Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Non-volatile in-memory computing by spintronics
Yu H., Ni L., Wang Y., Morgan & Claypool Publishers, San Rafael, CA, 2016. 186 pp. Type: Book (978-1-627052-94-8)
Date Reviewed: Dec 11 2017

With quintillions of calculations per second, exascale computing is a challenge for the world of scientific discovery and for advancing economic competitiveness. In certain applications such as climate change and climate modeling, precision medicine, energy systems, plasma physics and controlled fusion, large-scale data processing, machine learning, and artificial intelligence, exascale computing has extraordinary potential. The next generation of memory technologies enables new opportunities for exascale computing systems. With the possibility of integrating memory and logic into a single device, spintronics-based memory is an alternative approach under development.

Non-volatile in-memory computing by spintronics covers very interesting research topics in the field of in-memory-based computing as a challenge for exascale systems. The non-volatile, memory-based, in-memory computing architecture is the original contribution of the authors. Developing data encryption on a non-volatile memory-based hardware platform is another well-grounded subject. In the last part, the authors analyze how to develop machine-learning accelerators using data analytics on the in-memory architecture and machine learning results. The contributions in this book are of major interest to researchers, academics, and higher education students. The book has four chapters, each with its own extended list of references.

The aim of chapter 1, “Introduction,” is to offer several elementary notions of computer memory, in particular the concepts of non-volatile spintronic memory. Topics addressed for traditional memory architecture are the basic magnetization process, magnetization damping spin-transfer torque, magnetization dynamics, and domain wall propagation. Briefly presented at the end of the chapter, the subject of non-volatile in-memory computing as the next-generation architecture for streaming analytics highlights the capability to move computing to where the data resides.

Chapter 2, “Non-Volatile Spintronic Device and Circuit,” is the central part of the book. It is dedicated to spin-transfer torque magnetic random-access memory (STT-MRAM) and racetrack memory, and domain wall nanowire (DWNN), which execute both data storage and in-memory logic. Some feasible solutions are investigated based on magnetization dynamics and ion migration dynamics, and a new spintronics-based storage and logic implementation. Spintronic storage, spintronic logic, and spintronic interconnection are explained in detail in the second part of this chapter.

The in-memory advanced encryption standard and the domain wall-based SIMON block cipher are explained in detail in chapter 3, “In-Memory Data Encryption.” Area efficiency, low power, and high throughput in-memory encryption engines are some of the advantages of the solutions presented.

Chapter 4, “In-memory Data Analytics,” contains new results for data analytics on the in-memory architecture. The first part of the chapter explores an in-memory machine learning approach on non-volatile memory-based computing platforms by utilizing the MapReduce-based matrix multiplication. In-memory face recognition is the subject of the second part of the chapter. The investigation of this subject concerns energy-efficient STT-MRAM with spare-represented data, quality of service-aware adaptive current scaling, and STT-RAM-based hardware mapping.

This work focuses on specific research topics in the field of in-memory-based computing, with a special mention of the non-volatile, memory-based, in-memory computing architecture as the original contribution of the authors. The book is well written and argued, keenly referenced, and located within in-memory-based computing research. These are the main reasons why I recommend this book to researchers, academics and higher education students worldwide.

Reviewer:  Eugen Petac Review #: CR145701 (1802-0033)
Bookmark and Share
 
Performance of Systems (C.4 )
 
 
General (C.1.0 )
 
 
General (B.3.0 )
 
Would you recommend this review?
yes
no
Other reviews under "Performance of Systems": Date
A computer and communications network performance analysis primer
Stuck B., Arthurs E., Prentice-Hall, Inc., Upper Saddle River, NJ, 1985. Type: Book (9789780131639812)
Jun 1 1985
A mean value performance model for locking in databases
Tay Y., Suri R. (ed), Goodman N. Journal of the ACM 32(3): 618-651, 1985. Type: Article
Mar 1 1986
The relationship between benchmark tests and microcomputer price
Sircar S., Dave D. Communications of the ACM 29(3): 212-217, 1986. Type: Article
Nov 1 1986
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy