SiOx ReRAM selected for neuromorphic research
Neuromorphics in memory is a not uncommon research theme and has been pursued previously by IBM with phase change memory (see IBM uses phase-change memory for machine learning). Certain memory device types show similarities to biological neurons and companies, such as Mythic Inc, and Upmem SAS are looking at other processing-in-memory architectures.
The non-volatile memory research group at the IITD is led by Professor Manan Suri.
The use of in-memory processing has the potential to remove memory-processer bottleneck that limits the performance of conventional von Neumann architectures and also promises to reduce power consumption by reducing data movements. The approach is also a closer analog to the way brains perform.
Coby Hanoch, CEO of Weebit Nano, said: “While we remain absolutely committed to commercialising our SiOx ReRAM technology as soon as possible, we are also ensuring we leverage its full capability across advanced applications through our university program.”
Related links and articles:
News articles:
Weebit silicon-oxide ReRAM headed to 28nm, AI
IBM uses phase-change memory for machine learning
University College London spins out ReRAM startup
Weebit moves SiOx ReRAM on to 40nm
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
