THAL: An Actor System for Efficient and Scalable Concurrent Computing
Kim, Wooyoung
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/2142/81881
Description
Title
THAL: An Actor System for Efficient and Scalable Concurrent Computing
Author(s)
Kim, Wooyoung
Issue Date
1997
Doctoral Committee Chair(s)
Agha, Gul A.
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
This thesis studies how to support communication between actors efficiently. First, we discuss communication patterns commonly arising in many parallel applications in the context of an experimental actor-based language, THAL. The language provides as communication abstractions concurrent call/return communication, delegation, broadcast, and local synchronizaton constraints. The thesis shows how the abstractions are efficiently implemented on stock-hardware distributed memory multicomputers. Specifically, we describe an experimental runtime system and compiler. The THAL runtime system recognizes and exploits the cost difference between local and remote message scheduling; it transparently supports actor's location independence; and, it implements non-blocking remote actor creation to improve utilization of computation resources. The THAL compiler incorporates a number of analysis and transformation techniques which work hand in hand with the runtime system. Among the techniques are: global data flow analysis to infer type information--the compiler optimizes code for each message send according to the type of its receiver expression; concurrency restoration through dependence analysis and source-to-source transformation; concurrency control with dependence analysis which allows multiple threads to be active on an actor with thread safety, i.e., with no interference between the threads. Experiments on a stock-hardware distributed memory multicomputer (CM-5) show that the compiler and the run-time system yield efficiency and scalability on applications with sufficiently large granularity which are comparable to the performance of other less flexible systems.
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.
