Channel and Source Coding for Non-Volatile Flash Memories

verfasst von: Mohammed Rajab

Verlag: Springer Fachmedien Wiesbaden

Buchreihe : Schriftenreihe der Institute für Systemdynamik (ISD) und optische Systeme (IOS)

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Mohammed Rajab proposes different technologies like the error correction coding (ECC), sources coding and offset calibration that aim to improve the reliability of the NAND flash memory with low implementation costs for industrial application. The author examines different ECC schemes based on concatenated codes like generalized concatenated codes (GCC) which are applicable for NAND flash memories by using the hard and soft input decoding. Furthermore, different data compression schemes are examined in order to reduce the write amplification effect and also to improve the error correct capability of the ECC by combining both schemes.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

Nowadays, flash memory and especially NAND flash memory are very important storage medium in industrial application. NAND flash memory provides high-density, low-latency, fast-programming and erase operation speeds at low costs. Flash memories are mechanical shock-resistant non-volatile memories. Therefore, flash memories are very interesting for many devices that require high data reliability, e.g. for industrial robotics, scientific and medical instrumentation.

Mohammed Rajab

Chapter 2. Error characteristics and read threshold calibration for flash memories

Abstract

Nowadays, flash memory is commonly used in persistent storage devices. Increasing storage density and faster reading and programing speed lead to a degradation in flash memory reliability and lifetime. In this chapter, we introduce the basic background to NAND flash memory, which guides understanding the flash memory reliability problem.

Mohammed Rajab

Chapter 3. Source coding schemes for flash memories

Abstract

In this chapter, different lossless data compression schemes are presented for application in non-volatile flash memories. The objective of the lossless compression scheme is to reduce the amount of redundancy of the user data without losing the original data.

Mohammed Rajab

Chapter 4. A Source and channel coding approach for flash memories

Abstract

The introduction of MLC and TLC technologies reduced the reliability of flash memories significantly compared with SLC flash [65, 5]. With MLC and TLC flash cells the error probability varies for the different states. Hence asymmetric models are required to characterize the flash channel, e.g. the binary asymmetric channel (BAC) [66, 20, 21, 8].

Mohammed Rajab

Chapter 5. Product codes and generalized concatenated codes for flash memories

Abstract

Data reliability and integrity are important requirements for storage systems and is ensured by ECC. Traditionally, a binary symmetric channel (BSC) is used as channel model for flash memories and BCH codes are used for error correction [94, 72]. Recently, different concatenated coding schemes were proposed that have low error correcting capabilities.

Mohammed Rajab

Chapter 6. A soft-input decoder of GCC for application in flash memories

Abstract

In recent years, mostly hard-input algebraic decoding was used for error correction in flash memories [137, 94, 72]. ECC based on soft-input decoding can significantly improve the reliability of flash memories.

Mohammed Rajab

Chapter 7. Conclusions

Abstract

This dissertation has proposed various applicable techniques to improve the reliability of NAND flash memory. In summary, this dissertation makes the following contributions.

Mohammed Rajab

Backmatter

Titel: Channel and Source Coding for Non-Volatile Flash Memories
verfasst von: Mohammed Rajab
Verlag: Springer Fachmedien Wiesbaden
Electronic ISBN: 978-3-658-28982-9
Print ISBN: 978-3-658-28981-2
DOI: https://doi.org/10.1007/978-3-658-28982-9