Abstract
This paper explains the demonstration of a fast method of Okapi BM25 term weighting on graphics processing units (GPUs) for information retrieval by combining a GPU-based dictionary using a succinct data structure and data parallel primitives. The main problem with handling documents on GPUs is in processing variable length strings, such as the documents themselves and words. Processing variable sizes of data causes many idle cores, i.e., load imbalances in threads, due to the single instruction multiple data (SIMD) nature of the GPU architecture. Our term weighting method is carefully composed of efficient data parallel primitives to avoid load imbalance. Additionally, we implemented a high performance compressed dictionary on GPUs. As words are converted into identifiers (IDs) with this dictionary, costly string comparisons could be avoided. Our experimental results revealed that the proposed method of term weighting on GPUs performed up to 5\(\times \) faster than the MapReduce-based one on multi-core CPUs.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
