Using ML In EDA


Machine learning is becoming essential for designing chips due to the growing volume of data stemming from increasing density and complexity. Nick Ni, director of product marketing for AI at Xilinx, examines why machine learning is gaining traction at advanced nodes, where it’s being used today and how it will be used in the future, how quality of results compare with and without ML, and what... » read more

Changes In Auto Architectures


Automotive architectures are changing from a driver-centric model to one where technology supplements and in some cases replaces the driver. Hans Adlkofer, senior vice president and head of the Automotive Systems Group at Infineon, 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... » read more

Sensor Fusion Everywhere


How do you distinguish between background noise and the sound of an intruder breaking glass? David Jones, head of marketing and business development for intuitive sensing solutions at Infineon, looks at 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. » read more

Safe And Robust Machine Learning


Deploying machine learning in the real world is a lot different than developing and testing it in a lab. Quenton Hall, AI systems architect at Xilinx, 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. This involves everything ... » read more

Dynamically Reconfiguring Logic


Dynamic reconfiguration of semiconductor logic has been possible for years, but it never caught on commercially. Cheng Wang, co-founder and senior vice president of software and engineering at Flex Logix, 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 ... » read more

Making Lidar More Useful


Lidar, one of a trio of “vision” technologies slated for cars of the future, is improving both in terms of form and function. Willard Tu, director of automotive at Xilinx, talks with Semiconductor Engineering about different approaches and tradeoffs between cost, compute intensity and resolution, various range and field of view options, and why convolutional neural networks are so important... » read more

Configuring AI Chips


Change is almost constant in AI systems. Vinay Mehta, technical product marketing manager at Flex Logix, 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. Related Dynamically Reconfiguring Logic A differ... » read more

Shifting Auto Architectures


Domain controllers and gateways are being replaced by central processing modules and zonal gateways to handle all of the data traffic in a vehicle. Ron DiGiuseppe, automotive IP segment manager at Synopsys, talks with Semiconductor Engineering about how automotive applications are changing, what that means for engineering teams, and how they will shift as AI is increasingly deployed. » read more

Network Interface Card Evolution


Longer chip lifetimes, more data to process and move, and a slowdown in the rate of processor improvements has created a series of constantly shifting bottlenecks. Kartik Srinivasan, director of data center marketing at Xilinx, looks at one of those bottlenecks, the network interface card, why continuous enhancements and changes will be required, and how to extend the life of NICs as the networ... » read more

Customized Micro-Benchmarks For HW/SW Performance


Raw performance used to be the main focus of benchmarks, but they may have outlived their usefulness for many applications. Dana McCarty, vice president of sales and marketing for AI Inference Products at Flex Logix, 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... » read more

← Older posts Newer posts →