AnalogAI Selects memBrain™ SAGE Intellectual Property from Silicon Storage Technology® for its First Real-world Edge AI Processors
Proprietary on-device training built to dynamically adapt to real-world environments
AnalogAI has chosen memBrain™ Synaptic Analog Generative Engine (SAGE) neuromorphic hardware intellectual property (IP) from Microchip Technology’s Silicon Storage Technology® (SST®) subsidiary for its real-world edge AI processors. AnalogAI edge AI processors feature a hardware aware proprietary algorithm designed to simultaneously train and run inference on AI models in real-world environments.
AnalogAI is utilizing SST’s memBrain SAGE IP to deliver high levels of analog compute-in-memory (aCIM) performance at or below one watt for ultra-low power edge applications. By leveraging the robust silicon proven SST memBrain SAGE IP based on SST SuperFlash®, AnalogAI is developing new capabilities for real-world inference applications such as environment adapting humanoid robots, drones and vehicles.
“AnalogAI is pursuing innovative co-optimized solutions for edge AI inference that enable edge devices to adapt real-time to sudden changes in the environment,” said Mark Reiten, senior vice president of Microchip’s Intelligent Compute business unit. “As the core inference engine for AnalogAI’s first products, SST memBrain SAGE IP delivers the necessary compute performance coupled with the power efficiency AnalogAI requires to meet their application targets. We are pleased to welcome AnalogAI as the newest licensee of our SST memBrain IP, joining our rapidly expanding ecosystem.”
SST memBrain SAGE IP features:
- memBrain Tensor In-Memory Logic Element (TILE)
- memBrain solution optimized ESF3 bitcell which stores up to 8 bpc at nanoamp levels
- memBrain solution custom array, decoders and driver circuitry
- Optimized DACs and ADCs
- Summator and high voltage bias circuitry
- Nanoamp level bitcell control logic
- memBrain proprietary test circuitry
- SST memBrain technology documentation and simulation models
- Full IP integration service and support
“AnalogAI selected SST’s memBrain SAGE IP after an industry-wide search of available offerings and determined the silicon-proven memBrain SAGE IP best enabled us to accelerate our development time while still achieving the ultra-low-power and high performance required in our market segment,” said Jaejun Lee, AnalogAI’s chief executive officer. “Analog Compute-in-Memory is a rapidly emerging field, and at AnalogAI we are pioneering new functionality for edge AI devices requiring real-world adaptation.”
SST’s memBrain SAGE IP has been developed and deployed in 40 nm and 28 nm foundry processes using production-ready SuperFlash memory. The current technology roadmap includes 22 nm memBrain SAGE IP development. Designed to provide reliable, high-performance and low-power non-volatile storage directly on the chip, SuperFlash memory is widely used in applications that require fast access times, high endurance and data retention without the need for external memory components.
Pricing and Availability
Customers interested in SST’s memBrain IP solutions and SuperFlash technology should access the SST website or contact a regional SST sales executive for details. Those interested in AnalogAI’s products should visit the AnalogAI website or contact the AnalogAI team at contact@analog-ai.com.
Resources
High-res images available through Flickr or editorial contact (feel free to publish): Application image: www.flickr.com/photos/microchiptechnology/55472818028/sizes/o/
