Author's Latest Posts


Blog Review: Oct. 14


Arm's Hongsup Shin explains a machine learning application that can determine which tests are most likely to find hardware bugs, improving efficiency and reducing the number of tests that need to be run. Synopsys' Pieter van der Wolf and Dmitry Zakharov take a look at the increasing need for low power processors optimized for machine learning tasks as IoT, smart home, and wearable devices pr... » read more

Power/Performance Bits: Oct. 12


More stable quantum states Researchers at the University of Chicago found a way to make quantum systems retain coherency 10,000 times longer. The fragile nature of quantum states remains a challenge for developing practical applications of quantum computing, as they can be easily disrupted by background noise coming from vibrations, temperature changes or stray electromagnetic fields. Ap... » read more

Week In Review: Design, Low Power


Arm spun out Cerfe Labs to develop and license new types of non-volatile memories based on correlated electron materials (CeRAM) and ferroelectric transistors (FeFETs). Arm CeRAM researchers will join Cerfe Labs and assume ownership of the Arm joint development project with Symetrix Corporation. Read more about the new company and its technology in Cerfe Labs: Spin-On Memory. Tools & IP ... » read more

Blog Review: Oct. 7


In a blog for Arm, University of Southampton PhD student Sivert Sliper looks at how energy-driven and intermittent computing could be used to power trillions of IoT devices and introduces a SystemC-based simulator for such systems. Mentor's Chris Spear explains why transaction classes should extend from uvm_sequence_item rather than uvm_transaction when designing UVM testbenches. Cadence'... » read more

Power/Performance Bits: Oct. 6


Waste plastic supercapacitor Researchers from the University of California Riverside found a way to recycle waste plastic into energy storage devices. The work focused on polyethylene terephthalate plastic waste, or PET, which is found in soda bottles and many other consumer products. The researchers first dissolved pieces of PET plastic bottles in a solvent. Using electrospinning, they fab... » read more

Week In Review: Design, Low Power


Arteris IP will acquire the assets of Magillem Design Services, combining Arteris' NoC interconnect IP with Magillem's chip design and assembly environment. Magillem’s software products will continue to be offered separately from the Arteris interconnect IP offerings and the joined company will continue to execute on Magillem’s existing product and technology roadmaps. Substantially all Mag... » read more

Startup Funding: September 2020


It was a good month for startups, with big rounds in automotive, data centers, and AI. A new startup with big backing is taking aim at energy inefficiency in the data center, and another is looking to make the industrial IoT battery-free. SK Hynix founded a new company to analyze semiconductor manufacturing data, and one of China's EV companies sees a massive cash infusion. This month, we look ... » read more

Blog Review: Sept. 30


Synopsys' Fred Bals takes a look open source projects that, while popular, go understaffed or underfunded, how that can lead to potential security vulnerabilities, and why users who rely on them should consider stepping up to contribute. In a video, Mentor's Colin Walls explains the basic concepts of multicore systems as it relates to embedded programming. Cadence's Paul McLellan ponders ... » read more

Power/Performance Bits: Sept. 29


Implantable transmitter Researchers from Purdue University developed a fully implantable, wirelessly powered 2.4GHz radio-frequency transmitter chip for wireless sensor nodes and biomedical devices. The team says the transmitter chip consumes the lowest amount of energy per digital bit published to date, consuming an active-mode power of 70 μW at 10 Mbps while radiating -33 dBm of power, r... » read more

Week In Review: Design, Low Power


Tools & IP Arm added two new platforms to its product roadmap: the Neoverse V1, and the Neoverse N2, the second-generation N-series platform. The V1 platform supports Scalable Vector Extensions (SVE), provides 50% better single-threaded performance over N1, and targets high-performance cloud, HPC, and machine learning applications. The N2 provides 40% higher single-threaded performance com... » read more

← Older posts Newer posts →