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

Title: CAST: Contraction Algorithm for Symmetric Tensors

Abstract

Tensor contractions represent the most compute-intensive core kernels in ab initio computational quantum chemistry and nuclear physics. Symmetries in these tensor contractions makes them difficult to load balance and scale to large distributed systems. In this paper, we develop an efficient and scalable algorithm to contract symmetric tensors. We introduce a novel approach that avoids data redistribution in contracting symmetric tensors while also avoiding redundant storage and maintaining load balance. We present experimental results on two parallel supercomputers for several symmetric contractions that appear in the CCSD quantum chemistry method. We also present a novel approach to tensor redistribution that can take advantage of parallel hyperplanes when the initial distribution has replicated dimensions, and use collective broadcast when the final distribution has replicated dimensions, making the algorithm very efficient.

Authors:
; ; ; ; ;
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1178516
Report Number(s):
PNNL-SA-103757
KJ0402000
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: 43rd International Conference on Parallel Processing (ICPP 2014), September 9-12, 2014, Minneapolis, Minnesota, 261-272
Country of Publication:
United States
Language:
English
Subject:
tensor contractions; symmetry; distributed memory

Citation Formats

Rajbhandari, Samyam, NIkam, Akshay, Lai, Pai-Wei, Stock, Kevin, Krishnamoorthy, Sriram, and Sadayappan, Ponnuswamy. CAST: Contraction Algorithm for Symmetric Tensors. United States: N. p., 2014. Web. doi:10.1109/ICPP.2014.35.
Rajbhandari, Samyam, NIkam, Akshay, Lai, Pai-Wei, Stock, Kevin, Krishnamoorthy, Sriram, & Sadayappan, Ponnuswamy. CAST: Contraction Algorithm for Symmetric Tensors. United States. doi:10.1109/ICPP.2014.35.
Rajbhandari, Samyam, NIkam, Akshay, Lai, Pai-Wei, Stock, Kevin, Krishnamoorthy, Sriram, and Sadayappan, Ponnuswamy. Mon . "CAST: Contraction Algorithm for Symmetric Tensors". United States. doi:10.1109/ICPP.2014.35.
@article{osti_1178516,
title = {CAST: Contraction Algorithm for Symmetric Tensors},
author = {Rajbhandari, Samyam and NIkam, Akshay and Lai, Pai-Wei and Stock, Kevin and Krishnamoorthy, Sriram and Sadayappan, Ponnuswamy},
abstractNote = {Tensor contractions represent the most compute-intensive core kernels in ab initio computational quantum chemistry and nuclear physics. Symmetries in these tensor contractions makes them difficult to load balance and scale to large distributed systems. In this paper, we develop an efficient and scalable algorithm to contract symmetric tensors. We introduce a novel approach that avoids data redistribution in contracting symmetric tensors while also avoiding redundant storage and maintaining load balance. We present experimental results on two parallel supercomputers for several symmetric contractions that appear in the CCSD quantum chemistry method. We also present a novel approach to tensor redistribution that can take advantage of parallel hyperplanes when the initial distribution has replicated dimensions, and use collective broadcast when the final distribution has replicated dimensions, making the algorithm very efficient.},
doi = {10.1109/ICPP.2014.35},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2014},
month = {9}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: