Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206149382> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4206149382 endingPage "268" @default.
- W4206149382 startingPage "253" @default.
- W4206149382 abstract "Recently, a large number of convolutional neural network (CNN) inference services have emerged on high-performance Graphic Processing Units (GPUs). However, GPUs are high power consumption units, and the energy consumption increases sharply along with the deployment of deep learning tasks. Although previous studies have considered the latency Service-Level-Objective (SLO) of inference services, they fail to directly take account of the energy consumption. Our investigation shows that coordinating batching and dynamic voltage frequency scaling (DVFS) settings can decrease the energy consumption of CNN inference. But it is affected by (i) larger configuration spaces; (ii) GPUs’ underutilization while data are transferred between CPUs and GPUs; (iii) fluctuating workloads. In this paper, we propose EAIS, an energy-aware adaptive scheduling framework that is comprised of a performance model, an asynchronous execution strategy, and an energy-aware scheduler. The performance model provides valid information about the performance characteristics of CNN inference services to shrink the feasible configuration space. The asynchronous execution strategy overlaps data upload and GPU execution to improve the system processing capacity. The energy-aware scheduler adaptively coordinates batching and DVFS according to fluctuating workloads to minimize energy consumption while meeting latency SLO. Our experimental results on NVIDIA Tesla M40 and V100 GPUs show that, compared to the state-of-the-art methods, EAIS decreases the energy consumption by up to 28.02% and improves the system processing capacity by up to 7.22% while meeting latency SLO. Besides, EAIS has been proved to have good versatility under different latency SLO constraints." @default.
- W4206149382 created "2022-01-25" @default.
- W4206149382 creator A5011069823 @default.
- W4206149382 creator A5018288181 @default.
- W4206149382 creator A5050726636 @default.
- W4206149382 creator A5060479110 @default.
- W4206149382 date "2022-05-01" @default.
- W4206149382 modified "2023-09-30" @default.
- W4206149382 title "EAIS: Energy-aware adaptive scheduling for CNN inference on high-performance GPUs" @default.
- W4206149382 cites W2048085362 @default.
- W4206149382 cites W2116250234 @default.
- W4206149382 cites W2117539524 @default.
- W4206149382 cites W2131889098 @default.
- W4206149382 cites W2289252105 @default.
- W4206149382 cites W2559253174 @default.
- W4206149382 cites W2560530131 @default.
- W4206149382 cites W2762077810 @default.
- W4206149382 cites W2959492565 @default.
- W4206149382 cites W2973657294 @default.
- W4206149382 cites W3030601576 @default.
- W4206149382 cites W3043305612 @default.
- W4206149382 cites W3089559850 @default.
- W4206149382 cites W3117103847 @default.
- W4206149382 cites W639708223 @default.
- W4206149382 cites W3093818819 @default.
- W4206149382 doi "https://doi.org/10.1016/j.future.2022.01.004" @default.
- W4206149382 hasPublicationYear "2022" @default.
- W4206149382 type Work @default.
- W4206149382 citedByCount "8" @default.
- W4206149382 countsByYear W42061493822022 @default.
- W4206149382 countsByYear W42061493822023 @default.
- W4206149382 crossrefType "journal-article" @default.
- W4206149382 hasAuthorship W4206149382A5011069823 @default.
- W4206149382 hasAuthorship W4206149382A5018288181 @default.
- W4206149382 hasAuthorship W4206149382A5050726636 @default.
- W4206149382 hasAuthorship W4206149382A5060479110 @default.
- W4206149382 hasConcept C119599485 @default.
- W4206149382 hasConcept C120314980 @default.
- W4206149382 hasConcept C127413603 @default.
- W4206149382 hasConcept C149635348 @default.
- W4206149382 hasConcept C151319957 @default.
- W4206149382 hasConcept C154945302 @default.
- W4206149382 hasConcept C157742956 @default.
- W4206149382 hasConcept C162324750 @default.
- W4206149382 hasConcept C173608175 @default.
- W4206149382 hasConcept C18903297 @default.
- W4206149382 hasConcept C206729178 @default.
- W4206149382 hasConcept C21547014 @default.
- W4206149382 hasConcept C2742236 @default.
- W4206149382 hasConcept C2776214188 @default.
- W4206149382 hasConcept C2780165032 @default.
- W4206149382 hasConcept C31258907 @default.
- W4206149382 hasConcept C41008148 @default.
- W4206149382 hasConcept C76155785 @default.
- W4206149382 hasConcept C79403827 @default.
- W4206149382 hasConcept C82876162 @default.
- W4206149382 hasConcept C86803240 @default.
- W4206149382 hasConceptScore W4206149382C119599485 @default.
- W4206149382 hasConceptScore W4206149382C120314980 @default.
- W4206149382 hasConceptScore W4206149382C127413603 @default.
- W4206149382 hasConceptScore W4206149382C149635348 @default.
- W4206149382 hasConceptScore W4206149382C151319957 @default.
- W4206149382 hasConceptScore W4206149382C154945302 @default.
- W4206149382 hasConceptScore W4206149382C157742956 @default.
- W4206149382 hasConceptScore W4206149382C162324750 @default.
- W4206149382 hasConceptScore W4206149382C173608175 @default.
- W4206149382 hasConceptScore W4206149382C18903297 @default.
- W4206149382 hasConceptScore W4206149382C206729178 @default.
- W4206149382 hasConceptScore W4206149382C21547014 @default.
- W4206149382 hasConceptScore W4206149382C2742236 @default.
- W4206149382 hasConceptScore W4206149382C2776214188 @default.
- W4206149382 hasConceptScore W4206149382C2780165032 @default.
- W4206149382 hasConceptScore W4206149382C31258907 @default.
- W4206149382 hasConceptScore W4206149382C41008148 @default.
- W4206149382 hasConceptScore W4206149382C76155785 @default.
- W4206149382 hasConceptScore W4206149382C79403827 @default.
- W4206149382 hasConceptScore W4206149382C82876162 @default.
- W4206149382 hasConceptScore W4206149382C86803240 @default.
- W4206149382 hasFunder F4320335777 @default.
- W4206149382 hasLocation W42061493821 @default.
- W4206149382 hasOpenAccess W4206149382 @default.
- W4206149382 hasPrimaryLocation W42061493821 @default.
- W4206149382 hasRelatedWork W1882733036 @default.
- W4206149382 hasRelatedWork W1992741870 @default.
- W4206149382 hasRelatedWork W2104603305 @default.
- W4206149382 hasRelatedWork W2160425906 @default.
- W4206149382 hasRelatedWork W2298102683 @default.
- W4206149382 hasRelatedWork W2364921833 @default.
- W4206149382 hasRelatedWork W2508721143 @default.
- W4206149382 hasRelatedWork W2546696010 @default.
- W4206149382 hasRelatedWork W3096147599 @default.
- W4206149382 hasRelatedWork W4372272185 @default.
- W4206149382 hasVolume "130" @default.
- W4206149382 isParatext "false" @default.
- W4206149382 isRetracted "false" @default.
- W4206149382 workType "article" @default.