• Home
  • Search
  • Memory-efficient parallel tensor decompositions
  • Cite Icon26
  • https://doi.org/10.1109/hpec.2017.8091026Copy DOI Icon

Memory-efficient parallel tensor decompositions

  • Sep 1, 2017
  • Muthu Baskaran +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Tensor decompositions are a powerful technique for enabling comprehensive and complete analysis of real-world data. Data analysis through tensor decompositions involves intensive computations over large-scale irregular sparse data. Optimizing the execution of such data intensive computations is key to reducing the time-to-solution (or response time) in real-world data analysis applications. As high-performance computing (HPC) systems are increasingly used for data analysis applications, it is becoming increasingly important to optimize sparse tensor computations and execute them efficiently on modern and advanced HPC systems. In addition to utilizing the large processing capability of HPC systems, it is crucial to improve memory performance (memory usage, communication, synchronization, memory reuse, and data locality) in HPC systems. In this paper, we present multiple optimizations that are targeted towards faster and memory-efficient execution of large-scale tensor analysis on HPC systems. We demonstrate that our techniques achieve reduction in memory usage and execution time of tensor decomposition methods when they are applied on multiple datasets of varied size and structure from different application domains. We achieve up to 11× reduction in memory usage and up to 7× improvement in performance. More importantly, we enable the application of large tensor decompositions on some important datasets on a multi-core system that would not have been feasible without our optimization.

Similar Papers
  • Conference Article
  • Citations11

Fast and Scalable Distributed Tensor Decompositions

  • Sep 01, 2019
  • Muthu Baskaran +2
  • Book Chapter
  • Citations22

Middleware in Modern High Performance Computing System Architectures

  • Jan 01, 2007
  • Christian Engelmann +2
  • Conference Article
  • Citations24

HPAS

  • Aug 05, 2019
  • Emre Ates +6
  • Dissertation
  • Citations3

Energy Demand Response for High-Performance Computing Systems

  • Jun 08, 2018
  • Kishwar Ahmed
  • Supplementary Content

Design of robust scheduling methodologies for high performance computing

  • Jan 01, 2019
  • edoc (University of Basel)
  • Ali Mohammed
  • PDF
  • Book Chapter
  • Citations26

Machine Learning Predictions for Underestimation of Job Runtime on HPC System

  • Jan 01, 2018
  • Jian Guo +4
  • Conference Article
  • Citations6

Parallel Query Service for Object-centric Data Management Systems

  • May 01, 2020
  • Houjun Tang +3
  • Conference Article
  • Citations21

First Experiences in Performance Benchmarking with the New SPEChpc 2021 Suites

  • May 01, 2022
  • Holger Brunst +9
  • Conference Article
  • Citations3

Ten Years of the HPC Ecosystems Project - Transforming HPC in Africa for the past decade

  • Jul 17, 2024
  • Bryan Johnston +3
  • Book Chapter

Code Modernization Tools for Assisting Users in Migrating to Future Generations of Supercomputers

  • Jan 01, 2017
  • Ritu Arora +1
  • Conference Article

Multi-node Power/Performance Modeling for HPC System

  • Jun 01, 2019
  • Sangwoo Han +2
  • Conference Article
  • Citations19

Quantifying the impact of network congestion on application performance and network metrics

  • Sep 01, 2020
  • Yijia Zhang +4
  • Dissertation

Utilizing HPC Systems to Serve Compute-Intensive Tasks from a Data Lake Managing Sensitive Data

  • Jan 01, 2024
  • Hendrik Nolte
  • Single Report
  • Citations2

Resilience Design Patterns: A Structured Approach to Resilience at Extreme Scale (V.2.0)

  • Dec 16, 2022
  • Christian Engelmann +4
  • Conference Article
  • Citations19

DWPE, a new data center energy-efficiency metric bridging the gap between infrastructure and workload

  • Jul 01, 2014
  • Torsten Wilde +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.