Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203078652> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3203078652 abstract "DBSCAN is a popular clustering algorithm, which shows great success in many real-world applications. Its advantages come at the expense of massive computation, especially for computing the distance matrix. Driven by deep learning, many Artificial Intelligence (AI) chips have been developed. With efficient matrix multiplication units, AI chips can significantly accelerate the distance calculation. However, DBSCAN also needs to identify and count the neighbors for each point. It is challenging for most AI chips due to over-specialization. Moreover, the increasing data size and the limited device memory capacity force DBSCAN to follow a mini-batch manner. It results in a high data transfer overhead, which further hinders the performance of DBSCAN on AI chips. In this paper, we propose two novel techniques to address the challenges of accelerating the DBSCAN algorithm with AI chips: (1) new neighbor identification algorithms using bitwise operations only, while traditional solutions require the compare-and-select operations that are weakly supported in AI chips; and (2) two speculative execution strategies to reduce the data transfer overhead induced by mini-batches. Evaluations show that deploying distance matrix calculation to tensor cores achieves 2.61 × speedup on Nvidia RTX 3090. On Huawei Ascend 310, our neighbor identification algorithms achieve 17.88 × throughout of using CPUs for neighbor identification. The speculative execution strategies further reduce the execution time by 15.1% on average for normal datasets and up to 99.0% for sparse datasets." @default.
- W3203078652 created "2021-10-11" @default.
- W3203078652 creator A5030309370 @default.
- W3203078652 creator A5080045206 @default.
- W3203078652 date "2021-08-09" @default.
- W3203078652 modified "2023-10-17" @default.
- W3203078652 title "Accelerating DBSCAN Algorithm with AI Chips for Large Datasets" @default.
- W3203078652 cites W1992181154 @default.
- W3203078652 cites W2028562168 @default.
- W3203078652 cites W2061051181 @default.
- W3203078652 cites W2116721352 @default.
- W3203078652 cites W2143114052 @default.
- W3203078652 cites W2161336914 @default.
- W3203078652 cites W2740924709 @default.
- W3203078652 cites W2799132955 @default.
- W3203078652 cites W2962950337 @default.
- W3203078652 cites W2963466847 @default.
- W3203078652 cites W2963989532 @default.
- W3203078652 cites W2982219368 @default.
- W3203078652 cites W3001665736 @default.
- W3203078652 cites W3014988774 @default.
- W3203078652 cites W3017126053 @default.
- W3203078652 cites W3028763582 @default.
- W3203078652 cites W3093701126 @default.
- W3203078652 cites W3094406919 @default.
- W3203078652 cites W3096522494 @default.
- W3203078652 cites W3101543398 @default.
- W3203078652 cites W3104528661 @default.
- W3203078652 doi "https://doi.org/10.1145/3472456.3473518" @default.
- W3203078652 hasPublicationYear "2021" @default.
- W3203078652 type Work @default.
- W3203078652 sameAs 3203078652 @default.
- W3203078652 citedByCount "5" @default.
- W3203078652 countsByYear W32030786522022 @default.
- W3203078652 countsByYear W32030786522023 @default.
- W3203078652 crossrefType "proceedings-article" @default.
- W3203078652 hasAuthorship W3203078652A5030309370 @default.
- W3203078652 hasAuthorship W3203078652A5080045206 @default.
- W3203078652 hasConcept C111208986 @default.
- W3203078652 hasConcept C111919701 @default.
- W3203078652 hasConcept C11413529 @default.
- W3203078652 hasConcept C116834253 @default.
- W3203078652 hasConcept C121332964 @default.
- W3203078652 hasConcept C124101348 @default.
- W3203078652 hasConcept C154945302 @default.
- W3203078652 hasConcept C17349429 @default.
- W3203078652 hasConcept C173608175 @default.
- W3203078652 hasConcept C2779960059 @default.
- W3203078652 hasConcept C33704608 @default.
- W3203078652 hasConcept C41008148 @default.
- W3203078652 hasConcept C46576248 @default.
- W3203078652 hasConcept C59822182 @default.
- W3203078652 hasConcept C62520636 @default.
- W3203078652 hasConcept C68339613 @default.
- W3203078652 hasConcept C73555534 @default.
- W3203078652 hasConcept C84114770 @default.
- W3203078652 hasConcept C86803240 @default.
- W3203078652 hasConcept C94641424 @default.
- W3203078652 hasConceptScore W3203078652C111208986 @default.
- W3203078652 hasConceptScore W3203078652C111919701 @default.
- W3203078652 hasConceptScore W3203078652C11413529 @default.
- W3203078652 hasConceptScore W3203078652C116834253 @default.
- W3203078652 hasConceptScore W3203078652C121332964 @default.
- W3203078652 hasConceptScore W3203078652C124101348 @default.
- W3203078652 hasConceptScore W3203078652C154945302 @default.
- W3203078652 hasConceptScore W3203078652C17349429 @default.
- W3203078652 hasConceptScore W3203078652C173608175 @default.
- W3203078652 hasConceptScore W3203078652C2779960059 @default.
- W3203078652 hasConceptScore W3203078652C33704608 @default.
- W3203078652 hasConceptScore W3203078652C41008148 @default.
- W3203078652 hasConceptScore W3203078652C46576248 @default.
- W3203078652 hasConceptScore W3203078652C59822182 @default.
- W3203078652 hasConceptScore W3203078652C62520636 @default.
- W3203078652 hasConceptScore W3203078652C68339613 @default.
- W3203078652 hasConceptScore W3203078652C73555534 @default.
- W3203078652 hasConceptScore W3203078652C84114770 @default.
- W3203078652 hasConceptScore W3203078652C86803240 @default.
- W3203078652 hasConceptScore W3203078652C94641424 @default.
- W3203078652 hasFunder F4320321019 @default.
- W3203078652 hasLocation W32030786521 @default.
- W3203078652 hasOpenAccess W3203078652 @default.
- W3203078652 hasPrimaryLocation W32030786521 @default.
- W3203078652 hasRelatedWork W1509211761 @default.
- W3203078652 hasRelatedWork W1531488649 @default.
- W3203078652 hasRelatedWork W1989119024 @default.
- W3203078652 hasRelatedWork W2133693067 @default.
- W3203078652 hasRelatedWork W2187492663 @default.
- W3203078652 hasRelatedWork W2368219397 @default.
- W3203078652 hasRelatedWork W2391299576 @default.
- W3203078652 hasRelatedWork W3203078652 @default.
- W3203078652 hasRelatedWork W34241620 @default.
- W3203078652 hasRelatedWork W4290987788 @default.
- W3203078652 isParatext "false" @default.
- W3203078652 isRetracted "false" @default.
- W3203078652 magId "3203078652" @default.
- W3203078652 workType "article" @default.