DMCA
Stream Join Processing on Heterogeneous Processors
| Citations: | 2 - 0 self |
BibTeX
@MISC{Karnagel_streamjoin,
author = {Tomas Karnagel and Benjamin Schlegel and Dirk Habich and Wolfgang Lehner},
title = {Stream Join Processing on Heterogeneous Processors},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The window-based stream join is an important operator in all data streaming systems. It has often high resource requirements so that manyefficient sequential as well as parallel versions of it were proposed in the literature. The parallel stream join operators recently gain increasing interest because hardware is getting more and more parallel. Most of these operators, however, are only optimized for processors with homogeneous execution units (e.g., multi-core processors). Newly available processors with heterogeneous execution units cannot be exploited whereas such processors provide typically avery high peak performance. In this paper,wepropose an initial variant of awindow-based stream join operator that is optimized for processors with heterogeneous execution units. We provide an efficient load balancing approach to utilize all available execution units of aprocessor and further provide highly-optimized kernels that run on them. On our test machine with a4-core CPU and an integrated graphics processor, our operator achieves aspeedup of 69.2x compared to our single-threaded implementation. 1
Keyphrases
heterogeneous processor stream join processing heterogeneous execution unit available execution unit single-threaded implementation initial variant manyefficient sequential highly-optimized kernel window-based stream join integrated graphic processor homogeneous execution unit parallel version high peak performance test machine parallel stream join operator efficient load whereas processor a4-core cpu awindow-based stream join operator multi-core processor important operator available processor high resource requirement
