Week In Review: Auto, Security, Pervasive Computing


Automotive The U.S. Federal Trade Commission (FTC) sued Nvidia to block the company’s $40 billion acquisition of Arm. The FTC said in a press statement that “the proposed vertical deal would give one of the largest chip companies control over the computing technology and designs that rival firms rely on to develop their own competing chips. … the combined firm would have the means and in... » read more

Startup Funding: November 2021


There's nothing virtual about the level of interest in AR/VR startups. As the concept of the 'metaverse' becomes more widespread with Nvidia's recent GTC announcements and Facebook's rebranding, investors poured money into startups with enabling technology for augmented, virtual, and extended reality. Most of those are developing waveguides and other display technology that is light enough to b... » read more

Blog Review: Nov. 17


In a podcast, Arm's Geof Wheelwright and Hilary Tam chat about the importance of efforts to decarbonize compute and how low-power compute can help ensure that the benefits of technology outweigh the environmental cost. Synopsys' Graham Allan and Vikas Gautam consider what's driving demand for HBM3, what's different from the previous HBM2E specification, unique design considerations, and how ... » read more

Week In Review: Design, Low Power


Infineon reported fourth quarter 2021 financial results with revenue of €3.0 billion (~$3.4 billion), up 21% compared to the same quarter last year. For the full year, revenue was €11.1 billion (~$12.7 billion), an increase of 29% from the previous year. "In light of the continued high demand for semiconductors needed for the energy-efficient, connected world, we expect the 2022 fiscal year... » read more

Blog Review: Nov. 3


In a blog for Arm, Matthew Griffin of the 311 Institute warns that cybersecurity is an increasingly pressing problem, with large criminal organizations raking in large sums of money and attacks able to impact a wide range of physical systems. Cadence's Paul McLellan checks out Google's video encoder chip and how it helps lower the CPU recycles required by the vast number of videos uploaded t... » read more

What’s Next For Transistors And Chiplets


Sri Samavedam, senior vice president of CMOS Technologies at Imec, sat down with Semiconductor Engineering to talk about finFET scaling, gate-all-around transistors, interconnects, packaging, chiplets and 3D SoCs. What follows are excerpts of that discussion. SE: The semiconductor technology roadmap is moving in several different directions. We have traditional logic scaling, but packaging i... » read more

Week In Review: Design, Low Power


Nvidia acquired Oski Technology. Oski provides formal verification methodologies and consulting services, and Nvidia said that the acquisition will allow it to increase its investment in formal verification strategies. Oski's Gurugram, India, design center will become Nvidia's fourth engineering office in the country. Based in San Jose, Calif., it was founded in 2005. Terms of the deal were not... » read more

Week In Review: Auto, Security, Pervasive Computing


Automotive Synopsys and 3D virtual-environment company Dassault Systèmes are collaborating on an automotive lighting system development platform. Synopsys’ optical design tools — LucidShape, LightTools, and CODE V — will be integrated with Dassault Systèmes' 3DEXPERIENCE Platform, which is used by automotive teams from different disciplines to work together on designs and simulations. ... » read more

Blog Review: Oct. 13


Cadence's Paul McLellan checks out what Google learned in developing multiple generations of its TPU processor, including unequal advancement of logic and memory, the importance of compiler of compatibility, and designing for total cost of ownership. Siemens EDA's Jake Wiltgen argues for the importance of linting as part of eliminating systematic failures in designs complying with ISO 26262.... » read more

Blog Review: Oct. 6


Arizona State University's Jae-sun Seo and Arm's Paul Whatmough introduce a fully-parallel and fully-pipelined FPGA accelerator for sparse CNNs that can eliminate off-chip memory access and also efficiently support elementwise pruning of CNN weights. Cadence's Paul McLellan highlights trends seen at the recent Hot Chips, from machine learning and advanced packaging driving higher performance... » read more

← Older posts Newer posts →