DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김이섭 | - |
dc.contributor.author | Han, Yunki | - |
dc.contributor.author | 한윤기 | - |
dc.date.accessioned | 2024-07-25T19:30:27Z | - |
dc.date.available | 2024-07-25T19:30:27Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1044994&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320449 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[vi, 33 p. :] | - |
dc.description.abstract | As Graph Neural Networks (GNNs) have emerged as a mainstream algorithm in many research areas, designing a GNN accelerator becomes a new challenge. Compared to previous DNNs, GNNs include characteristics of both graph processing and neural networks. In this paper, we analyze the workload of GNNs executed on existing hardware platforms and identify the intensive DRAM access as the main bottleneck for accelerating GNNs. Focusing on this problem, we propose a series of schemes, both hardware and algorithm side, to reduce DRAM access. Our work achieves on average 3.67x, 5.36x, 3.49x speedup than the GPU on GCN, SAGE, and GAT. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 그래프 신경망▼a하드웨어 가속기▼a인공지능 가속기 디자인▼a하드웨어 및 알고리즘 공동 최적화▼a병렬 처리 | - |
dc.subject | Graph Neural Network▼aHardware accelerator▼aAI accelerator design▼aHardware and Algorithm co-optimization▼aParallel processing | - |
dc.title | Hardware and algorithm co-optimization for graph neural network acceleration | - |
dc.title.alternative | 그래프 신경망 가속을 위한 하드웨어 및 알고리즘 최적화 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Kim, Lee-Sup | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.