---
code_id: 45231
site_ownership_code: "SNL"
open_source: true
repository_link: "https://github.com/sandialabs/TuckerMPI"
project_type: "OS"
software_type: "S"
official_use_only: {}
developers:
- email: "woodynaustin@gmail.com"
  orcid: ""
  first_name: "Woody"
  last_name: "Austin"
  middle_name: ""
  affiliations:
  - "Sandia National Laboratories"
- email: "amklinv@sandia.gov"
  orcid: ""
  first_name: "Alicia"
  last_name: "Klinvex"
  middle_name: ""
  affiliations:
  - "Sandia National Laboratories"
- email: "ballard@wfu.edu"
  orcid: ""
  first_name: "Grey"
  last_name: "Ballard"
  middle_name: ""
  affiliations:
  - "Wake Forest University"
- email: "tgkolda@sandia.gov"
  orcid: ""
  first_name: "Tamara"
  last_name: "Kolda"
  middle_name: "G."
  affiliations:
  - "Sandia National Laboratories"
contributors: []
sponsoring_organizations:
- organization_name: "USDOE"
  funding_identifiers: []
  primary_award: "AC04-94AL85000"
  DOE: true
contributing_organizations: []
research_organizations:
- organization_name: "Sandia National Laboratories (SNL-NM), Albuquerque, NM (United\
    \ States)"
  DOE: true
related_identifiers: []
award_dois: []
release_date: "2016-09-21"
software_title: "TuckerCompressMPI v. 1.0"
acronym: "TuckerCompressMPI"
doi: "https://doi.org/10.11578/dc.20201001.6"
description: "As parallel computing trends towards the exascale, scientific data produced\
  \ by high-fidelity simulations are growing increasingly massive. For instance, a\
  \ simulation on a three-dimensional spatial grid with 512 points per dimension that\
  \ tracks 64 variables per grid point for 128 time steps yields 8 TB of data. By\
  \ viewing the data as a dense five-way tensor, we can compute a Tucker decomposition\
  \ to find inherent low-dimensional multilinear structure, achieving compression\
  \ ratios of up to 10000 on real-world data sets with negligible loss in accuracy.\
  \ So that we can operate on such massive data, we present the first-ever distributed-memory\
  \ parallel implementation for the Tucker decomposition, whose key computations correspond\
  \ to parallel linear algebra operations, albeit with nonstandard data layouts. Our\
  \ approach specifies a data distribution for tensors that avoids any tensor data\
  \ redistribution, either locally or in parallel. This software provides a method\
  \ for compressing large-scale multiway data."
programming_languages:
- "C++"
- "Shell"
- "CMake"
- "MATLAB"
- "Makefile"
- "Python"
version_number: "1.0"
country_of_origin: "United States"
project_keywords: []
licenses:
- "BSD 2-clause \"Simplified\" License"
recipient_org: "Sandia National Laboratories"
site_accession_number: "SCR #2148.0; 7258"
date_record_added: "2020-10-01"
date_record_updated: "2024-07-19"
is_file_certified: false
last_editor: "copyrightadmin@sandia.gov"
is_limited: false
links:
- rel: "citation"
  href: "https://www.osti.gov/doecode/biblio/45231"