SmCompactor: A workload-aware fine-grained resource management framework for GPGPUs
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Q. | - |
dc.contributor.author | Chung, H. | - |
dc.contributor.author | Son, Y. | - |
dc.contributor.author | Kim, Y. | - |
dc.contributor.author | Yeom, H.Y. | - |
dc.date.accessioned | 2022-01-25T03:41:35Z | - |
dc.date.available | 2022-01-25T03:41:35Z | - |
dc.date.issued | 2021-03 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/54361 | - |
dc.description.abstract | Recently, graphic processing unit (GPU) multitasking has become important in many platforms since an efficient GPU multitasking mechanism can enable more GPU-enabled tasks running on limited physical GPUs. However, current GPU multitasking technologies, such as NVIDIA Multi-Process Service (MPS) and Hyper-Q may not fully utilize GPU resources since they do not consider the efficient use of intra-GPU resources. In this paper, we present smCompactor, which is a fine-grained GPU multitasking framework to fully exploit intra-GPU resources for different workloads. smCompactor dispatches any particular thread blocks (TBs) of different GPU kernels to appropriate stream multiprocessors (SMs) based on our profiled results of workloads. With smCompactor, GPU resource utilization can be improved as we can run more workloads on a single GPU while their performance is maintained. The evaluation results show that smCompactor improves resource utilization in terms of the number of active SMs by up to 33% and it reduces the kernel execution time by up to 26% compared with NVIDIA MPS. | - |
dc.format.extent | 9 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Association for Computing Machinery | - |
dc.title | SmCompactor: A workload-aware fine-grained resource management framework for GPGPUs | - |
dc.type | Article | - |
dc.identifier.doi | 10.1145/3412841.3441989 | - |
dc.identifier.bibliographicCitation | Proceedings of the ACM Symposium on Applied Computing, pp 1147 - 1155 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 001108757100149 | - |
dc.identifier.scopusid | 2-s2.0-85104953199 | - |
dc.citation.endPage | 1155 | - |
dc.citation.startPage | 1147 | - |
dc.citation.title | Proceedings of the ACM Symposium on Applied Computing | - |
dc.type.docType | Proceedings Paper | - |
dc.subject.keywordAuthor | GPU multitasking | - |
dc.subject.keywordAuthor | GPU resource management | - |
dc.subject.keywordAuthor | HPC | - |
dc.subject.keywordAuthor | OS | - |
dc.subject.keywordAuthor | parallel computing | - |
dc.subject.keywordPlus | Multitasking | - |
dc.subject.keywordPlus | Program processors | - |
dc.subject.keywordPlus | Evaluation results | - |
dc.subject.keywordPlus | Fine grained | - |
dc.subject.keywordPlus | Graphic processing unit(GPU) | - |
dc.subject.keywordPlus | Multi-Processes | - |
dc.subject.keywordPlus | Resource management framework | - |
dc.subject.keywordPlus | Resource utilizations | - |
dc.subject.keywordPlus | Graphics processing unit | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.