DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim,Sangjin | ko |
dc.contributor.author | Lee, Juhyoung | ko |
dc.contributor.author | Im, Dongseok | ko |
dc.contributor.author | Yoo, Hoijun | ko |
dc.date.accessioned | 2021-11-04T06:43:19Z | - |
dc.date.available | 2021-11-04T06:43:19Z | - |
dc.date.created | 2021-10-26 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.citation | 35th Symposium on VLSI Circuits, VLSI Circuits 2021 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288773 | - |
dc.description.abstract | An efficient and high-speed 3D point cloud-based neural network processing unit (PNNPU) is proposed using the block-based point processing. It has three key features: 1) page-based point block memory management unit (PMMU) with linked list-based page table (LLPT) for on-chip memory footprint reduction, 2) hierarchical block-wise farthest point sampling (HFPS), and block skipping ball-query (BSBQ) for fast and efficient point processing, 3) Skipping-based max-pooling prediction (SMPP) for throughput enhancement. The PNNPU is fabricated in 65nm CMOS process and evaluated on the 3D object detection (3D OD) application. As a result, it shows 84.8 fps at 266.8mW power consumption and achieving 6.6-11.9 TOPS/W energy efficiency. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | PNNPU: A 11.9 TOPS/W High-speed 3D Point Cloud-based Neural Network Processor with Block-based Point Processing for Regular DRAM Access | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85111864047 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 35th Symposium on VLSI Circuits, VLSI Circuits 2021 | - |
dc.identifier.conferencecountry | JA | - |
dc.identifier.conferencelocation | Kyoto | - |
dc.identifier.doi | 10.23919/VLSICircuits52068.2021.9492450 | - |
dc.contributor.localauthor | Yoo, Hoijun | - |
dc.contributor.nonIdAuthor | Kim,Sangjin | - |
dc.contributor.nonIdAuthor | Lee, Juhyoung | - |
dc.contributor.nonIdAuthor | Im, Dongseok | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.