Author's Latest Posts


Using Memory Differently To Boost Speed


Boosting memory performance to handle a rising flood of data is driving chipmakers to explore new memory types and different ways of using existing memory, but it also is creating some complex new challenges. For most of the semiconductor design industry, memory has been a non-issue for the past couple of decades. The main concerns were price and size, but memory makers have been more than a... » read more

Material Choices In Printed Temperature Sensors


Vijaya Kayastha, lead device development engineer at Brewer Science, talks about what’s needed for printed temperature sensors, what happens when there are impurities in the materials, how these sensors respond to stress, and how costs compare to traditional sensors. » read more

In Memory And Near-Memory Compute


Steven Woo, Rambus fellow and distinguished inventor, talks about the amount of power required to move store data and to move it out of memory to where processing is done. This can include changes to memory, but it also can include rethinking compute architectures from the ground up to achieve up to 1 million times better performance in highly specialized systems. Related Find more ... » read more

The Danger Of Twin Supply Chains


No matter how the ongoing dispute between the United States and China turns out, damage already has been done. It's not the kind of damage that is immediately visible to the outside world. It's more of the long-term, policy-shift kind of problem, which over time will likely prove much worse. Many executives have termed recent sanctions on Huawei and other Chinese companies "China's Sputnik m... » read more

Memory In Microcontrollers


Gideon Intrater, CTO of Adesto, talks about how to use microcontrollers for applications where more memory is required, such as automotive, communication, and AI at the edge. Options include moving MCUs toward a more aggressive process node, adding external non-volatile memory, and execute-in-place types of architectures. » read more

Where 5G Works, And Where It Doesn’t


The rollout of 5G hype has begun. Companies are building 5G chipsets for mobile devices, and they are working on the infrastructure that will allow massive amounts of data to move freely between devices. There is little doubt that more bandwidth is required everywhere. Files are growing in size, particularly with streaming video and images and various flavors of AI and machine learning. This... » read more

How To Improve ML Power/Performance


Raymond Nijssen, vice president and chief technologist at Achronix, talks about the shift from brute-force performance to more power efficiency in machine learning processing, the new focus on enough memory bandwidth to keep MAC functions busy, and how dynamic range, precision and locality can be modified to improve speed and reduce power. » read more

Inferencing Efficiency


Geoff Tate, CEO of Flex Logix, talks with Semiconductor Engineering about how to measure efficiency in inferencing chips, how to achieve the most throughput for the lowest cost, and what the benchmarks really show. » read more

Paving The Way To Autonomous Driving


Over the past couple weeks, four major carmakers began pairing off to jointly develop autonomous vehicles. Numerous reports say Ford will sign a deal with Volkswagen, and BMW is working on Level 4 self-driving vehicles with Daimler, the parent of Mercedes Benz. While this speaks volumes about the enormous cost of developing artificial intelligence systems to drive vehicles, it also points th... » read more

Big Shifts In Big Data


The big data market is in a state of upheaval as companies begin shifting their data strategies from "nothing" or "everything" in the cloud to a strategic mix, squeezing out middle-market players and changing what gets shared, how that data is used, and how best to secure it. This has broad implications for the whole semiconductor supply chain, because in many cases it paves the way for ... » read more

← Older posts