• 전자통신동향분석
• /
• 제35권2호
• /
• pp.89-103
• /
• 2020

Knowledge of the technology, characteristics, and market trends of the latest CPUs used in smartphones, computers, and supercomputers and the research trends of leading US university experts gives an edge to policy-makers, business executives, large investors, etc. To this end, we describe three topics in detail at a level that can help educate the non-majors to the extent possible. Topic 1 comprises the design and manufacture of a CPU and the technology and trends of the smartphone SoC. Topic 2 comprises the technology and trends of the x86 CPU and supercomputer, and Topic 3 involves an optical network chip that has the potential to emerge as a major semiconductor chip. We also describe three techniques and experiments that can be used to implement the optical network chip.

• 전자통신동향분석
• /
• 제35권2호
• /
• pp.120-136
• /
• 2020

Knowledge of the technology, characteristics, and market trends of the latest CPUs used in smartphones, computers, and supercomputers and the research trends of leading US university experts gives an edge to policy-makers, business executives, large investors, etc. To this end, we describe three topics in detail at a level that can help educate the non-majors to the extent possible. Topic 1 comprises the design and manufacture of a CPU and the technology and trends of the smartphone SoC. Topic 2 comprises the technology and trends of the x86 CPU and supercomputer, and Topic 3 involves an optical network chip that has the potential to emerge as a major semiconductor chip. We also describe three techniques and experiments that can be used to implement the optical network chip.

• 전자통신동향분석
• /
• 제35권2호
• /
• pp.104-119
• /
• 2020

Knowledge of the technology, characteristics, and market trends of the latest CPUs used in smartphones, computers, and supercomputers and the research trends of leading US university experts gives an edge to policy-makers, business executives, large investors, etc. To this end, we describe three topics in detail at a level that can help educate the non-majors to the extent possible. Topic 1 comprises the design and manufacture of a CPU and the technology and trends of the smartphone SoC. Topic 2 comprises the technology and trends of the x86 CPU and supercomputer, and Topic 3 involves an optical network chip that has the potential to emerge as a major semiconductor chip. We also describe three techniques and experiments that can be used to implement the optical network chip.

• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.12-19
• /
• 1996

Many recent supercomputers employ a kind of switch-based multistage interconnection network architectrues (MINs) for constructing scalabel parallel compters. This paper proposed a new routing method, hybrid wormhole and virtual-cut through routing (HWCR) for the prevention of rapid performance degradation comming from a conflict in links usage at hot traffic situation. This HWCR through (VCT) for the fast removing temporal stagger, result in seamless flow of packet stream. When the blocked link is removed, wormhole routing is resumed. The HWCR method adopted a hierachical buffer scheme for improving the network performance and reducing the cost in BMINs. We could get optimum buffer size and communicatin latency through the computer simulation based on proposed HWCR, and the results were compared to those using wormhole and VCT.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.760-761
• /
• 2019

Smart manufacturing is a process of integrating computer-related technologies in production and by doing so, achieving more efficient production management. The recent development of supercomputers has led to the broad utilization of artificial intelligence (AI) and machine learning techniques useful in predicting specific patterns. Despite the usefulness of AI and machine learning techniques in smart manufacturing processes, there are many fundamental issues with the direct deployment of these technologies related to data management. In this paper, we focus on solving the outlier detection issue in smart manufacturing applications. More specifically, we apply a state-of-the-art outlier detection technique, called Elliptic Envelope, to detect anomalies in simulation-based collected data.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.261-267
• /
• 2023

Public research, which requires large computational resources, utilizes the supercomputers of the National Supercomputing Center in the Republic of Korea. The average utilization rate of resources over the past three years reached 80%. Therefore, to ensure the operational stability of this national infrastructure, specialized centers have been established to distribute the computational demand concentrated in the national centers. It is necessary to predict the computational demand accurately to build an appropriate resource scale. Therefore, it is important to estimate the inflow and outflow of computational demand between the national and specialized centers to size the resources required to construct specialized centers. We conducted a logit model analysis using the probabilistic utility theory to derive the preferences of individual users for future supercomputer resources. This analysis shows that the computational demand share of specialized centers is 59.5%, which exceeds the resource utilization plan of existing specialized centers.

• 전자통신동향분석
• /
• 제33권1호
• /
• pp.20-33
• /
• 2018

The calculation speed of quantum computing is expected to outperform that of existing supercomputers with regard to certain problems such as secure computing, optimization problems, searching, and quantum chemistry. Many companies such as Google and IBM have been trying to make 50 superconducting qubits, which is expected to demonstrate quantum supremacy and those quantum computers are more advantageous in computing power than classical computers. However, quantum computers are expected to be applicable to solving real-world problems with superior computing power. This will require large scale quantum computing with many more qubits than the current 50 qubits available. To realize this, first, quantum error correction codes are required to be capable of computing within a sufficient amount of time with tolerable accuracy. Next, a compiler is required for the qubits encoded by quantum error correction codes to perform quantum operations. A large-scale quantum computer is therefore predicted to be composed of three essential components: a programming environment, layout mapping of qubits, and quantum processors. These components analyze how many numbers of qubits are needed, how accurate the qubit operations are, and where they are placed and operated. In this paper, recent progress on large-scale quantum computing and the relation of their components will be introduced.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제10권2호
• /
• pp.81-88
• /
• 2006

슈퍼 컴퓨터의 등장으로 기존에는 풀지 못했던 과학적, 학술적인 문제들이 대부분 해결되었지만 슈퍼 컴퓨터 자체의 막대한 비용 문제는 여전히 풀지 못한 숙제로 남아 있다. 이에 일반 사용자의 컴퓨터의 유휴 자원을 통합하여 협업하는 그리드 컴퓨팅이라는 개념이 등장하였다. 한편 분산되어 있는 이기종의 시스템의 자원을 통합하여 관리하기 위해서 연결 지향적인 프로토콜들이 사용되었지만, 다른 프로토콜끼리는 호환성이 없는 등의 문제가 존재한다. 본 논문에서는 플랫폼 독립적인 XML 기반의 SOAP을 사용하는 웹 서비스를 이용하여 그리드 네트워크의 성능 정보를 관리해주는 시스템을 제안한다.

• Journal of Information Technology Applications and Management
• /
• 제10권3호
• /
• pp.1-22
• /
• 2003

P2P systems have been studied by many researchers in universities and commercial firms in recent years. In this study. we design and implement a system that makes UP for shortcomings of currently available P2P systems. Gnutella and Napster. The study also includes an efficiency analysis scheme conducted through a series of experimental data. The data sharing system of the study demonstrated duality of roles(client, service) of peers. But, their roles were separated from the existing client-server systems. Also, the study implements mechanism that shows the redundancy of data to communicate efficiently among peers for transferring data. The results of performance measure of the system shows that the amount of information shared by peers increases as the amount of peers increases but with no significant increase in response time. This constant response time is far more stable and faster than current file sharing systems. such as Gnutella and Napster. Business applications such as knowledge management, enterprise information portal management and transfer of data are done by use of supercomputers. They need to extend their systems to equip with more capacity and throughput as the number of clients increases. Moreover, they will face with more complicated problems if integration with new systems exists. If this JDSS is introduced to these business applications. it would easily augment scalability of the system with high performance at less expense.

• Journal of Information Processing Systems
• /
• 제2권2호
• /
• pp.101-106
• /
• 2006

Grid computing is an emerging technology that enables global resource sharing. In Korea, the $K^*$Grid provides an extremely powerful research environment to both industries and academia. As part of the $K^*$Grid project, we have constructed, together with the Korea Institute of Science and Technology Information and a number of domestic universities, a supercomputer Grid test bed which connects several types of supercomputers based on the globus toolkit. To achieve efficient networking in this Grid testbed, we propose a novel method of available bandwidth measurement, called Decoupled Capacity measurement with Initial Gap (DCIG), using packet trains. DCIG can improve the network efficiency by selecting the best path among several candidates. Simulation results show that DCIG outperforms previous work in terms of accuracy and the required measurement time. We also define a new XML schema for DCIG request/response based on the schema defined by the Global Grid Forum (GGF) Network Measurement Working Group (NM-WG).