GPU-accelerated co-design of induced dimension reduction: Algorithmic fusion and kernel overlap

Hartwig Anzt, Eduardo Ponce, Gregory D. Peterson, Jack Dongarra

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In this paper we present an optimized GPU co-design of the Induced Dimension Reduction (IDR) algorithm for solving linear systems. Starting from a baseline implementation based on the generic BLAS routines from the MAGMA software library, we apply optimizations that are based on kernel fusion and kernel overlap. Runtime experiments are used to investigate the benefit of the distinct optimization techniques for different variants of the IDR algorithm. A comparison to the reference implementation reveals that the interplay between them can succeed in cutting the overall runtime by up to about one third.

Original languageEnglish
Title of host publicationProceedings of Co-HPC 2015
Subtitle of host publication2nd International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in conjunction with SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450339926
DOIs
StatePublished - Nov 15 2015
Externally publishedYes
Event2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2015 - Austin, United States
Duration: Nov 15 2015 → …

Publication series

NameProceedings of Co-HPC 2015: 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in conjunction with SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2015
Country/TerritoryUnited States
CityAustin
Period11/15/15 → …

Funding

This material is based upon work supported by the U.S. Department of Energy (Award Number DE-SC-0010042), and NVIDIA.

FundersFunder number
U.S. Department of EnergyDE-SC-0010042
NVIDIA

    Keywords

    • Co-design
    • GPU
    • Induced Dimension Reduction (IDR)
    • Kernel fusion
    • Kernel overlap

    Fingerprint

    Dive into the research topics of 'GPU-accelerated co-design of induced dimension reduction: Algorithmic fusion and kernel overlap'. Together they form a unique fingerprint.

    Cite this