Blog Review: May 15

Optimizing with HLS; threat modeling; cybersecurity and government.

popularity

Cadence’s Sean Dart shares an example of the kind of optimizations HLS tools can perform that would be difficult to find and implement by hand-coding RTL.

Synopsys’ Taylor Armerding takes a look at three cybersecurity initiatives from the U.S. government, from an IoT bill to improved voting machines, and whether they’re likely to work.

In a video, Mentor’s Colin Walls points to why flashing an LED can be used as a way to indicate the health of an embedded system.

Arm’s Suresh Marisetty argues that threat modeling should be an important part of designing and deploying both devices and software along with a guide for how to put it into practice.

UltraSoC’s Jo Windel shares highlights from the recent Bristol RISC-V Meetup, including the challenges of using RISC-V for cryptographic workloads and an effort to develop an alternative.

A Rambus writer notes a DARPA project to develop new hardware security architectures and tools that provide security against hardware vulnerabilities.

PNI Sensor’s Becky Oh takes a look at the ways sensors and the IoT can work to improve the often poor parking situation in cities.

NXP’s Andrew Birnie considers how ECUs and MCUs are adapting to the unique needs of electrified vehicles and where a system-in-package approach can work.

And don’t miss the blogs highlighted in last week’s Low Power-High Performance newsletter:

Editor In Chief Ed Sperling argues that while new processors will be blazing fast, that doesn’t guarantee improvements in system speed.

Synopsys’ Jim Schultz explains why the requirements of advanced process nodes call for a closer look at an often-overlooked design step.

Rambus’ Shawn Nikoukary says advanced extraction tools and accurate models are key to a successful GDDR6 implementation.

Mentor’s Harry Foster questions whether increased verification effort pays off.

SEMI’s Lara Chamness looks at what’s behind the surge in photomask revenues.

Flex Logix’s Geoff Tate explains how to build an inference chip on the edge.

Mentor’s Diana Dearin clues us in to things to think about before and at DAC.

Rambus’ Ben Levine explains why it’s problematic when different applications from different entities run in the same secure domain.

ClioSoft’s Ranjit Adhikary says that it is no longer feasible to manage design data in ad hoc, home-grown ways.

Arm’s Rhonda Dirvin warns that continued expansion of edge devices calls for new ways to expand compute capabilities.



Leave a Reply


(Note: This name will be displayed publicly)