Blog Review: Oct. 10

Neural network sparsity; memory slowdown possible; efficient code.

popularity

In a video, Cadence’s Megha Daga dives into sparsity in neural networks and how it affects bandwidth, performance, and power efficiency.

In a video, Mentor’s Colin Walls takes a look at efficient embedded code, and why that means different things at different times.

Synopsys’ Eric Huang argues that in the realm of video standards, HDMI, DisplayPort, and USB Type-C are set to continue competing for a long time.

SEMI’s Clark Tseng and Sungho Yoon examine the future of the memory market and whether we’re headed for a slowdown with a look at the top three memory suppliers’ inventory and memory fab equipment investments.

A National Instruments writer highlights four key trends impacting radar technology, from gallium nitride components to higher bandwidth data buses for sensor fusion.

Industry blogger Stewart Randall digs into the initial Chinese reaction to accusations of implanting spy chips in servers and whether it’s becoming a dangerous time for China’s electronics manufacturing industry.

ANSYS’ Shawn Wasserman points to how computational fluid dynamics were used in creating a new medical implant for treatment of pancreatic cancer.

Arm’s Thomas Kurian checks out the ways IoT, and Bluetooth Low Energy beacons in particular, is changing how inventory and supply chains are managed.

Intel’s Todd Garrigues points to a new survey gauging the general feelings consumers have for technology and which areas they find the most exciting.

Plus, check out the featured blogs from the latest IoT, Security & Automotive and Packaging, Test & Materials newsletters:

Editor In Chief Ed Sperling contends that putting complex algorithms into billions of things radically changes the landscape.

Executive Editor Ann Steffora Mutschler observes that meeting OEM requirements for safety includes a human component as well as technology changes.

Mentor’s Andrew Macleod finds that while the basics of design remain the same, automotive ICs rely more heavily on advanced tools.

Rambus’ Nisha Amshul argues that the IoT cannot rely solely upon security practices designed for conventional devices.

ClioSoft blogger Anand Shirahatti points to a gap between the reality and the promise of simplicity and low engineering cost for mature IP.

Achronix’s Alok Sanghavi explains why closing timing in an eFPGA takes multiple designers, making a defined methodology important.

Synopsys’ Manuel Mota digs into creating functional safety through redundancy when implementing ADCs.

Editor In Chief Ed Sperling contends that new materials, applications and packaging are changing the economics of testing chips.

Technical Editor Katherine Derbyshire finds many companies have requirements that don’t fit neatly into the CMOS roadmap.

Kandou’s Jeff McGuire digs into how to push toward the Shannon signaling capacity using less energy.

Advantest’s Judy Davies observes that AI is here, and it’s already helping to make lives better.



Leave a Reply


(Note: This name will be displayed publicly)