Loading...
Loading...

Go to the content (press return)

Implementing OmpSs support for regions of data in architectures with multiple address spaces

Author
Bueno, J.; Martorell, X.; Badia, R.M.; Ayguade, E.; Labarta, J.
Type of activity
Presentation of work at congresses
Name of edition
27th International Conference on Supercomputing
Date of publication
2013
Presentation's date
2013-06
Book of congress proceedings
ICS'13: proceedings of the 2013 ACM International Conference on Supercomputing: June 10-14, 2013: Eugene, Oregon, USA
First page
359
Last page
368
Publisher
ACM
DOI
https://doi.org/10.1145/2464996.2465017 Open in new window
Repository
http://hdl.handle.net/2117/20120 Open in new window
URL
http://dl.acm.org/citation.cfm?id=2465017 Open in new window
Abstract
The need for features for managing complex data accesses in modern programming models has increased due to the emerging hardware architectures. HPC hardware has moved towards clusters of accelerators and/or multicores, architectures with a complex memory hierarchy exposed to the programmer. We present the implementation of data regions on the OmpSs programming model, a high-productivity annotation-based programming model derived from OpenMP. This enables the programmer to specify regions of stri...
Citation
Bueno, J. [et al.]. Implementing OmpSs support for regions of data in architectures with multiple address spaces. A: ICS - International Conference on Supercomputing. "ICS’13: Proceedings of the 2013 ACM International Conference on Supercomputing: June 10–14, 2013: Eugene, Oregon, USA". ACM, 2013, p. 359-368.
Keywords
Cluster programming, Non-contiguous memory access, Openmp, Run-time environments
Group of research
CAP - High Performace Computing Group

Participants