Hardwarebeschleunigung von Semantic Web Datenbanken durch dynamisch rekonfigurierbare FPGAs
Funded by:
- DFG
Runtime:
- 2013 - 2015
Project Coordinator:
- Prof. Dr. rer. nat. habil. Sven Groppe
- Prof. Dr.-Ing. Thilo Pionteck
Research Associate:
- Dennis Heinrich, M.Sc.
Motivation
The importance of the Semantic Web has steadily increased in recent years. Evidence of this includes, among other things, the increasing number of Semantic Web tools and applications developed and in use.
The core idea of the Semantic Web is to make machine processing more precise by including the meaning of symbols. The required linking of different data sets is carried out using database systems. With the constantly growing size of databases, classic database systems, but also specially adapted Semantic Web database systems, are increasingly reaching their limits. Especially in the area of Semantic Web databases, there are now data sets with billions of entries, which are very time-consuming to process using purely software-based solutions.
Goals and Procedure
As part of this project, a hardware/software system is to be researched and developed that outsources time-consuming operations to a programmable logic component (FPGA, Field Programmable Gate Array). The cost-intensive operations intended for hardware acceleration include both the individual steps of index creation and the actual query processing for Semantic Web databases. The functions to be outsourced to the FPGA during query processing are determined at runtime. In order to be able to provide an optimal hardware accelerator depending on the request, corresponding data paths are built from basic elements using partial dynamic reconfiguration of the FPGA at runtime.
Innovation and Prospects
The innovation of this project includes new approaches and methods for hardware-acceleration of Semantic Web databases by utilizing the unique features of FPGAs.
Project Partners
- Institute of Information Systems (IFIS), University of Lübeck
- Institute of Conmputer Engineering (ITI), University of Lübeck
Link to Project Details
Dissertation
Dennis Heinrich:
Parallel Execution Approaches on Data and Index Structures in the Context of Semantic Web Database Management Systems
eingereicht Mai 2018, angenommen 06. Juni 2018, mündl. Prüfung am 19.09.2018 (Doktorvater: Groppe), Thesis
Publications
2020
Hardware-aided update acceleration in a hybrid Semantic Web database system, The Journal of Supercomputing , vol. 76, no. 10, pp. 7961--7984, 2020.
Datei: | s11227-018-2462-y |
Bibtex: | @article{heinrich20hardware, author = {Dennis Heinrich and Stefan Werner and Christopher Blochwitz and Thilo Pionteck and Sven Groppe}, title = {Hardware-aided update acceleration in a hybrid Semantic Web database system}, journal = {The Journal of Supercomputing}, volume = {76}, number = {10}, pages = {7961--7984}, year = {2020}, url = {https://doi.org/10.1007/s11227-018-2462-y} } |
2018
Hardware-Accelerated Index Construction for Semantic Web, in International Conference on Field-Programmable Technology ({FPT}), Naha, Okinawa, Japan , 2018. pp. 278--281.
DOI: | 10.1109/FPT.2018.00053 |
Datei: | FPT.2018.00053 |
Bibtex: | @inproceedings{Blochwitz2018_15, title = {Hardware-Accelerated Index Construction for Semantic Web}, author = {Christopher Blochwitz and Julian Wolff and Mladen Berekovic and Dennis Heinrich and Sven Groppe and Jan Moritz Joseph and Thilo Pionteck}, booktitle = {International Conference on Field-Programmable Technology ({FPT}), Naha, Okinawa, Japan}, year = {2018}, url = {https://doi.org/10.1109/FPT.2018.00053} } |
2017
Hardware-Accelerated Radix-Tree Based String Sorting for Big Data Applications, in 30th International Conference on Architecture of Computing Systems ({ARCS}), Vienna, Austria , 2017. pp. 47--58.
DOI: | 10.1007/978-3-319-54999-6\_4 |
Datei: | 978-3-319-54999-6\_4 |
Search \& Update Optimization of a B+ Tree in a Hardware aided Semantic Web Database System, in Proceedings of the 7th International Conference on Emerging Databases (EDB), Busan, Korea , Springer, 2017.
Datei: | 978-981-10-6520-0_18 |
Semi-static operator graphs for accelerated query execution on FPGAs, Microprocessors and Microsystems - Embedded Hardware Design , vol. 53, pp. 178--189, 2017.
DOI: | 10.1016/j.micpro.2017.07.010 |
Datei: | j.micpro.2017.07.010 |
2016
Accelerated join evaluation in Semantic Web databases by using FPGAs, Concurrency and Computation: Practice and Experience , vol. 28, no. 7, pp. 2031--2051, 2016.
DOI: | 10.1002/cpe.3502 |
Datei: | cpe.3502 |
Bibtex: | @ARTICLE{Werner2015, author = {Stefan Werner and Dennis Heinrich and Marc Stelzner and Volker Linnemann and Thilo Pionteck and Sven Groppe}, title = {Accelerated join evaluation in Semantic Web databases by using FPGAs}, journal = {Concurrency and Computation: Practice and Experience}, year = {2015}, volume = {28}, number = {7}, pages = {2031--2051}, month = {May 18}, doi = {http://dx.doi.org/10.1002/cpe.3502} } |
Constructing Large-Scale Semantic Web Indices for the Six {RDF} Collation Orders, OJBD , vol. 2, no. 1, pp. 11--25, 2016.
Datei: | urn:nbn:de:101:1-201705194418 |
Runtime Adaptive Hybrid Query Engine based on FPGAs, OJDB , vol. 3, no. 1, pp. 21--41, 2016. RonPub.
Datei: | urn:nbn:de:101:1-201705194645 |
Bibtex: | @Article{OJDB_2016v3i1n02_Werner, author = {Stefan Werner and Dennis Heinrich and Sven Groppe and Christopher Blochwitz and Thilo Pionteck}, title = {Runtime Adaptive Hybrid Query Engine based on FPGAs}, journal = {Open Journal of Databases (OJDB)}, issn = {2199-3459}, year = {2016}, volume = {3}, number = {1}, pages = {21--41}, url = {http://www.ronpub.com/publications/OJDB_2016v3i1n02_Werner.pdf}, publisher = {RonPub}, bibsource = {RonPub}, abstract = {This paper presents the fully integrated hardware-accelerated query engine for large-scale datasets in the context of Semantic Web databases. As queries are typically unknown at design time, a static approach is not feasible and not flexible to cover a wide range of queries at system runtime. Therefore, we introduce a runtime reconfigurable accelerator based on a Field Programmable Gate Array (FPGA), which transparently incorporates with the freely available Semantic Web database LUPOSDATE. At system runtime, the proposed approach dynamically generates an optimized hardware accelerator in terms of an FPGA configuration for each individual query and transparently retrieves the query result to be displayed to the user. During hardware-accelerated execution the host supplies triple data to the FPGA and retrieves the results from the FPGA via PCIe interface. The benefits and limitations are evaluated on large-scale synthetic datasets with up to 260 million triples as well as the widely known Billion Triples Challenge.} } |
2015
Hybrid FPGA approach for a B+ tree in a Semantic Web database system, in 10th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), Bremen, Germany , 2015. pp. 1--8.
DOI: | 10.1109/ReCoSoC.2015.7238093 |
Datei: | ReCoSoC.2015.7238093 |
PatTrieSort - External String Sorting based on Patricia Tries, OJDB , vol. 2, no. 1, pp. 36--50, 2015.
Datei: | urn:nbn:de:101:1-201705194627 |
{An optimized Radix-Tree for hardware-accelerated index generation for Semantic Web Databases}, in International Conference on ReConFigurable Computing and FPGAs (ReConFig) , Cancun, Mexico , 2015.
Distributed Join Approaches for W3C-Conform {SPARQL} Endpoints, OJSW , vol. 2, no. 1, pp. 30--52, 2015.
Datei: | urn:nbn:de:101:1-201705194910 |
Automated composition and execution of hardware-accelerated operator graphs, in 10th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), Bremen, Germany , 2015. pp. 1--8.
DOI: | 10.1109/ReCoSoC.2015.7238078 |
Datei: | ReCoSoC.2015.7238078 |
An optimized radix-tree for hardware-accelerated dictionary generation for semantic web databases, in International Conference on ReConFigurable Computing and FPGAs (ReConFig), Riviera Maya, Mexico , 2015. pp. 1--7.
DOI: | 10.1109/ReConFig.2015.7393291 |
Datei: | ReConFig.2015.7393291 |
2014
A Self-Optimizing Cloud Computing System for Distributed Storage and Processing of Semantic Web Data, OJCC , vol. 1, no. 2, pp. 1--14, 2014.
Datei: | urn:nbn:de:101:1-201705194478 |
P-LUPOSDATE: Using Precomputed Bloom Filters to Speed Up SPARQL Processing in the Cloud, OJSW , vol. 1, no. 2, pp. 25--55, 2014.
Datei: | urn:nbn:de:101:1-201705194858 |
Parallel and Pipelined Filter Operator for Hardware-Accelerated Operator Graphs in Semantic Web Databases, in 14th IEEE International Conference on Computer and Information Technology (CIT), Xi'an, China , 2014. pp. 539--546.
DOI: | 10.1109/CIT.2014.162 |
Datei: | CIT.2014.162 |