Authors:
- This book gives a new view on how the processors for HPC, AI and Data Science should be designed. Traditional approaches are, even when called "quantitative", evolutionary, in the sense that the starting point is the existing software optimized to existing processors. In this book, first the applications are classified into several categories, so that their requirements can be summarized. Then the concept of the efficiency is introduced as the guiding principle for the processor design
- The efficiency is simply defined as the fraction of electricity (and also silicon die area) used in the combinatorial logics for arithmetic operations. In many of modern processors, efficiencies in this sense are surprisingly low, implying that there is huge room of improvements. Also, writing application software for these modern processors has become very difficult
- In this book, examples of designs with very high efficiency are presented, with the overview on how the application software can be developed, based on the author's experience on the development of SIMD parallel processors
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (7 chapters)
-
Front Matter
-
Back Matter
About this book
In chapter 2, the history of the development of high-performance processor is overviewed, to discuss what quantity we can use to measure the efficiency of these processors. The proposed quantity is the ratio between the minimum possible energy consumption and the actual energy consumption for a given application using a given semiconductor technology. In chapter 3, whether or not this quantity can be used in practice is discussed, for many real-world applications.
In chapter 4, general-purpose processors in the past and present are discussed from this viewpoint. In chapter 5, how we can actually design processors with near-optimal efficiencies is described, and in chapter 6 how we can program such processors. This book gives a new way to look at the field of the design of high-performance processors.
Authors and Affiliations
-
Kobe University, Kobe, Japan
Junichiro Makino
About the author
He has developed a series of special-purpose computers for many-body problems (GRAPE) and SIMD many-core processors (GRAPE-DR, MN-Core).
Bibliographic Information
Book Title: Principles of High-Performance Processor Design
Book Subtitle: For High Performance Computing, Deep Neural Networks and Data Science
Authors: Junichiro Makino
DOI: https://doi.org/10.1007/978-3-030-76871-3
Publisher: Springer Cham
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer Nature Switzerland AG 2021
Hardcover ISBN: 978-3-030-76870-6Published: 21 August 2021
Softcover ISBN: 978-3-030-76873-7Published: 22 August 2022
eBook ISBN: 978-3-030-76871-3Published: 20 August 2021
Edition Number: 1
Number of Pages: XIV, 160
Number of Illustrations: 19 b/w illustrations, 8 illustrations in colour
Topics: Processor Architectures, System Performance and Evaluation, Algorithm Analysis and Problem Complexity