DASH: Data Structures and Algorithms with Support for Hierarchical Locality
Research output: Contribution to book/Conference proceedings/Anthology/Report › Conference contribution › Contributed › peer-review
Contributors
Abstract
DASH is a realization of the PGAS (partitioned global address space) model in the form of a C++ template library. Operator overloading is used to provide global-view PGAS semantics without the need for a custom PGAS (pre-) compiler. The DASH library is implemented on top of our runtime system DART, which provides an abstraction layer on top of existing one-sided communication substrates. DART contains methods to allocate memory in the global address space as well as collective and one-sided communication primitives. To support the development of applications that exploit a hierarchical organization, either on the algorithmic or on the hardware level, DASH features the notion of teams that are arranged in a hierarchy. Based on a team hierarchy, the DASH data structures support locality iterators as a generalization of the conventional local/global distinction found in many PGAS approaches.
Details
Original language | English |
---|---|
Title of host publication | Euro-Par 2014: Parallel Processing Workshops |
Publisher | Springer, Cham |
Pages | 542-552 |
Number of pages | 11 |
ISBN (print) | 978-3-319-14312-5 |
Publication status | Published - 2014 |
Peer-reviewed | Yes |
Publication series
Series | Lecture Notes in Computer Science, Volume 8806 |
---|---|
ISSN | 0302-9743 |
Conference
Title | 20th Euro-Par International Workshops |
---|---|
Duration | 25 - 26 August 2014 |
City | Porto |
Country | Portugal |
External IDs
WOS | 000354785000046 |
---|---|
Scopus | 84920100746 |
Keywords
Keywords
- High Performance Computing, Template Library, Distribute Memory Machine, Data Container, Global Address Space