Memory Mass Storage

The phenomenon of memory, thought as a general property of some natural or artificial systems, can be analyzed only within the frame of a process approach to reality. In this view, some epistemological paradigms, related to the notions of autopoiesis, self-organization, and self-reference, seem to bear a profound relevance for the essence of memory, as function ensuring temporal coherence to complex systems. On the other hand, the meta-mnemonic power of memory systems, that can self-represent themselves, potentially gives rise to self-referential paradoxes. These antinomies involve some critical logical issues: the problem of self-encoding within a formal untyped language, the threat of infinite regress, and the need for non-isomorphic models of memory. Many formal and/or computational models and notions have been developed to cope with such issues, in the last few decades, by logicians and mathematicians – like indication calculus, hyperset theory, co-algebras – all aimed at explaining self-reference as a constitutive and non-paradoxical process in complex systems, like living organisms or concurrent information systems. Most of these ideas may suggest new metaphors and models to think about memory and may induce further reflection toward a definition of the essential systemic nature of the phenomenology of remembering involving and connecting together different notions, as self-description, reversibility, entropy, and life itself. Moreover, the application of these models to the problem of memory could bring to consider some general epistemological issues, related to the structural coupling between the notions of time and consciousness.

This chapter describes the basic storage technologies such as traditional paper, magnetic, optical, semiconductor, and uncommon memories, providing an outline of the history and a brief technical description of each device in terms of its volatility, accessibility, addressability, capacity, and performance.

This chapter gives an overview of probe-based data storage research over the last three decades, encompassing all aspects of a probe recording system. Following the division found in all mechanically addressed storage systems, the different subsystems (media, read/write heads, positioning, data channel, and file system) will be discussed. In the media subsection various recording media will be treated, such as polymer based, phase change, ferroelectric and magnetic. In the probe array subsection various generations of thermal probes will be discussed, as well as examples of alternative write probes using currents, electric or magnetic fields, and different principles for data detection. Special attention is paid to parallel readout of probe arrays. In the positioning section, examples will be shown of electric and magnetic scanners, either precision engineered or realized by micromachining technologies, or combinations thereof. In the systems subsection the data channel will be discussed, including the read/write electronics circuitry, data detection, and coding algorithms. Special attention is paid to the writing strategy and considerations for probe-based storage file systems.

The objective of this chapter is to provide the readers with a basic technical overview of modern hard disk drives. As a mainstream data storage media, magnetic recording hard disk drives have been enjoying a steady increase in areal recording density for more than four decades, with a rate at least as dramatic as what has been predicted by Moore’s Law for the increase of transistor density in integrated circuits. Thanks to continuous advances in recording materials, read and write heads, and read channel signal processing and error correction coding, the areal density increase in hard disk drives appears to be well on track and is steadily moving toward achieving the milestone of 1 Tb/in². This chapter will provide an overview of modern hard disk drive systems with the focus on recording channel modeling and advanced signal processing and coding techniques being used in current design practice.

Solid-state drives (SSD) represents the state of the art of mass storage solutions. They can be looked at as the evolution of Hard Disks which eventually “lost” the mechanical arm moving onto a rotating magnetic disk in favor of using solid-state nonvolatile memory chips to store data. This simple difference makes an SSD the preferred choice if read/write access time, power consumption and dimensions are the key requirements of the application. Cost and endurance are instead the reasons why traditional Hard Disks still survive in specific areas. The chapter starts with an historical evolution of the Hard Disk and moves then on its main features and parameters. Interface communication protocol is presented in more detail, being it inherited as it is by the SSDs. A glance on the Internal SSD HW and FW architecture is given with a particular focus on FTL (Flash Translation Layer) which assumes the use of NAND flash as NVM memory. Finally a brief analysis of market-segment coverage possibilities of SSD is presented.

Hand-handled, wireless world represents the most challenging environment for package technology where all the system performances must be densely stacked. Chip scale package (CSP) is the generic term for packages approaching chip size, and the fine-pitch versions of BGA have become the most widely used kind of CSP for system miniaturization. With the introduction of the new feature, where heterogeneous semiconductor devices are stacked together within a single package working at extremely high frequencies, the package design in terms of system simulation – mechanical, electrical, and thermal – is becoming one of most important development activities for delivering robust system solutions. In this chapter, the package historical trends against the system evolution will be discussed, analyzing the principal integration challenging. Among them, this chapter will focus on thin die thickness trend, taking into account the new process technology and the related impact on the device characteristics. This is considered as one of the most important back-end technologies, enabling the new era of the package integration and miniaturization. New interconnection technologies among dies will also be reviewed and discussed by deeply analyzing the features of through silicon via process. This process will allow the new interconnection scheme for microelectronics for the next decade.

NAND Flash memory has become the preferred nonvolatile choice for portable consumer electronic devices. Features such as high density, low cost, and fast write times make NAND perfectly suited for media applications where large files of sequential data need to be loaded into the memory quickly and repeatedly. This chapter starts with an overview of the basic functionalities of the NAND Flash storage. Popular devices like Flash cards are then described as an example of NAND-based systems. The last part of this chapter deals with all the state-of-the-art technologies used to reduce the equivalent bit size. In particular, the reader will find an overview of the multilevel storage and of the 3D solutions from single-die 3D architectures to packages containing multiple dies.

In recent 30 years, optical data storage has undergone persistent development in response to the ever-growing information storage demands as a result of technological and market competition from magnetic and semiconductor memory technology. This chapter reviews basic principles and some important R&D progress on popular optical disk technology and other high-density optical storage technologies, such as superresolution, near-field, and three-dimensional optical storage technologies.

This chapter will deal with natural forms of learning and memory, with particular emphasis on the vertebrate and human brain function. The topographical and temporal organization of multiple interacting memory systems will be first described at the cognitive and psychological level. Recent developments in pharmacology and molecular genetics will then be discussed to provide a state-of-the-art description of the molecular and cellular mechanisms underlying memory formation, consolidation, retrieval, and reconsolidation. Finally, a comparative analysis between natural and artificial memory devices will be outlined.

This chapter discusses about semiconductor memories. We will see what does it means, today, to “remember” using solid-state electronics. Volatile memory and non-volatile memory will be analyzed, starting from the concept of the electrical parameter modification, capacitance, resistance, threshold, etc., to storage information. RAM and floating gate memory architecture and their working operations will be discussed.