Loading...
Loading...

Go to the content (press return)

Runtime vs. manual data distribution for architecture-agnostic shared-memory programming models

Author
Nikolopoulos, D.; Ayguade, E.; Polychronopoulos, C.
Type of activity
Journal article
Journal
Journal of parallel and distributed computing
Date of publication
2002-08
Volume
30
Number
4
First page
225
Last page
254
DOI
https://doi.org/10.1023/A:1019899812171 Open in new window
Repository
http://hdl.handle.net/2117/117287 Open in new window
URL
http://link.springer.com/article/10.1023%2FA%3A1019899812171 Open in new window
Abstract
This paper compares data distribution methodologies for scaling the performance of OpenMP on NUMA architectures. We investigate the performance of automatic page placement algorithms implemented in the operating system, runtime algorithms based on dynamic page migration, runtime algorithms based on loop scheduling transformations and manual data distribution. These techniques present the programmer with trade-offs between performance and programming effort. Automatic page placement algorithms ar...
Citation
Nikolopoulos, D., Ayguade, E., Polychronopoulos, C. Runtime vs. manual data distribution for architecture-agnostic shared-memory programming models. "Journal of parallel and distributed computing", Agost 2002, vol. 30, núm. 4, p. 225-254.
Keywords
Data distribution, OpenMP, Operating systems, Performance evaluation, Runtime systems
Group of research
CAP - High Performace Computing Group

Participants