Powering The Future Of Flight: Designing A Hydrogen-Powered eVTOL


A large, bustling city surrounds you — crowded streets and tall buildings reaching toward the sky. You’re late for an appointment. However, instead of hopping into a car, you look above for your ride: an electric vertical takeoff and landing (eVTOL) vehicle. It is a small aircraft that takes off and lands vertically like helicopters, uses sustainable electric propulsion systems, and is inte... » read more

A Software-First Mindset for Driving Efficiency and Sustainability for Industrial IoT


Schneider Electric, Arm, and system integrators Witekio and Capgemini have produced a software-defined platform for industrial automation and energy management. The platform uses cloud-native techniques to create a flexible, energy-efficient reference design that uses virtualization to enable real-time, mixed-criticality services at the embedded edge. Read more here. » read more

Joint Interdisciplinary Work To Enable Novel, Industry-Ready Chiplet Solutions


Fraunhofer is going to establish the Chiplet Center of Excellence (CCoE), which is a unique research activity based on Fraunhofer‘s long experience and broad research portfolio in design, implementation and test of 2.5 and 3D integrated electronic systems. The Center aims at establishing a common understanding among the partners and at creating a suitable chiplet development methodology. This... » read more

Decoding Glitch Power at the RTL Stage


In the context of analyzing digital semiconductor circuits, a glitch is any unwanted or unused signal transition, or toggle. A glitch is often a transient signal that is much shorter than a clock period and therefore is not captured by the next register stage. We also encounter full transition glitches, or transport glitches, which refer to toggles in a data path circuit that cover a full clock... » read more

Real-World Applications Of Computational Fluid Dynamics


More powerful chips are enabling chips to process more data faster, but they're also having a revolutionary impact on how that data can be used. Simulations that used to take days or weeks now can be completed in a matter of hours, and multi-physics simulations that were implausible to even consider are now very much in the realm of what is possible. Parviz Moin, professor of mechanical enginee... » read more

Research Bits: Aug. 5


Measuring temperature with neutrons Researchers from Osaka University, National Institutes for Quantum Science and Technology, Hokkaido University, Japan Atomic Energy Agency, and Tokamak Energy developed a way to rapidly measure the temperature of electronic components inside a device using neutrons. The technique, called ‘neutron resonance absorption’ (NRA), examines neutrons being ab... » read more

Making Electronics More Efficient


Projections about the amount of energy required for AI in data centers and other electronic devices are putting a spotlight on more efficient electronics. But making chips and systems more efficient is an enormous challenge. It used to be as simple as turning down the voltage or moving to the next process node, but those approaches are no longer yielding the same kinds of benefits as in the pas... » read more

Where Power Savings Really Count


Experts at the Table: Semiconductor Engineering sat down to discuss why and where improvements in architectures and data movement will have the biggest impact, with Hans Yeager, senior principal engineer, architecture, at Tenstorrent; Joe Davis, senior director for Calibre interfaces and EM/IR product management at Siemens EDA; Mo Faisal, CEO of Movellus; Trey Roessig, CTO and senior vice presi... » read more

Research Bits: July 30


Embedded thermoelectric devices Researchers from the University of Pittsburgh and Carnegie Mellon University propose using locally embedded thermoelectric devices (TEDs) to perform active cooling inside circuits. “Circuits like clock generators and arithmetic and logic units (ALU) create high-frequency heat fluxes with their peak hot spots occurring on the microprocessor,” said Feng Xio... » read more

ConvNext Runs 28X Faster Than Fallback


Two months ago in our blog we highlighted the fallacy of using a conventional NPU accelerator paired with a DSP or CPU for “fallback” operations. (Fallback Fails Spectacularly, May 2024). In that blog we calculated what the expected performance would be for a system with a DSP needing to perform the new operations found in one of today’s leading new ML networks – ConvNext. The result wa... » read more

← Older posts Newer posts →