Introduction to nonvolatile memory technologies

Abstract Dynamic Random Access Memory (DRAM) has been the leading main memory technology during the last four decades. In deep submicron regime, however, scaling DRAM comes with several challenges caused by charge leakage and imprecise charge placement. Phase Change Memory (PCM) technology is known as one of the most promising technologies to replace DRAM. Compared to competitive non-volatile memories like NAND Flash, Spin Transfer Torque random-access memory (STT-RAM), Magnetoresistive random-access memory (MRAM), PCM benefits from best attributes of fast random access, negligible leakage energy, superior scalability, high density, and operating in both Single-level Cell (SLC) and Multilevel Cell (MLC) storage levels without imposing large storage overhead. Unfortunately, density advantage of MLC PCM devices comes at the cost of lower write endurance that results in fast wear-out of memory cells. Adding to it, other preliminary concerns for PCM applicability are related to low resilience to soft errors because of resistance drift, higher latency and energy consumption. To alleviate this issue, recent studies have proposed redirection or correction schemes, but all suffer from poor throughput and latency. None of the techniques proposed in the literature to improve the lifetime and reliability of PCM memories consider the impressive characteristic of PCMs to easily shape-shifting from SLC to MLC storage level using some negligible overhead of read/write circuits. We exploit this remarkable ability to propose some new techniques to improve the durability and reliability of PCMs in this book. This chapter gives an overview of non-volatile memory technologies, memory hierarchy in modern computers, PCM technology maturity and finally introduce the structure of the book and its chapters.