Paper Title: Advanced NAND Management Using Machine Learning (ML)

Paper Abstract: Advanced NAND management algorithms can greatly improve the performance and efficiency of large-scale deployments of SSD's. Non-volatile memory technologies are constantly evolving to meet market demand and with each technology evolution, the complexity of managing the NAND media has increased. A key technology in SSD hardware and firmware is error correction performance through the life cycle of the SSD which requires more efficient algorithms to ensure high reliability and the lowest bit error rates. Traditional error correction techniques based on Low-density parity-check codes (LDPC) or Bose-Chaudhuri-Hochquenghem code (BCH) alone is no longer sufficient to handle the Bit-Error Rates (BERs) efficiently, and there is a strong need to assist the error correction algorithms using other supporting technologies such as Machine Learning (ML) for better NAND management. In this presentation, we will provide an overview of these technology advancements and explore an example of how an ML application advances NAND management.

Paper Author: Ramyakanth Edupuganti, Staff Applications Engineer, Microchip Technology

Author Bio: Ramyakanth (Ram) Edupuganti is working as an Technical Staff Applications Engineer for NVMe controllers in the Datacenter solutions business unit of Microchip Technology. He has contributed to the development of NVMe SSDs and storage products working closely with several enterprise customers. With his passion for new technologies, Ram has special interests in developing newer applications and innovative solutions for challenging problems. Previously he has presented at Flash Memory Summit on "use of Controller Memory Buffers in NVMe Controllers" and "Implementing Computational Storage with Existing SSD Controller Resources", and now he is excited to share his findings on how Advanced NAND management can be done using Machine Learning (ML)