Highly-Efficient Parallel Convolution Acceleration by Using Multiple GPUs

被引：0

作者：

Sun, Kuangyuan ^{[1
]}

Li, Shuai ^{[1
]}

Luo, Yukui ^{[1
]}

Renteria, Raul ^{[1
]}

Choi, Ken ^{[1
]}

机构：

[1] IIT, Dept Elect & Comp Engn, VLSI Design & Automat Lab, 3301 S Dearborn St, Chicago, IL 60616 USA

来源：

PROCEEDINGS INTERNATIONAL SOC DESIGN CONFERENCE 2017 (ISOCC 2017) | 2017年

关键词：

Convolutional neural network; parallel acceleration; multiple GPUs;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Convolutional Neural Network (CNN) is a powerful tool in machine learning area. However, the convolution computation is time-consuming, which limited the application on embedded system. In this paper, we introduce a parallel convolution acceleration implementation by using multiple GPUs Mali-T628 MP6 on embedded system Odroid XU4 and have tested its time reduction and GPU utilization. The result show that the execution time is reduced 25.8% on average.

引用

页码：300 / 301

页数：2

共 50 条

[21] Speeding towards the highly-efficient shipyard
不详
NAVAL ARCHITECT, 1996, : 3 - 3
[22] Highly-Efficient Selection of Aptamers for Quantitative Fluorescence Detecting Multiple IAV Subtypes
Wang, Meng
Chen, Jianjun
Zhang, Zhi-Ling
ANALYTICAL CHEMISTRY, 2024, 96 (38) : 15347 - 15354
[23] Highly-Efficient Persistent FIFO Queues
Fatourou, Panagiota
Giachoudis, Nikos
Mallis, George
STRUCTURAL INFORMATION AND COMMUNICATION COMPLEXITY, SIROCCO 2024, 2024, 14662 : 238 - 261
[24] Future highly-efficient optical networks
Willner, AE
2005 Conference on Lasers & Electro-Optics (CLEO), Vols 1-3, 2005, : 1052 - 1054
[25] Acceleration of virtual screening using GPUs
Sirimulla, Suman
Koebel, Mathew
Schmadeke, Grant
ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2015, 250
[26] Highly-efficient 20 TW Ti:sapphire laser system using optimized diverging beams for laser wakefield acceleration experiments
Nam, Inhyuk
Kim, Minseok
Lee, Tae Hee
Lee, Seung Woo
Suk, Hyyong
CURRENT APPLIED PHYSICS, 2015, 15 (04) : 468 - 472
[27] Restacked melon as highly-efficient photocatalyst
Wang, Yanlong
Zhang, Yang
Li, Baozhong
Luo, Kun
Shi, Kaiyuan
Zhang, Li
Li, Yi
Yu, Tianjun
Hu, Wentao
Xie, Chenlong
Wu, Yingju
Su, Lei
Dong, Xiao
Zhao, Zhisheng
Yang, Guoqiang
NANO ENERGY, 2020, 77
[28] Clean and highly-efficient utilization of coal
Yue, Guangxi
Lyu, Junfu
Li, Shuiqing
FRONTIERS IN ENERGY, 2021, 15 (01) : 1 - 3
[29] Acceleration of In-Core LU-Decomposition of Dense MoM Matrix by Parallel usage of Multiple GPUs
Mrdakovic, Branko Lj.
Kostic, Milan M.
Olcan, Dragan I.
Kolundzija, Branko M.
2017 IEEE INTERNATIONAL CONFERENCE ON MICROWAVES, ANTENNAS, COMMUNICATIONS AND ELECTRONIC SYSTEMS (COMCAS), 2017, : 372 - 375
[30] NTTFusion: Efficient Number Theoretic Transform Acceleration on GPUs
Wang, Zhiwei
Li, Peinan
Hou, Rui
Meng, Dan
2023 IEEE 41ST INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, ICCD, 2023, : 357 - 365

← 1 2 3 4 5 →