AI processor boosts performance, power efficiency
Stephen LawAutomation / Robotics Semiconductors AI chip Processor
PERCEIVE Ergo 2 AI processor enables larger, more complex neural networks inside edge devices, including transformer networks for language and imaging, while drawing less than 100 milliwatts of compute power. Device provides performance required for more complex use cases, including those requiring transformer models, larger neural networks, multiple networks operating simultaneously, and multimodal inputs, while maintaining industry-leading power efficiency.
Processor expands user ability to build more ambitious designs and products, including transformer models for language or visual processing, video processing at higher frame rates, and even combining multiple, large neural networks in a single application. Device runs up to four times faster than firm’s first-generation Ergo chip and delivers more processing power than typical chips designed for tiny ML.
Print this page