Institutional Repository
Technical University of Crete
EN  |  EL

Search

Browse

My Space

A generic high throughput architecture for stream processing

Rousopoulos Christos, Karandeinos Ektor, Chrysos Grigorios, Dollas Apostolos, Pnevmatikatos Dionysios

Full record


URI: http://purl.tuc.gr/dl/dias/CB1579C1-ADC3-483D-85A1-52010D9CE731
Year 2017
Type of Item Conference Full Paper
License
Details
Bibliographic Citation C. Rousopoulos, E. Karandeinos, G. Chrysos, A. Dollas and D.N. Pnevmatikatos, "A generic high throughput architecture for stream processing," in 27th International Conference on Field Programmable Logic and Applications, 2017. doi:10.23919/FPL.2017.8056796 https://doi.org/10.23919/FPL.2017.8056796
Appears in Collections

Summary

Stream join is a fundamental and computationally expensive data mining operation for relating information from different data streams. This paper presents two FPGA-based architectures that accelerate stream join processing. The proposed hardware-based systems were implemented on a multi-FPGA hybrid system with high memory bandwidth. The experimental evaluation shows that our proposed systems can outperform a software-based solution that runs on a high-end, 48-core multiprocessor platform by at least one order of magnitude. In addition, the proposed solutions outperform any other previously proposed hardware-based or software-based solutions for stream join processing. Finally, our proposed hardware-based architectures can be used as generic templates to map stream processing algorithms on reconfigurable logic, taking into consideration real-world challenges and restrictions.

Services

Statistics