[1] [1] ALPERT C J, LI Z, MOFFITT M D, et al. What makes a design difficult to route ［C］ // Proceed ACM ISPD. San Francisco, CA, USA. 2010: 7-12.

[2] [2] LI Z, ALPERT C J, NAM G J, et al. Guiding a physical design closure system to produce easier-to-route designs with more predictable timing ［C］ // Proceed DAC. San Francisco, CA, USA. 2012: 465-470.

[3] [3] SHI D, DAVOODI A. TraPL: track planning of local congestion for global routing ［C］ // Proceed DAC. Austin, TX, USA. 2017: 1-6.

[4] [4] HAN Y, ANCAJAS D M, CHAKRABORTY K, et al. Exploring high-throughput computing paradigm for global rouing ［J］. IEEE Trans Very Large Scale Integr Syst, 2014, 22(1): 155-167.

[5] [5] WANG L C. Experience of data analytics in EDA and test-principles, promises, and challendges ［J］. IEEE Trans Comput-Aided Des Integr Circ Syst, 2017, 36(6): 885-898.

[6] [6] TABRIZI A F, RAKAI L, DARAV N K, et al. A machine learning framework to identify detailed routing short violations from a placed netlist ［C］ // Proceed DAC. San Francisco, CA, USA. 2018: 1-6.

[7] [7] CHAN W T J, HO P H, KAHNG A B, et al. Routability optimization for industrial designs at sub-14 nm process nodes using machine learning ［C］ // Proceed ACM ISPD. Portland, OR, USA. 2017: 15-21.

[9] [9] BODINE F. Reducing cell placement congestion using targeted pattern halos ［C］ // Proceed SNUG. Boston, MA, USA. 2014: 23-26.