Weebit - 2021and beyond, page-9952

Something else I'll be keeping an eye out for in 2022 from WBT / Cea Leti

the application of reram in the 'storage class memory market'.

the main stumbling block initially was variability mitigation .....CEA leti have solved the issue by the application of 'nanosecond voltage pulses to nanoscale reram memory devices'
this breakthrough has the additional 'value add' advantage of 5 orders of magnitude reduced energy expenditure.

This 'value add' opens the way for larger capacity implementation....SCM. ie reram placed between DRAM and storage memory filling a known gap in the hierarchy....meeting the latency and bandwidth requirements with high speed and good endurance ...... variability mitigated.



add to that the low cost - cheapest per bit manufacture - ease of adoption and integration to new and old fab equipment alike, lower cost mask adoption (5 - 8% saving on current cost) and a strategy of low cost implementation = increased profitability via increased volume sales over time = ...$$$$

Cea / Leti went further in their summation / attribution: (March 2021)
ReRAM is seen as a good candidate for artificial intelligence (AI) and machine learning applications and for its potential to mimic how the human brain learns and processes information at the neuron and synaptic level. Scaling neuromorphic architectures are believed to benefit from ReRAM devices because they are significantly smaller and more energy-efficient than current AI data centers which used DRAM, flash, and even High Bandwidth Memory (HBM).

exciting times in 22/23
I don't pay much attention to the sp these days.... no need really

not my opinion - the findings of our research partner as published 'Advances in emerging memory'

GLA