Various GPU memory utilisation exploration for large RDF search

Choksuchat, Chidchanok; Chantrapornchai, Chantana

doi:10.1504/ijcse.2018.096029

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The targeted thread block size and grid size equal to 1024 and 480 respectively, which yield the best performance on our machine. Other tests that explore the other block size and grid size are demonstrated in [35].…”

Section: Methodsmentioning

confidence: 99%

“…Although it is possible to use a fast search, the fast search usually needs preprocessing such as creating prefix/suffix tables or implicit state machines. The construction of the preprocessed table requires space and time overhead for different search strings [35]. Our framework assumes simplicity by using thousand threads to do brute force matching.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

TripleID-Q: RDF Query Processing Framework Using GPU

Chantrapornchai

Choksuchat

2018

IEEE Trans. Parallel Distrib. Syst.

Self Cite

View full text Add to dashboard Cite

Resource Description Framework (RDF) data represents information linkage around the Internet. It uses Internationalized Resources Identifier (IRI) which can be referred to external information. Typically, an RDF data is serialized as a large text file which contains millions of relationships. In this work, we propose a framework based on TripleID-Q, for query processing of large RDF data in a GPU. The key elements of the framework are 1) a compact representation suitable for a Graphics Processing Unit (GPU) and 2) its simple representation conversion method which optimizes the preprocessing overhead. Together with the framework, we propose parallel algorithms which utilize thousands of GPU threads to look for specific data for a given query as well as to perform basic query operations such as union, join, and filter. The TripleID representation is smaller than the original representation 3-4 times. Querying from TripleID using a GPU is up to 108 times faster than using the traditional RDF tool. The speedup can be more than 1,000 times over the traditional RDF store when processing a complex query with union and join of many subqueries.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%