A Survey of Software Techniques for Using Non-Volatile Memories for Storage and Main Memory Systems

Non-volatile memory (NVM) devices, such as Flash, phase change RAM, spin transfer torque RAM, and resistive RAM, offer several advantages and challenges when compared to conventional memory technologies, such as DRAM and magnetic hard disk drives (HDDs). In this paper, we present a survey of software techniques that have been proposed to exploit the advantages and mitigate the disadvantages of NVMs when used for designing memory systems, and, in particular, secondary storage (e.g., solid state drive) and main memory. We classify these software techniques along several dimensions to highlight their similarities and differences. Given that NVMs are growing in popularity, we believe that this survey will motivate further research in the field of software technology for NVMs.

1 Introduction

For all computing systems ranging from hand-held embedded systems to massive supercomputers, memory systems play the primary role in determining their power consumption, reliability, and, unquestionably, application performance. The ever-increasing data-intensive nature of state-of-the-art applications demands significantly higher performance within the constraints of power and cost, beyond what conventional memory technologies can provide. For example, more than 100 hours of video and 250 K photos are uploaded every minute to YouTube [1] and Facebook [2], respectively. Similarly, it is expected that future extreme-scale systems will deal with several exabytes of data; using hard disk to support checkpoint/restart in these systems can degrade their performance by more than 50 percent [3]. Further, these systems will require at least 100 petabytes of main memory, which, if designed with today's DDR3 DRAM, would consume 52 MW power, which is far more than the 20 MW power budget mandated for the entire system [4], [5], [6].