Chip Industry Week In Review


Amkor will provide turnkey advanced packaging and test services to TSMC in Amkor's planned facility in Peoria, Arizona, in a deal announced on Thursday. The companies jointly specified the packaging technologies, such as TSMC’s Integrated Fan-Out (InFO) and Chip on Wafer on Substrate (CoWoS). President Biden signed into law a bill that exempts some semiconductor projects funded by the U.S.... » read more

Chip Industry Week In Review


By Jesse Allen, Liz Allan, and Gregory Haley A potential government shutdown beginning in November would be "massively disruptive" for the Commerce Department as it continues to disburse critical funding featured in the CHIPS Act to boost semiconductor research and development in the U.S., according to Secretary Gina Raimondo. Global semiconductor industry sales totaled $44 billion in Aug... » read more

Week In Review: Design, Low Power


Arm is expected to list solely on a U.S. stock exchange when it goes public again later this year, forgoing the London Stock Exchange for now, the BBC reports. Global investment banks expect the offering to value the company between $30 billion and $70 billion, according to Bloomberg. Disaggregating chips into specialized processors, memories, and architectures is becoming necessary for cont... » read more

Week In Review: Manufacturing, Test


The more than 1,400 attendees at this week’s IEDM, which celebrated the 75th anniversary of the transistor, were clearly focused on making the next 75 years of semiconductors even more remarkable than the last. Intel, Samsung, TSMC, STMicroelectronics, GlobalFoundries and imec announced breakthrough devices, materials, and even integration approaches. These included: Intel showcased adva... » read more

Week In Review: Auto, Security, Pervasive Computing


Automotive, mobility Cadence is now an official technology partner of the McLaren Formula 1 Team. The team will use Cadence’s Fidelity CFD Software to look at the computational fluid dynamics (CFD) of the airflow around the race cars and predict how a car design will affect the airflow. Infineon uncorked its XENSIV 60 GHz automotive radar sensor for in-cabin monitoring systems. One use ca... » read more

Easier And Faster Ways To Train AI


Training an AI model takes an extraordinary amount of effort and data. Leveraging existing training can save time and money, accelerating the release of new products that use the model. But there are a few ways this can be done, most notably through transfer and incremental learning, and each of them has its applications and tradeoffs. Transfer learning and incremental learning both take pre... » read more

11 Ways To Reduce AI Energy Consumption


As the machine-learning industry evolves, the focus has expanded from merely solving the problem to solving the problem better. “Better” often has meant accuracy or speed, but as data-center energy budgets explode and machine learning moves to the edge, energy consumption has taken its place alongside accuracy and speed as a critical issue. There are a number of approaches to neural netw... » read more

Developers Turn To Analog For Neural Nets


Machine-learning (ML) solutions are proliferating across a wide variety of industries, but the overwhelming majority of the commercial implementations still rely on digital logic for their solution. With the exception of in-memory computing, analog solutions mostly have been restricted to universities and attempts at neuromorphic computing. However, that’s starting to change. “Everyon... » read more

Blog Review: May 5


Arm's William Wang considers how to increase the performance and programmability of persistent applications through using battery to protect the on-chip volatile cache hierarchy. Cadence's Paul McLellan finds that ransomware is getting more sophisticated, and more difficult to eradicate and defend against, with potentially life-threatening consequences. Synopsys' Jonathan Knudsen digs int... » read more

Edge-Inference Architectures Proliferate


First part of two parts. The second part will dive into basic architectural characteristics. The last year has seen a vast array of announcements of new machine-learning (ML) architectures for edge inference. Unburdened by the need to support training, but tasked with low latency, the devices exhibit extremely varied approaches to ML inference. “Architecture is changing both in the comp... » read more

← Older posts