Neuromorphic vision project; computational lithography; fluid mechanics; 112G SerDes.
Codasip’s Tora Fridholm introduces the NimbleAI project, an effort to design a neuromorphic sensing and processing 3D integrated chip that implements an always-on sensing stage, highly specialized event-driven processing kernels and neural networks to perform visual inference of selected stimuli using the bare minimum amount of energy.
Synopsys’ Anjaneya Thakar discusses computational lithography, optical proximity correction, and Nvidia’s recently announced cuLitho software library that enables mask synthesis software to run on GPUs.
Siemens’ Simon Fischer takes a lighthearted look at the history of fluid mechanics along with the innovations and some key people that enabled modern computational fluid dynamics.
Cadence’s Paul McLellan points to some new challenges for designing 112G extended long reach SerDes PHYs, such as the shift to PAM4 signaling, and the markets it targets.
Ansys’ Nathan Blattau explains the importance of adding the appropriate underfills and adhesives to PCBs to ensure that components can survive aggressive mechanical shock, drop, vibration, and temperature cycling events.
Keysight’s Anubhab Sahu looks into the network communications that happens in the background while people wait for ChatGPT to respond to their questions and investigates the hostnames that it uses, custom HTTP headers, and its API traffic.
SEMI’s Ashley Huang checks in on efforts to reduce carbon emissions of the semiconductor industry and the double-edged sword of advanced manufacturing producing lower-power chips while consuming more to make them.
Arm’s Laura Armitstead details recent updates to the Cortex-M23 processor that add enhanced capabilities for safety-critical automotive applications, such as transient fault protection for devices that are too area and cost sensitive for a where a dual-core lockstep approach, as well as interface protection for the detection of faults at the boundary of the CPU.
Plus, check out the blogs featured in the latest Manufacturing, Packaging & Materials newsletter:
Technical Editor Katherine Derbyshire digs into resistive RAM switching with Frenkel pairs.
Coventor’s Timothy Yang compares a physical vapor deposition and ion beam etch method to conventional trench etch followed by damascene deposition.
SEMI’s Bettina Weiss points out that while planning for the long term is important, so is the ability to quickly adjust to disruptions.
Synopsys’ Guy Cortez shows the value of integrating data from design through manufacturing in a single platform when sleuthing why parts fail at final test.
Leave a Reply