AlphaICs, AI fabless semiconductor company that develops edge inference and edge learning technologies, has announced the availability of engineering samples of ‘Gluon’ - an 8 TOPS Edge AI inference co-processor to customers in surveillance, industrial, retail, auto, and Industrial IoT verticals which carries best-in-class FPS/Watt performance.
Gluon will be shipped with a complete (Software Development Kit) SDK that enables easy deployment of neural networks. The advanced edge inference chip delivers the capability for customers to add AI capability in the current X86 / ARM-based systems, resulting in significant cost savings it said in a press statememt.
Gluon provides the best fps/watt performance in the market for classification and detection Neural Networks – 32 Frames Per Second (FPS)/watt for Yolo-V2, a leading object detection model & 22 Frames Per Second (FPS)/Watt for VGG-19, a leading classification model, it said.
To accelerate its market foray into highly demanding silicon markets, AlphaICs has established a channel partner relationship with CBC Co. Ltd, a Japanese enterprise offering video surveillance products for their customers.
"CBC has been working with AlphaICs for close to two years and we are excited to be its marketing partner in Japan. Gluon was showcased at Japan AI Expo in October 2021 and generated great interest from Japanese customers for vision applications based on its superior performance. AlphaICs co-processor strategy is well received, and we are very excited to take this technology to our customers” said Kazuhiko Kondo, Executive Officer, CBC Co., Ltd.
AlphaICs CEO Pradeep Vajram said, “Gluon is future-ready and is well-positioned to address the AI vision applications for surveillance, retail, industrial, and smart city markets.”
Early last year the company raised $8 million to advance the development of Gluon based on the proprietary architecture RAPTM. AlphaICs’ highly scalable and modular architecture uses a specialized Instruction Set Architecture that is specifically optimized for AI.
