Abstract
Routing congestion is one of the many factors that need to be minimized during the physical design phase of large integrated circuits. In this article, we propose a novel congestion estimation method, called MEDUSA, that consists of three parts: (1) a feature extraction and “hyper-image” encoding; (2) a congestion estimation method using a fixed-resolution convolutional neural network model that takes a tile of this hyper-image as input and makes accurate congestion predictions for a small region of the circuit; and (3) a sliding-window method for repeatedly applying this convolutional neural network on a layout, thereby producing higher-resolution congestion maps for arbitrarily large circuits. The proposed congestion estimation approach works with both 2D (collapsed) and 3D global routing. Using both quantitative metrics and qualitative visual inspection, congestion maps produced with MEDUSA show better accuracy than prior estimation techniques.
Global routers typically use estimation techniques during their first router iteration and then switch to using actual congestion information extracted from the intermediate router solutions. Experimental results within the same global router infrastructure show a significant impact on quality after the first routing iteration; other estimation techniques result in an average of 22% to 54% higher initial overflow counts. This initial quality improvement carries through to the final global routing solution, with other estimation techniques needing up to 5% more routing iterations and up to 3× more runtime, on average. Compared with other global routers, MEDUSA achieves comparable wire length results and lower total overflow counts (more legal global routing solutions) and is typically faster.
- [1] . 2008. ISPD 2008 Global Routing Contest. Retrieved April 10, 2023 from http://www.ispd.cc/contests/08/ispd08rc.html.Google Scholar
- [2] . 2020. High-definition routing congestion prediction for large-scale FPGAs. In Proceedings of the 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC’20). 26–31.Google ScholarDigital Library
- [3] . 2022. CircuitNet: An open-source dataset for machine learning applications in electronic design automation (EDA). Science China Information Sciences 65 (2022), 227401. Google ScholarCross Ref
- [4] . 2017. Routability optimization for industrial designs at sub-14Nm process nodes using machine learning. In Proceedings of the International Symposium on Physical Design.15–21. Google ScholarDigital Library
- [5] . 2008. NTHU-Route 2.0: A fast and stable global router. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design. 338–343. Google ScholarCross Ref
- [6] . 2020. Dr. CU: Detailed routing by sparse grid graph and minimum-area-captured path search. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39, 9 (2020), 1902–1915. Google ScholarCross Ref
- [7] . 2009. High-performance global routing with fast overflow reduction. In Proceedings of the Asia and South Pacific Design Automation Conference. 582–587. Google ScholarCross Ref
- [8] . 2008. FLUTE: Fast lookup table based rectilinear steiner minimal tree algorithm for VLSI design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 27, 1 (2008), 70–83.Google ScholarDigital Library
- [9] . 2019. 2019 CAD contest: LEF/DEF based global routing. In Proceedings of the 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD’19). IEEE, Los Alamitos, CA, 1–4.Google ScholarCross Ref
- [10] . 1968. A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics 4, 2 (1968), 100–107. Google ScholarCross Ref
- [11] . 2011. Ripple: An effective routability-driven placer by iterative cell movement. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design. 74–79. Google ScholarDigital Library
- [12] . 2011. Routability-driven analytical placement for mixed-size circuit designs. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design. 80–84. Google ScholarDigital Library
- [13] . 2019. Routability-driven macro placement with embedded CNN-based prediction model. In Proceedings of the 2019 Design, Automation, and Test in Europe Conference and Exhibition (DATE’19). 180–185. Google ScholarCross Ref
- [14] . 2020. Transforming global routing report into DRC violation map with convolutional neural network. In Proceedings of the 2020 International Symposium on Physical Design (ISPD’20). ACM, New York, NY, 57–64. Google ScholarDigital Library
- [15] . 2022. TritonRoute-WXL: The open-source router with integrated DRC engine. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41, 4 (2022), 1076–1089. Google ScholarCross Ref
- [16] . 2002. Pattern routing: Use and theory for increasing predictability and avoiding coupling. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 21, 7 (
July 2002), 777–790. Google ScholarDigital Library - [17] . 2011. A SimPLR method for routability-driven placement. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design.67–73. Google ScholarDigital Library
- [18] . 2019. CongestionNet: Routing congestion prediction using deep graph neural networks. In Proceedings of the 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC’19). 217–222.Google ScholarCross Ref
- [19] . 1961. An algorithm for path connections and its applications. IRE Transactions on Electronic Computers EC-10, 3 (1961), 346–365.Google ScholarCross Ref
- [20] . 2020. DRC hotspot prediction at sub-10nm process nodes using customized convolutional network. In Proceedings of the 2020 International Symposium on Physical Design (ISPD’20). ACM, New York, NY, 135–142. Google ScholarDigital Library
- [21] . 2020. CUGR: Detailed-routability-driven 3D global routing with probabilistic resource model. In Proceedings of the 2020 57th ACM/IEEE Design Automation Conference (DAC’20). 1–6. Google ScholarCross Ref
- [22] . 2013. NCTU-GR 2.0: Multithreaded collision-aware global routing with bounded-length maze routing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 32, 5 (
May 2013), 709–722. Google ScholarDigital Library - [23] . 2012. A fast maze-free routing congestion estimator with hybrid unilateral monotonic routing. In Proceedings of the IEEE/ACM International Conference on Computer-Aided Design. 713–719. Google ScholarDigital Library
- [24] . 2001. Estimating routing congestion using probabilistic analysis. In Proceedings of the International Symposium on Physical Design.112–117. Google ScholarDigital Library
- [25] . 2018. A comparative study of local net modeling using machine learning. In Proceedings of the 2018 on Great Lakes Symposium on VLSI (GLSVLSI’18). ACM, New York, NY, 273–278. Google ScholarDigital Library
- [26] . 2007. Fast and accurate routing demand estimation for efficient routability-driven placement. In Proceedings of the 2007 Design, Automation and Test in Europe Conference and Exhibition (DATE’07). 1–6. Google ScholarCross Ref
- [27] . 2019. Eh? Predictor: A deep learning framework to identify detailed routing short violations from a placed netlist. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39, 6 (2019), 1177–1190.Google ScholarCross Ref
- [28] . 2018. A machine learning framework to identify detailed routing short violations from a placed netlist. In Proceedings of the Design Automation Conference. Article
48 , 6 pages. Google Scholar - [29] . 2004. Probabilistic congestion prediction. In Proceedings of the International Symposium on Physical Design.204–209. Google ScholarDigital Library
- [30] . 2018. RouteNet: Routability prediction for mixed-size designs using convolutional neural network. In Proceedings of the International Conference on Computer-Aided Design. Article
80 , 8 pages. Google ScholarDigital Library - [31] . 2011. MGR: Multi-level global router. In Proceedings of the 2011 IEEE/ACM International Conference on Computer-Aided Design (ICCAD’11). 250–255. Google ScholarDigital Library
- [32] . 2009. FastRoute 4.0: Global router with efficient via minimization. In Proceedings of the Asia and South Pacific Design Automation Conference.576–581. Google Scholar
- [33] . 2019. Congestion-aware global routing using deep convolutional generative adversarial networks. In Proceedings of the 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD (MLCAD’19). 1–6.Google ScholarCross Ref
Index Terms
- MEDUSA: A Multi-Resolution Machine Learning Congestion Estimation Method for 2D and 3D Global Routing
Recommendations
Per-packet global congestion estimation for fast packet delivery in networks-on-chip
Networks-on-chip (NOCs) are becoming the de facto communication fabric to connect cores and cache banks in chip multiprocessors (CMPs). Routing algorithms, as one of the key components that influence NOC latency, are the subject of extensive research. ...
Is probabilistic congestion estimation worthwhile?
SLIP '05: Proceedings of the 2005 international workshop on System level interconnect predictionFast congestion prediction is essential for congestion reduction techniques at different stages of the flow. Probabilistic congestion estimation methods model congestion after placement by considering the probability a wire will be routed over different ...
Routing congestion estimation with real design constraints
DAC '13: Proceedings of the 50th Annual Design Automation ConferenceTo address the routability issue, routing congestion estimators (RCE) become essential in industrial design flow. Recently, several RCEs [1-4] based on global routing engines are developed, but they typically ignore the effects of routing on timing so ...
Comments