CPU-GPU hybrid computing for feature extraction from video stream

被引：5

作者：

Lee, Sungju ^{[1
]}

Kim, Heegon ^{[1
]}

Park, Daihee ^{[1
]}

Chung, Yongwha ^{[1
]}

Jeong, Taikyeong ^{[2
]}

机构：

[1] Korea Univ, Dept Comp & Informat Sci, Sejong, South Korea

[2] Seoul Womens Univ, Dept Comp Sci & Engn, Seoul, South Korea

来源：

IEICE ELECTRONICS EXPRESS | 2014年 / 11卷 / 22期

关键词：

CPU; GPU; heterogeneous computing; feature extraction;

D O I：

10.1587/elex.11.20140932

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we propose a way to distribute the video analytics workload into both the CPU and GPU, with a performance prediction model including characteristics of feature extraction from the video stream data. That is, we estimate the total execution time of a CPU-GPU hybrid computing system with the performance prediction model, and determine the optimal workload ratio and how to use the CPU cores for the given workload. Based on experimental results, we confirm that our proposed method can improve the speedups of three typical workload distributions: CPU-only, GPU-only, or CPU-GPU hybrid computing with a 50:50 workload ratio.

引用

页数：8

共 50 条

[41] Exploration on Task Scheduling Strategy for CPU-GPU Heterogeneous Computing System
Fang, Juan
Zhang, Jiaxing
Lu, Shuaibing
Zhao, Hui
[J]. 2020 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI 2020), 2020, : 306 - 311
[42] Application of hybrid CPU-GPU computing platform in large-scale geotechnical finite element analysis
Beijing Jiaotong University, Beijing
100044, China
[J]. Tumu Gongcheng Xuebao, 6 (105-112):
[43] A Hybrid B plus -tree as Solution for In-Memory Indexing on CPU-GPU Heterogeneous Computing Platforms
Shahvarani, Amirhesam
Jacobsen, Hans-Arno
[J]. SIGMOD'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2016, : 1523 - 1538
[44] Securing AI Inference in the Cloud: Is CPU-GPU Confidential Computing Ready?
Mohan, Apoorve
Ye, Mengmei
Franke, Hubertus
Srivatsa, Mudhakar
Liu, Zhuoran
Gonzalez, Nelson Mimura
[J]. 2024 IEEE 17TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING, CLOUD 2024, 2024, : 164 - 175
[45] Supporting Energy-Efficient Computing on Heterogeneous CPU-GPU Architectures
Siehl, Kyle
Zhao, Xinghui
[J]. 2017 IEEE 5TH INTERNATIONAL CONFERENCE ON FUTURE INTERNET OF THINGS AND CLOUD (FICLOUD 2017), 2017, : 134 - 141
[46] A comparison of Algebraic Multigrid Bidomain solvers on hybrid CPU-GPU architectures
Centofanti, Edoardo
Scacchi, Simone
[J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 423
[47] Hybrid CPU-GPU constraint checking: Towards efficient context consistency
Sui, Jun
Xu, Chang
Cheung, S. C.
Xi, Wang
Jiang, Yanyan
Cao, Chun
Ma, Xiaoxing
Lu, Jian
[J]. INFORMATION AND SOFTWARE TECHNOLOGY, 2016, 74 : 230 - 242
[48] Hybrid CPU-GPU execution support in the skeleton programming framework SkePU
Ohberg, Tomas
Ernstsson, August
Kessler, Christoph
[J]. JOURNAL OF SUPERCOMPUTING, 2020, 76 (07): : 5038 - 5056
[49] Efficient irregular wavefront propagation algorithms on hybrid CPU-GPU machines
Teodoro, George
Pan, Tony
Kurc, Tahsin M.
Kong, Jun
Cooper, Lee A. D.
Saltz, Joel H.
[J]. PARALLEL COMPUTING, 2013, 39 (4-5) : 189 - 211
[50] Improving Dense Linear Equation Solver on Hybrid CPU-GPU System
Cao, Zhichao
Xu, Shiming
Xue, Wei
Chen, Wenguang
[J]. 2009 10TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS, AND NETWORKS (ISPAN 2009), 2009, : 556 - +

← 1 2 3 4 5 →