FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186289964> ?p ?o ?g. }

• W3186289964 endingPage "26" @default.
• W3186289964 startingPage "1" @default.
• W3186289964 abstract "With the proliferation of applications with machine learning (ML), the importance of edge platforms has been growing to process streaming sensor, data locally without resorting to remote servers. Such edge platforms are commonly equipped with heterogeneous computing processors such as GPU, DSP, and other accelerators, but their computational and energy budget are severely constrained compared to the data center servers. However, as an edge platform must perform the processing of multiple machine learning models concurrently for multimodal sensor data, its scheduling problem poses a new challenge to map heterogeneous machine learning computation to heterogeneous computing processors. Furthermore, processing of each input must provide a certain level of bounded response latency, making the scheduling decision critical for the edge platform. This article proposes a set of new heterogeneity-aware ML inference scheduling policies for edge platforms. Based on the regularity of computation in common ML tasks, the scheduler uses the pre-profiled behavior of each ML model and routes requests to the most appropriate processors. It also aims to satisfy the service-level objective (SLO) requirement while reducing the energy consumption for each request. For such SLO supports, the challenge of ML computation on GPUs and DSP is its inflexible preemption capability. To avoid the delay caused by a long task, the proposed scheduler decomposes a large ML task to sub-tasks by its layer in the DNN model." @default.
• W3186289964 created "2021-08-02" @default.
• W3186289964 creator A5006429670 @default.
• W3186289964 creator A5017067532 @default.
• W3186289964 creator A5034451791 @default.
• W3186289964 creator A5037553165 @default.
• W3186289964 creator A5047149607 @default.
• W3186289964 date "2021-07-17" @default.
• W3186289964 modified "2023-10-06" @default.
• W3186289964 title "SLO-Aware Inference Scheduler for Heterogeneous Processors in Edge Platforms" @default.
• W3186289964 cites W1677182931 @default.
• W3186289964 cites W1972916106 @default.
• W3186289964 cites W1989099984 @default.
• W3186289964 cites W2002478203 @default.
• W3186289964 cites W2016531398 @default.
• W3186289964 cites W2034181225 @default.
• W3186289964 cites W2092877006 @default.
• W3186289964 cites W2119112357 @default.
• W3186289964 cites W2136849599 @default.
• W3186289964 cites W2167866796 @default.
• W3186289964 cites W2191835017 @default.
• W3186289964 cites W2194775991 @default.
• W3186289964 cites W2604514113 @default.
• W3186289964 cites W2610406889 @default.
• W3186289964 cites W2623902153 @default.
• W3186289964 cites W2626129225 @default.
• W3186289964 cites W2772526503 @default.
• W3186289964 cites W2787114603 @default.
• W3186289964 cites W2794670651 @default.
• W3186289964 cites W2807807191 @default.
• W3186289964 cites W2903254051 @default.
• W3186289964 cites W2906791813 @default.
• W3186289964 cites W2922395136 @default.
• W3186289964 cites W2928897890 @default.
• W3186289964 cites W2931092525 @default.
• W3186289964 cites W2931743911 @default.
• W3186289964 cites W2963728985 @default.
• W3186289964 cites W2979359324 @default.
• W3186289964 cites W2982157693 @default.
• W3186289964 cites W2984200518 @default.
• W3186289964 cites W2990894474 @default.
• W3186289964 cites W3007788310 @default.
• W3186289964 cites W3016842236 @default.
• W3186289964 cites W3016939927 @default.
• W3186289964 cites W3034544214 @default.
• W3186289964 cites W3047401492 @default.
• W3186289964 cites W3100944043 @default.
• W3186289964 cites W3105888187 @default.
• W3186289964 cites W4231332361 @default.
• W3186289964 cites W4236099117 @default.
• W3186289964 cites W4236853429 @default.
• W3186289964 doi "https://doi.org/10.1145/3460352" @default.
• W3186289964 hasPublicationYear "2021" @default.
• W3186289964 type Work @default.
• W3186289964 sameAs 3186289964 @default.
• W3186289964 citedByCount "5" @default.
• W3186289964 countsByYear W31862899642022 @default.
• W3186289964 countsByYear W31862899642023 @default.
• W3186289964 crossrefType "journal-article" @default.
• W3186289964 hasAuthorship W3186289964A5006429670 @default.
• W3186289964 hasAuthorship W3186289964A5017067532 @default.
• W3186289964 hasAuthorship W3186289964A5034451791 @default.
• W3186289964 hasAuthorship W3186289964A5037553165 @default.
• W3186289964 hasAuthorship W3186289964A5047149607 @default.
• W3186289964 hasBestOaLocation W31862899641 @default.
• W3186289964 hasConcept C111919701 @default.
• W3186289964 hasConcept C11413529 @default.
• W3186289964 hasConcept C120314980 @default.
• W3186289964 hasConcept C138236772 @default.
• W3186289964 hasConcept C153740404 @default.
• W3186289964 hasConcept C154945302 @default.
• W3186289964 hasConcept C162307627 @default.
• W3186289964 hasConcept C162324750 @default.
• W3186289964 hasConcept C172430144 @default.
• W3186289964 hasConcept C18903297 @default.
• W3186289964 hasConcept C206729178 @default.
• W3186289964 hasConcept C206952183 @default.
• W3186289964 hasConcept C21547014 @default.
• W3186289964 hasConcept C2776214188 @default.
• W3186289964 hasConcept C2778456923 @default.
• W3186289964 hasConcept C2780165032 @default.
• W3186289964 hasConcept C2781041963 @default.
• W3186289964 hasConcept C31258907 @default.
• W3186289964 hasConcept C41008148 @default.
• W3186289964 hasConcept C45374587 @default.
• W3186289964 hasConcept C79974875 @default.
• W3186289964 hasConcept C84462506 @default.
• W3186289964 hasConcept C86803240 @default.
• W3186289964 hasConcept C9390403 @default.
• W3186289964 hasConcept C93996380 @default.
• W3186289964 hasConceptScore W3186289964C111919701 @default.
• W3186289964 hasConceptScore W3186289964C11413529 @default.
• W3186289964 hasConceptScore W3186289964C120314980 @default.
• W3186289964 hasConceptScore W3186289964C138236772 @default.
• W3186289964 hasConceptScore W3186289964C153740404 @default.
• W3186289964 hasConceptScore W3186289964C154945302 @default.
• W3186289964 hasConceptScore W3186289964C162307627 @default.
• W3186289964 hasConceptScore W3186289964C162324750 @default.

• next