Imperial College London
Alternate

ProfessorPaulKelly

Faculty of Engineering, Department of Computing

Professor of Software Technology
 
 
 
//

Contact

 

+44 (0)20 7594 8332p.kelly Website

 
 
//

Location

 

Level 3 (upstairs), William Penney Building, room 304William Penney LaboratorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Bodin:2016:10.1145/2967938.2967963,
author = {Bodin, B and Nardi, L and Zia, MZ and Wagstaff, H and Shenoy, GS and Emani, M and Mawer, J and Kotselidis, C and Nisbet, A and Lujan, M and Franke, B and Kelly, PHJ and O’Boyle, M},
doi = {10.1145/2967938.2967963},
publisher = {IEEE},
title = {Integrating Algorithmic Parameters into Benchmarking and Design Space Exploration in 3D Scene Understanding},
url = {http://dx.doi.org/10.1145/2967938.2967963},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - System designers typically use well-studied benchmarks toevaluate and improve new architectures and compilers. Wedesign tomorrow's systems based on yesterday's applications.In this paper we investigate an emerging application,3D scene understanding, likely to be signi cant in the mobilespace in the near future. Until now, this application couldonly run in real-time on desktop GPUs. In this work, weexamine how it can be mapped to power constrained embeddedsystems. Key to our approach is the idea of incrementalco-design exploration, where optimization choices that concernthe domain layer are incrementally explored togetherwith low-level compiler and architecture choices. The goalof this exploration is to reduce execution time while minimizingpower and meeting our quality of result objective.As the design space is too large to exhaustively evaluate,we use active learning based on a random forest predictorto  nd good designs. We show that our approach can, forthe  rst time, achieve dense 3D mapping and tracking in thereal-time range within a 1W power budget on a popular embeddeddevice. This is a 4.8x execution time improvementand a 2.8x power reduction compared to the state-of-the-art.
AU  - Bodin,B
AU  - Nardi,L
AU  - Zia,MZ
AU  - Wagstaff,H
AU  - Shenoy,GS
AU  - Emani,M
AU  - Mawer,J
AU  - Kotselidis,C
AU  - Nisbet,A
AU  - Lujan,M
AU  - Franke,B
AU  - Kelly,PHJ
AU  - O’Boyle,M
DO  - 10.1145/2967938.2967963
PB  - IEEE
PY  - 2016///
TI  - Integrating Algorithmic Parameters into Benchmarking and Design Space Exploration in 3D Scene Understanding
UR  - http://dx.doi.org/10.1145/2967938.2967963
UR  - http://hdl.handle.net/10044/1/38354
ER  -
Download