"Machine-independent ""and"" and ""or"" parallel execution of logic programs"
Ramkumar, Balkrishna
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/19811
Description
Title
"Machine-independent ""and"" and ""or"" parallel execution of logic programs"
Author(s)
Ramkumar, Balkrishna
Issue Date
1991
Doctoral Committee Chair(s)
Kale, Laxmikant V.
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Computer Science
Language
eng
Abstract
Parallel machines are becoming increasingly cheap and more easily available. Commercial companies have already announced MIMD machines with more than 8000 processors. This prompts three questions: Should the programmer have to rewrite existing software for each new machine that comes along? Should it be necessary for the programmer to have intimate knowledge of the target machine in order to program it efficiently? Is it necessary for the programmer to identify the parallelism in programs explicitly?
Our thesis is that the answer is 'no' on all three counts. We demonstrate that it is possible for users to write parallel programs in a machine independent manner. We address this problem at two levels. We first describe the design and implementation of a parallel run time support system called the Chare kernel that provides a uniform interface to the programmer on the class of MIMD machines. This support system makes it possible for programmers to write machine independent programs efficiently. We choose the logic programming paradigm where a high level specification of the problem is possible and it is amenable to the implicit detection of parallelism. We have designed and implemented a compiler that exploits AND and OR parallelism in logic programs. We have developed an emulator for abstract machine code generated by our compiler as an application on the Chare kernel which runs without modification on shared memory and nonshared memory machines alike.
This thesis discusses addresses algorithmic issues relating to the design and implementation of an efficient parallel Prolog compiler on both shared and nonshared machines. This work differs significantly from most other related research, in part due to their dependence on a global memory address space. This work is the first to demonstrate that nonshared machines like the Intel and NCUBE hypercubes can be exploited effectively for the parallel execution of logic programs. It also provides a convincing demonstration of machine independent parallel programming.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
