IP Library › Granted Patent US 12,730,959
Granted Patent B2
US 12,730,959 · App. 17/950,080 · Granted Sep 8, 2026

Using a machine-trained network to perform physical design

Inventors: Akira Fujimura (Saratoga, CA); Nagesh Shirali (San Jose, CA); Donald Oriordan (Sunnyvale, CA)
Assignee: D2S, INC.
G06F30/398G06F30/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,730,959
App. No.
17/950,080
Filed
Sep 21, 2022
Granted
Sep 8, 2026
Kind
B2
Examiner
LEE, ERIC D
Art Unit
2851
USPC
716/110
Abstract

A method of some embodiments receives an initial first physical design of a circuit. The method uses a machine-trained network to generate a second physical design that is a prediction of how the first physical design will look at a subsequent manufacturing stage. The method then uses the second physical design to modify the first physical design. Examples of such modifications include modifying a set of one or more routes in the first physical design and/or modifying a set of placement locations of a set of one or more sub-circuits or circuit components defined in the first physical design.

Claims (49)

1 . A method for performing physical design, the method comprising:

receiving a first physical design layout that specifies a design for at least a portion of an integrated circuit (IC) that is to be manufactured;

supplying the first physical design to a machine-trained network that generates a second physical design layout that is a prediction of how the first physical design layout will be produced when manufactured as an IC on a wafer; and

using the second physical design layout to modify the first physical design layout, said using the second physical design layout comprising using a router to modify a set of one or more routes defined in the first physical design layout, wherein after the physical design is completed and a final physical design layout is produced, a set of one or more masks are produced based on the final physical design layout and a set of lithographic processes use the produced set of masks to manufacture the IC.

2 . The method of claim 1 , wherein using the second physical design layout further comprises:

generating a display of the second physical design layout for a designer to review;

receiving, through a user interface, modifications to the first physical design layout; and

modifying the first physical design layout based on the received modifications,

wherein the designer reviews the generated display to determine whether the second physical design layout meets a set of one or more design considerations.

3 . The method of claim 1 , wherein using the second physical design layout further comprises using a placer to perform a set of placement operations that modify locations of a set of circuit components in the physical design.

4 . The method of claim 1 , wherein using the second physical design layout further comprises using the second physical design layout to determine whether a set of one or more design constraints has been met,

wherein using the router comprises modifying the set of one or more routes defined in the first physical design layout after determining that the second physical design layout does not meet a design constraint in the set of design constraints.

5 . The method of claim 1 , wherein using the second physical design layout further comprises:

using the second physical design layout to compute a physical design cost for the first physical design layout; and

using the computed cost to determine whether a set of one or more changes to the first physical design layout should be accepted.

6 . The method of claim 1 further comprising:

receiving a set of manufacturing parameters for manufacturing the IC based on the first physical design layout; and

using the set of manufacturing parameters to define a set of parameters of the machine-trained network before the machine-trained network is used to generate the second physical design layout.

7 . The method of claim 6 , wherein the set of manufacturing parameters comprises a set of manufacturing variances that expresses a range of one or more variations in using a particular manufacturing process to manufacture design components according to the first physical design layout.

8 . The method of claim 7 , wherein the set of manufacturing variances comprises a set of variations in a set of manufacturing processes used to manufacture the IC from the first physical design layout.

9 . The method of claim 8 , wherein the set of manufacturing processes comprises a set of processes to manufacture the set of masks used to fabricate the IC.

10 . The method of claim 1 further comprising receiving a set of manufacturing parameters for manufacturing the IC based on the first physical design layout,

wherein supplying the first physical design to the machine-trained network comprises using the set of manufacturing parameters along with the first physical design layout as inputs to the machine-trained network in order to generate the second physical design layout.

11 . The method of claim 10 , wherein the set of manufacturing parameters comprises a set of manufacturing variances that expresses a range of one or more variations in using a particular manufacturing process to manufacture design components according to the first physical design layout.

12 . The method of claim 1 , wherein the machine-trained network produces an output that comprises the second physical design layout.

13 . The method of claim 1 , wherein the machine-trained network produces a set of parameters, the method further comprising using the set of parameters produced by the machine-trained network to generate the second physical design layout.

14 . The method of claim 13 , wherein the set of parameters express one or more manufacturing ranges, each manufacturing range expressing a range of variations for manufacturing one component in the first physical design layout.

15 . The method of claim 1 , wherein;

the first and second physical design layouts each comprises a plurality of shapes of a plurality of design components;

a group of shapes in the second physical design layout represent predicted manufactured shapes of a group of shapes in the first physical design layout; and

using the second physical design layout further comprises determining whether one or more shapes in the second physical design layout satisfy one or more design considerations.

16 . The method of claim 15 , wherein the design considerations are design constraints and the determination comprises determining whether one or more shapes in the second physical design layout violate one or more design constraints.

17 . The method of claim 16 , wherein the design constraints comprise a set of capacitance constraints.

18 . The method of claim 16 , wherein the design constraints comprise a set of distance constraints.

19 . The method of claim 15 , wherein determining whether one or more shapes in the second physical design layout satisfy one or more design considerations comprises:

providing a display of the second physical design layout and identifying a set of locations in the second physical design layout that should be reviewed to assess whether a set of shapes at the identified set of locations satisfy design considerations.

20 . The method of claim 19 , wherein using the second physical design layout further comprises:

receiving user input regarding a group of locations in the second physical design layout that should be modified;

identifying a group of locations in the first physical design layout that corresponds to the group of locations in the second physical design layout; and

modifying the first physical design layout at the identified group of locations in the first physical design layout.

21 . The method of claim 1 , wherein the machine-trained network receives one or more patterns as inputs and produces an output that represents a transformed pattern for each input pattern, each transformed pattern representing a predicted manufactured appearance of its corresponding input pattern.

22 . A method for performing physical design, the method comprising:

receiving a first physical design;

using a machine-trained network to generate a second physical design that is a prediction of how the first physical design will be produced at a subsequent manufacturing stage; and

using the second physical design to modify the first physical design, wherein said modifying the first physical design comprises using a router to modify a set of one or more routes defined in the first physical design by defining a new route for at least one net in the first physical design.

23 . A method for performing physical design, the method comprising:

receiving a first physical design;

using a machine-trained network to generate a second physical design that is a prediction of how the first physical design will be produced at a subsequent manufacturing stage; and

using the second physical design to modify the first physical design, wherein said modifying the first physical design comprises using a placer to modify a set of placement locations in the first physical design of a set of one or more circuits defined in the first physical design.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 16, 2023
From: FUJIMURA, AKIRA; SHIRALI, NAGESH; ORIORDAN, DONALD
To: D2S, INC.
Reel/Frame 063973/0552 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 19, 2023
From: FUJIMURA, AKIRA; SHIRALI, NAGESH; ORIORDAN, DONALD
To: D2S, INC.
Reel/Frame 063708/0830 →
Continuity (2)
Provisional Application 63247295 · Sep 22, 2021
Related Publication 20230092665A1 · Mar 23, 2023
References Cited (179)
US 5187671A · Cobb · 1993 [cited by applicant]
US 5808330A · Rostoker et al. · 1998 [cited by applicant]
US 6407434B1 · Rostoker et al. · 2002 [cited by applicant]
US 6480990B1 · Sharp et al. · 2002 [cited by applicant]
US 6829757B1 · Teig et al. · 2004 [cited by applicant]
US 6877146B1 · Teig et al. · 2005 [cited by applicant]
US 6928633B1 · Teig et al. · 2005 [cited by applicant]
US 6973634B1 · Teig et al. · 2005 [cited by applicant]
US 7096449B1 · Teig et al. · 2006 [cited by applicant]
US 7107564B1 · Teig et al. · 2006 [cited by applicant]
US 7117468B1 · Teig et al. · 2006 [cited by applicant]
US 7269817B2 · Heng et al. · 2007 [cited by applicant]
US 7310793B1 · Teig et al. · 2007 [cited by applicant]
US 7441220B2 · Hetzel et al. · 2008 [cited by applicant]
US 7526748B2 · Kotani et al. · 2009 [cited by applicant]
US 7754401B2 · Fujimura et al. · 2010 [cited by applicant]
US 7784010B1 · Balsdon et al. · 2010 [cited by applicant]
US 8473875B2 · Fujimura et al. · 2013 [cited by applicant]
US 8818072B2 · Ong et al. · 2014 [cited by applicant]
US 10012900B2 · Kim et al. · 2018 [cited by applicant]
US 10346740B2 · Zhang et al. · 2019 [cited by applicant]
US 10444629B2 · Zable · 2019 [cited by applicant]
US 10520830B2 · Kicken et al. · 2019 [cited by applicant]
US 10628546B1 · Colwell et al. · 2020 [cited by applicant]
US 10670973B2 · Zou et al. · 2020 [cited by applicant]
US 10678142B2 · Jheng et al. · 2020 [cited by applicant]
US 10783292B1 · Clewes et al. · 2020 [cited by applicant]
US 10923318B2 · Gledhill et al. · 2021 [cited by applicant]
US 10949595B2 · Tsutsui et al. · 2021 [cited by applicant]
US 11043359B2 · Nakamura et al. · 2021 [cited by applicant]
US 11132489B1 · Liu et al. · 2021 [cited by applicant]
US 20040210863A1 · Culp et al. · 2004 [cited by applicant]
US 20050132306A1 · Smith et al. · 2005 [cited by applicant]
US 20050138593A1 · Okumura · 2005 [cited by applicant]
US 20050229134A1 · Hetzel et al. · 2005 [cited by applicant]
US 20050251771A1 · Robles · 2005 [cited by applicant]
US 20060066417A1 · Yamanaga et al. · 2006 [cited by applicant]
US 20060190911A1 · Stivers · 2006 [cited by applicant]
US 20080028352A1 · Birch et al. · 2008 [cited by applicant]
US 20080109766A1 · Song et al. · 2008 [cited by applicant]
US 20080115099A1 · Patra · 2008 [cited by applicant]
US 20100035168A1 · Nakajima et al. · 2010 [cited by applicant]
US 20110089345A1 · Komagata et al. · 2011 [cited by applicant]
US 20110239181A1 · Uchino · 2011 [cited by applicant]
US 20120094219A1 · Fujimura et al. · 2012 [cited by applicant]
US 20120151422A1 · White · 2012 [cited by examiner]
US 20130022929A1 · Komagata et al. · 2013 [cited by applicant]
US 20130031524A1 · He et al. · 2013 [cited by applicant]
US 20130159943A1 · Agarwal et al. · 2013 [cited by applicant]
US 20130283216A1 · Pearman et al. · 2013 [cited by applicant]
US 20130283218A1 · Fujimura et al. · 2013 [cited by applicant]
US 20160125120A1 · Yu et al. · 2016 [cited by applicant]
US 20160328511A1 · Ning et al. · 2016 [cited by applicant]
US 20170185711A1 · Fujiwara · 2017 [cited by applicant]
US 20170194126A1 · Bhaskar et al. · 2017 [cited by applicant]
US 20170357911A1 · Liu et al. · 2017 [cited by applicant]
US 20180067900A1 · Mos et al. · 2018 [cited by applicant]
US 20190146355A1 · Jheng et al. · 2019 [cited by applicant]
US 20190147134A1 · Wang et al. · 2019 [cited by applicant]
US 20190197213A1 · Ungar · 2019 [cited by applicant]
US 20190206041A1 · Fang et al. · 2019 [cited by applicant]
US 20190377849A1 · Sha et al. · 2019 [cited by applicant]
US 20190385300A1 · Baidya et al. · 2019 [cited by applicant]
US 20200051781A1 · Fujimura et al. · 2020 [cited by applicant]
US 20200065453A1 · Kim et al. · 2020 [cited by applicant]
US 20200134131A1 · Tien et al. · 2020 [cited by applicant]
US 20200159884A1 · Kim et al. · 2020 [cited by applicant]
US 20200184137A1 · Tsutsui et al. · 2020 [cited by applicant]
US 20200364394A1 · Yu et al. · 2020 [cited by applicant]
US 20200380089A1 · Gheith et al. · 2020 [cited by applicant]
US 20200380362A1 · Cao et al. · 2020 [cited by applicant]
US 20200387660A1 · Cecil · 2020 [cited by applicant]
US 20210048741A1 · Lugg et al. · 2021 [cited by applicant]
US 20210181620A1 · Poonawala et al. · 2021 [cited by applicant]
US 20210216697A1 · Brink et al. · 2021 [cited by applicant]
US 20210279878A1 · Adler et al. · 2021 [cited by applicant]
US 20210397172A1 · Slachter et al. · 2021 [cited by applicant]
US 20220035237A1 · Lee et al. · 2022 [cited by applicant]
US 20220050381A1 · Biswas et al. · 2022 [cited by applicant]
US 20220128899A1 · Fujimura et al. · 2022 [cited by applicant]
US 20220187713A1 · Middlebrooks · 2022 [cited by examiner]
US 20220299881A1 · Zheng et al. · 2022 [cited by applicant]
US 20220350951A1 · Tong et al. · 2022 [cited by applicant]
US 20230024684A1 · Fujimura et al. · 2023 [cited by applicant]
US 20230027655A1 · Fujimura et al. · 2023 [cited by applicant]
US 20230032510A1 · Fujimura et al. · 2023 [cited by applicant]
US 20230107556A1 · Tao et al. · 2023 [cited by applicant]
US 20230153505A1 · Chang et al. · 2023 [cited by applicant]
US 20230168660A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230169245A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230169246A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230169247A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230186009A1 · Fujimura et al. · 2023 [cited by applicant]
US 20230205972A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230214571A1 · Apte et al. · 2023 [cited by applicant]
US 20230229836A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230229840A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230229844A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230267265A1 · Oriordan · 2023 [cited by applicant]
US 20230274065A1 · Fujimura · 2023 [cited by applicant]
US 20230274066A1 · Fujimura · 2023 [cited by applicant]
US 20230274067A1 · Fujimura · 2023 [cited by applicant]
US 20230274068A1 · Fujimura · 2023 [cited by applicant]
US 20230274069A1 · Fujimura · 2023 [cited by applicant]
US 20230274070A1 · Fujimura · 2023 [cited by applicant]
US 20230274071A1 · Fujimura · 2023 [cited by applicant]
US 20230281374A1 · Fujimura · 2023 [cited by applicant]
US 20230282635A1 · Fujimura · 2023 [cited by applicant]
US 20230297756A1 · Ruic · 2023 [cited by applicant]
US 20230306177A1 · Fujimura · 2023 [cited by applicant]
US 20230351087A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230351088A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230351089A1 · Oriordan et al. · 2023 [cited by applicant]
US 20230359804A1 · Oriordan · 2023 [cited by applicant]
US 20240119214A1 · Oriordan et al. · 2024 [cited by applicant]
US 20240288764A1 · Hamouda · 2024 [cited by applicant]
CN 107438842A · 2017 [cited by applicant]
CN 111758072A · 2020 [cited by applicant]
CN 113168085A · 2021 [cited by applicant]
CN 113168115A · 2021 [cited by applicant]
EP 3951496A1 · 2022 [cited by applicant]
JP 2007536581A · 2007 [cited by applicant]
JP 2012181298A · 2012 [cited by applicant]
JP 2019114295A · 2019 [cited by applicant]
JP 2021509208A · 2021 [cited by applicant]
KR 102170578B1 · 2020 [cited by applicant]
KR 20210010897A · 2021 [cited by applicant]
KR 102377411B1 · 2022 [cited by applicant]
KR 20260035214A · 2026 [cited by applicant]
TW I710763B · 2020 [cited by applicant]
TW 202113501A · 2021 [cited by applicant]
TW 202121050A · 2021 [cited by applicant]
WO 2018125220A1 · 2018 [cited by applicant]
WO 2020193095A1 · 2020 [cited by applicant]
WO 2021041963A1 · 2021 [cited by applicant]
WO 2021043936A1 · 2021 [cited by applicant]
WO 2022086825A1 · 2022 [cited by applicant]
Ajayi, Tutu, et al., “OpenROAD: Toward a Self-Driving, Open-Source Digital Layout Implementation Tool Chain,” Proceedings of Government Microcircuit Applications and Critical Technology Conference, Jan. 1, 2019, 6 pages… [cited by applicant]
Ao, Jianchang, et. al., “Delay-Driven Layer Assignment in Global Routing under Multi-tier Interconnect Structure,” ISPD '13: Proceedings of the 2013 ACM International Symposium on Physical Design, Mar. 2013, 7 pages, AC… [cited by applicant]
Author Unknown, “D2S Enables “Stitchless” Full-Chip Inverse Lithography Technology in a Single Day for the Multi-Beam Era,” Press Release, Sep. 16, 2019, 3 pages, D2S, Inc., San Jose, California, USA. [cited by applicant]
Author Unknown, “D2S Unveils Industry's First Mask-Wafer Double Simulation Platform,” Press Release, Sep. 20, 2011, 3 pages, D2S, Inc., San Jose, California, USA. [cited by applicant]
Author Unknown, “Deep reinforcement learning,” Wikipedia, Sep. 21, 2020, 2 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “Design rule checking,” Wikipedia, May 27, 2020, 4 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “Marching squares,” Wikipedia, Dec. 30, 2019, 9 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “Multiple patterning,” Wikipedia, Oct. 10, 2020, 22 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “Optical proximity correction,” Wikipedia, Apr. 28, 2019, 5 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “Rasterisation,” Wikipedia, Aug. 21, 2020, 4 pages, Wikipedia.com. [cited by applicant]
Author Unknown, “TrueMask® DS,” Exact Date Unknown but Before May 2020, 3 pages, D2S, Inc., retrieved from https://design2silicon.com/products/truemask-ds/. [cited by applicant]
Author Unknown, “TrueMask® ILT Backgrounder Stitchless Full-Chip ILT in a Day,” Backgrounder, Sep. 2019, 6 pages, D2S, Inc., San Jose, California, USA. [cited by applicant]
Author Unknown, “TrueMask® ILT,” Exact Date Unknown but Before May 2020, 7 pages, D2S, Inc., retrieved from https://design2silicon.com/products/truemask-ilt/. [cited by applicant]
Cecil, Thomas, et al., “Establishing Fast, Practical, Full-Chip ILT Flows Using Machine Learning,” SPIE Proceedings 11327, Optical Microlithography XXXIII, Mar. 23, 2020, 19 pages, vol. 1132706, SPIE, San Jose, Californ… [cited by applicant]
Chen, Kun-Yuan, et al., “Full-Chip Application of Machine Learning SRAFs on DRAM Case Using Auto Pattern Selection,” SPIE Proceedings 10961, Optical Microlithography XXXII, Oct. 10, 2019, 13 pages, vol. 1096108, SPIE, S… [cited by applicant]
Chen, Tai-Chen, “Multilevel Full-Chip Gridless Routing With Applications to Optical-Proximity Correction,” Jun. 2007, 13 pages, IEEE, retrieved from http://cc.ee.ntu.edu.tw/~ywchang/Papers/tcad07-mgr.pdf. [cited by applicant]
Jia, Ningning, et al., “Machine Learning for Inverse Lithography: using stochastic gradient descent for robust photomask synthesis,” Journal of Optics, Apr. 1, 2010, 9 pages, vol. 12, IOP Publishing, retrieved from http… [cited by applicant]
Kwan, Joe, et al., “Applying Machine Learning Techniques to Accelerate Advanced Process Yield Ramp,” Jan. 5, 2021, 29 pages, Siemens Digital Industries Software, Munich, Germany. [cited by applicant]
Lin, Yibo, et al., “Machine Learning for Yield Learning and Optimization,” 2018 IEEE International Test Conference (ITC), University of Texas, Oct. 29-Nov. 1, 2018, 10 pages, IEEE, Phoenix, AZ, USA. [cited by applicant]
Liu, Peng, “Mask Synthesis Using Machine Learning Software and Hardware Platforms,” SPIE Proceedings 11327, Optical Microlithography XXXIII, Mar. 23, 2020, 17 pages, vol. 1132707, SPIE, San Jose, California, USA. [cited by applicant]
Mitchell, Robin, “IMEC Demonstrates Buried Power Rails in FinFET CMOS,” Mar. 17, 2021, 6 pages, EPM, retrieved from https://www.electropages.com/blog/2021/03/imec-demonstrates-buried-power-rails-finfet-cmos. [cited by applicant]
Mitra, Joydeep, et al., “RADAR: RET-Aware Detailed Routing Using Fast Lithography Simulations,” Proceedings 2005, 42nd Design Automation Conference, Jun. 13-17, 2005, 6 pages, IEEE, retrieved from https://citeseerx.ist.… [cited by applicant]
Naik, Mehul, “Challenges to Interconnect Scaling at 3nm and Beyond,” Applied Materials, Jun. 14, 2021, 9 pages, Applied Materials, Inc., retrieved from https://www.appliedmaterials.com/us/en/blog/blog-posts/challenges-t… [cited by applicant]
Pang, Linyong (Leo), et al., “Study of Mask and Wafer Co-design That Utilizes a New Extreme SIMD Approach to Computing in Memory Manufacturing: Full-Chip Curvilinear ILT in a Day,” SPIE Proceedings 11148, Photomask Tech… [cited by applicant]
Pang, Linyong, “Inverse Lithography Technology: 30 years from concept to practical, full-chip reality,” Journal of Micro/Nanopatterning, Materials, and Metrology, Aug. 31, 2021, 49 pages, vol. 20(3), SPIE, retrieved fro… [cited by applicant]
Pang, Linyong, et al., “How GPU-Accelerated Simulation Enables Applied Deep Learning for Masks and Wafers,” Month Unknown 2019, 10 pages, D2S, Inc., San Jose, California, USA. [cited by applicant]
Pang, Linyong, et al., “Making Digital Twins using the Deep Learning Kit (DLK),” Month Unknown 2019, 13 pages, D2S, Inc., San Jose, California, USA. [cited by applicant]
Pradipta, Geraldo, et al., “A Machine Learning Based Parasitic Extraction Tool,” Oct. 31, 2019, 3 pages, University of Minnesota, Minneapolis, Minnesota, USA. [cited by applicant]
Prasad, Divya, “Can we Bury our Scaling Problems with Buried Power Rails and Back-side Power Delivery?,” Mar. 5, 2020, 8 pages, Arm Limited, retrieved from https://community.arm.com/arm-research/b/articles/posts/can-we-… [cited by applicant]
Rahman, M. Sohel, et. al., “MultiResUNet: Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation,” Feb. 2019, 25 pages, retrieved from https://arxiv.org/pdf/1902.04049.pdf. [cited by applicant]
Ren, Haoxing (Mark), “Machine Learning and Deep Learning Applications in Design Automation and Practical Issues,” Dac 19 Tutorial, Month Unknown 2019, 55 pages, Nvidia Corporation, Santa Clara, California, USA. [cited by applicant]
Ronneberger, Olaf, et. al., “U-Net: Convolutional Networks for Biomedical Image Segmentation,” May 2015, 8 pages, retrieved from https://arxiv.org/pdf/1505.04597.pdf. [cited by applicant]
Shi, Xuelong, et al., “Physics based feature Vector Design: a Critical Step Towards Machine Learning based Inverse Lithography,” SPIE Proceedings 11327, Optical Microlithography XXXIII, Mar. 23, 2020, 8 pages, vol. 1132… [cited by applicant]
Sole, Marc Pons, “Layout Regularity for Design and Manufacturability,” Doctoral Thesis, Jul. 8, 2012, 185 pages, Technical University of Catalonia, Barcelona, Spain. [cited by applicant]
Sperling, Ed, “Design Rule Complexity Rising,” Semiconductor Engineering—Deep Insights for the Tech Industry, Apr. 19, 2018, 16 pages, SMG, retrieved from https://semiengineering.com/design-rule-complexity-rising/. [cited by applicant]
Teig, Steven L., “The X architecture: not your father's diagonal wiring,” SLIP '02: Proceedings of the 2002 international workshop on System-level interconnect prediction, Apr. 6, 2002, 5 pages, ACM, retrieved from http… [cited by applicant]
Wang, Shibing, et al., “Efficient Full-Chip SRAF Placement Using Machine Learning for Best Accuracy and Improved Consistency,” SPIE Proceedings 10587, Optical Microlithography XXXI, Mar. 20, 2018, 10 pages, vol. 105870N… [cited by applicant]
Wang, Shibing, et al., “Machine Learning Assisted SRAF Placement for Full Chip,” SPIE Proceedings 10451, Photomask Technology 2017, Oct. 16, 2017, 8 pages, vol. 104510D, SPIE, Monterey, California, USA. [cited by applicant]
Yang, Dingcheng, et al., “CNN-Cap: Effective Convolutional Neural Network Based Capacitance Models for Full-Chip Parasitic Extraction,” 2021 International Conference on Computer Aided Design, Jul. 14, 2021, 9 pages, IEE… [cited by applicant]
Shao, Hao-Chiang, et. al., “From IC Layout to Die Photograph: A CNN-Based Data-Driven Approach” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 40, No. 5, May 2021, pp. 957-970, IEEE. [cited by applicant]
Staepelaere, David Joseph, “Geometric Transformations for a Rubber-band Sketch,” Master's Thesis, Sep. 1992, 71 pages, University of California at Santa Cruz, Santa Cruz, CA. [cited by applicant]
Dounde, Amit, et al., “A Study of Curvilinear Routing in IN5 Standard Cells: Challenges and Opportunities,” Photomask Technology 2019, Sep. 26, 2019, p. 48, SPIE. [cited by applicant]