Hailo, a Tel Aviv-based AI chipmaker, today announced that it is now sampling its Hailo-8 chips, the first of its deep learning processors. The new chip promises up to 26 tera operations per second (TOPS), and the company is now testing it with a number of select customers, mostly in the automotive industry.
Hailo first appeared on the radar last year, when it raised a $12.5 million Series A round. At the time, the company was still waiting for the first samples of its chips. Now, the company says that the Hailo-8 will outperform all other edge processors and do so at a smaller size and with fewer memory requirements. “By designing an architecture that relies on the core properties of neural networks, edge devices can now run deep learning applications at full scale more efficiently, effectively, and sustainably than traditional solutions, while significantly lowering costs,” the company explains.
The company also argues that its chip outperforms Nvidia’s comparable Javier Xavier AGX in some benchmarks, all while using less power and hence running cooler — something that’s especially important in small IoT devices.
We’ll have to see if that works out in practice once more engineers get their hands on these chips, of course, but there can be no doubt that the demand for AI chips on the edge continues to increase. A few years ago, after all, the market shifted away from a focus on centralizing all processing in the cloud to moving to the edge, in an effort to improve latency, reduce bandwidth cost and provide a more stable platform that doesn’t depend on network connectivity.
Like Mobileye before it (which was later acquired by Intel), Hailo is working with OEMs and tier-1 suppliers in the automotive industry to bring its chip to market, but it’s also looking at other verticals, including smart home products and really any industry where a high-performance AI chip is needed for object detection and segmentation, for example.
“In recent years, we’ve witnessed an ever-growing list of applications unlocked by deep learning, which were made possible thanks to server-class GPUs,” said Orr Danon, CEO of Hailo. “However, as industries are increasingly powered and even upended by AI, there is a crucial need for an analogous architecture that replaces processors of the past, enabling deep learning to run devices at the edge. Hailo’s chip was designed from the ground up to do just that.”