On the Diversity of Memory and Storage Technologies

Abstract

The last decade has seen tremendous developments in memory and storage technologies, starting with Flash Memory and continuing with the upcoming Storage-Class Memories. Combined with an explosion of data processing, data analytics, and machine learning, this led to a segmentation of the memory and storage market. Consequently, the traditional storage hierarchy, as we know it today, might be replaced by a multitude of storage hierarchies, with potentially different depths, each tailored for specific workloads. In this context, we explore in this "Kurz Erklärt" the state of memory technologies and reflect on their future use with a focus on data management systems.

Persistent Memory I/O Primitives

“…While our work proposes low-level optimizations, Swanson et al evaluate PMem with various storage engines as well as file systems. Until now, software or hardware-based simulations, or emulations based on speculative performance characteristics, have been used to evaluate possible system architectures [4,25,27,29]. The number of persistent index structures [3,9,14,21,34,37] is large, and has been summarized by Götze et.…”

Recent Progress in Selector and Self‐Rectifying Devices for Resistive Random‐Access Memory Application

“…[ 38 ] From an industrial viewpoint, the phase‐change material has the potential to become a next‐generation nonvolatile device; therefore, Intel and Micron Technology have developed a phase‐change‐material‐based 3D X‐point nonvolatile memory architecture. [ 39 ] There is a structural difference between the magnetic and ferroelectric RS devices and the aforementioned RS memory devices. For instance, spin‐transfer torque‐based memory devices utilize a magnetic tunnel junction comprising a tunnel barrier sandwiched between ferromagnetic layers in addition to the transistor as a selector element.…”

Building blocks for persistent memory

“…While our work proposes low-level optimizations, Swanson et al evaluate PMem with various storage engines as well as file systems. Until now, software or hardware-based simulations, or emulations based on speculative performance characteristics, have been used to evaluate possible system architectures [3,36,38,40]. The number of persistent index structures [2,9,15,[27][28][29]48,52,53] is large, and has been summarized by Götze et.…”