Himax and Seeed Studio Collaborate to Debut the Industry’s Most Innovative Battery-Powered Endpoint AI Vision Processing Module at CES 2024

Pioneering the Future of Endpoint AI Devices with Ultralow Power Consumption and High-Speed AI Inference Power, WiseEye2 AI Processor Empowers the Most Versatile and Extensive AI Capabilities

TAINAN, Taiwan and SHENZHEN, China, Jan. 02, 2024 (GLOBE NEWSWIRE) -- Himax Technologies, Inc. (Nasdaq: HIMX) (“Himax” or “Company”), a leading supplier and fabless manufacturer of display drivers and other semiconductor products, today announced that the Company, in collaboration with Seeed Studio, the IoT hardware partner providing services that empower developers to implement their projects and products for digital transformation, will unveil a cutting-edge battery-powered endpoint AI vision processing module, Grove Vision AI Module V2, at CES 2024. This processing module features Himax’s WiseEye2 AI processor HX6538 (“WE2”), renowned for its extremely low power consumption and exceptional AI inference performance, offering the most versatile and extensive AI development capabilities. Positioned at the forefront of the industry, the processing module serves as a powerful endpoint AI development platform, paving the way for future AI applications.

Himax’s WiseEye^TM Smart Image Sensing solution has been well adopted in a wide variety of endpoint AI applications. The new generation WE2 AI processor is built upon the success of its predecessor chip, WE1. WE2 leverages the advanced Cortex-M55 and Ethos U55 architecture to deliver 32 times faster inference speed and 50 times greater energy efficiency when compared to WE1. These enhancements allow the WE2 to enable more endpoint AI computational requirements while maintaining ultralow power consumption. The WE2 features a multi-layered power management structure and incorporates Dynamic Voltage Frequency Scaling (DVFS) technology, to achieve microampere level power consumption. WE2 also incorporates impressive security features, including a Physical Unclonable Function (PUF) security mechanism that ensures each chip possesses a unique identity, mitigating the risks of unauthorized access and counterfeiting, thus enhancing the chip security. Additionally, the built-in RSA and ECC hardware encryption and decryption engines achieve millisecond-level fast secure boot, further ensuring secure and efficient data transmission.