Tech

Report: Edge AI chip startup Hailo to go public with SPAC merger

It is reported that the Chipmaker, Hailo Technologies Ltd. is preparing to list its shares in a merger with a special purpose manufacturing company.

Calcalist revealed the plan today, citing official documents from Hailo’s developer, Delek Automotive. The offering is reportedly designed to save the producer money during an “urgent need to raise funds.” Hailo laid off about 10% of its workforce in January and took out a $9 million loan at the same time.

The company, which makes artificial intelligence chips for connected devices, was worth $1.2 billion by 2024. Delek’s filings indicate that the planned stock listing will reduce Hailo’s value to less than $500 million.

A SPAC is an investment vehicle created for the sole purpose of taking another business public. Partnering with such a company provides a faster path to public markets than a regular listing. It also removed the need for startups to organize a road show, a series of events designed to bring in institutional investors.

Hailo chips are used in cameras, industrial robots and a wide range of other devices. They are based on an architecture that the company describes as structure-driven data flow architecture. Hailo says the technology can run workloads more efficiently than competing processing methods.

The artificial neurons of a neural network are organized into groups called layers. The first layer performs the initial calculations involved in responding to the AI ​​input and sends the result to the second layer for further processing. That second layer completes the second set of calculations, sharing the output with the third layer and so on.

Each layer runs on a different stage of the host device’s processor. Hailo’s architecture-driven data flow architecture places the layers in adjacent chip layers, reducing the distance that data must travel between them. Reducing data movement reduces both processing latency and power consumption.

One of Hailo’s most advanced chips, the Hailo-10H, can perform 40 million calculations per second when processing INT4 data. It uses about 2.5 watts of power and can withstand temperatures up to 221 degrees Fahrenheit. Hailo also offers several chips specially optimized for cameras and a PCIe card that can be connected to servers.

The company ships its chips with a set of software tools designed to ease customers’ AI projects. There is a runtime called HailoRT that can link together up to 16 Hailo devices into an inference cluster. Additionally, Hailo offers a set of pre-trained AI models configured to run on its chips.

Calcalist did not specify which SPAC the company will partner with in its listing or the amount of capital it hopes to raise. However, the report revealed that Hailo plans to float its shares in the coming months on the US stock market.

Photo: Hailo

Support our mission to keep content open and free by engaging with the CUBE community. Join CUBE’s Alumni Trust Networkwhere technology leaders connect, share wisdom and create opportunities.

  • 15M+ viewers of CUBE videosenabling conversations across AI, cloud, cybersecurity and more
  • 11.4k+ CUBE alumni – Connect with more than 11,400 technology and business leaders who are shaping the future through a unique network based on trust.

About SiliconANGLE Media

SiliconANGLE Media is a recognized leader in digital media innovation, technology that integrates breakthrough, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, CUBE Network, CUBE Research, CUBE365, CUBE AI and CUBE SuperStudios – with leading locations in Silicon Valley and the New York Stock Exchange – SiliconANGLE Media works at the intersection of media, technology and AI.

Founded by technology visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media products that reach 15+ million elite technology professionals. Our new ownership of CUBE AI Video Cloud is starting to engage with audiences, using CUBEai.com’s neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button