Microchip buys Neuronix AI Labs, matching FPGAs, computer vision

Microchip Technology recently announced that it acquired four-year-old computer vision and AI start-up Neuronix AI Labs to expand its capabilities for power-efficient, AI-enabled edge solutions delivered via FPGAs.

The move by Microchip, a Chandler, Arizona, FPGA manufacturer, comes as computer vision technology enhanced with AI capabilities is set to be deployed broadly in smart factories, automotive, smartphones, and an array of other edge devices. 

Microchip’s acquisition of Sunnyvale, California-based Neuronix AI Labs also is the latest in a string of deals that have seen computer vision start-ups gobbled up by larger technology firms. Not long after Microchip made its acquisition announcement, news also leaked that Apple reportedly had acquired French computer vision firm Datakalab. In addition, recently acquired security-focused vision AI company Pangiam, and Siemens in February bought machine vision software concern Inspekto.

Meanwhile, the FPGA market is becoming a hotbed of competition, with AI capabilities as the table stakes, as has been demonstrated by Intel’s spin-off and rebooting of its FPGA business, and AMD’s recent expansion into low-power FPGAs.

Neuronix AI Labs provides neural network sparsity optimization technology that enables a reduction in power, size and calculations for tasks such as image classification, object detection and semantic segmentation, while maintaining high accuracy, according to a Microchip statement, which added that those capabilities mesh well with Microchip’s mid-range PolarFire FPGAs and SoCs in terms of low power consumption, reliability and security capabilities. 

Microchip said that adding the start-ups technology to low and mid-range FPGAs will provide those devices with a boost in AI/ML processing horsepower, and help Microchip to develop cost-effective, large-scale edge deployments of components designed for use in computer-vision applications on systems that have cost, size and power constraints.

Microchip also said the deal will result in allowing non-FPGA designers to harness powerful parallel processing capabilities using industry-standard AI frameworks without requiring in-depth knowledge of FPGA design flow. The combination of Neuronix AI intellectual property and Microchip’s existing compilers and software design kits allows for AI/ML algorithms to be implemented on customizable FPGA logic without a need for register-transfer level (RTL) expertise or intimate knowledge of the underlying FPGA fabric.

“The acquisition of Neuronix AI Labs’ technology will enhance our power efficiency for FPGAs and SoCs deployed in intelligent edge systems that utilize AI/ML algorithms,” said Bruce Weyer, corporate vice president of Microchip’s FPGA business unit. “Neuronix technology combined with our VectorBlox design flow produces an increase in neural network performance efficiency and delivers outstanding GOPS/watt performance in our low-power PolarFire FPGAs and SoCs. Systems designers will now be able to architect and deploy small-footprint hardware that was previously difficult to build due to size, thermal or power constraints.”

Yaron Raz, CEO of Neuronix AI Labs., added, “Neuronix AI Labs has been laser-focused on producing best-in-class neural network acceleration architectures and algorithms that can transform user expectations of size, power, performance and cost. Joining the Microchip team offers us a unique opportunity to scale and align with an FPGA portfolio that has set industry standards for power efficiency.”