Saved in:
Bibliographic Details
Main Authors: Hou, Yubo, Zhuang, Furen, Kundu, Partha Pratim, Kircali, Sezin Ata, Wang, Jie, Rotaru, Mihai Dragos, Rahul, Dutta, James, Ashish
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11187
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912898799894528
author Hou, Yubo
Zhuang, Furen
Kundu, Partha Pratim
Kircali, Sezin Ata
Wang, Jie
Rotaru, Mihai Dragos
Rahul, Dutta
James, Ashish
author_facet Hou, Yubo
Zhuang, Furen
Kundu, Partha Pratim
Kircali, Sezin Ata
Wang, Jie
Rotaru, Mihai Dragos
Rahul, Dutta
James, Ashish
contents The rapid growth of electronics has accelerated the adoption of 2.5D integrated circuits, where effective automated chiplet placement is essential as systems scale to larger and more heterogeneous chiplet assemblies. Existing placement methods typically focus on minimizing wirelength or transforming multi-objective optimization into a single objective through weighted sum, which limits their ability to handle competing design requirements. Wirelength reduction and thermal management are inherently conflicting objectives, making prior approaches inadequate for practical deployment. To address this challenge, we propose TDPNavigator-Placer, a novel multi-agent reinforcement learning framework that dynamically optimizes placement based on chiplet's thermal design power (TDP). This approach explicitly assigns these inherently conflicting objectives to specialized agents, each operating under distinct reward mechanisms and environmental constraints within a unified placement paradigm. Experimental results demonstrate that TDPNavigator-Placer delivers a significantly improved Pareto front over state-of-the-art methods, enabling more balanced trade-offs between wirelength and thermal performance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11187
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TDPNavigator-Placer: Thermal- and Wirelength-Aware Chiplet Placement in 2.5D Systems Through Multi-Agent Reinforcement Learning
Hou, Yubo
Zhuang, Furen
Kundu, Partha Pratim
Kircali, Sezin Ata
Wang, Jie
Rotaru, Mihai Dragos
Rahul, Dutta
James, Ashish
Machine Learning
Artificial Intelligence
The rapid growth of electronics has accelerated the adoption of 2.5D integrated circuits, where effective automated chiplet placement is essential as systems scale to larger and more heterogeneous chiplet assemblies. Existing placement methods typically focus on minimizing wirelength or transforming multi-objective optimization into a single objective through weighted sum, which limits their ability to handle competing design requirements. Wirelength reduction and thermal management are inherently conflicting objectives, making prior approaches inadequate for practical deployment. To address this challenge, we propose TDPNavigator-Placer, a novel multi-agent reinforcement learning framework that dynamically optimizes placement based on chiplet's thermal design power (TDP). This approach explicitly assigns these inherently conflicting objectives to specialized agents, each operating under distinct reward mechanisms and environmental constraints within a unified placement paradigm. Experimental results demonstrate that TDPNavigator-Placer delivers a significantly improved Pareto front over state-of-the-art methods, enabling more balanced trade-offs between wirelength and thermal performance.
title TDPNavigator-Placer: Thermal- and Wirelength-Aware Chiplet Placement in 2.5D Systems Through Multi-Agent Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.11187