Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!mintaka!spdcc!iecc!compilers-sender From: ds@juniper.cray.com (David Sielaff) Newsgroups: comp.compilers Subject: Re: Compilers for parallel computing Keywords: parallel, optimize, books Message-ID: <91-05-097@comp.compilers> Date: 23 May 91 06:34:03 GMT References: <91-05-095@comp.compilers> Sender: compilers-sender@iecc.cambridge.ma.us Reply-To: ds@juniper.cray.com (David Sielaff) Organization: Cray Research, Inc., Eagan, MN Lines: 49 Approved: compilers@iecc.cambridge.ma.us In article <91-05-095@comp.compilers> you write: >[suggestions wanted on these and other books] > >Gelernter and Nicolau: Languages and compilers for parallel computing (Pitman) > >Polychronopoulos: Parallel programming and compilers (Kluwer Academic) > >Wolfe: Optimizing supercompilers for supercomputers (Pitman) > >Zima and Chapman: Supercompilers for parallel and vector computers (Addison >Wesley) The Wolfe book is a reprint of his PhD thesis (if I'm not mistaken - I've read his thesis, but have only seen the book in bookstores). Anyway, it's a good book, but more of an overview of the subject, basically, here's what dependence analysis is, and here's how you use it, and here's a bunch of things you can do with it. I think it's definitely worth the time to read. I've browsed through the Polychronopoulos book, and it looked good, but I couldn't tell you anything more about it. Another good book to look at along these lines is: Utpal Bannerjee: Dependence Analysis for Supercomputing (Kluwer Academic) This book has a very thorough treatment of dependence analysis, but not much else (doesn't tell you what good it does, only what it is). It tries to be a theoretical foundation for the study of dependence analysis and its use it various areas (such as parallelizing compilers). Probably read this book after Wolfe's. >Can anybody recommend one of these, or any other? ... I don't know of any good books on other approaches to parallelism, such as functional/data flow programming (not completely the same thing, but...). I have heard of one book on the subject, however: Boleslaw Szymanski: Parallel Functional Programming Languages and Compilers (ACM) I personally would like to read it sometime, but I don't know if it has even been published yet (wasn't out the last time I checked). I guess that's my list of books, and once you've got that down, there's a lot of information that lives in articles and tech reports that hasn't made it to books yet. Dave Sielaff Cray Research, Inc. C Compiler Guy -- Send compilers articles to compilers@iecc.cambridge.ma.us or {ima | spdcc | world}!iecc!compilers. Meta-mail to compilers-request.