skip to main content

DOE PAGESDOE PAGES

Title: Evolution of a minimal parallel programming model

Here, we take a historical approach to our presentation of self-scheduled task parallelism, a programming model with its origins in early irregular and nondeterministic computations encountered in automated theorem proving and logic programming. We show how an extremely simple task model has evolved into a system, asynchronous dynamic load balancing (ADLB), and a scalable implementation capable of supporting sophisticated applications on today’s (and tomorrow’s) largest supercomputers; and we illustrate the use of ADLB with a Green’s function Monte Carlo application, a modern, mature nuclear physics code in production use. Our lesson is that by surrendering a certain amount of generality and thus applicability, a minimal programming model (in terms of its basic concepts and the size of its application programmer interface) can achieve extreme scalability without introducing complexity.
Authors:
 [1] ;  [2] ;  [1]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
  2. Middle Tennessee State Univ., Murfreesboro, TN (United States)
Publication Date:
Grant/Contract Number:
AC02-06CH11357
Type:
Accepted Manuscript
Journal Name:
International Journal of High Performance Computing Applications
Additional Journal Information:
Journal Volume: 2017; Journal ID: ISSN 1094-3420
Publisher:
SAGE
Research Org:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING
OSTI Identifier:
1400403

Lusk, Ewing, Butler, Ralph, and Pieper, Steven C. Evolution of a minimal parallel programming model. United States: N. p., Web. doi:10.1177/1094342017703448.
Lusk, Ewing, Butler, Ralph, & Pieper, Steven C. Evolution of a minimal parallel programming model. United States. doi:10.1177/1094342017703448.
Lusk, Ewing, Butler, Ralph, and Pieper, Steven C. 2017. "Evolution of a minimal parallel programming model". United States. doi:10.1177/1094342017703448. https://www.osti.gov/servlets/purl/1400403.
@article{osti_1400403,
title = {Evolution of a minimal parallel programming model},
author = {Lusk, Ewing and Butler, Ralph and Pieper, Steven C.},
abstractNote = {Here, we take a historical approach to our presentation of self-scheduled task parallelism, a programming model with its origins in early irregular and nondeterministic computations encountered in automated theorem proving and logic programming. We show how an extremely simple task model has evolved into a system, asynchronous dynamic load balancing (ADLB), and a scalable implementation capable of supporting sophisticated applications on today’s (and tomorrow’s) largest supercomputers; and we illustrate the use of ADLB with a Green’s function Monte Carlo application, a modern, mature nuclear physics code in production use. Our lesson is that by surrendering a certain amount of generality and thus applicability, a minimal programming model (in terms of its basic concepts and the size of its application programmer interface) can achieve extreme scalability without introducing complexity.},
doi = {10.1177/1094342017703448},
journal = {International Journal of High Performance Computing Applications},
number = ,
volume = 2017,
place = {United States},
year = {2017},
month = {4}
}