Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems
We present a novel approach to parallel materialisation (i.e., fixpoint computation) of datalog programs in centralised, main-memory, multi-core RDF systems. Our approach comprises an algorithm that evenly distributes the workload to cores, and an RDF indexing data structure that supports efficient,...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
AAAI Press
2014
|
| Subjects: |
| _version_ | 1826317682285215744 |
|---|---|
| author | Motik, B Nenov, Y Piro, R Horrocks, I Olteanu, D |
| author_facet | Motik, B Nenov, Y Piro, R Horrocks, I Olteanu, D |
| author_sort | Motik, B |
| collection | OXFORD |
| description | We present a novel approach to parallel materialisation (i.e., fixpoint computation) of datalog programs in centralised, main-memory, multi-core RDF systems. Our approach comprises an algorithm that evenly distributes the workload to cores, and an RDF indexing data structure that supports efficient, 'mostly' lock-free parallel updates. Our empirical evaluation shows that our approach parallelises computation very well: with 16 physical cores, materialisation can be up to 13.9 times faster than with just one core. |
| first_indexed | 2024-03-06T19:32:03Z |
| format | Conference item |
| id | oxford-uuid:1dc87c23-6baf-4c09-b04a-e0410598f545 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-03-11T16:57:47Z |
| publishDate | 2014 |
| publisher | AAAI Press |
| record_format | dspace |
| spelling | oxford-uuid:1dc87c23-6baf-4c09-b04a-e0410598f5452025-03-05T10:19:44ZParallel OWL 2 RL materialisation in centralised, main-memory RDF systemsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:1dc87c23-6baf-4c09-b04a-e0410598f545Description LogicsComputer ScienceEnglishOxford University Research Archive - ValetAAAI Press2014Motik, BNenov, YPiro, RHorrocks, IOlteanu, DWe present a novel approach to parallel materialisation (i.e., fixpoint computation) of datalog programs in centralised, main-memory, multi-core RDF systems. Our approach comprises an algorithm that evenly distributes the workload to cores, and an RDF indexing data structure that supports efficient, 'mostly' lock-free parallel updates. Our empirical evaluation shows that our approach parallelises computation very well: with 16 physical cores, materialisation can be up to 13.9 times faster than with just one core. |
| spellingShingle | Description Logics Computer Science Motik, B Nenov, Y Piro, R Horrocks, I Olteanu, D Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title | Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title_full | Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title_fullStr | Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title_full_unstemmed | Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title_short | Parallel OWL 2 RL materialisation in centralised, main-memory RDF systems |
| title_sort | parallel owl 2 rl materialisation in centralised main memory rdf systems |
| topic | Description Logics Computer Science |
| work_keys_str_mv | AT motikb parallelowl2rlmaterialisationincentralisedmainmemoryrdfsystems AT nenovy parallelowl2rlmaterialisationincentralisedmainmemoryrdfsystems AT piror parallelowl2rlmaterialisationincentralisedmainmemoryrdfsystems AT horrocksi parallelowl2rlmaterialisationincentralisedmainmemoryrdfsystems AT olteanud parallelowl2rlmaterialisationincentralisedmainmemoryrdfsystems |