Zur Startseite gehen
0,00 €*
Cover: 9783030768737 | Principles of High-Performance Processor Design | Junichiro Makino
Dekorationsartikel gehören nicht zum Leistungsumfang.
Principles of High-Performance Processor Design
For High Performance Computing, Deep Neural Networks and Data Science
Taschenbuch von Junichiro Makino
Sprache: Englisch

137,95 €*

inkl. MwSt.

Versandkostenfrei per Post / DHL

Lieferzeit 4-7 Werktage

Kategorien:
Beschreibung
This book describes how we can design and make efficient processors for high-performance computing, AI, and data science. Although there are many textbooks on the design of processors we do not have a widely accepted definition of the efficiency of a general-purpose computer architecture. Without a definition of the efficiency, it is difficult to make scientific approach to the processor design. In this book, a clear definition of efficiency is given and thus a scientific approach for processor design is made possible.
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.
This book describes how we can design and make efficient processors for high-performance computing, AI, and data science. Although there are many textbooks on the design of processors we do not have a widely accepted definition of the efficiency of a general-purpose computer architecture. Without a definition of the efficiency, it is difficult to make scientific approach to the processor design. In this book, a clear definition of efficiency is given and thus a scientific approach for processor design is made possible.
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.
Über den Autor
Junichiro Makino received PhD from the University of Tokyo. After he received PhD, he worked at University of Tokyo, the National Astronomical Observatory of Japan, and Tokyo Institute of Technology. Since Apr 2014, he is a subleader of the exascale computing project and the team leader of the Co-design team, AICS, RIKEN, and since Mar 2016 he works also at Kobe University. His research interests are stellar dynamics, large-scale scientific simulation and high-performance computing.
He has developed a series of special-purpose computers for many-body problems (GRAPE) and SIMD many-core processors (GRAPE-DR, MN-Core).
Zusammenfassung

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

Inhaltsverzeichnis
Introduction.- Traditional approaches and their limitations.- The lower limit of energy consumption.- Analysis of past and present processors.- "Near-optimal" designs.- Software.- Present, Past and Future.
Details
Erscheinungsjahr: 2022
Genre: Informatik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Seiten: 176
Inhalt: xiv
160 S.
19 s/w Illustr.
8 farbige Illustr.
160 p. 27 illus.
8 illus. in color.
ISBN-13: 9783030768737
ISBN-10: 3030768732
Sprache: Englisch
Ausstattung / Beilage: Paperback
Einband: Kartoniert / Broschiert
Autor: Makino, Junichiro
Auflage: 1st ed. 2021
Hersteller: Springer International Publishing
Springer International Publishing AG
Maße: 235 x 155 x 10 mm
Von/Mit: Junichiro Makino
Erscheinungsdatum: 22.08.2022
Gewicht: 0,277 kg
preigu-id: 122451960
Über den Autor
Junichiro Makino received PhD from the University of Tokyo. After he received PhD, he worked at University of Tokyo, the National Astronomical Observatory of Japan, and Tokyo Institute of Technology. Since Apr 2014, he is a subleader of the exascale computing project and the team leader of the Co-design team, AICS, RIKEN, and since Mar 2016 he works also at Kobe University. His research interests are stellar dynamics, large-scale scientific simulation and high-performance computing.
He has developed a series of special-purpose computers for many-body problems (GRAPE) and SIMD many-core processors (GRAPE-DR, MN-Core).
Zusammenfassung

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

Inhaltsverzeichnis
Introduction.- Traditional approaches and their limitations.- The lower limit of energy consumption.- Analysis of past and present processors.- "Near-optimal" designs.- Software.- Present, Past and Future.
Details
Erscheinungsjahr: 2022
Genre: Informatik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Seiten: 176
Inhalt: xiv
160 S.
19 s/w Illustr.
8 farbige Illustr.
160 p. 27 illus.
8 illus. in color.
ISBN-13: 9783030768737
ISBN-10: 3030768732
Sprache: Englisch
Ausstattung / Beilage: Paperback
Einband: Kartoniert / Broschiert
Autor: Makino, Junichiro
Auflage: 1st ed. 2021
Hersteller: Springer International Publishing
Springer International Publishing AG
Maße: 235 x 155 x 10 mm
Von/Mit: Junichiro Makino
Erscheinungsdatum: 22.08.2022
Gewicht: 0,277 kg
preigu-id: 122451960
Warnhinweis

Ähnliche Produkte

Ähnliche Produkte

Taschenbuch
Cover: 9783519005094 | Moderne Kryptographie | Eine Einführung | Thomas Wilke (u. a.) | Buch
Moderne Kryptographie
Eine Einführung
EAN: 9783519005094
Sprache: Deutsch
Von/Mit: Thomas Wilke (u. a.)

32,99 €*

Lieferzeit 1-2 Werktage

Taschenbuch
Cover: 9783319218908 | Quantum Information Processing with Finite Resources | Tomamichel | IX
Quantum Information Processing with Finite Resources
Mathematical Foundations
EAN: 9783319218908
Sprache: Englisch
Von/Mit: Marco Tomamichel

66,40 €*

Lieferzeit 4-7 Werktage

Taschenbuch
Cover: 9783540420620 | Drawing Graphs | Methods and Models | Dorothea Wagner (u. a.) | Buch
Drawing Graphs
Methods and Models
EAN: 9783540420620
Sprache: Englisch
Von/Mit: Dorothea Wagner (u. a.)

54,95 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9783869620879 | Innovation der Persuasion | Holger Schramm (u. a.) | Taschenbuch
Innovation der Persuasion
Die Qualität der Werbe- und Markenkommunikation in neuen Medienwelten
EAN: 9783869620879
Sprache: Deutsch
Von/Mit: Holger Schramm (u. a.)

29,50 €*

Lieferzeit 1-2 Wochen

Buch
Cover: 9789814447638 | Voronoi Diagrams and Delaunay Triangulations | Aurenhammer (u. a.)
VORONOI DIAGRAMS AND DELAUNAY TRIANGULATIONS
EAN: 9789814447638
Sprache: Englisch
Von/Mit: Rolf Klein & Der-Tsai Franz Aurenhammer

98,40 €*

Lieferzeit 2-3 Wochen

Buch
Cover: 9783540634461 | Algebraic Aspects of Cryptography | Neal Koblitz | Buch | Englisch
Algebraic Aspects of Cryptography
EAN: 9783540634461
Sprache: Englisch
Von/Mit: Neal Koblitz

165,95 €*

Lieferzeit 2-3 Wochen

Taschenbuch
Cover: 9781484239384 | Practical React Native | Frank Zammetti | Taschenbuch | Paperback | xv
Practical React Native
Build Two Full Projects and One Full Game using React Native
EAN: 9781484239384
Sprache: Englisch
Von/Mit: Frank Zammetti

69,30 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9781941043134 | Fundamentals of Data Science Part III | Machine Learning | Maruskin
Fundamentals of Data Science Part III
Machine Learning
EAN: 9781941043134
Sprache: Englisch
Von/Mit: Jared M. Maruskin

70,80 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9781394251322 | Teach Yourself VISUALLY MacBook Pro and MacBook Air | Guy Hart-Davis
Teach Yourself VISUALLY MacBook Pro and MacBook Air
EAN: 9781394251322
Sprache: Englisch
Von/Mit: Guy Hart-Davis

28,80 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9780321117847 | Algorithmics | The Spirit of Computing | David Harel (u. a.) | Buch
Algorithmics
The Spirit of Computing
EAN: 9780321117847
Sprache: Englisch
Von/Mit: David Harel (u. a.)

99,95 €*

Lieferzeit 1-2 Wochen

Diese Website verwendet Cookies, um eine bestmögliche Erfahrung bieten zu können. Mehr Informationen ...