SST & IHWK Collaborate on Analogue Compute Platform to Support Edge AI Implementations
13 September 2023
To help those developing and deploying computing hardware for artificial intelligence (AI) inferencing workloads to be undertaken at the network edge, Intelligent Hardware Korea (IHWK) has created a cutting-edge neuromorphic computing platform.
Silicon Storage Technology (SST) - a subsidiary of Microchip - has made a major contribution to this. The company has supplied an evaluation system through use of its memBrain non-volatile memory (NVM) embedded computing technology. This power-efficient memory resource is optimised for performing vector matrix multiplication (VMM) work on neural networks, by leveraging an analogue in-memory compute arrangement. Generative AI models, autonomous vehicles, medical diagnosis, voice processing, security/surveillance and commercial drones are just some of the places that are expected to benefit.
“By using proven NVM rather than alternative off-chip memory solutions to perform neural network computation and store weights, Microchip’s memBrain computing-in-memory technology is poised to eliminate the massive data communications bottlenecks otherwise associated with performing AI processing at the network’s edge,” states SST VP Mark Reiten. “Working with IHWK, the universities and early adopter customers is a great opportunity to further prove our technology for neural processing and advance our involvement in the AI space.”
Sanghoon Yoon, IHWK Branch Manager adds; “Our experts on non-volatile and emerging memory have validated that Microchip’s memBrain product based on proven NVM technology is the best option when it comes to creating in-memory computing systems.”
Contact Details and Archive...