Blog Review: May 6

Quantization and algorithms; remote security; 1G.


In a blog for Arm, Javier Fernandez-Marques of Oxford University digs into how to make the best use of quantized neural network models and why it’s so important to consider what algorithms will be running when deciding which model architecture to implement, and which quantization strategy to adopt for the model.

Synopsys’ Taylor Armerding explains why, with a largely remote workforce, it may be time to consider a red team assessment: hiring ethical hackers to help find security vulnerabilities in the organization before someone else does.

Mentor’s Chris Spear shows how to make a variable that can be accessed across multiple classes and solves potential naming problems in SystemVerilog.

Cadence’s Paul McLellan looks back at the history of mobile, starting with ‘1G’ analog, radio interference, and the first cell phone service in the world.

Ansys’ Harish Radhakrishnan explains the science behind adhesives, why some surfaces stick together, and why it’s an important property for materials design.

SEMI’s Nishita Rao chats with Thomas Sonderman of SkyWater Technology, a fab making microfluidic MEMS used in COVID-19 testing and research to identify mutations of the virus.

For a change from reading, check out some of our latest videos:

Carmakers and their suppliers compete for dominance, creating challenges across the electronics industry, in Who Owns A Car’s Chip Architecture.

Using Big Data For Yield And Reliability explores what is required to ensure chips will work as expected.

DDR PHY Training takes a look at keeping DRAM in sync with changing product specs and market shifts.

Different applications require very different process architectures, in Stream Vs. Pool Data Processing.

Last-Level Cache improves performance with more on-chip data storage.

Tackling a big bottleneck inside of data centers calls for a PCIe 5.0 Drill-Down.

Leave a Reply

(Note: This name will be displayed publicly)