skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Structured hints : extracting and abstracting domain expertise.

Abstract

We propose a new framework for providing information to help optimize domain-specific application codes. Its design addresses problems that derive from the widening gap between the domain problem statement by domain experts and the architectural details of new and future high-end computing systems. The design is particularly well suited to program execution models that incorporate dynamic adaptive methodologies for live tuning of program performance and resource utilization. This new framework, which we call 'structured hints', couples a vocabulary of annotations to a suite of performance metrics. The immediate target is development of a process by which a domain expert describes characteristics of objects and methods in the application code that would not be readily apparent to the compiler; the domain expert provides further information about what quantities might provide the best indications of desirable effect; and the interactive preprocessor identifies potential opportunities for the domain expert to evaluate. Our development of these ideas is progressing in stages from case study, through manual implementation, to automatic or semi-automatic implementation. In this paper we discuss results from our case study, an examination of a large simulation of a neural network modeled after the neocortex.

Authors:
; ; ; ; ; ; ;
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC); National Science Foundation (NSF)
OSTI Identifier:
951258
Report Number(s):
ANL/MCS-TM-303
TRN: US200911%%414
DOE Contract Number:  
DE-AC02-06CH11357
Resource Type:
Technical Report
Country of Publication:
United States
Language:
ENGLISH
Subject:
97 MATHEMATICS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; COMPUTER CODES; DESIGN; IMPLEMENTATION; NEURAL NETWORKS; PERFORMANCE

Citation Formats

Hereld, M., Stevens, R., Sterling, T., Gao, G. R., Mathematics and Computer Science, California Inst. of Tech., Louisiana State Univ., and Univ. of Delaware. Structured hints : extracting and abstracting domain expertise.. United States: N. p., 2009. Web. doi:10.2172/951258.
Hereld, M., Stevens, R., Sterling, T., Gao, G. R., Mathematics and Computer Science, California Inst. of Tech., Louisiana State Univ., & Univ. of Delaware. Structured hints : extracting and abstracting domain expertise.. United States. doi:10.2172/951258.
Hereld, M., Stevens, R., Sterling, T., Gao, G. R., Mathematics and Computer Science, California Inst. of Tech., Louisiana State Univ., and Univ. of Delaware. Mon . "Structured hints : extracting and abstracting domain expertise.". United States. doi:10.2172/951258. https://www.osti.gov/servlets/purl/951258.
@article{osti_951258,
title = {Structured hints : extracting and abstracting domain expertise.},
author = {Hereld, M. and Stevens, R. and Sterling, T. and Gao, G. R. and Mathematics and Computer Science and California Inst. of Tech. and Louisiana State Univ. and Univ. of Delaware},
abstractNote = {We propose a new framework for providing information to help optimize domain-specific application codes. Its design addresses problems that derive from the widening gap between the domain problem statement by domain experts and the architectural details of new and future high-end computing systems. The design is particularly well suited to program execution models that incorporate dynamic adaptive methodologies for live tuning of program performance and resource utilization. This new framework, which we call 'structured hints', couples a vocabulary of annotations to a suite of performance metrics. The immediate target is development of a process by which a domain expert describes characteristics of objects and methods in the application code that would not be readily apparent to the compiler; the domain expert provides further information about what quantities might provide the best indications of desirable effect; and the interactive preprocessor identifies potential opportunities for the domain expert to evaluate. Our development of these ideas is progressing in stages from case study, through manual implementation, to automatic or semi-automatic implementation. In this paper we discuss results from our case study, an examination of a large simulation of a neural network modeled after the neocortex.},
doi = {10.2172/951258},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Mar 16 00:00:00 EDT 2009},
month = {Mon Mar 16 00:00:00 EDT 2009}
}

Technical Report:

Save / Share: