Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/18705D60-AFEE-471D-9021-78AA46304792 | ||
| Year | 2016 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Charalabos Kritikakis, "Platform based on reconfigurable computing", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2016 https://doi.org/10.26233/heallink.tuc.65968 | ||
| Appears in Collections |
Stream join is one of the most fundamental operations to relate information from different streams. The challenging task is to use systems with memory and run-time constraints in order to store and analyze massive volumes of streaming data. Hence, it is important to maximize the processing which is done on-the-fly as the streaming data arrives. This paper presents an FPGA-based architecture that maps the most performance-efficient stream join algorithm, i.e. ScaleJoin, to reconfigurable logic. The system was fully implemented on a Convey HC-2ex hybrid computer and experimental performance evaluation shows that the proposed system outperforms by up to one order of magnitude the corresponding fully optimized software-based solution running on a high-end 48-core multiprocessor platform, by exploiting the high internal bandwidth of present-day FPGAs. The proposed architecture can be used as a generic template for mapping other stream processing algorithms, taking into consideration real-world challenges.
Copyright © DIAS 2013
