Microchip Technology Inc. via its Silicon Storage Technology (SST) subsidiary, has released the memBrain neuromorphic memory solution, which improves system architecture implementation of VMM through an analog in-memory compute method, enhancing AI inference at the edge.
The memBrain solution gathers synaptic weights in the on-chip floating gate, enhancing system latency, delivering 10 to 20 times lower power and significantly reduced overall BOM.
“As technology providers for the automotive, industrial and consumer markets continue to implement VMM for neural networks, our architecture helps these forward-facing solutions realize power, cost and latency benefits,” said SST’s VP of the license division, Mark Reiten. “Microchip will continue to deliver highly reliable and versatile SuperFlash memory solutions for AI applications.”
SST will be appearing at the 2019 Flash Memory Summit from August 6-8, 2019, at the Santa Clara Convention Center in Santa Clara, CA to highlight its analog memory solution and present Microchip’s memBrain product tile array-based architecture at the AI/ML session track.