2021 Top Tech Videos

What engineers were watching in 2021.


While the world’s chip shortage dominated the 2021 headlines, the semiconductor industry blazed new trails with the increased electrification of cars, focused AI applications, improving power/performance, better utilization of data deluges, dealing with design challenges in advanced nodes and much more focus on chip security.

Semiconductor Engineering’s Tech Talks reflected these focus areas. Of the videos published in 2021, here are the highlights from our channel areas:

Low Power- High Performance
Improving Power & Performance Beyond Scaling discusses architectural changes inside of servers and data centers to allow pooling of resources such as memory. That has a big impact on power efficiency and overall performance, but it also allows data centers to customize their architectures and prioritized resources with much more granularity than they can do today.
Low-Power Always-On Circuits looks at “always on” devices and the challenge to make sure these devices don’t consume a lot of power while the rest of a device is powered down, that it remains secure, and that it can quickly wake up whatever other functions are needed.
Problems In The Power Grid examines needs to be done to fix the power grid, particularly as more cars are electrified and more electronic devices are mobile.
Changes in Sensors And DSPs talks about why processing is moving closer to the end point, how to save energy through reduced area and sensor fusion, and the impact of specialization, 3D capture and always-on circuits.
Data Overload In The Data Center discusses which architectures and interfaces work best for different applications.

Systems & Design
Working With RISC-V looks at what’s available, what’s missing, and what’s next.
Better Quality RTL talks about identifying bugs, improving the overall quality of the verification, what happens when different blocks are used in a design, and how to improve efficiency in the verification process.
Next-Gen SerDes Roadmap digs into the performance roadmap for moving data within server racks and between different racks, where the bottlenecks are today, and how they will be addressed in the future.
EDA In The Cloud discusses the benefits of moving EDA tools to the cloud, why it has been slow to take off, and what will drive this trend in the future.
Next-Gen Design Challenges digs into the intersection of scale complexity and systemic complexity, the rising number of corners, and the reduced margin with which to buffer a slew of physical effects.
1.6 Tb/S Ethernet Challenges talks about the impact of next-generation Ethernet on switches, the types of data that need to be considered, the causes of data growth, and the size and structure of data centers, both in the cloud and at the edge.

Manufacturing, Packaging & Materials

What’s Changing In DRAM looks at the impact of shrinking features and increasing density, including variation, thermal effects and aging, as well as effects such as micro-loading and DRAM stacking.
Open Cavity Plastic Packaging talks about why it’s so important to use existing package footprints, what are the challenges in replacing the circuitry inside a package, and which markets are clamoring for this approach.
Changing The Rules For Chip Scaling discusses the incessant drive for chip density, how to improve that density through other means than just scaling, and why this is so important for the chip industry.

Test, Measurement & Analytics
Growing Challenges With Wafer Bump Inspection talks about the shift toward middle-of-line and how that is affecting inspection and metrology, why there is so much concern over co-planarity and alignment, how variation can add up and create reliability and yield issues, how much inspection is considered sufficient, and how the data collected from inspection is used.
Design For Test Data looks at a subtle but significant shift for designing testability into chips so that test data can be used at multiple stages during a device’s lifetime.
Optimizing AI Systems talks about what’s changed and how to optimize these new devices and systems by monitoring them from within.
Total Critical Area For Optimizing Test Patterns advises why it’s so important to predict where defects are most likely to occur in these designs, and how to optimize test patterns to be able to quickly target those areas with test.
Monitoring Performance From Inside A Chip talks about using data to identify potential problems before they result in failures in the field, and why it’s essential to monitor these devices throughout their expected lifetimes.

Automotive, Security & Pervasive Computing
Radiation Hardening Chips For Outer Space talks about different striations in the Earth’s atmosphere, how those various levels can affect radiation, and what impact that has on the functionality of increasingly dense chip circuits over extended periods of time.
End-To-End Traceability looks at how to deal with gaps that can impact reliability.
Sensor Fusion Everywhere examines what types of sensors are being developed, what happens when different sensors are combined, what those sensors are being used for today, and what they will be used for in the future.
Dynamically Reconfiguring Logic explains why this capability has been so difficult to utilize, what’s changed, how a soft logic layer can be used to control when to read, compute, steer, and write data back to memory, and to optimize performance and behavior for a particular application or use case, and how to program these devices.
Network Interface Card Evolution looks at minimizing the impact of shifting bottlenecks in the data flow.
Customized Micro-Benchmarks For HW/SW Performance talks about why companies need to develop and utilize their own specific models to accurately gauge hardware and software performance, which can be slowed by bottlenecks in I/O and across different convolution layers.

Securing ICs With Information Flow Analysis looks at tracking how data moves is essential for secure designs.
Security In FPGAs And SoCs. Chip security is becoming a bigger problem across different markets, with different emerging standards and more sophisticated attacks. This tech talk looks at current and future threats and what can be done about them.
Creating IoT Devices That Will Remain Secure examines the impact of security on IoT adoption, why resilience across a system is the new target for secure designs, and how to minimize the impact of less secure devices.
Changes In Auto Architectures looks at the different levels of automation in a vehicle, what’s involved in the shift from domain to zonal architectures, why a mix of processors will be required, and how these systems will handle, store, partition, and prioritize data.
Making Lidar More Useful discusses problems and potential solutions in assisted and autonomous vehicle technology.
Shifting Auto Architectures talks about how automotive applications are changing, what that means for engineering teams, and how they will shift as AI is increasingly deployed.

Using ML In EDA. Why this is becoming a requirement for designing complex chips.
Safe And Robust Machine Learning examines security implications on both the inferencing and training side, the potential for disruptions to accuracy, and how accessible these models and algorithms will be when they are used at the edge and in the cloud.
Configuring AI Chips talks about the need for flexible architectures to deal with continual modifications in algorithms, more complex convolutions, and unforeseen system interactions, as well as the ability to apply all of this over longer chip lifetimes.

For more Semiconductor Engineering videos, check out the full list in our YouTube channel here, or deep-dive into more technology topics in our Knowledge Center, the index for the site.

Interested in a topic not covered? We would like to hear from you ([email protected]).

Leave a Reply

(Note: This name will be displayed publicly)