Predict and Write: Using K-Means Clustering to Extend the Lifetime of NVM Storage
This addresses the problem of NVM storage lifetime for systems using K/V-stores, representing an incremental improvement over existing techniques.
The paper tackles the limited write endurance of non-volatile memory (NVM) by proposing Predict and Write (PNW), a K/V-store that uses clustering to reduce bit flips for PUT/UPDATE operations, achieving reductions of up to 85% in total bit flips and 56% in cache lines compared to state-of-the-art methods.
Non-volatile memory (NVM) technologies suffer from limited write endurance. To address this challenge, we propose Predict and Write (PNW), a K/V-store that uses a clustering-based machine learning approach to extend the lifetime of NVMs. PNW decreases the number of bit flips for PUT/UPDATE operations by determining the best memory location an updated value should be written to. PNW leverages the indirection level of K/V-stores to freely choose the target memory location for any given write based on its value. PNW organizes NVM addresses in a dynamic address pool clustered by the similarity of the data values they refer to. We show that, by choosing the right target memory location for a given PUT/UPDATE operation, the number of total bit flips and cache lines can be reduced by up to 85% and 56% over the state of the art.