• Two joint academic papers on AI-based metrology technology presented
• Gauss Labs’s innovative technology improves process control and equipment productivity in semiconductor manufacturing
• Gauss Labs is at the forefront, leading industrial AI efforts to transform the manufacturing industry

Seoul, February 29, 2024

SK hynix Inc. (or “the company”, www.skhynix.com) and Gauss Labs announced today that they participated in the SPIE AL¹ 2024, an international conference held in San Jose, California, and presented two papers based on the latest technology for AI-based metrology.

¹SPIE Advanced Lithography + Patterning (SPIE AL): A conference hosted by the Society of Photo-Optical Instrumentation Engineers (SPIE), the most prestigious international society in optics and photonics following foundation in 1955, where overall lithography technology for drawing semiconductor circuits are discussed
²Metrology: Measuring the physical and electrical characteristics to ensure that requirements are met in the manufacturing process

Figure 1. Gauss Labs CEO Mike Kim(center) poses with his colleagues

SK hynix has been collaborating closely with Gauss Labs in various areas to increase semiconductor yield and productivity, and the results of this collaboration are published in these two papers.

In the paper “Model Aggregation for Virtual Metrology for High-Volume Manufacturing,” Gauss Labs introduces “aggregated AOM³“, an algorithm that increases the prediction accuracy of its AI-based virtual metrology solution, Panoptes VM (Virtual Metrology).

³Adaptive Online Model (AOM): Modelling algorithms that address data changes due to process state changes and maintain high predictability

Since its adoption in December 2022, SK hynix used Panoptes VM to conduct virtual measurements on more than 50 million wafers so far, which translates to more than one wafer per second. The company was able to improve process variability⁴ by 29% thanks to this technology.

⁴Variability: The scale of the quality variation of the products from a certain process. It is important to maintain a low process variability in order to keep the product quality consistent.

The latest algorithm by Gauss Labs, the aggregated AOM, pools processing machines, chambers, etc. that share the same pattern and models them together. According to Gauss Labs, this solves the challenge of data shortage while further increasing the prediction accuracy.

In its second paper, “Universal Denoiser to Improve Metrology Throughput,” Gauss Labs introduces a “universal denoiser”, which removes random variations (noise) from CD-SEM⁵ images. Measurements from CD-SEM images are taken at nanometer scale, so it is extremely important to remove noise in order to take measurements accurately.

⁵Critical Dimension Scanning Electron Microscope (CD-SEM): Equipment that combines electronic and infrared optical microscopes to measure the size, shape, and position of semiconductor patterns

Gauss Labs’s universal denoiser uses AI to remove noise from various types of images at once. Through a series of extensive tests with SK hynix, Gauss Labs observed image acquisition time reduced to as much as ¼, compared to conventional technology. Gauss Labs states that this technology is expected to improve the productivity of metrology equipment by 42%.

Mike Kim, CEO of Gauss Labs, said that his company is working on research and development for applications of industrial AI in real-world semiconductor manufacturing fabs. “We will continue to launch innovative AI-based solutions to revolutionize manufacturing.”

Authors

• Minsuk Shin^a, Minju Jung^a, Simon Zabrocki^a, Doh-Hyung Ro^b, Hyeon-Kyeong Jeong^b, Dongkyun Yim ^a, “Model aggregation for virtual metrology in high-volume manufacturing,” SPIE Advanced Lithography + Patterning (2024)
• Yonghyun Kim^a, Seyun Kim^a, Hoon Byun^a, Sang-Gil Park^a, Tae Jong Lee^b, Seong Il Lee^b, Min Woo Kang^b, Il Koo Kim^a, “Universal denoiser to improve metrology throughput,” SPIE Advanced Lithography + Patterning (2024)

^aGauss Labs
^bSK hynix

Disclaimer

These materials are not an offer for sale of the securities of SK hynix Inc. in the United States. The securities may not be offered or sold in the United States absent registration with the U.S. Securities and Exchange Commission or an exemption from registration under the U.S. Securities Act of 1933, as amended. SK hynix Inc. does not intend to register any offering in the United States or to conduct a public offering of securities in the United States.

About SK hynix Inc.

SK hynix Inc., headquartered in Korea, is the world’s top tier semiconductor supplier offering Dynamic Random Access Memory chips (“DRAM”), flash memory chips (“NAND flash”) and CMOS Image Sensors (“CIS”) for a wide range of distinguished customers globally. The Company’s shares are traded on the Korea Exchange, and the Global Depository shares are listed on the Luxembourg Stock Exchange. Further information about SK hynix is available at www.skhynix.com, news.skhynix.com.

About Gauss Labs Inc.

Gauss Labs develops innovative industrial AI solutions and software products to make factories more intelligent by leveraging machine-generated data. It was founded in August 2020 and now has two international locations in Silicon Valley, CA, and Seoul, Korea. Further information about Gauss Labs is available at www.gausslabs.ai.

Media Contact

SK hynix Inc.
Global Public Relations

Technical Leader
Sooyeon Lee
E-Mail: global_newsroom@skhynix.com

Technical Leader
Kanga Kong
E-Mail: global_newsroom@skhynix.com

The post Gauss Labs and SK hynix Publish the Latest Results on AI-based Semiconductor Metrology Technology at SPIE AL 2024 first appeared on SK hynix Newsroom.

Looking to improve operational efficiency and yield in its semiconductor manufacturing process, SK hynix has turned to an artificial intelligence (AI) solution. Gauss Labs, an industrial AI startup SK hynix invested in, launched an AI-based virtual metrology (VM) solution software product called Panoptes VM in November 2022. Right after in December 2022, SK hynix began using Panoptes VM in its mass production fabs.

Panoptes VM predicts manufacturing process outcomes using sensor data. The product is named after Panoptes in Greek mythology, the all-seeing giant with 100 eyes. Accordingly, Panoptes VM is designed to monitor everything that happens during the manufacturing process.

Panoptes VM was first applied to thin film vapor deposition¹, a crucial process that coats a thin film on a wafer. The thickness and refractive index of the thin film are key process outcomes that are directly related to the quality of a semiconductor chip. However, measuring these process outcomes for such a thin film would take a great deal of time and resources, so it is infeasible to make measurements for all wafers.

SK hynix now relies on Panoptes VM to resolve this problem. Combining prediction values generated by Panoptes VM with APC², SK hynix reduced process variability³ by 21.5% on average, which also led to improvement in yield. SK hynix and Gauss Labs are considering plans to expand this technology to various processes beyond thin film vapor deposition.

¹Thin Film Vapor Deposition: A process that coats the top of a wafer by forming a thin film — a very fine layer of material on a substrate surface, e.g., insulated semiconductor, glass, and ceramic — via a physical or chemical reaction such as vacuum deposition or sputtering.

²APC (Advanced Process Control): A solution that finds optimal process conditions for equipment during a manufacturing process.

³Process Variability: The amount of fluctuation in the quality of manufactured products in respective processes. As the probability of defects falls when the fluctuation decreases, the process variability should be managed within a certain level.

Analyzing the real sensor data with AI technology, prediction models by Panoptes VM achieve a high level of accuracy comparable to physical metrology equipment. Consequently, virtual metrology allows manufacturers to monitor essentially all wafers and opens up endless possibilities through predicted values.

Mike Kim, CEO of Gauss Labs, said: “Gauss Labs is solving the most challenging problems in manufacturing by using state-of-the-art AI technology and creating real impact and values in practice. With Panoptes VM at the forefront, we will continue to develop products that will lead innovation in manufacturing.”

Regarding the adoption of Panoptes VM, Young-sik Kim, EVP of Manufacturing/Technology at SK hynix, said: “SK hynix is making concerted efforts with Gauss Labs to realize smart factories with a next level of intelligence. We will continue to maintain our technological edge by incorporating AI technology into all stages of semiconductor manufacturing. The arrival of Panoptes VM is just the beginning.”

Interview with the People Behind Panoptes VM

AI is considered one of the main drivers of the 4th Industrial Revolution, but it’s not widely known how AI is actually applied in the industry. This is due to the difficulty of commercializing and adopting industrial AI solutions in practice. Yet, Gauss Labs and SK hynix managed to introduce AI to semiconductors, one of the most complex manufacturing sectors.

Dong Kyun Yim is a project manager at Gauss Labs who has led the launch of Panoptes VM. Doh-hyung Noh is a technical leader in the AI/DA Solution Development Team at SK hynix who has ensured that Panoptes VM will be applied effectively in real production. Hyeon-kyeong Jeong is a technical leader in the Thin Film Technology Strategy Team at SK hynix, who has been working to improve the thin film deposition process by linking Panoptes VM to APC.

Q. We heard that Gauss Labs specializes in industrial AI solutions. What is industrial AI and what role does it play?

▲ Dong Kyun Yim is explaining the effect and value of industrial AI.

Yim “Industrial AI literally means analyzing and utilizing data in industrial settings using AI technology. Gauss Labs believes that AI has the biggest impact in the following five areas of manufacturing: “yield & quality management”, “planning, scheduling & dispatching”, “process & equipment control”, “equipment maintenance” and “process monitoring”.

“Consumer-oriented AI services such as customer service chatbots and product recommendations are already familiar to most people. However, industrial AI is still an esoteric concept to many as it takes a longer time to be commercialized due to higher accuracy and reliability requirements compared to consumer-oriented AI. For example, it’s quite obvious that inaccurate analysis of a manufacturing process will be much more damaging than an inaccurate recommendation of a consumer product.

“Industrial AI has yet to reach the commercialization level of consumer AI, which also means that it can be considered a blue ocean with endless opportunities. Gauss Labs has been focusing on products for manufacturing process monitoring and recently launched Panoptes VM, which has been deployed by SK hynix since December 2022.”

Q. What is virtual metrology?

▲ Doh-hyung Noh is explaining the concept and necessity of virtual metrology.

Noh “Metrology refers to the measurement of a product’s quality during a manufacturing process. But since it takes an enormous amount of time and resources to measure process outcomes, sampling is typical in high-volume manufacturing. In other words, only a fraction of the products is measured instead of measuring them all. Virtual metrology spares physical measurements and, instead, predicts the quality of products that have not been sampled by leveraging machine-generated data such as equipment sensor data.”

Jeong “More concretely, Panoptes VM for thin film deposition predicts process outcomes such as the refractive index and thickness of the film deposited on the wafer by analyzing data such as pressure, temperature, distance, amount of gas, and electric current inside the equipment chamber during the thin film deposition process. Achieving the effect of a complete measurement without actually conducting one is the advantage of using Panoptes VM.

“In semiconductor manufacturing, the demand for metrology is increasing more and more as product patterns get miniaturized. Nonetheless, with a limit on increasing physical metrology, the need for virtual metrology is growing. The very concept of virtual metrology has existed for some time, with numerous attempts to introduce it in real production.”

▲ Taken from a promotional video of Panoptes VM (Source: Gauss Labs’ official YouTube channel)

Q. Do you mean that there were many challenges to putting virtual metrology into practice?

▲ Hyeon-kyeong Jeong is discussing the technical challenges of incorporating virtual metrology for the thin film deposition process.

Jeong “First of all, it was not easy to analyze process outcomes because there were not a lot of actual metrology data. In addition, it required a huge effort to find meaningful parameters among hundreds of various sensor data that affected the process outcomes. In short, it was difficult to create a virtual metrology model with high accuracy.”

Noh “There were also many challenges caused by data drift and shift⁴. Data drift occurs when the state of equipment changes over time, and data shift stems from equipment maintenance. These effects can lead to an additional workload on process engineers who have to update the model continuously to account for changes in the data itself.”

⁴Data drift and shift: Gradual and sudden changes in the statistical distribution of the data.

Q. How does Panoptes VM overcome these challenges?

▲ Hyeon-kyeong Jeong, Dong Kyun Yim, Doh-hyung Noh, and Simon Zabrocki (from Gauss Labs) are discussing Panoptes VM.

Yim “Panoptes VM collects data from multiple machines performing the same process and recommends important parameters for predicting process outcomes using AI technology. It also allows engineers to customize prediction models based on their domain knowledge⁵. This combination of AI algorithms and human knowledge results in an even more elaborate selection of parameters necessary for predicting process outcomes. This naturally leads to high accuracy.

“Moreover, Panoptes VM offers an automatic model update function that uses AI to constantly learn data trends to detect and incorporate changes such as data drift and shift in real time. This relieves engineers from the need to constantly monitor and update the model.”

⁵Domain knowledge: Expertise in a specific field.

Q. What are the expected benefits of Panoptes VM?

Jeong: “When the virtual measurement results from Panoptes VM are connected to process control⁶ such as APC, the process variability decreases and the yield increases. This is because the process can be controlled even at the single-wafer level. In fact, we witnessed the process variability decrease by 21.5% on average as a result of the early introduction of Panoptes VM to main process steps, which was followed by a corresponding yield improvement.

“Additionally, we can prevent quality control accidents. In the past, it used to take a long time to identify issues in a process and take proper actions because metrology sampling cycles were long. With Panoptes VM predicting process outcomes for every wafer, engineers can now detect and resolve anomalies in process and equipment rapidly.”

⁶Process control: The ability to monitor and adjust a process to obtain a desired output.

Q. How did your work change after Panoptes VM was introduced?

▲ (From left) Hyeon-kyeong Jeong, Doh-hyung Noh, and Dong Kyun Yim are sharing experiences of using Panoptes VM.

Jeong “The ability to analyze data has improved for engineers while the workload of analysis itself has decreased. In the past, we could obtain only a few process outcomes from sampling, but we can now secure comprehensive all-wafer data for analysis. It is easier to grasp the correlation between equipment sensor data and process outcomes, and the insights thus obtained can be applied back to Panoptes VM to create a virtuous cycle of growth.”

Q. What is your plan following the introduction of Panoptes VM?

Noh “We plan to expand process areas to adopt Panoptes VM. Currently, it’s only applied to the thin film process, but tests are already underway for other processes. We will continue to work closely with Gauss Labs to advance into the mass production stage.”

Yim “In addition to Panoptes VM, Gauss Labs is also developing Panoptes RCA (Root Cause Analysis) and Panoptes IM (Image Metrology). Panoptes RCA identifies true causes of abnormalities during the manufacturing process and will be released early this year. Panoptes IM measures process outcomes from various images and will be released later this year. Gauss Labs will stay committed to helping field engineers with AI technology.”

The post SK hynix Deploys Gauss Labs’s AI-Based Virtual Metrology Solution to Predict Wafer Manufacturing Process Outcomes first appeared on SK hynix Newsroom.

^※ Gauss Labs is an AI software startup based in Silicon Valley, USA, founded in August 2020 with capital investment from SK hynix. In November, the company will release PANOPTES VM (Virtual Metrology), an AI-based software solution developed by the company that predicts process performance on unmeasured wafers using sensor data from semiconductor equipment and data measured through wafers. Through this, Gauss Labs is expected to be in a unique position to spearhead industrial AI innovation to the next level.

Since 2021, Gauss Labs has been offering internships to foster global talents for developing cutting-edge industrial AI solutions, and it continues to provide opportunities for growth by building on AI knowledge gained so far and applying it to projects carried out on actual industrial sites.

Positions across five roles are available for this internship opportunity: Applied Scientist (Machine Learning & Data Science), Applied Scientist (Computer Vision & Image Processing), AI Engineer, Computer Vision & Image Processing Engineer, and Software Engineer. In addition to an interview, candidates may be asked to take a coding test.

Applicants can apply until October 17 (Mon) through the Gauss Labs website (https://jobs.lever.co/gausslabs). Successful applicants will be notified individually in November. Finalists will work full-time in Seoul for 9 weeks from the end of December this year, with the option of continuing to participate in the project on a part-time basis beginning in March and during the semester. After the project is completed, those who have displayed excellent performance will be given the opportunity to intern in Silicon Valley for around 8 weeks. All lodging expenses and return flights from Seoul will be fully covered by Gauss Labs.

Mike Young-Han Kim, CEO of Gauss Labs, said, “The ‘Grow with Gauss’ global internship allows participants to gain hands-on experience working on real-world projects in the field of industrial AI. It offers infinite growth potential through mentoring from Gauss Labs members who are equipped with the world’s best AI technological skills.”

The post AI Startup Gauss Labs Recruits for Global Internship Program first appeared on SK hynix Newsroom.

In August 2020, “Gauss Labs Inc.”, a company specializing in industrial AI, was officially launched with its headquarters in Silicon Valley, U.S. SK hynix plans to invest its initial capital of USD 55 million until 2022. Gauss Labs is the first independent corporation from SK Group that focuses on AI — and reflects SK Group’s resolution to create its future value through AI.

The first task of Gauss Labs is to develop AI solutions to tackle the challenges in semiconductor manufacturing and to enhance production efficiency at SK hynix. What kind of future awaits SK hynix with these AI solutions of Gauss Labs? The SK hynix newsroom team met Young-Han Kim, CEO of Gauss Labs to talk about it in detail.

Image Download

SK’s Deep Change through AI, the Birth of “Gauss Labs”

“We should utilize innovative technologies such as AI and digital transformation (DT) to create social value, expand our market, and help our customers pursue happiness,” said Mr. Tae-won Chey, the Chairman of SK Group at SK Icheon Forum in August last year. He also emphasized his will to accelerate SK’s “Deep Change” through technological advances such as AI by saying, “If we fail to utilize innovative technologies, we cannot guarantee the future of SK.”

As AI emerged as one of the major focal points, SK Group has evaluated the possibility of establishing an independent entity specializing in AI since last year. The Group decided to make its very first move in semiconductor manufacturing, which plays a significant role on global economy in general and Korean economy in particular. With soaring manufacturing complexity from continued technology migration, cutting-edge semiconductor industry can benefit from applying AI in overall chip processing.

Image Download

CEO Kim also predicted that AI will bring a huge efficiency boost to semiconductor industry, and help SK hynix secure its unique competitiveness in the current market environment.

“SK hynix has recently signed an agreement to acquire Intel’s NAND memory and storage business, and is preparing to establish a large-scale semiconductor cluster in Yongin, South Korea. This suggests that the semiconductor business portfolio, which already accounts for a large portion of SK Group’s business, is continuously expanding. In line with this, Gauss Labs’ first mission is directed toward innovating the semiconductor manufacturing field so to respond to global market changes proactively and secure a high level of competitiveness.”

The technical challenges SK hynix is facing also influenced this decision. At the moment, the semiconductor industry around the world is facing the limitations of technology migration. Many semiconductor companies are investing in technology development to realize advanced technology that can engrave fine circuits in a small area, while struggling to improve profitability by enhancing cost competitiveness. To maximize efficiency in all these fields, the industry formed a consensus that innovative technologies such as AI should be introduced to semiconductor manufacturing processes.

“Semiconductor industry is often called “the pinnacle of precise manufacturing”. When manufacturing DRAM or NAND Flash chips, 600 to 700 process steps have to be executed, which take longer than 90 days and incur various difficult challenges. Addressing these problems, I believe, will have a great impact on the broader manufacturing industry. This is why the semiconductor sector is particularly attractive in the industrial AI field.”

AI Solutions: A Breakthrough in Overcoming the Limitations of Semiconductor Technology Migration

Gauss Labs aims to revolutionize semiconductor manufacturing by utilizing an enormous amount of data generated in the field and developing AI solutions that can maximize production efficiency. As the initial stage of this endeavor, Gauss Labs has been collaborating with the AI/DT Solution Development Team and Data Architecture Team in SK hynix’s Manufacturing Technology Division since April this year to identify major problems in the field.

Semiconductor manufacturing consists of hundreds of complex processes. To secure profitability, it is essential to improve the yield by reducing the variation in the process outcomes. To achieve this, Gauss Labs plans to make the overall semiconductor manufacturing process smarter in five thematic areas: process control, equipment maintenance, yield management, scheduling, and metrology (measurement) and inspection.

Image Download

“AI technology can also contribute to monitoring tasks, which are growing in importance as semiconductor manufacture is becoming more and more precise. Some defects on wafers that are difficult to detect with the human eyes can be easily identified by computer vision algorithms.”

The five areas set by Gauss Labs are expected to become the standards in the process of establishing a “Smart Fab” at SK hynix in the future. Regarding this, CEO Kim said, “Various divisions within the Company such as Manufacturing Technology, R&D, and Digital Transformation (DT) are working together to chart the future of SK hynix as an intelligent company. There are still many hurdles in breaking the limitations of technology migration and securing a high level of competitiveness, but overcoming these hurdles is exactly what Gauss Labs is built to accomplish.”

“To Become No.1 in the Industrial AI Field”

One of the most important missions for Gauss Labs, which has just taken its first step, to survive and thrive in the competitive market, is securing top talents in AI. Gauss Labs is planning to recruit around 20 global AI experts by the end of this year, with the goal of growing the company with 200 some scientists and engineers by 2025 at its U.S. headquarters and Korean office.

Image Download

“Gauss Labs will treat best players with the highest level of compensations they deserve. But more importantly, Gauss Labs will present them with exciting challenges their brains deserve. We believe that AI talents we are looking for have a common spirit of asking hard questions with great curiosity and discovering novel answers on their own. Semiconductor manufacturing has no shortage of difficult problems, and successful solutions have tremendous economic impacts — in a billion-dollar scale. But most importantly, working together as a team on worthwhile challenges is an invaluable opportunity for each and every one of us to grow. Gauss Labs guarantees all of these and more.”

AI services have prevailed mainly in business-to-consumer (B2C) areas until recently, but now the importance of AI is surging in business-to-business (B2B) areas including manufacturing industry. Amid this trend, Gauss Labs is drawing a big picture of becoming an AI-specialized company that encompasses SK’s manufacturing affiliates and global manufacturing companies by expanding its business with SK hynix continuously. Gauss Labs also expects that someday there will be an opportunity for an initial public offering (IPO) in the global market if its plans and goals are achieved one by one.

“The ultimate goal of Gauss Labs is to become the No. 1 company in industrial AI. IPO will be an important milestone. As our motto says, we will march on to ‘normalize AI’ in every industry.”

The post Interview with Young-Han Kim, CEO of Gauss Labs: “To Overcome Challenges in Manufacturing Industry through AI” first appeared on SK hynix Newsroom.