiplier, based on which the convolutional neural networks can be seamlessly incorporated as the agent network. The agent …

abstract applications arxiv circuits cs.ar cs.lg design framework however optimization paper reinforcement reinforcement learning space type