The High Performance Fortran Handbook (Scientific and...

Features

• Cover Type: Paperback with 345 pages
• Published by: The MIT Press November 1, 1993
• Written in: English
• ISBN 10 Number: 0262610949
• ISBN 13 Number: 978-0262610940
• Book Dimensions: 9 x 8.1 x 0.8 inches
• Weighs: 1.8 pounds

Book Description
High Performance Fortran (HPF) is a set of extensions to Fortran expressing parallel execution at a relatively high level. For the thousands of scientists, engineers, and others who wish to take advantage of the power of both vector and parallel supercomputers, five of the principal authors of HPF have teamed up here to write a tutorial for the language.

There is an increasing need for a common parallel Fortran that can serve as a programming interface with the new parallel machines that are appearing on the market. While HPF does not solve all the problems of parallel programming, it does provide a portable, high-level expression for data-parallel algorithms that brings the convenience of sequential Fortran a step closer to today's complex parallel machines.

About The Author
Charles H. Koelbel is Program Director, Advanced Computational Research, National Science Foundation. David B. Loveman is Senior Program Manager of the High Performance Computing Group at Digital Equipment Corporation. Robert S. Schreiber is Senior Scientist at the Research Institute for Advanced Computer Science. Guy L. Steele Jr. is Senior Scientist at Sun Microsystems. Mary E. Zosel is a member of the research staff at Lawrence Livermore National Laboratories.

Reader Reviews
This review is from: The High Performance Fortran Handbook (Hardcover) Fortran is alive and well, Java and C++ notwithstanding. It still does a lot of the heavy lifting in numerical computing of all kinds. But, in order to stay relevant, it's had to change with the high-end machines that run those computations. Fortran ninety came a long way from F77, but not far enough. It offers fair constructs for vectorizing and for loop-level parallelism in the computation. HPF does the other half of the job: it talks about the memory structures needed to put the data where the processing is, or close to it. It mentions the processors, of course, but its real value is in abstracting non-uniform memory access in terms natural to the Fortran programmer. Really using a parallel computer means coordinating the processors and memories closely; in Fortran terms, the code and the arrays that it processes. The authors do a great job of integrating HPF into F90 programming practice. This can, however, be confusing to a reader who's not already fluent in F90. If that's you, I strongly recommend an F90 reference to keep at your side while you read this. It's not for beginners, but beginners don't have the problems that supercomputers address. If performance computing is your world, then this is an outstanding resource. //wiredweird Comment | | (Report this)