Bigger buffer k-d trees on multi-many-core systems
Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review
A buffer k -d tree is a k -d tree variant for massively-parallel nearest neighbor search. While providing valuable speed-ups on modern many-core devices in case both a large number of reference and query points are given, buffer k -d trees are limited by the amount of points that can fit on a single device. In this work, we show how to modify the original data structure and the associated workflow to make the overall approach capable of dealing with massive data sets. We further provide a simple yet efficient way of using multiple devices given in a single workstation. The applicability of the modified framework is demonstrated in the context of astronomy, a field that is faced with huge amounts of data.
Original language | English |
---|---|
Title of host publication | High Performance Computing for Computational Science – VECPAR 2018 : 13th International Conference, São Pedro, Brazil, September 17–19, 2018, Revised Selected Papers |
Publisher | Springer |
Publication date | 2019 |
Pages | 202-214 |
ISBN (Print) | 978-3-030-15995-5 |
ISBN (Electronic) | 978-3-030-15996-2 |
DOIs | |
Publication status | Published - 2019 |
Event | 13th International Conference on High Performance Computing in Computational Science - São Pedro, Brazil Duration: 17 Sep 2018 → 19 Sep 2018 |
Conference
Conference | 13th International Conference on High Performance Computing in Computational Science |
---|---|
Land | Brazil |
By | São Pedro |
Periode | 17/09/2018 → 19/09/2018 |
Series | Lecture Notes in Computer Science |
---|---|
Volume | 11333 |
ISSN | 0302-9743 |
Links
- https://arxiv.org/abs/1512.02831
Submitted manuscript
ID: 166494866