Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
2026-06-08 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors focus on arranging big blocks (macros) on computer chips, which affects how well the final chip works. They point out that the order in which these blocks are placed is very important and can cause problems if done poorly early on. To improve this, they created OrderPlace, a method that uses an advanced language model to find better sequences for placing macros. Their approach tries many strategies and uses a quick way to test them before choosing the best. Tests show that OrderPlace finds better orders than previous methods, reducing the total wire length needed on standard chip design tests.
Macro placementChip physical designCombinatorial optimizationPlacement sequencingHeuristicsProxy evaluationISPD 2005 benchmarksWirelengthLarge language models (LLMs)Greedy algorithms
Authors
Shibing Mo, Jing Liu, Jianchu Xu, Ruilin Wu
Abstract
Macro placement is a fundamental step in modern chip physical design, playing a crucial role in determining the solution quality of high-dimensional combinatorial optimization problems. Despite recent advancements in machine learning for spatial coordinate determination, the temporal dimension of placement sequencing remains largely governed by static heuristics. In this work, we demonstrate that the placement sequence is not merely a preprocessing step but a decisive factor in optimization, where suboptimal early decisions trigger irreversible domino effects that constrain the solution space. To harness this unexplored dimension, we propose \textbf{OrderPlace}, a proxy-guided LLM evolution framework for automatically discovering macro placement order strategies. Instead of relying on manually crafted heuristics such as area- or connectivity-based ordering, OrderPlace explores a broader space of code-level policies, ranging from static scoring metrics to dynamic physics-inspired mechanisms. To mitigate the prohibitive cost of evaluating sequences, we introduce a lightweight proxy evaluation mechanism that efficiently filters candidates using a deterministic greedy probe. Experimental results on the standard ISPD 2005 benchmarks demonstrate that OrderPlace discovers novel ordering strategies. Compared with WireMask-EA and the state-of-the-art method EGPlace, OrderPlace reduces wirelength by 34.04\% and 14.08\%, respectively.