[comp.lang.fortran] Supercomputers & FORTRAN Book

rchrd@lll-crg.llnl.gov (Richard Friedman) (11/24/88)

Readers of this newsgroup might be interested in the following book
just published by Academic Press :

          A GUIDEBOOK TO FORTRAN ON SUPERCOMPUTERS

             John Levesque and Joel Williamson
               Pacific-Sierra Research Corp.

The blurb reads as follows:

  "This book is intended to be used intensively by FORTRAN programmers
who use supercomputers.  All previous books on this topic have either 
addressed very academic, abstract topics and examples that were not 
general enough to be applied to a large collection of FORTRAN programs.
The abundant examples used in the book cover a large range of DO loop
characteristics whose discussion can be applied to existing FORTRAN
programs.  This is the first book that addresses "real world" FORTRAN
examples that can be used to demonstrate how FORTRAN programs can be 
optimized systematically.  Many of the restructuring examples from the 
book could be used immediately to optimize a reader's FORTRAN code
for a substantial savings in execution time.  FORTRAN programmers in all
application areas will find this volume essential to their work."
  
  "This book, the first of its kind, explains in detail both the
underlying architecture of today's supercomputers and the manner by
which a compiler maps FORTRAN code onto that architecture.  Most
important, the constructs preventing full optimizations are outlined,
and specific strategies for restructuring a program are provided."

November, 1988  218pp $40  ISBN 0-12-444760-0
Academic Press   1-800-321-5068
PSR: 916 621 1600 (Placerville, Ca.)
-- 
 ...Richard Friedman [rchrd]  Berkeley, CA.                         
    rchrd@well.uucp        -or-
   {ucbvax,lll-lcc,pacbell,hplabs}!well!rchrd
[If anyone reads it and wants to send in a review, even a very short one,
I'd be pleased to post it.  -John]
--
Send compilers articles to ima!compilers or, in a pinch, to Levine@YALE.EDU
Plausible paths are { decvax | harvard | yale | bbn}!ima
Please send responses to the originator of the message -- I cannot forward
mail accidentally sent back to compilers.  Meta-mail to ima!compilers-request