Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design

Tao Yu, Peng Gao, Fei Wang, Ru-Yue Yuan

TL;DR

An end‐to‐end placement method, SRLPlacer, based on reinforcement learning that can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability.

Abstract

Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end-to-end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing on the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability. Codes are available at https://github.com/zhouyusd/SRLPlacer.

Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design

TL;DR

An end‐to‐end placement method, SRLPlacer, based on reinforcement learning that can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability.

Abstract

Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end-to-end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing on the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability. Codes are available at https://github.com/zhouyusd/SRLPlacer.
Paper Structure (17 sections, 3 equations, 4 figures, 4 tables)

This paper contains 17 sections, 3 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. State Space
  5. Action Space
  6. Rewards
  7. Overall Reward
  8. Immediate Reward
  9. Policy Network
  10. Environment
  11. Experiments
  12. Benchmark and Settings
  13. Metrics
  14. Ablation Study
  15. Quantitative Analysis
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Overview pipeline of our proposed placement method, SRLPlacer. Orange squares indicate macro cells, while blue dots represent standard cells.
  • Figure 2: Overview architecture of the policy network.
  • Figure 3: Visualized placement results of four adaptec-class test cases of our SRLPlace in the ISPD2005 benchmark. The orange square represents the macro cell, and the blue region represents the layout of standard cells.
  • Figure 4: Visualized placement results of four bigblue-class test cases of our SRLPlace in the ISPD2005 benchmark. The orange square represents the macro cell, and the blue region represents the layout of standard cells.