DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 유민수 | - |
dc.contributor.author | Kim, Jiin | - |
dc.contributor.author | 김지인 | - |
dc.date.accessioned | 2024-08-08T19:30:14Z | - |
dc.date.available | 2024-08-08T19:30:14Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097302&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321777 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[iv, 25 p. :] | - |
dc.description.abstract | Maximizing the utilization of graphics processing unit (GPU) resources becomes a crucial factor in directly reducing a data center’s Total cost of ownership (TCO). To address this, GPU partitioning technology has been developed, enabling the simultaneous execution of multiple workloads by dividing a single GPU. However, research on the analysis of characteristics when GPU partitioning technology is applied in real-world machine learning inference systems has not been actively conducted. This thesis analyzes workloads when utilizing GPU partitioning technology to enhance the efficiency of machine learning inference systems. Specifically, we focus on aspects such as resource utilization, throughput, and latency in the context of GPU partitioning. Based on the characterization results, we propose an efficient batching system for GPU partitioning-based machine learning inference to optimize the performance of the overall system further. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 머신 러닝▼a그래픽 처리 장치 분할 기술▼a머신 러닝 추론▼a배칭 | - |
dc.subject | Machine learning▼aGPU partitioning▼aInference▼aBatching | - |
dc.title | Workload characterization for gpu partitioning-based machine learning inference server | - |
dc.title.alternative | GPU 분할 기술이 적용된 머신 러닝 추론 서버의 특성 분석 및 활용 방안 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Rhu, Minsoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.