Flash Signal Processing and NAND/ReRAM SSD
The widespread use of NAND Flash memories in SSDs has unleashed new avenues of innovation for the enterprise and client computing. System-wide architectural changes are required to make full use of the advantages of SSDs in terms of performance, reliability and power. Signal processing technologies are becoming more and more popular to countermeasure all the parasitic effects of a Flash NAND array: the first part of this chapter deals with such techniques.
On the other side, the emerging storage class memories (SCM) such as PCRAM, FeRAM, ReRAM and MRAM are becoming a viable alternative to commonly used volatile and nonvolatile memories. Being bit-alterable like DRAM and nonvolatile like a Flash memory, together with CMOS-process compatibility, these non-volatile random access memories have a potential to revolutionize various aspects of the computing platform architectures. A 3D TSV-integrated SSD with hybrid memory configuration which uses storage class memories (SCMs) and NAND Flash memories is a promising solution for the future memory system. This chapter describes the signal processing technologies and data management which realizes the high speed operation, low power consumption and high reliability of the SCM and NAND Flash integrated hybrid SSDs.
- 1.S. Tanakamaru et al., Over 10-times extended lifetime, 76% reduced error Solid-State Drives (SSDs) with error prediction LDPC architecture and error recovery scheme, in IEEE International Solid-State Circuits Conference (ISSCC), 2012, San Francisco, CA, USA, pp. 424–425Google Scholar
- 3.R. Motwani et al., Low Density Parity Check (LDPC) Codes and the NEED for Stronger ECC, in Flash Memory Summit (2011)Google Scholar
- 4.C. Kim et al., A 21 nm high performance 64 Gb MLC NAND flash memory with 400 MB/s asynchronous toggle DDR interface, in Symposium on VLSI Circuits Dig. Tech. Papers, 2011, Kyoto, Japan, pp. 196–197Google Scholar
- 6.A. Serov et al., Statistical retention modeling in floating-gate cell: ONO scaling, in IRPS, 2009, Montreal, QC, Canada, pp. 887–890Google Scholar
- 7.S. Tanakamaru et al., 95%-lower-BER 43%-lower-power intelligent Solid-State Drive (SSD) with asymmetric coding and stripe pattern elimination algorithm, in ISSCC Dig. Tech. Papers, 2011, pp. 204–205Google Scholar
- 8.J. Yang, High-efficiency SSD for reliable data storage systems, in Flash Memory Summit (2011)Google Scholar
- 9.B. Vigoda, LDPC error correction using probability processing circuits, in Flash Memory Summit (2010)Google Scholar
- 10.H. Fujii et al., x11 performance increase, x6.9 endurance enhancement, 93% energy reduction of 3D TSV-integrated hybrid ReRAM/MLC NAND SSDs by data fragmentation suppression, in IEEE Symposium on VLSI Circuits, Hawaii, 2012Google Scholar
- 11.Y.S. Chen et al., Challenges and opportunities for HfOX based resistive random access memory, IEDM, pp. 717–720 (2011)Google Scholar
- 12.K. Higuchi et al., 50 nm HfO2 ReRAM with 50-times endurance enhancement by set/reset turnback pulse & verify scheme, in SSDM, 2011, pp. 1011–1012Google Scholar
- 13.T. Hatanaka et al., A 60% higher write speed, 4.2 Gbps, 24-channel 3D-Solid State Drive (SSD) with NAND flash channel number detector and intelligent program-voltage booster, in IEEE Symposium on VLSI Circuits, University of Tokyo, Tokyo, Japan, June 2010, pp. 233–234Google Scholar