Tran Minh Quan (5th year UNIST CSE PhD student) and Professor Won-Ki Jeong’s paper entitled with “A fast discrete wavelet transform using hybrid parallelism on GPUs” was accepted for publication in IEEE Transactions on Parallel and Distributed Systems.

A research paper entitled “Quantifying the Performance Impact of Large Pages on In-Memory Big-Data Workloads” has been accepted for publication at IISWC’16. The paper is co-authored by a UNIST CSE graduate student (Jinsu Park), a UNIST CSE undergraduate student (Myeonggyun Han), and a UNIST CSE professor (Dr. Woongki Baek).

The paper presented by Gyuhyun Lee (3rd year UNIST CSE PhD student) and co-authored by Tran Minh Quan (5th year UNIST CSE PhD student) and Prof. Won-Ki Jeong is selected as the best paper at Korea Computer Graphics Society (KCGS) Conference 2016.

UNIST CSE Postdoc Dr. Jaeho Kim, graduate student Eunjae Lee, and Professor Sam H. Noh’s paper titled “I/O Scheduling Schemes for Better I/O Proportionality on Flash-based SSDs” was accepted for publication at MASCOTS 2016. This paper analyzes I/O behavior on a shared SSD among multiple Virtual Machines (VMs) and shows that performance SLOs (Service Level

Hongik Univ. J. Hyun Kim, UNIST CSE Postdoc Dr. Young Je Moon, Professor Sam H. Noh’s paper “An Experimental Study on the Effect of Asymmetric Memory Latency of New Memory on Application Performance” was accepted for publication at MASCOTS 2016. As DRAM reaches its density limitation, New memory technology such as STT-RAM and PCM are

                                                    * Title: Persistent Memory Architecture Research at UCSC – Workload Characterization and Hardware Support for Persistence * Speaker: Prof. Jishen Zhao (University of California) * Time: 2016. 7. 14

* Title: Si-integrated micro-cavity lasers for silicon photonics, fundamental physics studies, and bio-applications   * Speaker: Prof. Il-Sug Chung (Technical University of Denmark )   * Time: 2016.07.08 (Fri.) 3pm   * Location: EB1, E104 Biography Il-Sug Chung received his B.Sc. and M.Sc. in physics from KAIST, Korea and Ph.D. in information and communications (Optoelectronics) from

2016  ECE  Special Seminar Title: Acquisition and Analysis of Mouse Brain Vasculature Speaker: Prof. Jaerock  Kwon  (Kettering University) Time: 2016.06.30 (Thu.) 4pm Location: EB1, E204   Prof. Jaerock  Kwon  *Bio: Jaerock Kwon, Ph.D. Associate Professor of Computer Engineering Director of Brain-Inspired Intelligent Systems (BI2S) Lab Co-Director of Mobile Intelligent Robotics (MIR) Lab Electrical and Computer

ICPP (International Conference on Parallel Processing) is a historic conference with a tradition of excellence in parallel computing field. This year, ICPP accepted 53 papers out of 251 submissions and two of them are UNIST graduate students’ papers, Jinsu Park and Woongki Baek, “RCHC: a Holistic Runtime System for Concurrent Heterogeneous Computing,” Moohyeon Nam, Jinwoong

A UNIST CSE graduate student, Jinsu Park and Prof. Woongki Baek (corresponding author)’s paper, titled “HAP: a Heterogeneity-Conscious Runtime System for Adaptive Pipeline Parallelism”, was accepted for publication at Euro-Par 2016. This work proposes a heterogeneity-conscious runtime system for adaptive pipeline parallelism (HAP). HAP dynamically controls the full heterogeneous multiprocessing system resources to improve the

Professor Kyunghan Lee (School of Electrical and Computer Engineering) has been selected to be the winner of the 2016 IEEE William R. Bennett Prize Paper Award.

Artificial Intelligence will change the life styles of human. UNIST Faculties are researching about Artificial Intelligence to contribute to a society.   Prof. Jaesik Choi (School of Electrical and Computer Engineering) researches about the artificial intelligence at UNIST. His team is studying about the automatic statistician which is available to predict and analyze the stock

UNIST CSE graduate students, Jaewon Kwak, Eunji Hwang, Prof. Beomseok Nam, and Prof. Young-ri Choi (corresponding author)’s paper, titled “In-memory Caching Orchestration for Hadoop”, was accepted for publication at CCGrid 2016. This work exploits techniques to effectively orchestrate HDFS in-memory caching for Hadoop, which is a de facto standard big data analytics platform. By leveraging

  In this paper, using molecular dynamics simulations as a case study, we propose a framework to guide users to select the optimal VM configurations that satisfy their requirements for scientific parallel computing in virtualized clusters. For molecular dynamics computation on a cluster of VMs, the guidance framework uses artificial neural networks which are trained

    Multibeam satellite can benefit from path diversity by routing to ground stations that relay signals to the end users through terrestrial networks, in addition to sending signals directly to end-user terminals. We investigate a cross-layer dynamic transmission control in station-assisted satellite networks and develop an optimal solution that is amenable to implementation with

ICSL (Prof. Jaehyouk Choi)’s paper “A 0.56 – 2.92 GHz Wideband and Low Phase Noise Quadrature LO-Generator Using a Single LC-VCO for 2 – 4G Multi-Standard Cellular Transceivers” has been accepted for publication in IEEE Journal of Solid-State Circuits (Authors: Heein Yoon, Yongsun Lee, Younghyun Lim, and Jaehyouk Choi)

[Congratulation!] Professor Sam H. Noh invited to serve as program committee (PC) member.

“Exploiting Massive Parallelism for Indexing Multi-Dimensional Datasets on the GPU”, authored by UNIST ECE graduate student Jinwoong Kim, professor Won-Ki Jeong, and professor Beomseok Nam, was selected as a featured article in the August 2015 issue of IEEE TPDS. The article is available for free to all readers at the journal’s webpage.

The UNIST research team, composed of Changhee Joo, Hyoil Kim, Kyunghan Lee, and Hyun Jong Yang, took a first step toward near-zero end-to-end latency, which propels us to commercialization of 5G

Prof. Jaesik Choi and research team (Probabilistic Artificial Intelligence Lab, PAI-Lab) start a new research/development project, A Robust Plant Monitoring System based on Multi-Dimensional Sound Source Localization and Particles Dehaze.