Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2014 | Book

Introduction Read chapter Read first chapter

Flash Memories

Economic Principles of Performance, Cost and Reliability Optimization

Author: Detlev Richter

Publisher: Springer Netherlands

Book Series : Springer Series in Advanced Microelectronics

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik"

Login to get access
insite
SEARCH

About this book

The subject of this book is to introduce a model-based quantitative performance indicator methodology applicable for performance, cost and reliability optimization of non-volatile memories. The complex example of flash memories is used to introduce and apply the methodology. It has been developed by the author based on an industrial 2-bit to 4-bit per cell flash development project. For the first time, design and cost aspects of 3D integration of flash memory are treated in this book.

Cell, array, performance and reliability effects of flash memories are introduced and analyzed. Key performance parameters are derived to handle the flash complexity. A performance and array memory model is developed and a set of performance indicators characterizing architecture, cost and durability is defined.

Flash memories are selected to apply the Performance Indicator Methodology to quantify design and technology innovation. A graphical representation based on trend lines is introduced to support a requirement based product development process.

The Performance Indicator methodology is applied to demonstrate the importance of hidden memory parameters for a successful product and system development roadmap.

Flash Memories offers an opportunity to enhance your understanding of product development key topics such as:

· Reliability optimization of flash memories is all about threshold voltage margin understanding and definition;
· Product performance parameter are analyzed in-depth in all aspects in relation to the threshold voltage operation window;
· Technical characteristics are translated into quantitative performance indicators;
· Performance indicators are applied to identify and quantify product and technology innovation within adjacent areas to fulfill the application requirements with an overall cost optimized solution; · Cost, density, performance and durability values are combined into a common factor – performance indicator - which fulfills the application requirements

Table of Contents

Frontmatter
Chapter 1. Introduction
Abstract
Economic rules have a strong impact on technology and design and define or impact the architecture trends in the semiconductor industry. The scope of this work is to develop a model-based performance indicator methodology applicable for performance, cost and reliability optimization of non-volatile memories.
Detlev Richter
Chapter 2. Fundamentals of Non-Volatile Memories
Abstract
The subject of this chapter is to introduce the fundamentals of non-volatile memories. An overview about electron and non-electron based cells is given followed by a cell assessment for high density non-volatile memories. The link between memory cell and memory array performance parameters is introduced and in depth analysed for NAND and NOR array architectures. The design specific aspects of sensing and program and erase algorithm techniques are introduced for floating gate and charge trapping cell based flash memories.
Detlev Richter
Chapter 3. Performance Figures of Non-Volatile Memories
Abstract
The selection of one memory architecture during the system development process is based on an assessment of cost per bit, scalability, and power efficiency and performance values.
Detlev Richter
Chapter 4. Fundamentals of Reliability for Flash Memories
Abstract
The focus of this chapter is the link between reliability specification parameter and the flash behaviour over lifetime.
Detlev Richter
Chapter 5. Memory Based System Development and Optimization
Abstract
The availability of multi-core microprocessors, fast embedded RAM’s and large non-volatile solid-state memories with high data bandwidth influence the system architecture. The principles of optimization of high performance microprocessors and electronic systems are well described in the literature [1–3]. The established hardware-software co-design has to be improved by a concurrent design approach of the system and the application specification and software [4]. The end of the microprocessor GHz race has enforced the adaption of multi-core microprocessor architectures. The need of energy optimized systems continuously forces architectures with distributed calculation power surrounded by embedded memories. The calculation power has to be increased generation by generation which is ensured by multi-core microprocessor architectures. The semiconductor memories were developed as commodity parts fulfilling system requirement specifications in the past. The full system optimization potential of solid-state non-volatile memories can be utilized if the system architecture including the multi-core microprocessor is designed to offer the best support for flash memories. The issue is how to reduce the complexity of flash based memory sub-systems to derive cost, durability and performance optimized decisions on system architecture level based on quantitative values. The subject of this work is to introduce a model-based quantitative performance indicator methodology applicable for performance, cost and reliability optimization of non-volatile memories and memory-centric systems. This chapter describes the current separated development processes, introduces a set of efficiency parameter and describes the non-volatile complexity dilemma.
Detlev Richter
Chapter 6. Memory Optimization: Key Performance Indicator Methodology
Abstract
This chapter introduces the model-based quantitative performance indicator methodology applicable for performance, cost and reliability optimization of non-volatile memories. The complex example of NAND flash memories is used to develop the methodology based on a benchmarking of NAND flash product innovations along the CMOS shrink roadmap. A performance and array model is introduced and a set of performance indicators characterizing architecture, cost and durability is defined.
Detlev Richter
Chapter 7. System Optimization Based on Performance Indicator Models
Abstract
The industry is adapting multi-core microprocessor hardware in various application areas. The available additional calculation power accelerates the change from hardware into software based solutions.
Detlev Richter
Chapter 8. Conclusion and Outlook
Abstract
Non-volatile memories were selected to introduce a model-based quantitative performance indicator methodology. The complex example of flash memories is used to introduce and apply the methodology to quantify product innovation during the memory development process. Non-volatile solid-state storage systems are a key enabler technology for mostly all mobile devices and for multi-core based systems in general. The development requirements for flash memories are extremely high managing the non-volatile design and technology complexity, achieving the cost targets and incorporating disruptive innovation at the right moment in time.
Detlev Richter
Backmatter
Metadata
Title
Flash Memories
Author
Detlev Richter
Copyright Year
2014
Publisher
Springer Netherlands
Electronic ISBN
978-94-007-6082-0
Print ISBN
978-94-007-6081-3
DOI
https://doi.org/10.1007/978-94-007-6082-0