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

Title: A brief summary on formalizing parallel tensor distributions redistributions and algorithm derivations.

Abstract

Large-scale datasets in computational chemistry typically require distributed-memory parallel methods to perform a special operation known as tensor contraction. Tensors are multidimensional arrays, and a tensor contraction is akin to matrix multiplication with special types of permutations. Creating an efficient algorithm and optimized im- plementation in this domain is complex, tedious, and error-prone. To address this, we develop a notation to express data distributions so that we can apply use automated methods to find optimized implementations for tensor contractions. We consider the spin-adapted coupled cluster singles and doubles method from computational chemistry and use our methodology to produce an efficient implementation. Experiments per- formed on the IBM Blue Gene/Q and Cray XC30 demonstrate impact both improved performance and reduced memory consumption.

Authors:
 [1];  [1];  [1]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1222973
Report Number(s):
SAND-2015-8453
607241
DOE Contract Number:  
AC04-94AL85000
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English

Citation Formats

Schatz, Martin D., Kolda, Tamara G., and van de Geijn, Robert. A brief summary on formalizing parallel tensor distributions redistributions and algorithm derivations.. United States: N. p., 2015. Web. doi:10.2172/1222973.
Schatz, Martin D., Kolda, Tamara G., & van de Geijn, Robert. A brief summary on formalizing parallel tensor distributions redistributions and algorithm derivations.. United States. https://doi.org/10.2172/1222973
Schatz, Martin D., Kolda, Tamara G., and van de Geijn, Robert. 2015. "A brief summary on formalizing parallel tensor distributions redistributions and algorithm derivations.". United States. https://doi.org/10.2172/1222973. https://www.osti.gov/servlets/purl/1222973.
@article{osti_1222973,
title = {A brief summary on formalizing parallel tensor distributions redistributions and algorithm derivations.},
author = {Schatz, Martin D. and Kolda, Tamara G. and van de Geijn, Robert},
abstractNote = {Large-scale datasets in computational chemistry typically require distributed-memory parallel methods to perform a special operation known as tensor contraction. Tensors are multidimensional arrays, and a tensor contraction is akin to matrix multiplication with special types of permutations. Creating an efficient algorithm and optimized im- plementation in this domain is complex, tedious, and error-prone. To address this, we develop a notation to express data distributions so that we can apply use automated methods to find optimized implementations for tensor contractions. We consider the spin-adapted coupled cluster singles and doubles method from computational chemistry and use our methodology to produce an efficient implementation. Experiments per- formed on the IBM Blue Gene/Q and Cray XC30 demonstrate impact both improved performance and reduced memory consumption.},
doi = {10.2172/1222973},
url = {https://www.osti.gov/biblio/1222973}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2015},
month = {9}
}