TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. A Quantitative Study of Locality in GPU Caches
 
Options

A Quantitative Study of Locality in GPU Caches

Publikationstyp
Conference Paper
Date Issued
2020-07
Sprache
English
Author(s)
Lal, Sohan  
Juurlink, Ben H. H.  
TORE-URI
http://hdl.handle.net/11420/12247
First published in
Lecture notes in computer science  
Number in series
12471 LNCS
Start Page
228
End Page
242
Citation
20th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS 2020)
Contribution to Conference
20th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2020  
Publisher DOI
10.1007/978-3-030-60939-9_16
Publisher Link
https://depositonce.tu-berlin.de/bitstream/11303/11220.2/8/lal_juurlink_2020.pdf
Scopus ID
2-s2.0-85093870476
Traditionally, GPUs only had programmer-managed caches. The advent of hardware-managed caches accelerated the use of GPUs for general-purpose computing. However, as GPU caches are shared by thousands of threads, they are usually a victim of contention and can suffer from thrashing and high miss rate, in particular, for memory-divergent workloads. As data locality is crucial for performance, there have been several efforts focusing on exploiting data locality in GPUs. However, there is a lack of quantitative analysis of data locality and data reuse in GPUs. In this paper, we quantitatively study the data locality and its limits in GPUs. We observe that data locality is much higher than exploited by current GPUs. We show that, on the one hand, the low spatial utilization of cache lines justifies the use of demand-fetched caches. On the other hand, the much higher actual spatial utilization of cache lines shows the lost spatial locality and presents opportunities for further optimizing the cache design.
Subjects
Data locality
GPU caches
Memory divergence
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback