Chip Industry Week In Review

By The SE Staff - 11 Apr, 2025 - Comments: 0

Don't have time to read this? Check out Semiconductor Engineering's Inside Chips podcast. The U.S. Department of Commerce is investigating TSMC for potential export control violations involving Huawei chips, reports Reuters. The probe follows TechInsights' teardown of a Huawei AI accelerator chip last year. The foundry, meanwhile, maintains it has not shipped any chips to Huawei since 2020... » read more

Implementing AI Activation Functions

By Bryon Moyer - 10 Apr, 2025 - Comments: 0

Activation functions play a critical role in AI inference, helping to ferret out nonlinear behaviors in AI models. This makes them an integral part of any neural network, but nonlinear functions can be fussy to build in silicon. Is it better to have a CPU calculate them? Should hardware function units be laid down to execute them? Or would a lookup table (LUT) suffice? Most architectures inc... » read more

Transforming The Semiconductor Industry: Future Roadmap For Generative AI On The Edge

By Expedera - 09 Apr, 2025 - Comments: 0

In the third of a three-part series, Expedera, in conjunction with the Global Semiconductor Alliance’s Emerging Technologies (EmTech) group explores “Transforming the Semiconductor Industry: Future Roadmap for Generative AI on the Edge”. This white paper explores key applications for Generative AI and the features they enable, as well as an examination of how model growth and differing mo... » read more

Unlocking Generative AI On The Edge Across The Semiconductor Value Chain

By Expedera - 12 Mar, 2025 - Comments: 0

In the second of a three-part series, Expedera, in conjunction with the Global Semiconductor Alliance’s Emerging Technologies (EmTech) group, explores “Unlocking Generative AI on the Edge across the Semiconductor Value Chain”. Included in this white paper is an examination of how members of the value chain (including IP providers, EDA vendors, fabless chip makers, foundries, OSATs, OEMs, ... » read more

Normalization Keeps AI Numbers In Check

By Bryon Moyer - 13 Feb, 2025 - Comments: 0

AI training and inference are all about running data through models — typically to make some kind of decision. But the paths that the calculations take aren’t always straightforward, and as a model processes its inputs, those calculations may go astray. Normalization is a process that can keep data in bounds, improving both training and inference. Foregoing normalization can result in at... » read more

The Impact of Generative AI on the Edge for the Semiconductor Industry

By Expedera - 12 Feb, 2025 - Comments: 0

In the first of a three-part series, Expedera, in conjunction with the Global Semiconductor Alliance’s Emerging Technologies (EmTech) group, explores “The Impact of Generative AI on the Edge for the Semiconductor Industry”. In this white paper, the working group explores the evolution of Generative AI (GenAI), and how the rapidly evolving semiconductor industry can enable GenAI innovation... » read more

What’s The Best Way To Sell An Inference Engine?

By Bryon Moyer - 16 Jan, 2025 - Comments: 0

The burgeoning AI market has seen innumerable startups funded on the strength of their ideas about building faster, lower-power, and/or lower-cost AI inference engines. Part of the go-to-market dynamic has involved deciding whether to offer a chip or IP — with some newcomers pivoting between chip and IP implementations of their ideas. The fact that some companies choose to sell chips while... » read more

NPU Acceleration For Multimodal LLMs

By Pat Donnelly - 12 Dec, 2024 - Comments: 0

Transformer-based models have rapidly spread from text to speech, vision, and other modalities. This has created challenges for the development of Neural Processing Units (NPUs). NPUs must now efficiently support the computation of weights and propagation of activations through a series of attention blocks. Increasingly, NPUs must be able to process models with multiple input modalities with ac... » read more

Is In-Memory Compute Still Alive?

By Bryon Moyer - 12 Dec, 2024 - Comments: 1

In-memory computing (IMC) has had a rough go, with the most visible attempt at commercialization falling short. And while some companies have pivoted to digital and others have outright abandoned the technology, developers are still trying to make analog IMC a success. There is disagreement regarding the benefits of IMC (also called compute-in-memory, or CIM). Some say it’s all about reduc... » read more

Chip Companies Play Bigger Role In Shaping University Curricula

By Liz Allan - 02 Dec, 2024 - Comments: 0

A shortage of senior engineers with the necessary skills and experience is forcing companies to hire and train fresh graduates, a more time-consuming process but one that allows them to rise through the ranks using the companies' preferred technology and systems. Universities and companies share the goal of helping a graduate become productive in the workplace as quickly as possible, and the... » read more

← Older posts

tag: Expedera