Mixed-Cell-Height Legalization Considering Technology and Region Constraints

Zhu, Ziran; Li, Xingquan; Chen, Yuhang; Chen, Jianli; Wang, Zihao; Chang, Yao‐Wen

doi:10.1109/tcad.2020.2976674

Cited by 16 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A legal placement can be produced by using greedy heuristics [7,39,9], dynamic programming [33], Integer Linear Programming (ILP) [17] or modeling the problem as a Linear Complementarity Problem (LCP) [6,26]. During legalization, it is important to observe the spatial characteristics of the problem.…”

Section: Legalization Problemmentioning

confidence: 99%

“…Among the legalization algorithms available in the literature, HAO [26], ZIR [39] and ODP (from OpenDP) [9] are the only ones adapted to the ICCAD 2017 benchmark. While all three bring improvements over previous works and incorporate routability and technology constraints to the problem formulation, none of them is clearly the best one for all the circuits in the benchmarks.…”

Section: Legalization Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Netto

Fabre

Fontana

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Machine learning models have been used to improve the quality of different physical design steps, such as timing analysis, clock tree synthesis and routing. However, so far very few works have addressed the problem of algorithm selection during physical design, which can drastically reduce the computational effort of some steps. This work proposes a legalization algorithm selection framework using deep convolutional neural networks. To extract features, we used snapshots of circuit placements and used transfer learning to train the models using pre-trained weights of the Squeezenet architecture. By doing so we can greatly reduce the training time and required data even though the pre-trained weights come from a different problem. We performed extensive experimental analysis of machine learning models, providing details on how we chose the parameters of our model, such as convolutional neural network architecture, learning rate and number of epochs. We evaluated the proposed framework by training a model to select between different legalization algorithms according to cell displacement and wirelength variation. The trained models achieved an average F-score of 0.98 when predicting cell displacement and 0.83 when predicting wirelength variation. When integrated into the physical design flow, the cell displacement model achieved the best results on 15 out of 16 designs, while the wirelength variation model achieved that for 10 out of 16 designs, being better than any individual legalization algorithm. Finally, using the proposed machine learning model for algorithm selection resulted in a speedup of up to 10x compared to running all the algorithms separately.

show abstract

Section: Legalization Problemmentioning

confidence: 99%

Section: Legalization Algorithmsmentioning

confidence: 99%

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Netto

Fabre

Fontana

et al. 2022

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…The algorithm should be capable of handling double row-height cells and allow cells to be moved horizontally within their bins. Different from previous works [12][13][14], which adopt the quadratic term of displacement as their objective, we formulate the row-based placement legalization problem as a novel ILP which can be solved quickly and optimally. The notations are listed in Table 4.…”

Section: Ilp-based Legalization (Horizontal Movement)mentioning

confidence: 99%

Dynamic IR-drop ECO optimization by cell movement with current waveform staggering and machine learning guidance

Huang

Chen

Wang

et al. 2020

Proceedings of the 39th International Conference on Computer-Aided Design

View full text Add to dashboard Cite

“…Seeking to achieve richer cell libraries, implementing logic designs using mixed-height (i.e., routing tracks like 9-track and 12-track) or double-row-height standard cells are recently proposed [11]- [14]. Smaller-height cells feature compact area and lower power dissipation, but are weaker in drive strength.…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Digital Design Optimization via Improved Drive Granularity Standard Cells

Cao

Bale

Trefzer

2021

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

Mixed-Cell-Height Legalization Considering Technology and Region Constraints

Cited by 16 publications

References 25 publications

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Algorithm Selection Framework for Legalization Using Deep Convolutional Neural Networks and Transfer Learning

Dynamic IR-drop ECO optimization by cell movement with current waveform staggering and machine learning guidance

Multi-Objective Digital Design Optimization via Improved Drive Granularity Standard Cells

Contact Info

Product

Resources

About