Machine learning OPC with generative adversarial networks

Ciou, Weilun; Hu, Tony; Tsai, Yi-Yen; Hsuan, Chung-Te; Yang, Elvis; Yang, Tahone; Chen, Kuang-Chao

doi:10.1117/12.2606715

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The forward process of the diffusion model describes obtaining pure noise 𝑦 𝑇 ~ N(0, I) at a large time step T by progressively adding Gaussian noise to data 𝑦 𝑡−1 at each time step t-1, where t ranges from 1 to T, as illustrated in Equation ( 6). This equation is an equivalent formulation to Equation (5). Furthermore, Eq.…”

Section: Model Architecture and Training Algorithm For Diffusion Modelmentioning

confidence: 99%

“…The conventional layout re-targeting approach involves multiple manual trial-and-error processes, with numerous iterations for the optimization of sizing values, resulting in an excessively long turn-around time (TAT). Leveraging the substantial growth of machine learning in chip manufacturing [3][4][5], we demonstrate the application of this technique to achieve highly accurate and efficient solutions for complex predictions and inferences on sizing values. Our proposed deep learning-assisted layout re-targeting method requires only one iteration to predict sizing values, significantly reducing TAT and compensating for errors in model or mask correction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing lithography printability through deep generative models for layout re-targeting

Chiu,

Hu,

Hsuan

et al. 2024

DTCO and Computational Patterning III

View full text Add to dashboard Cite

As layout schemes become increasingly complex for advanced technology nodes, challenges such as large edge placement error (EPE) and poor OPC convergence in optical proximity correction (OPC) can lead to significant yield losses. To overcome these issues, widely adopted strategies include layout re-targeting before OPC and mask feature modification after OPC for mask synthesis. The former entails adjusting the after-development inspection critical dimension (ADI CD) target of the original design layout. However, this process often relies on a time-consuming trial-and-error iterative approach to determine optimal sizing values for specific layouts. In recent years, machine learning techniques have shown promise in computational lithography, offering efficiency improvements. Leveraging the advantages of machine learning for guidance on layout re-targeting has the potential to reduce turnaround time.This paper presents a methodology that incorporates deep generative models into the layout re-targeting flow to propose proper sizing values for the layout of 3D NAND channel holes. Initially, we train two different deep generative models, namely Generative Adversarial Networks (GANs) and the Diffusion Model. These models are employed to infer sizing values for pre-OPC patterns through model prediction, utilizing input error data. Subsequently, the inferred sizing values are input into the design rule check (DRC) commands for polygon movement. Experimental results demonstrate that both deep generative models can predict layout sizing in the re-targeting flow, resulting in significantly improved accuracy of ADI CD and reduced turnaround time compared to the traditional trial-and-error approach.

show abstract

Section: Model Architecture and Training Algorithm For Diffusion Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing lithography printability through deep generative models for layout re-targeting

Chiu,

Hu,

Hsuan

et al. 2024

DTCO and Computational Patterning III

View full text Add to dashboard Cite

show abstract

“…Recent state-of-the-art ML-RET methods use image-based input by converting design patterns into image slices [5,[7][8][9]. The ML model then translates the input images and transfers it to the optimized photomask domain to produce an image with the final photomask shapes.…”

Section: Image-based Photomask Correctionmentioning

confidence: 99%

Novel End-to-End Production-Ready Machine Learning Flow for Nanolithography Modeling and Correction

Habib,

H. Fahmy,

F. Abu-ElYazeed

2024

AAIML

View full text Add to dashboard Cite

Mask optimization for optical lithography requires extensive processing to perform the Resolution Enhancement Techniques (RETs) required to transfer the design data to a working Integrated Circuits (ICs). The processing power and computational runtime for RETs tasks is ever increasing due to the continuous reduction of the feature size and the expansion of the chip area. State-of-the-art research sought Machine Learning (ML) technologies to reduce runtime and computational power, however ML-RETs are still not enabled for IC production flows yet. In this study, we analyze the reasons holding back ML computational lithography from being production ready. We present a novel flow that enables end-to-end mask optimization in addition to high scalability and consistency.

show abstract

Machine learning optical proximity correction with generative adversarial networks

Ciou

Tsai

et al. 2022

J. Micro/Nanopattern. Mats. Metro.

Self Cite

View full text Add to dashboard Cite

Background: Algorithmic breakthroughs in machine learning (ML) have allowed increasingly more applications developed for computational lithography, gradually shifting focus from hotspot detection to inverse lithography and optical proximity correction (OPC). We proposed a pixelated mask synthesis method utilizing deep-learning techniques, to generate afterdevelopment-inspection (ADI) contour and mask feature generation.Aim: Conventional OPC correction consists of two parts, the simulation model which predicts the expected contour signal, and the correction script that modifies the actual layout. With practicality in mind, we collected modeling wafer data from scratch, then implemented ML models to reproduce conventional OPC actions, mask to contour prediction, and design to mask correction.Approach: Two generative adversarial networks (GANs) were constructed, a pix2pix model was first trained to learn the correspondences between mask image and paired ADI contour image collected on wafer. The second model is embedded into machine learning mask correction (ML-OPC) framework, output mask is optimized through minimizing pixel difference between design target and simulated contour.Results: Two different magnification SEM image datasets were collected and studied, with the higher magnification showing better simulator pixel accuracy. Supervised training of the correction model provided a quick prototype mask synthesis generator, and combination of unsupervised training allowed mask pattern synthetization from any given design layout. Conclusions:The experimental results demonstrated that our ML-OPC framework was able to mimic conventional OPC model in producing exquisite mask patterns and contours. This ML-OPC framework could be implemented across full chip layout.

show abstract

Machine learning OPC with generative adversarial networks

Cited by 4 publications

References 0 publications

Enhancing lithography printability through deep generative models for layout re-targeting

Enhancing lithography printability through deep generative models for layout re-targeting

Novel End-to-End Production-Ready Machine Learning Flow for Nanolithography Modeling and Correction

Machine learning optical proximity correction with generative adversarial networks

Contact Info

Product

Resources

About