Advanced Computing in the Age of AI | Friday, March 29, 2024

Investors Flock to AI Chip Startups 

via Shutterstock

As the market for AI processors continues to expand, well-heeled chip startups are emerging to challenge market leaders like Nvidia.

Among them is the Israeli startup, Hailo, which announced a $60 million funding round on Thursday (March 5) that will be used to fund the rollout of its deep learning chip.

The Series B round was led by existing investors along with new funders ABB Technology Ventures, NEC Corp. and London-based Latitude Ventures. ABB’s venture arm focuses on industrial automation and robotics while Japan’s NEC (TYO: 6701) is an IT and networking giant.

Tel Aviv-based Hailo raised $12 million in a Series A funding round last June that included Ourcrowd.com, Maniv Mobility, NextGear Ventures and angel investors. The startup has so far raised $88 million.

The chip maker recently launched its Hailo-8 AI deep learning processor designed to be embedded in edge devices. The neural network-based chip architecture is billed as enabling edge devices to handle deep learning applications that previously ran only in the cloud.

The deep learning chip is based on a proprietary design dubbed the “Structure-Defined Dataflow Architecture” that tops out at 26 tera operations per second. Hailo claims its AI chip outperforms other edge processors in terms of size, performance and reduced power consumption.

Hailo’s deep learning architecture reconfigures memory, control and compute as well as the “relations between them,” the startup said. The goal is reducing size, power consumption and price to provide local processing of sensor data in real time.

For example, NEC said this week it plans to use Hailo’s deep learning technology for “intelligent video analytics” applications.

Hailo’s leadership includes Orr Danon, CEO and co-founder, who previously served in the Israeli Defense Force’s technology unit, and CTO Avi Baum, a former senior engineer at Texas Instruments (NASDAQ: TXN). Its development team includes hardware and software engineers who previously worked at Intel, Broadcom (NASDAQ: AVGO) and Mellanox (NASDAQ: MLNX).

“The new funding will help us expedite the deployment of new levels of edge computing capabilities in smart devices and intelligent industries around the world, including areas such as mobility, smart cities, industrial automation, smart retail and beyond,” Danon said.

The booming AI chip market is being fueled by emerging processor architectures for GPUs, FPGAs and ASICs used for deep learning and vector processing tasks. Moreover, leading applications like automotive, computing and healthcare are creating a wave of new AI applications.

Hailo said this week it is targeting edge computing markets like “partially autonomous vehicles,” smart cameras, drones along with augmented reality and virtual reality applications. AR technology has, for example, been making steady headway for so-called Industry 4.0 applications, including aerospace manufacturing.

Increased investment in AI chip makers reflects the shift to edge computing that often requires in-memory processing of deep learning algorithms as a way of reducing data movement. Hence, new architectures are moving high-bandwidth memory closer to processor cores.

In another recent example, memory maker Micron Technology recently unveiled a deep learning accelerator framework that combines hardware and software to accelerate and reduce power consumption in FPGAs backed with high-bandwidth memory.

AI technology “is changing the shape of the chip market, redefining traditional processor architectures and memory interfaces to suit new performance demands,” IHS Markit noted. The market tracker forecasts the nascent AI processor market will reach $68.5 billion by the mid-2020s.

 

About the author: George Leopold

George Leopold has written about science and technology for more than 30 years, focusing on electronics and aerospace technology. He previously served as executive editor of Electronic Engineering Times. Leopold is the author of "Calculated Risk: The Supersonic Life and Times of Gus Grissom" (Purdue University Press, 2016).

EnterpriseAI