Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
High performance computing : modern systems and practices
Sterling T., Anderson M., Brodowicz M., Morgan Kaufmann Publishers Inc., Cambridge, MA, 2018. 718 pp. Type: Book (978-0-124201-58-3)
Date Reviewed: Aug 6 2018

Either a layperson in programming or an experienced serial programming expert will like this textbook, which presents all the flavors of large-scale and parallel computing. All the relevant topics are covered to varying extents, but generally the book is aimed at beginners in high-performance computing (HPC). For such readers, the book presents a lot of interesting information in a very accessible way.

The textbook is not limited to theoretical data; it also introduces concrete programming examples and ways of configuring/instructing a (super)computer. Thus, it can also be used for laboratory exercises. The content covered includes: main concepts and a historical overview of the area (chapter 1); basic computer architectures (chapter 2); clusters (chapter 3); benchmarking for high-performance computers (chapter 4); the SLURM and Portable Batch System (PBS) resource managers (chapter 5); symmetric multiprocessor architectures (chapter 6); fundamentals of the OpenMP language (chapter 7); the message-passing interface (chapter 8); algorithms showing the power of parallelization (chapter 9); various libraries supporting parallelization (chapter 10); operating system basics (chapter 11); some concepts on visualization (chapter 12); performance monitoring in computer systems (chapter 13); debugging (chapter 14); accelerator architectures, including graphics processing units (GPUs) (chapter 15); the OpenACC framework (chapter 16); storage systems (chapter 17); file systems (chapter 18); the MapReduce model (chapter 19); and the idea of checkpointing (chapter 20). The final chapter (21) elaborates on some potential avenues for future development. Appendix A presents the basics of C with examples of parallelizable algorithms, and Appendix B covers the fundamentals of the Linux command-line interface (CLI). The book ends with a glossary of basic terms and an index.

The chapters were constructed in a clear and systematic manner: first, a brief definition of the problem (often intertwined with a historical sketch, including biographical notes and memo boxes); then, the topic is extended; and finally, as befits a regular textbook, a summary of the main ideas and a selection of questions and exercises. Each chapter includes its own set of references. It is worth noting that Sterling, one of the authors, has made considerable contributions to the HPC field. The writing is easy to understand and the book is really aimed at readership. It could work as a standalone textbook for a course in computer architectures and parallel computing.

More reviews about this item: Amazon

Reviewer:  Piotr Cholda Review #: CR146186 (1811-0550)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Super (Very Large) Computers (C.5.1 ... )
 
 
Parallel Processors (C.1.2 ... )
 
 
System Architectures (C.0 ... )
 
Would you recommend this review?
yes
no
Other reviews under "Super (Very Large) Computers": Date
Parallel supercomputing: methods, algorithms and applications
Carey G. (ed) John Wiley & Sons, Inc., New York, NY,1989. Type: Divisible Book
Dec 1 1991
Supercomputers: algorithms, architectures, and scientific computation
Matsen F. (ed), Tajima T., University of Texas Press, Austin, TX, 1986. Type: Book (9780292703889)
Dec 1 1991
Evaluating supercomputers
van der Steen A., Chapman & Hall, Ltd., London, UK, 1990. Type: Book (9780442311988)
Dec 1 1991
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