News register
Search section
Search area
News Type
News type
Search date
Search word OR
List of related articles
Contents of related articles
No info was found
List of related articles
Contents of related articles
No info was found
View details
Information

07/05/2018 HYU News > Academics > 이달의연구자

Title

[Excellent R&D] Laying the Stepping Stones for Future Software Technology

Professor Won You-jip (Department of Computer Science and Engineering)

이창현

Copy URL / Share SNS

http://www.hanyang.ac.kr/surl/q2me

Contents
From chemistry to physics, scientific fields take great strides every day. This is even more the case for computer science, with the world having embarked on the 4th industrial revolution - a revolution created through an extensive integration of information technology. Technologies such as artificial intelligence, big data, and the Internet of Things (IoT) have already been brought to reality to a certain extent. In light of these advances, the improvements in software technology by Professor Won You-jip (Department of Computer Science and Engineering) have received grand recognitions for tearing down the barriers to continuous development.
 
The interview with Won You-jip (Department of Computer Science and Engineering) was held in his office on July 4th, 2018.

A rough explanation of Won's research would be as follows: if we modify a standard computer, expanding its memory capacity by 100 times, and increasing the number of Central Processing Units (CPU) to 100, the seemingly improved computer would not be 100 times faster than before. In fact, it would be even slower than the standard version. The essential problem lies in the software; the algorithm for the new computer would have to be redesigned to manage the expanded resources in the most efficient manner.
 
“It would be like driving a supercar on an unpaved road,” explained Won, providing a metaphor to emphasize the pointlessness of developing hardware without the sufficient software to manage it. However, the reality is that the speed of software development has remained rather stagnant compared to the restless development of hardware technology. On this point, Won’s research has received a passionate welcome by the international community for paving new roads for the future of software technology.
 
Althernative designs for CPU management and Input/Output management as proposed by Won's research
(Photo courtesy of Won Youjip)

In a nutshell, Won provided key technologies for operating systems to support scalability, that is, the ability to add more CPUs, and for them to quickly make full use of the software. To elaborate, he categorized the roles of operating systems into CPU management, huge memory management, and file input/output management, and developed essential technologies for each domain after an analysis of the latest trends and prospective future of their hardware. Won essentially solidified the possibility of scalability, maximized the used of large-scale memory space, and improved the I/O management to prevent operation delays.
 
Won’s research was greatly facilitated with the help of the Electronics and Telecommunications Research Institute (ETRI), who granted access to their super computer for research and experiments. With their assistance and his dedication, Won has been recognized as the forerunner in his field, having won two Best Paper Awards from conferences held by USENIX, also known as The Advanced Computing Systems Association. Won was awarded two among the three Best Paper Awards ever given to recipients in Korea. No other countries in Asia have ever won the award.
 
USENIX conferences are the most respected and historical in the field, with the programming language JAVA having been introduced in one of their past conferences. Won considered being awardedthe award for best paper at USENIX to be an extreme honor.

Once Won introduces the final version of his work, it is expected to allow software to be designed for manycore (computers with many cores) hardware to be built in 50 to 60 years-time. It will support super computers, allowing AI calculations and machine deep learning. Furthermore, it will be applied to servers to maximize the use of their resources, contributing significantly to their efficiency. Won’s findings not only enable future technology, but make it economic and efficient.
 
Won is also a dedicated instructor. When asked of his greatest aspiration, Won answered that his wish is for his students to become the best developers of Silicon Valley. He interacts with his students on a frequent basis, well above the domains of lab work. A piece of advice that he had for his students was to become the best. “Rise above your failures, keep your head up, and become the best in your field,” commented Won. He believes that regardless of the skill or profession, if there is something you want to do, you should "Start digging and get to the bottom of it.”





Lee Chang-hyun          pizz1125@hanyang.ac.kr
Photos by Kang Cho-hyun
Copy URL / Share SNS

0 Comments