Hyeonsang Eom
Seoul National University · 情報科学
研究室紹介
Professor Hyeonsang Eom's research lab focuses on system-level performance optimization for modern storage and networking systems, with an emphasis on reducing software overhead and improving resource utilization. The lab explores innovative controller designs—such as out-of-order flash memory controllers and intelligent routing algorithms—that exploit hardware parallelism and dynamic resource prediction. Key research directions include high-performance I/O systems, efficient simulation methodologies, and performance-aware system tuning for distributed and data-intensive workloads. The lab also investigates advanced metrics and mechanisms to guide application and system-level optimizations in dynamic environments.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15Ozone (O3) is a flash memory controller that increases the performance of a flash storage system by executing multiple flash operations out of order. In the O3 flash controller, data dependencies are the only ordering constraints on the execution of multiple flash operations. This allows O3 to exploit the multichip parallelism inherent in flash memory much more effectively than interleaving. The O3 controller also provides a prioritized handling of flash operations, equipping flash management so
Fast storage devices are an emerging solution to satisfy data-intensive applications. They provide high transaction rates for DBMS, low response times for Web servers, instant on-demand paging for applications with large memory footprints, and many similar advantages for performance-hungry applications. In spite of the benefits promised by fast hardware, modern operating systems are not yet structured to take advantage of the hardware’s full potential. The software overhead caused by an OS, negl
This paper presents a family of simulators that have been developed for data-intensive applications, and a methodology to select the most efficient one based on a user-supplied requirement for accuracy. The methodology consists of a series of tests that select an appropriate simulation based on the attributes of the application. In addition, each simulator provides two estimates of application execution time: one for the minimum expected time and the other for the maximum. We present the results
We introduce a new performance metric, called Load Balancing Factor (LBF), to assist programmers with evaluating different tuning alternatives. The LBF metric differs from traditional performance metrics since it is intended to measure the performance implications of a specific tuning alternative rather than quantifying where time is spent in the current version of the program. A second unique aspect of the metric is that it provides guidance about moving work within a distributed or parallel pr
In link-state routing, routes are determined based on estimates of the current delays on the links.Ideally, a data packet should be routed based on the delays it will encounter at each link of the path at the time the packet gets to the link.To address this issue, we have developed a new approach that improves link-state routing by estimating and using the future link delays encountered by data packets.In link-state routing, link-delay estimates are periodically flooded throughout the network.Th
In link-state routing, routes are determined based on the estimates of the current delays on the links, i.e. without considering the dynamics of the link-delay information. Ideally, a data packet should be routed based on the delays it will encounter at each link of the path at the time the packet gets to the link. To address this issue, we have designed a new routing software that improves link-state routing by estimating and using the future link delays encountered by data packets. In link-sta