PhysEDA: Physics-Aware Learning Framework for Efficient EDA With Manhattan Distance Decay

TL;DR

PhysEDA introduces a physics-informed learning framework for EDA tasks, reducing complexity and improving transferability by integrating Manhattan distance decay into attention and reinforcement learning models.

Contribution

It proposes PhysEDA, combining Physics-Structured Linear Attention and Potential-Based Reward Shaping to enhance efficiency and accuracy in EDA applications.

Findings

56.8% improvement in zero-shot cross-scale transfer

14x inference speedup with 98.5% memory savings

10.8% additional gain in sparse-reward DPP

Abstract

Electronic design automation (EDA) addresses placement, routing, timing analysis, and power-integrity verification for integrated circuits. Learning methods -- attention (Transformer) and reinforcement learning (RL) -- have recently emerged on EDA tasks, yet face two common bottlenecks: vanilla attention's quadratic complexity limits scaling, and data-scarce models overfit statistical noise and amplify weak long-range correlations against the underlying physics. We observe that EDA tasks share a physical prior -- pairwise electrical and routing interactions decay exponentially along Manhattan distance -- and integrate it as a unified inductive bias into both architecture and training. We propose PhysEDA, comprising two components Physics-Structured Linear Attention (PSLA) folds the separable Manhattan decay into the linear-attention kernel as a multiplicative bias, reducing complexity from quadratic to linear; Potential-Based Reward Shaping (PBRS) constructs a physical potential from the same kernel, providing dense reward signal under sparse RL while preserving the optimal policy via the policy-invariance theorem. Across three EDA scenarios -- decoupling-capacitor placement, macro placement, and IR-drop prediction -- PhysEDA improves zero-shot cross-scale transfer by 56.8% and achieves 14x inference speedup with 98.5% memory savings on 100x100 grids; PBRS adds another 10.8% in sparse-reward DPP.