Stammdaten

Titel: FusionCL: a machine-learning based approach for OpenCL kernel fusion to increase system performance
Untertitel:
Kurzfassung:

Employing general-purpose graphics processing units (GPGPU) with the help of OpenCL has resulted in greatly reducing the execution time of data-parallel applications by taking advantage of the massive available parallelism. However, when a small data size application is executed on GPU there is a wastage of GPU resources as the application cannot fully utilize GPU compute-cores. There is no mechanism to share a GPU between two kernels due to the lack of operating system support on GPU. In this paper, we propose the provision of a GPU sharing mechanism between two kernels that will lead to increasing GPU occupancy, and as a result, reduce execution time of a job pool. However, if a pair of the kernel is competing for the same set of resources (i.e., both applications are compute-intensive or memory-intensive), kernel fusion may also result in a significant increase in execution time of fused kernels. Therefore, it is pertinent to select an optimal pair of kernels for fusion that will result in significant speedup over their serial execution. This research presents FusionCL, a machine learning-based GPU sharing mechanism between a pair of OpenCL kernels. FusionCL identifies each pair of kernels (from the job pool), which are suitable candidates for fusion using a machine learning-based fusion suitability classifier. Thereafter, from all the candidates, it selects a pair of candidate kernels that will produce maximum speedup after fusion over their serial execution using a fusion speedup predictor. The experimental evaluation shows that the proposed kernel fusion mechanism reduces execution time by 2.83× when compared to a baseline scheduling scheme. When compared to state-of-the-art, the reduction in execution time is up to 8%.

Schlagworte: Scheduling, Kernel fusion, High-performance computing, Machine learning
Publikationstyp: Beitrag in Zeitschrift (Autorenschaft)
Art der Veröffentlichung Online Publikation
Erschienen in: Computing
Computing
zur Publikation
 ( )
Erscheinungsdatum: 03.06.2021
Titel der Serie: -
Bandnummer: -
Heftnummer: -
Erstveröffentlichung: Ja
Version: -
Seite: S. 1 - 32

Identifikatoren

ISBN: -
ISSN: 1436-5057
DOI: http://dx.doi.org/10.1007/s00607-021-00958-2
AC-Nummer: -
Homepage: https://link.springer.com/article/10.1007/s00607-021-00958-2
Open Access
  • Online verfügbar (nicht Open Access)

Zuordnung

Organisation Adresse
Fakultät für Technische Wissenschaften
 
Institut für Informationstechnologie
Universitaetsstr. 65-67
9020 Klagenfurt am Wörthersee
Österreich
   martina.steinbacher@aau.at
http://itec.aau.at/
zur Organisation
Universitaetsstr. 65-67
AT - 9020  Klagenfurt am Wörthersee

Kategorisierung

Sachgebiete
  • 1020 - Informatik
Forschungscluster Kein Forschungscluster ausgewählt
Zitationsindex
  • Science Citation Index Expanded (SCI Expanded)
Informationen zum Zitationsindex: Master Journal List
Peer Reviewed
  • Ja
Publikationsfokus
  • Science to Science (Qualitätsindikator: II)
Klassifikationsraster der zugeordneten Organisationseinheiten:
Arbeitsgruppen
  • Distributed Multimedia Systems

Kooperationen

Organisation Adresse
HITEC University
Cantt، Taxila, Rawalpindi
47080 Punjag
Pakistan
Cantt، Taxila, Rawalpindi
PK - 47080  Punjag
National University of Computer and Emerging Sciences
A.K Brohi Road, Sector H-11/4
Islamabad
Pakistan
A.K Brohi Road, Sector H-11/4
PK  Islamabad
Western Norway University of Applied Sciences
Postbox 7030
5020 Bergen
Norwegen
Postbox 7030
NO - 5020  Bergen
School of Computing and Artificial Intelligence, Southwest Jiaotong University
111 N 1st Section, 2nd Ring Rd, Sha Xi Mei Shi Yi Tiao Jie, Jinniu Qu
Chengdu
China
111 N 1st Section, 2nd Ring Rd, Sha Xi Mei Shi Yi Tiao Jie, Jinniu Qu
CN  Chengdu

Beiträge der Publikation

Keine verknüpften Publikationen vorhanden