Agentic AI In Chip Manufacturing


Agentic AI — breaking AI into individual agents that can work together and collaboratively — will be the real game changer for AI in chip manufacturing. By taking humans out of the loop, these agents can be programmed using natural language to automatically solve problems and improve efficiency. Jon Herlocker, vice president and general manager of software analytics at Cohu, talks  about w... » read more

Reliability And Traceability In Advanced Packages


The move from planar SoCs to advanced packages can improve performance and provide flexibility in large designs, which are difficult to fit onto a single reticle-sized die. But ensuring the device works as expected remains a challenge. There are multiple packaging options to choose from — 2.5D, fan-out wafer-level packaging, 3D-ICs, and various types of system-in-package — and many possible... » read more

Generative AI In Chip Manufacturing


Generative AI is a natural-language or text-based query, predicting patterns based on a massive set of data. While most of the attention has been focused on chatbots and copilots, it also can be used to identify small, transient aberrations in semiconductor manufacturing that are otherwise difficult to find. Jon Herlocker, vice president and general manager of software analytics at Cohu, talks ... » read more

AI-Driven Collaboration In Chip Manufacturing


3D chips and multi-die assemblies can offer significant improvements in performance and power, but the tradeoff is the increased amount of time and money it takes to generate working silicon. There are more process steps, more interactions between processes, and more data to manage throughout the manufacturing flow — so much, in fact, that it has now reached well beyond what even the best eng... » read more

Challenges In Testing Photonics In Chips


The semiconductor industry has spent decades improving reliability and consistency by standardizing when and how to test it, how to collect critical data from those tests, and what to do with that data. But electrical test data is very different from silicon photonics, which is being bundled into these SoCs and multi-die assemblies alongside traditional electrical components. Aftkhar Aslam, CEO... » read more

Advanced Process Control In Semiconductor Manufacturing


Fifth in a seven-part series: Advanced process control for semiconductor wafers is evolving in ways that can significantly improve yield and reduce scrap. As dimensions shrink, the need to improve manufacturing processes and reduce variability requires more precision. "Classic" APC was a step in the right direction, identifying problems in a process chamber, for example, and automating adjustme... » read more

Using AI/ML To Find And Correlate IC Test Data


What causes low yield in wafers? Usually it's due to design or process changes, but sometimes yield issues occur even if there haven't been any changes from one manufacturing lot to the next. Finding the cause requires some sleuthing, and the best approach for pinpointing problems is to mine design, process, and manufacturing data, and to correlate that data by date and time, by which equipment... » read more

Virtual Metrology In Semiconductor Manufacturing


Fourth in a seven-part series: Virtual metrology may never be 100% perfect because of the almost unlimited number of changes in a fab tools and the unique chip and wafer designs they're being used to process. But there are places where virtual metrology does make sense. Jon Herlocker, vice president and general manager of software analytics at Cohu, talks about why virtual metrology will never ... » read more

Virtual Twins: Layers Of Challenges


Virtual twins can provide deep insights into complex systems at any point in time, but creating them requires integrating a stack of abstractions that don't naturally go together. One abstraction may be mechanical, another electrical, and the data used to create those abstraction layers needs to be fused together logically and updated over time. David Fried, corporate vice president at Lam Rese... » read more

Using AI For Fault Detection And Classification In Manufacturing


Third in a seven-part series: Classic fault detection and classification has some classic problems. It's reactive, time-consuming to set up, and any product change involves significant man-hours. Even then, it still misses a lot of problems, which result in scrap. This is where machine learning can excel, because it can sift through huge amounts of data from thousands of sensors and find outlie... » read more

← Older posts