Fujitsu Develops Technology to Automatically Adjust Computing Accuracy to Accelerate AI Processing by 10 Fold
KAWASAKI, Japan, Oct, 25 2019 - (JCN Newswire) - Fujitsu Laboratories, Ltd. has announced the development of new "Content-Aware Computing" technology that can control accuracy while increasing computing speeds. The technology was developed in response to the increasing demand for computing power accompanying the evolution and popularization of AI technologies. Applying this new technology to deep learning tasks promises to accelerate computing speeds by up to ten times, making it easier to utilize AI for an increasing variety of future applications.
|Figure 1. Speed-up by making to narrow bit width of match to progress of study|
In recent years, the spread of AI technologies in areas like image recognition and speech translation has contributed to increasing demands for processing power, straining existing technologies to their limits. New types of GPUs and specialized processors optimized for AI applications of this nature have been developed in response to this trend. AI tasks are calculated in a variety of environments depending on the specific application, ranging from cloud environment to edge computing contexts. Technologies that offer both stability and fast processing will prove increasingly necessary to deliver the computing power required to deal with demanding AI tasks.
Graphics processing units (GPUs) and dedicated processors have improved computing performance, but they have not caught up with the computational demands of AI. As a means of further streamlining performance for AI tasks, there is a growing interest in technologies that lessen the computational burden and increase speed. In calculating neural network algorithms in deep learning, for instance, one method for achieving higher performance speeds is to reduce the operation precision from 32 bits to 8 bits and carrying out parallel operations 4 times. Unfortunately, the operation result also deteriorates if the operation precision is uniformly lowered. For this reason, a trained expert must painstakingly determine which area's calculation accuracy should be reduced by trial and error. This method proves time-consuming to adjust, requiring readjustment whenever the input data or execution environment changed.
About the Newly Developed Technology
To overcome these challenges, Fujitsu has developed "Content-Aware Computing" technology that automatically controls and speeds up calculation accuracy. This allows for faster AI processing in a variety of execution environments, including GPUs, CPUs, clouds, and edges. The features of this technology are as follows.
1. Automatic bit reduction in technology
Neural networks generally have a numerical range in which each layer converges to a similar numerical value as the learning progresses. Based on the distribution of the numerical range of each layer in the neural network during calculation, the degree of application of the calculation accuracy is determined according to the learning situation, such as wide bit width when the distribution is wide, and narrow bit width when the learning is advanced and converged (Figure 1). This allows deep learning to be up to three times faster than before while reducing the degradation of calculation results.
2. Synchronous mitigation technology that enables high-speed execution in a parallel environment with performance fluctuation
In a cloud environment or other environment where many applications share the CPU, there may be a significant delay in response to some nodes due to communication conflicts, interrupted handling, etc. On the other hand, in each operation of parallel processing, the amount of reduction in processing time when the processing is terminated and the degree of influence on the operation result are estimated, and the termination time of each operation is controlled so that the processing time can be reduced to the maximum extent without deteriorating the operation result. This enables faster parallel processing, leading to confirmed performance of up to 3.7 times faster in deep learning calculations.
Ultimately, the newly developed technology "Content-Aware Computing" can accelerate processing for AI tasks by up to 10 times. By incorporating this technology into AI frameworks and libraries, it becomes possible to speed up AI processing in cloud environments and data centers using GPUs and CPUs with built-in low-bit computing functions.
Moving forward, Fujitsu aims to incorporate this technology into an AI framework that is widely used and will serve as a foundation for the execution of AI services using deep learning.
About Fujitsu Laboratories
Founded in 1968 as a wholly-owned subsidiary of Fujitsu Limited, Fujitsu Laboratories Ltd. is one of the premier research centers in the world. With a global network of laboratories in Japan, China, the United States and Europe, the organization conducts a wide range of basic and applied research in the areas of Next-generation Services, Computer Servers, Networks, Electronic Devices, and Advanced Materials. For more information, please see http://www.fujitsu.com/jp/group/labs/en/.
About Fujitsu Ltd
Fujitsu is the leading Japanese information and communication technology (ICT) company, offering a full range of technology products, solutions, and services. Approximately 132,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. For more information, please see www.fujitsu.com.
This release can be found at https://www.fujitsu.com/global/about/resources/news/press-releases/2019/.
Fujitsu Laboratories Ltd.
Advanced Computer Systems Project
E-mail: [email protected]
Public and Investor Relations
Source: Fujitsu Ltd
Copyright ©2019 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.
More Latest Release >>
MITSUBISHI MOTORS' eK X & eK Wagon Kei Cars Win RJC Car of the Year 2020
Nov 13, 2019 19:39 JST
MHI Aero Engines Makes First Shipment of Domestically Assembled Pratt & Whitney GTF PW1200G Engine for the Mitsubishi SpaceJet
Nov 13, 2019 16:01 JST
Fujitsu Launches New PRIMEHPC Supercomputers Using Fugaku Technology
Nov 13, 2019 10:37 JST
Cray and Fujitsu Partner to Power Supercomputing in the Exascale Era
Nov 13, 2019 10:02 JST
MITSUBISHI MOTORS Introduces XPANDER CROSS
Nov 12, 2019 18:01 JST
DENSO Recognized with "Friend of ASEAN Award" at the ASEAN Business Awards (ABA) 2019
Nov 11, 2019 17:07 JST
Lexus Electric Debuts in China
Nov 11, 2019 16:38 JST
Fujitsu Expands Mid-career Recruitment
Nov 11, 2019 10:33 JST
Double Shanghai Podium for TOYOTA GAZOO Racing
Nov 11, 2019 09:11 JST
TOYOTA GAZOO Racing goes all-in for another title in Australia
Nov 08, 2019 19:33 JST
Honda Releases Consolidated Financial Summary for the Fiscal 2nd Quarter Ended September 30, 2019
Nov 08, 2019 15:09 JST
Mitsubishi Model A Selected as Historic Car by JAHFA
Nov 08, 2019 14:49 JST
BYD, Toyota Agree to Establish Joint Company for Battery Electric Vehicle Research and Development
Nov 07, 2019 19:12 JST
MITSUBISHI MOTORS Restyles Mirage and Attrage Compact Models
Nov 07, 2019 11:58 JST
Hitachi and Centre Leon Berard Cancer Center in Lyon to Launch a Research Collaboration in the Fight Against Cancer with AI
Nov 07, 2019 07:25 JST
Fujitsu Improves Efficiency in Cancer Genomic Medicine in Joint AI Research with the Institute of Medical Science at the University of Tokyo
Nov 07, 2019 05:09 JST
ULVAC launches Smartphone-Direct Pirani Gauge "SWU10-U"
Nov 06, 2019 17:00 JST
Showa Denko (SDK) Announces 2019 Third Quarter Financial Results
Nov 06, 2019 16:00 JST
NEC Showcases Industry-leading Digital Finance Solutions at Inaugural SFF X Switch 2019
Nov 06, 2019 15:11 JST
Suzhou Tongji Blockchain Research Institute and Fujitsu Research and Development Center start Research Collaboration on Blockchain Technology
Nov 06, 2019 11:45 JST