中文 English

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. » 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

Security In FPGAs And SoCs


Chip security is becoming a bigger problem across different markets, with different emerging standards and more sophisticated attacks. Jason Moore, senior director of engineering at Xilinx, talks with Semiconductor Engineering about current and future threats and what can be done about them. » read more

Securing ICs With Information Flow Analysis


Following the data has new meaning when it comes to security. Alric Althoff, senior hardware security engineer at Tortuga Logic, talks about tracking the flow of data through a hardware design over time, including what happens with roots of trust, how this works with existing tools and methodologies, and what to think about when tracing potential security risks. » read more

IP Safe Enough To Use In Cars


IP that is used for functional safety needs to respond to events that can happen, whether those are planned or random. Jody Defazio, vice president of IP quality and functional safety at Synopsys, talks with Semiconductor Engineering about ASIL compliance, what the different levels mean, and the impact of using chips developed at the most advanced process nodes in automotive applications. » read more

Faster Inferencing At The Edge


Cheng Wang, senior vice president of engineering at Flex Logix, talks about inferencing at the edge, what are some of the main considerations in designing and choosing an inferencing chip, why programmability and modularity are important, and how hardware-software co-design with algorithms can improve performance and power. » read more

AI Inference Acceleration


Geoff Tate, CEO of Flex Logix, talks about considerations in choosing an AI inference accelerator, how that fits in with other processing elements on a chip, what tradeoffs are involved with reducing latency, and what considerations are the most important. » read more

← Older posts