Microchip introduced the memBrain™ neuromorphic memory solution which is an analog memory technology to resolve challenge faced by battery powered and deeply embedded devices. The memBrain™ neuromorphic memory solution is based on Silicon Storage Technology (SST)’s proven SuperFlash® technology and optimized to perform vector matrix multiplication (VMM) for neural networks. The new analog flash memory solution enhances AI inference at the edge and improves system architecture implementation of VMM through an analog in-memory compute approach.
The memBrain™ neuromorphic memory solution resolves the bottleneck problem for neural net computing and stores synaptic weights in the on-chip floating gate, offering significant improvements in system latency. The solution reduces the overall BOM and delivers 10 to 20 times lower power compared to traditional digital DSP and SRAM/DRAM based approaches. The memBrain solution is an ideal solution for the companies looking to advance machine learning capacities in edge devices. Also, the solution is ideal for any AI application due to its ability to significantly reduce power.
For development, the Silicon Storage Technology (SST) provides design services for both its memBrain solution and SuperFlash technology, along with a software toolkit for neural network model analysis.
The memBrain™ neuromorphic memory solution will be showcased by SST in August Second week 2019. For more information visit Microchip’s Website.