DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoo, Hoi-Jun | - |
dc.contributor.advisor | 유회준 | - |
dc.contributor.author | Kim, Sangjin | - |
dc.date.accessioned | 2022-04-27T19:31:25Z | - |
dc.date.available | 2022-04-27T19:31:25Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948692&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296020 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iii, 26 p. :] | - |
dc.description.abstract | A low-power graph convolutional network (GCN) is proposed for accelerating 3D point cloud semantic segmentation (PCSS) in real-time on mobile devices. Three key features enable the low power GCN-based 3D PCSS. First, the new hardware friendly GCN algorithm, sparse grouping based dilated graph convolution (SG-DGC) is proposed and reduce power consumption through the reduction of computation and external memory access (EMA). SG-DGC reduces 71.7% of the overall computation and 76.9% of EMA through the sparse grouping of the point cloud. Proposed processor accelerate the GCN with the two-level pipeline (TLP) consisting of the point-level pipeline (PLP) and group-level pipelining (GLP). The PLP enables point-level module-wise fusion (PMF) which reduces 47.4% of EMA with minimal additional on-chip memory footprint through point-level execution. The GLP increased the core utilization by 21.1% through balancing the workload of graph generation and graph convolution with the loosened data dependency through SG-DGC and enable 1.1× higher throughput. Finally, center point feature reuse (CPFR) reuse computation results of the redundant operation and reduces 11.4% of computation. The processor is implemented with 65nm CMOS technology, and the 4.0mm$^2$ 3D PCSS processor show 95mW power consumption while operating in real-time of 30.8 frames-per-second 3D PCSS with 4k points. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 그래프 컨볼루션 네트워크▼a딥 뉴럴 네트워크▼a점 구름▼a의미론 분할▼a모바일 혼합 현실 기기▼a저전력 가속기 | - |
dc.subject | Graph convolutional network▼aDeep neural network▼aPoint cloud▼aSemantic segmentation▼aMobile mixed reality device▼aLow-power accelerators | - |
dc.title | (A) low-power graph convolutional network processor for real-time 3D point cloud semantic segmentation | - |
dc.title.alternative | 실시간 3D 점 구름 분할을 위한 저전력 그래프 컨볼루션 네트워크 프로세서 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김상진 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.