Title | Efficient Phase-Functioned Real-time Character Control in Mobile Games: A TVM Enabled Approach |
Author | |
Corresponding Author | Meng, Jintao; Deng, Minwen |
DOI | |
Publication Years | 2022-08-29
|
Conference Name | 51st International Conference on Parallel Processing, ICPP 2022
|
ISBN | 9781450397339
|
Source Title | |
Conference Date | August 29, 2022 - September 1, 2022
|
Conference Place | Virtual, Online, France
|
Publisher | |
Abstract | In this paper, we propose a highly efficient computing method for game character control with phase-functioned neural networks (PFNN). The primary challenge to accelerate PFNN on mobile platforms is that PFNN dynamically produces weight matrices with an argument, phase, which is individual to each game character. Therefore existing libraries that generally assume frozen weight matrices are inefficient to accelerate PFNN. The situation becomes even worse when multiple characters are present. To address the challenges, we reformulate the equations and leverage the deep learning compiler stack TVM to build a cross-platform, high-performance implementation. Evaluations reveal that our solutions deliver close-to-peak performance on various platforms, from high-performance servers to energy-efficient mobile platforms. This work is publicly available at https://github.com/turbo0628/pfnn_tvm. © 2022 ACM. |
SUSTech Authorship | Others
|
Language | English
|
Indexed By | |
Funding Project | This work was partly supported by the National Key Research and Development Program of China Grant No. 2021YFF1200100 and 2021YFF1200104, Strategic Priority CAS Project XDB38050100, the Key Research and Development Project of Guangdong Province under grant No. 2021B0101310002, the National Science Foundation of China under grant No. U1813203, the Shenzhen Basic Research Fund under grant No. KQTD20200820113106007, the General Program of Key Technology from Shenzhen under grant No. JSGG20190220164202211 and JSGG20191129110221063. We also want to thank the editors and reviewers for their professional comments which have greatly improved this manuscript.
|
EI Accession Number | 20230913635586
|
EI Keywords | Computer games
; Energy efficiency
; Program compilers
|
ESI Classification Code | Ergonomics and Human Factors Engineering:461.4
; Energy Conservation:525.2
; Computer Applications:723.5
|
Data Source | EV Compendex
|
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/519782 |
Affiliation | 1.Tencent Ai Lab, Shenzhen, China 2.Shenzhen Institue of Advanced Technology, Chinese Academy of Science, Shenzhen, China 3.Southern University of Science and Technology, Shenzhen, China |
Recommended Citation GB/T 7714 |
Lan, Haidong,Zhu, Wenxi,Wu, Du,et al. Efficient Phase-Functioned Real-time Character Control in Mobile Games: A TVM Enabled Approach[C]:Association for Computing Machinery,2022.
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment