research-article

Fast ECO Leakage Optimization Using Graph Convolutional Network

Authors:

Wonjae Lee,

Yonghwi Kwon,

Youngsoo ShinAuthors Info & Claims

GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSI

Pages 187 - 192

https://doi.org/10.1145/3386263.3406916

Published: 07 September 2020 Publication History

Get Access

Abstract

At the very late design stage, engineering change order (ECO) leakage optimization is often performed to swap some cells for the ones with lower leakage, e.g. the cells with higher threshold voltage (Vth) or with longer gate length. It is very effective but time consuming due to iterative nature of swap and timing check with correction. We introduce a graph convolutional network (GCN) for quick ECO leakage optimization. GCN receives a number of input parameters that model the current timing information of a netlist as well as the connectivity of the cells in a form of a weighted connectivity matrix. Once it is trained, GCN predicts exact Vth (with Vth given by commercial ECO leakage optimization as a reference) of 83% of cells, on average of test circuits. The remaining 17% of cells are responsible for some negative timing slack. To correct such timing as well as to remove any minimum implant width (MIW) violations, we propose a heuristic Vth reassignment. The combined GCN and heuristic achieve 52% reduction of leakage, which can be compared to 61% reduction from commercial ECO, but with less than half of runtime.

Supplementary Material

MP4 File (3386263.3406916.mp4)

Presentation video

Download
105.87 MB

References

[1]

A. T. El-Thakeb et al., "Performance evaluation of FinFET based SRAM under statistical VT variability," in Proc. Int. Conf. on Microelectronics, Dec. 2014, pp. 88--91.

Google Scholar

[2]

T. Luo et al., "Total power optimization combining placement, sizing and multi-Vt through slack distribution management," in Proc. Asia and South Pacific Design Automation Conf., Mar. 2008, pp. 352--357.

Google Scholar

[3]

J. Li et al., "Leakage power reduction for deeply-scaled FinFET circuits operating in multiple voltage regimes using fine-grained gate-length biasing technique," in Proc. Design, Automation and Test in Europe Conf. and Exh., Mar. 2015, pp. 1579--1582.

Crossref

Google Scholar

[4]

J. T. Shah et al., "Circuit optimization for leakage power reduction using multi-threshold voltages for high performance microprocessors," in Proc. Int. Symp. on Physical Design, Mar. 2007, pp. 67--74.

Google Scholar

[5]

H. Abrishami et al., "Post sign-off leakage power optimization," in Proc. Design Automation Conf., Jun. 2011, pp. 453--458.

Google Scholar

[6]

J. Bruna et al., "Spectral networks and locally connected networks on graphs," in Int. Conf. on Learning Representations, Apr. 2014.

Google Scholar

[7]

A. B. Kahng and H. Lee, "Minimum implant area-aware gate sizing and placement," in Proc. Great Lakes Symp. on VLSI, May 2014, pp. 57--62.

Google Scholar

[8]

W.-K. Mak et al., "Minimum implant area-aware placement and threshold voltage refinement," IEEE Trans. on Computer-Aided Design, vol. 36, no. 7, pp. 1103--1112, Jul. 2017.

Crossref

Google Scholar

[9]

P. Gupta et al., "Gate-length biasing for runtime-leakage control," IEEE Trans. on Computer-Aided Design, vol. 25, no. 8, pp. 1475--1485, Aug. 2006.

Digital Library

Google Scholar

[10]

T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," in Proc. Int. Conf. on Learning Representations, Apr. 2017.

Google Scholar

[11]

Opencores benchmarks. [Online]. Available: http://www.opencores.org

Google Scholar

[12]

M. Martins et al., "Open cell library in 15nm FreePDK technology," in Proc. Int. Symp. on Physical Design, Mar. 2015, pp. 171--178.

Google Scholar

[13]

M. Abadi et al., "TensorFlow: A system for large-scale machine learning," in USENIX Symp. on Operating Systems Design and Implementation, Nov. 2016, pp. 265--283.

Google Scholar

[14]

D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. Int. Conf. for Learning Representations, May 2015.

Google Scholar

Cited By

View all

Jeon JKahng AKang JKim JWoo M(2024)SLO-ECO: Single-Line-Open Aware ECO Detailed Placement and Detailed Routing Co-Optimization2024 25th International Symposium on Quality Electronic Design (ISQED)10.1109/ISQED60706.2024.10528730(1-8)Online publication date: 3-Apr-2024
https://doi.org/10.1109/ISQED60706.2024.10528730
Cheng CHoltz CKahng ALin BMallappa U(2023)DAGSizer: A Directed Graph Convolutional Network Approach to Discrete Gate Sizing of VLSI GraphsACM Transactions on Design Automation of Electronic Systems10.1145/357701928:4(1-31)Online publication date: 17-May-2023
https://dl.acm.org/doi/10.1145/3577019
Cao PHe GDing WZhang ZWang KYang J(2023)Efficient and Accurate ECO Leakage Optimization Framework With GNN and Bidirectional LSTMIEEE Transactions on Very Large Scale Integration (VLSI) Systems10.1109/TVLSI.2023.328325631:9(1413-1424)Online publication date: Sep-2023
https://doi.org/10.1109/TVLSI.2023.3283256
Show More Cited By

Index Terms

Fast ECO Leakage Optimization Using Graph Convolutional Network
1. Hardware
  1. Electronic design automation
  2. Power and energy
    1. Power estimation and optimization
      1. Circuits power issues

Recommendations

Nanoscale CMOS circuit leakage power reduction by double-gate device
ISLPED '04: Proceedings of the 2004 international symposium on Low power electronics and design

Leakage power for extremely scaled (Leff = 25 nm) double-gate devices is examined. Numerical two-dimensional simulation results for double-gate CMOS device/circuit power are presented from physics principle, identifying that double-gate technology is an ...
Gate oxide leakage and delay tradeoffs for dual-t_oxcircuits

Gate oxide tunneling current (I_gate) is comparable to subthreshold leakage current in CMOS circuits when the equivalent physical oxide thickness (T_ox) is below 15 Å. Increasing the value of T_ox reduces the leakage at the expense of increased delay, and ...
Ultra-low-leakage, Robust FinFET SRAM Design Using Multiparameter Asymmetric FinFETs
Special Issue on Nanoelectronic Circuit and System Design Methods for the Mobile Computing Era and Regular Papers

Memory arrays consisting of Static Random Access Memory (SRAM) cells occupy the largest area on chip and are responsible for significant leakage power consumption in modern microprocessors. With the transition from planar Complementary Metal-Oxide-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSI

September 2020

597 pages

ISBN:9781450379441

DOI:10.1145/3386263

General Chairs:
Tinoosh Mohsenin
University of Maryland, Baltimore County, USA
,
Weisheng Zhao
Beihang University, China
,
Program Chairs:
Yiran Chen
Duke University, USA
,
Onur Mutlu
ETH Zurich, Switzerland

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 September 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Badges

Honorable Mention

Author Tags

Qualifiers

Research-article

Funding Sources

Conference

GLSVLSI '20

GLSVLSI '20: Great Lakes Symposium on VLSI 2020

September 7 - 9, 2020

Virtual Event, China

Acceptance Rates

Overall Acceptance Rate 312 of 1,156 submissions, 27%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
408
Total Downloads

Downloads (Last 12 months)53
Downloads (Last 6 weeks)7

Reflects downloads up to 10 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Jeon JKahng AKang JKim JWoo M(2024)SLO-ECO: Single-Line-Open Aware ECO Detailed Placement and Detailed Routing Co-Optimization2024 25th International Symposium on Quality Electronic Design (ISQED)10.1109/ISQED60706.2024.10528730(1-8)Online publication date: 3-Apr-2024
https://doi.org/10.1109/ISQED60706.2024.10528730
Cheng CHoltz CKahng ALin BMallappa U(2023)DAGSizer: A Directed Graph Convolutional Network Approach to Discrete Gate Sizing of VLSI GraphsACM Transactions on Design Automation of Electronic Systems10.1145/357701928:4(1-31)Online publication date: 17-May-2023
https://dl.acm.org/doi/10.1145/3577019
Cao PHe GDing WZhang ZWang KYang J(2023)Efficient and Accurate ECO Leakage Optimization Framework With GNN and Bidirectional LSTMIEEE Transactions on Very Large Scale Integration (VLSI) Systems10.1109/TVLSI.2023.328325631:9(1413-1424)Online publication date: Sep-2023
https://doi.org/10.1109/TVLSI.2023.3283256
Wang KCao PWang T(2022)A Graph Neural Network Method for Fast ECO Leakage Power OptimizationProceedings of the 27th Asia and South Pacific Design Automation Conference10.1109/ASP-DAC52403.2022.9712486(196-201)Online publication date: 17-Jan-2022
https://dl.acm.org/doi/10.1109/ASP-DAC52403.2022.9712486

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Nanoscale CMOS circuit leakage power reduction by double-gate device

Gate oxide leakage and delay tradeoffs for dual-t_oxcircuits

Ultra-low-leakage, Robust FinFET SRAM Design Using Multiparameter Asymmetric FinFETs