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

[41] Parallel Electronic Structure Calculations Using Multiple Graphics Processing Units (GPUs)
Hakala, Samuli
Havu, Ville
Enkovaara, Jussi
Nieminen, Risto
APPLIED PARALLEL AND SCIENTIFIC COMPUTING (PARA 2012), 2013, 7782 : 63 - 76
[42] Towards highly-efficient liquid crystal microlasers
Araoka, Fumito
Takezoe, Hideo
ORGANIC PHOTONIC MATERIALS AND DEVICES XIII, 2011, 7935
[43] Efficient Parallel Stencil Convolution in Haskell
Lippmeier, Ben
Keller, Gabriele
HASKELL 11: PROCEEDINGS OF THE 2011 ACM SIGPLAN HASKELL SYMPOSIUM, 2011, : 59 - 70
[44] Designed, highly-efficient FED phosphors and screens
Bolchouchine, VA
Goldburt, ET
Levonovitch, BN
Litchmanova, VN
Sochtine, NP
JOURNAL OF LUMINESCENCE, 2000, 87-9 (87) : 1277 - 1279
[45] Efficient Parallel Stencil Convolution in Haskell
Lippmeier, Ben
Keller, Gabriele
ACM SIGPLAN NOTICES, 2011, 46 (12) : 59 - 70
[46] PARALLEL COMPUTATION OF MULTIPLE SPACE TRAJECTORIES USING GPUS AND INTERPOLATED GRAVITY MODELS
Arora, Nitin
Russell, Ryan P.
Vittaldev, Vivek
ASTRODYNAMICS 2013, PTS I-III, 2014, 150 : 2881 - 2897
[47] Highly-Efficient Preparation of Key Intermediate of Huperzine A
Xie Kai-ming
GREEN POWER, MATERIALS AND MANUFACTURING TECHNOLOGY AND APPLICATIONS III, PTS 1 AND 2, 2014, 484-485 : 157 - 160
[48] Highly-Efficient Wait-Free Synchronization
Fatourou, Panagiota
Kallimanis, Nikolaos D.
THEORY OF COMPUTING SYSTEMS, 2014, 55 (03) : 475 - 520
[49] HIGHLY-EFFICIENT COLUMN LIQUID-CHROMATOGRAPHY
YASHIN, YI
ZHURNAL VSESOYUZNOGO KHIMICHESKOGO OBSHCHESTVA IMENI D I MENDELEEVA, 1983, 28 (01): : 18 - 25
[50] Highly-Efficient Wait-Free Synchronization
Panagiota Fatourou
Nikolaos D. Kallimanis
Theory of Computing Systems, 2014, 55 : 475 - 520

← 1 2 3 4 5 →