An Optimal Alignment-Driven Iterative Closed-Loop Convergence Framework for High-Performance Ultra-Large Scale Layout Pattern Clustering

TL;DR

This paper introduces an efficient, optimal alignment-driven iterative framework for high-performance clustering of large-scale layout patterns in VLSI design, significantly improving speed and accuracy over existing methods.

Contribution

It presents a novel hybrid alignment algorithm and a set cover-based clustering model with a multi-stage pruning mechanism, enabling scalable and precise pattern clustering.

Findings

Achieved over 100x speedup compared to baseline.

Reduced data complexity by 93.4% through clustering.

Secured First Place in the 2025 China Postgraduate EDA Challenge.

Abstract

With the aggressive scaling of VLSI technology, the explosion of layout patterns creates a critical bottleneck for DFM applications like OPC. Pattern clustering is essential to reduce data complexity, yet existing methods struggle with computational prohibitiveness ($O(N^2)$ comparisons), sub-optimal discrete sampling for center alignment, and difficult speed-quality trade-offs. To address these, we propose an Optimal Alignment-Driven Iterative Closed-Loop Convergence Framework. First, to resolve alignment ambiguity, we introduce a hybrid suite of high-performance algorithms: an FFT-based Phase Correlation method for cosine similarity constraints, and a Robust Geometric Min-Max strategy for edge displacement constraints that analytically solves for the global optimum. Second, we model clustering as a Set Cover Problem (SCP) using a Surprisal-Based Lazy Greedy heuristic within a coarse-to-fine iterative refinement loop to ensure convergence. Additionally, a multi-stage pruning mechanism filters over 99% of redundant computations. Experimental results on the 2025 China Postgraduate EDA Elite Challenge benchmark demonstrate a 93.4% compression ratio relative to raw inputs and an over 100x speedup compared to the official baseline, effectively handling tens of thousands of patterns in seconds. Securing First Place among 77 teams, this approach proves its superiority in solving the NP-Hard layout clustering problem with an optimal balance of scalability and precision.