AI edge chip startup Hailo lands $136M

Hailo, a startup establishing AI accelerator chips for edge devices, today announced that it raised $136 million in a series C funding round led by Poalim Equity and entrepreneur Gil Agmon, with participation from ABB Technology Ventures, Latitude Ventures, OurCrowd, Carasso Motors, Comasco, Shlomo Group, Talcar Corporation, and Automotive Equipment. The capital brings Hailo’s total raised to $224 million, and CEO Orr Danon says the firm will place the funds toward mass manufacturing of its existing chips and the development of next-generation hardware in new and current markets.

AI edge chips are coming into vogue as enterprises commence to recognize the rewards of localized computing. Deloitte estimates that in 2020, more than 750 million edge AI chips — chips or components of chips that carry out or accelerate machine finding out tasks on-device — have been sold globally. This quantity, representing $2.6 billion in income, is more than twice the 300 million AI chips the firm anticipated would sell in 2017, a 3-year compound annual development price of 36%.

Hailo’s Hailo-8 processor features an architecture that ostensibly consumes significantly less energy than rival AI chips although incorporating RAM, application handle, and a heat-dissipating style. Under the hood of the Hailo-8, sources such as memory, handle, and compute blocks are distributed all through the complete of the chip, and Hailo’s application analyzes the needs of every AI algorithm and allocates the suitable modules.

“I founded Hailo in 2017 along with colleagues from the Israeli Defense Forces’ elite technology unit. While working with my cofounder Rami Feig on cybersecurity solutions for internet of things, a lesser-known term — ‘deep learning’ — kept popping up throughout our research,” Danon told VentureBeat. “Eventually, we brought together Avi Baum, an expert in machine learning, and Hadar Zeitlin, a smart mobility guru, to develop a new deep learning solution that aimed to solve the shortcomings of aging computer architecture in order to enable smart devices to operate more effectively and efficiently at the edge. After Rami’s unfortunate passing [in 2018], Avi, Hadar, and I carried through his vision of creating Hailo’s groundbreaking processor.”

AI at the edge

“Edge AI” describes architectures in which AI models are processed locally, on hardware at the edge of a network. As edge AI setups generally only call for a microprocessor and sensors, not an web connection, they can course of action information and make predictions in genuine time — or close to it.

The small business worth of edge AI could be substantial. According to Markets and Markets, the edge AI market place is anticipated to develop from $590 million in 2020 to $1.83 billion by 2026. Digital well being care, manufacturing, and retail firms are specifically probably to expand their use of edge computing for the reason that of the technology’s capability to strengthen response occasions and save bandwidth although enabling significantly less constrained information evaluation.

“Smart retail, for instance, requires hundreds of cameras in-store, where data must be processed locally, quickly, and efficiently with minimal latency. Smart cities require similar output from a multitude of cameras and sensors — otherwise, critical city management tasks such as improving transportation flow will be much harder to achieve,” Danon continued. “For all of these industries and more, Hailo’s AI chip can process full resolution data streams in real time, enabling cameras to detect objects from greater distances. The processor is also capable of processing multiple camera streams on a single device, making it more cost-effective.”

The Hailo-8 is capable of 26 tera-operations per second (TOPs), which operates out to 2.8 TOPs per watt. In a test carried out by Hailo, the Hailo-8 outperformed hardware like Nvidia’s Xavier AGX, Intel’s Myriad-X, and Google’s Edge TPU modules on various AI semantic segmentation and object detection benchmarks. At an image resolution of 224 x 224 pixels per inch, the chip processed 672 frames per second compared with the Xavier AGX’s 656 frames and employed 1.67 watts (equating to 2.8 TOPs per watt) versus the Nvidia chip’s 32 watts (.14 TOPs per watt).

Hailo not too long ago announced the launch of its M.2 and Mini PCIe higher-AI acceleration modules, which are based about the Hailo-8 chip. Foxconn and Socionext are two of the initially publicly disclosed consumers just after NEC, Macnica, and ABB Technology — Foxconn’s BOXIedge edge computing platform features Hailo’s M.2 module. Previously, Hailo mentioned it is working to make its chips into merchandise from OEMs and tier-1 automotive corporations in fields such as sophisticated driver-help systems and industries like robotics, medicine, and intelligent cities and properties.

According to Danon, Hailo, which has more than 160 personnel, doubled its client base to upwards of one hundred clientele all through the initially two quarters of 2021 and expanded its presence globally, opening offices in Tokyo, Taipei, Munich, and Silicon Valley in California.

“AI, more specifically AI at the edge, will continue to drive innovation across sectors in the coming years … As businesses seek solutions that ensure their devices are more powerful, versatile, responsive and secure, the cloud will continue giving way to the edge in the coming years. Though a hybrid model will certainly take center stage, those who succeed in implementing AI at the edge will gain an edge across the board,” Danon mentioned.

Hailo has rivals in Deep Vision, Alexera, Sima.ai, AIStorm, Quadric, and Flex Logix, which are similarly establishing chips customized for AI workloads. Mobileye, the Tel Aviv company Intel acquired for $15.3 billion in March 2017, also presents a laptop vision processing remedy for AVs in its EyeQ item line. Baidu last July unveiled Kunlun, a chip for edge computing on devices and in the cloud by way of datacenters. And Arm debuted two new AI edge computing chips in February.

Originally appeared on: TheSpuzz