• Journal of IKEEE
• /
• v.21 no.1
• /
• pp.77-80
• /
• 2017

In this paper, we proposed a way to improve performance of GP-GPU by deletion of superscalar issue from its original form. At first, we simplified the structure of stream processor in order to eliminate superscalar issue. Under this condition, preservation of hardware size and increasing of thread number were followed by functional improvement of GP-GPU. As the number of thread was getting larger, we proposed the new model of warp scheduler which adjusts the group of thread. This superscalar issue-deleted warp scheduler transferred the instructions to warp which was activated by Round Robin Scheduling. Performance comparison was conducted by Gaussian filtering and the results indicated that our newly designed GP-GPU showing 7.89 times better in its performance than original one.

• Journal of IKEEE
• /
• v.21 no.1
• /
• pp.92-95
• /
• 2017

In this paper, we proposed a way to improve function of small scale GP-GPU. Instead of using superscalar which increase scheduling-complexity, we suggested the application of simple core to maximize GP-GPU performance. Our studies also demonstrated that simplified Stream Processor is one of the way to achieve functional improvement in GP-GPU. In addition, we found that developing of optimal thread-assigning method in Warp Scheduler for specific application improves functional performance of GP-GPU. For examination of GP-GPU functional performance, we suggested the thread-assigning way which coordinated with Deep-Learning system; a part of Neural Network. As a result, we found that functional index in algorithm of Neural Network was increased to 90%, 98% compared with Intel CPU and ARM cortex-A15 4 core respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.177-180
• /
• 2010

RFID를 기반으로 유비쿼터스 환경의 응용 서비스를 지원하는 미들웨어는 지속적으로 끊임없이 입력되는 데이터 스트림을 실시간으로 처리하고 응용 서비스에서 요구하는 결과를 획득하여 전달해야 한다. 이와 같은 요구사항을 만족하기 위해 데이터 스트림 관리 시스템(DSMS)이 제안되었으며 다양한 연구가 시도되고 있다. 본 논문에서는 대량의 이벤트가 입력되는 환경에서 우선순위가 높은 질의를 실시간으로 처리하기 위한 DSMS를 제안하고 있다. 본 연구는 스탠포드의 STREAM 프로젝트를 활용하여 설계 및 구현하였으며, 각 쿼리를 State Thread로 동작시키는 방법을 이용하였다. 쓰레드 라이브러리의 스케줄러 부분을 실시간 스케줄러로 개선하는 작업을 진행하였으며, 실험을 통하여 쓰레드 스케줄러가 질의에 대해서 실시간으로 스케줄링을 할 수 있음을 보이고 있다.

• International Journal of Air-Conditioning and Refrigeration
• /
• v.10 no.3
• /
• pp.147-152
• /
• 2002

When a liquid is supplied through a nozzle onto a relatively non-wetting inclined solid surface, a narrow rivulet forms. There exist several regimes of rivulet flow depending on various flow conditions. In this paper, the fundamental mechanism behind the transition of a linear rivulet to a droplet flow is investigated. The experiments show that the droplet flow emerges due to the necking of a liquid thread near the nozzle. Based on the observation, it is argued that when the retraction velocity of a liquid thread exceeds its axial velocity, the bifurcation of the liquid thread occurs, and this argument is experimentally verified.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.252-264
• /
• 2020

Korea has launched the world-wide first terrestrial UHD broadcast services on May 31, 2017. While the existing HDTV broadcast services use MPEG-2 TS (Tranport Stream) standard for multiplexing and delivering compressed media with additional data, the terrestrial UHD broadcast services use MMT (MPEG Media Transport) standard, which is the next-generation standard beyond MPEG-2 TS. However, the production cost of UHD contents is so high that only a part of the total broadcast time is filled with UHD contents and the UHD time portion is planned to be gradually increased. On the other hand, the ATSC 3.0 standard that uses MMT is not yet used in full-fledged broadcast services in North America. Hence MMT broadcast equipment is still at an early stage with high prices. In this paper we implemented a multi-thread software running on an ordinary PC that can be utilized to realize a low-cost converter that converts the output of an existing MPEG-2 TS multiplexer to an MMTP (MMT Protocol) packet stream. We also verified the functionality of the software through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1723-1728
• /
• 2010

In this paper we concentrate design and develop method about Multi-Channel Internet Radio Platform to broadcast music contents in large outlet and between spaces to protect music contents which have drastically widespread demage. we provide application concept and design rule of hardware path for Multi-Channel Connection and Multi Stream.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.965-973
• /
• 2019

In this paper, Stereo 4K@60fps 360 VR real-time video capture system which consists of video stream capture, video encoding and stitching module is been designed. The system captures stereo 4K@60fps 360 VR video by stitching 6 of 2K@60fps stream which are captured through HDMI interface from 6 cameras in real-time. In video capture phase, video is captured from each camera using multi-thread in real-time. In video encoding phase, raw frame memory transmission and parallel encoding are used to reduce the resource usage in data transmission between video capture and video stitching modules. In video stitching phase, Real-time stitching is secured by stitching calibration preprocessing.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.817-828
• /
• 2017

It is very hard to find the system which processes single 10Gbps stream, and the related application is also rare. But in the field of science such as physics and astronomy, these high speed systems have been widely used and now more upgraded performance is expected. For this reason, high speed network based storage which captures and records 10Gbps level of packets was developed for the support of small astronomical company in KASI. But for the use of the system in research, system performance should be not only evaluated but also optimized. In this paper, we first implement system environment for the performance evaluation and discuss the experiment procedure and solution to acquire numerical results.

• The KIPS Transactions:PartA
• /
• v.15A no.5
• /
• pp.259-268
• /
• 2008

Multi-Core processors have become main-stream microprocessors in recent years. Servers based on these multi-core processors are widely adopted in High Performance Computing (HPC) and commercial business applications as well. These servers provide increased level of parallelism, thus can potentially boost the performance for applications. However, the shared resources among multiple cores on the same chip can become hot spots and act as performance bottlenecks. Therefore it is essential to optimize the use of shared resources for high performance and scalability for the multi-core servers. In this paper, we conduct experimental studies to analyze the positive and negative effects of the resource sharing on the performance of HPC applications. Through the analyses we also characterize the performance of multi-core servers.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.19-24
• /
• 2004

A novel fast parallel NTGST is proposed for high resolution computer vision inspection of the BLUs in a LCD production line. The conventional computation- intensive NTGST algorithm is modified and its C codes are optimized into fast NTGST to be adapted to the SIMD parallel architecture. And then, the input inspection image is partitioned and allocated to each of the P processors in multi-threaded implementation, and the NTGST is executed on SIMD architecture of N data items simultaneously in each thread. Thus, the proposed inspection system can achieve the speedup of O(NP). Experiments using Dual-Pentium III processor with its MMX and extended MMX SIMD technology show that the proposed parallel NTGST is about Sp=8 times faster than the conventional NTGST, which shows the scalability of the proposed system implementation for the fast, high resolution computer vision inspection of the various sized BLUs in LCD production lines.