• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.9-15
• /
• 2017

With the development of semiconductor integration technology, central processing units and storage devices have been miniaturized and performance has been rapidly developed, interconnection network technology is becoming a more important factor in terms of the performance of high performance computing system. In this paper, we analyze the trend of interconnection network technology used in high performance computing. Interconnect technology, which is the most widely used in the Supercomputer Top 500(2017. 06.), is an Infiniband. Recently, Ethernet is the second highest share after InfiniBand due to the emergence of 40/100Gbps Gigabit Ethernet technology. Gigabit Ethernet, where latency performance is lower than InfiniBand, is preferred in cost-effective medium-sized data centers. In addition, top-end HPC systems that demand high performance are devoting themselves from Ethernet and InfiniBand technologies and are attempting to maximize system performance by introducing their own interconnect networks. In the future, high-performance interconnects are expected to utilize silicon-based optical communication technology to exchange data with light.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.81-90
• /
• 2013

During the past decade, many changes and attempts have been tried and are continued developing new technologies in the computing area. The brick wall in computing area, especially power wall, changes computing paradigm from computing hardwares including processor and system architecture to programming environment and application usage. The high performance computing (HPC) area, especially, has been experienced catastrophic changes, and it is now considered as a key to the national competitiveness. In the late 2000's, many leading countries rushed to develop Exascale supercomputing systems, and as a results tens of PetaFLOPS system are prevalent now. In Korea, ICT is well developed and Korea is considered as a one of leading countries in the world, but not for supercomputing area. In this paper, we describe architecture design of MAHA supercomputing system which is aimed to develop 300 TeraFLOPS system for bio-informatics applications like human genome analysis and protein-protein docking. MAHA supercomputing system is consists of four major parts - computing hardware, file system, system software and bio-applications. MAHA supercomputing system is designed to utilize heterogeneous computing accelerators (co-processors like GPGPUs and MICs) to get more performance/$, performance/area, and performance/power. To provide high speed data movement and large capacity, MAHA file system is designed to have asymmetric cluster architecture, and consists of metadata server, data server, and client file system on top of SSD and MAID storage servers. MAHA system softwares are designed to provide user-friendliness and easy-to-use based on integrated system management component - like Bio Workflow management, Integrated Cluster management and Heterogeneous Resource management. MAHA supercomputing system was first installed in Dec., 2011. The theoretical performance of MAHA system was 50 TeraFLOPS and measured performance of 30.3 TeraFLOPS with 32 computing nodes. MAHA system will be upgraded to have 100 TeraFLOPS performance at Jan., 2013.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.47-48
• /
• 2012

스마트폰의 발전 속도는 어플리케이션의 복잡도 증가 속도에 못 미치며, 스마트폰에서 보다 고 사양의 어플리케이션을 수행하기를 원하는 사용자가 늘고 있다. 또한 스마트폰의 성능이 향상됨에 따라 배터리 소모와 발열량도 증가하여 이는 사용자에게 큰 부담이 되고 있다. 이러한 상황에서 클라우드 컴퓨팅은 스마트폰에서 고사양의 어플리케이션을 손쉽게 실행하도록 도와주며 스마트폰의 배터리 소모와 발열량도 줄여줄 수 있다. 하지만 클라우드 컴퓨팅 기능이 탑재된 어플리케이션을 개발하는 것은 개발자에게 큰 부담이기 때문에 본 연구에서는 안드로이드용 클라우드 컴퓨팅 프레임워크를 제안하여 어플리케이션 개발자들이 손쉽게 클라우드 컴퓨팅 기능이 탑재된 어플리케이션을 개발하도록 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.1278-1281
• /
• 2007

초고속 인터넷망이 발달됨으로써 분산 컴퓨팅 시스템 구축이 용이해졌다. 분산 컴퓨팅 시스템은 저비용과 유휴 계산 자원의 활용으로 기존의 슈퍼컴퓨터와 유사한 능력을 발휘할 수 있다는 장점을 지닌다. 암호 알고리즘의 실질적인 안전성 요소인 키의 길이는 전수조사 계산량에 의존한다. 키 전수조사를 위한 대용량 계산은 슈퍼컴퓨터, 클러스터, 분산 컴퓨팅 등의 환경에 따라 세부적인 메커니즘에 차이를 보인다. 본 논문에서는 분산 컴퓨팅 시스템을 소개하고, 이러한 환경 하에서 암호 알고리즘의 키 전수조사 작업을 수행하기 위한 세부적인 절차에 대해서 논하고, 구체적으로 키 전수조사 작업을 효율적으로 수행하기 위한 방법을 제안한다.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.23-31
• /
• 2019

Deep learning is a hot topic in both academic and industrial fields. Deep learning applications can be categorized into two areas. The first category involves applications such as Google Alpha Go using interfaces with human operators to run complicated inference engines in high-performance servers. The second category includes embedded applications for mobile Internet-of-Things devices, automotive vehicles, etc. Owing to the characteristics of the deployment environment, applications in the second category should be bounded by certain H/W and S/W restrictions depending on their running environment. For example, image recognition in an autonomous vehicle requires low latency, while that on a mobile device requires low power consumption. In this paper, we describe issues faced by embedded applications and review popular inference engines. We also introduce a project that is being development to satisfy the H/W and S/W requirements.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.3
• /
• pp.60-71
• /
• 2017

Smart devices such as smart phones, smart TVs, and smart pads have become essential devices in recent years. As the popularity and demand grows, the performance of smart devices is also getting better and users are dealing with a lot of things such as education and business using smart devices instead of desktop. However, smart devices that still have poor performance compared to desktop, even with improved performance, have difficulty running high performance applications due to limited resources. In this paper, we propose a load balancing algorithm applying the characteristics of smart devices to overcome the resource limitations of devices. in order to verify the algorithm, we implemented the algorithm after adding the distributed processing system service in Android platform. After constructing the cluster on the smart device, various experiments were conducted. Through the analysis of the test results, it is confirmed that the proposed algorithm efficiently improves the overall distributed processing performance by effectively aggregating different amounts of computing resources in heterogeneous smart devices.

• Broadcasting and Media Magazine
• /
• v.22 no.4
• /
• pp.11-17
• /
• 2017

본 고에서는 멀티 응용 데이터 플랫폼으로 진화하고 있는 하둡(Hadoop) 2.0의 주요 특징과 관련된 다양한 데이터 처리 프레임워크들에 대해서 기술하고자 한다. 기존의 맵리듀스(MapReduce) 기반의 배치 처리(Batch Processing)에 최적화되어 있던 하둡 1.0과는 달리, YARN의 등장과 함께 시작된 하둡 2.0 플랫폼은 다양한 형태의 데이터 처리 워크플로우들(Batch, Interactive, Streaming 등)을 지원할 수 있는 기능을 제공하고 있다. 또한, 최근에는 고성능컴퓨팅 분야에서 주로 활용되던 기술들도 하둡 2.0 플랫폼에서 지원되고 있다. 마지막으로 YARN 어플리케이션 개발 사례로서 본 연구팀에서 개발 중에 있는 Many-Task Computing (MTC) 응용을 위한 신규 데이터 처리 프레임워크를 소개한다.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.15-22
• /
• 2015

In this paper, we present a case study for a drug repositioning simulation based on distributed supercomputing technology that requires highly efficient processing of large-scale computations. Drug repositioning is the application of known drugs and compounds to new indications (i.e., new diseases), and this process requires efficient processing of a large number of docking tasks with relatively short per-task execution times. This mechanism shows the main characteristics of a Many-Task Computing (MTC) application, and as a representative case of MTC applications, we have applied a drug repositioning simulation in our HTCaaS system which can leverage distributed supercomputing infrastructure, and show that efficient task dispatching, dynamic resource allocation and load balancing, reliability, and seamless integration of multiple computing resources are crucial to support these challenging scientific applications.

• Journal of KIISE:Databases
• /
• v.37 no.5
• /
• pp.228-237
• /
• 2010

Although conventional index structures provide various nearest-neighbor search algorithms for high-dimensional data, there are additional requirements to increase search performances as well as to support index scalability for large scale data. To support these requirements, we propose a distributed high-dimensional indexing structure based on cluster systems, called a Distributed Vector Approximation-tree (DVA-tree), which is a two-level structure consisting of a hybrid spill-tree and VA-files. We also describe the algorithms used for constructing the DVA-tree over multiple machines and performing distributed k-nearest neighbors (NN) searches. To evaluate the performance of the DVA-tree, we conduct an experimental study using both real and synthetic datasets. The results show that our proposed method contributes to significant performance advantages over existing index structures on difference kinds of datasets.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.457-459
• /
• 2003

클러스터 시스템은 상대적으로 가격이 싼 컴퓨터를 고성능의 네트워크(Network)로 묶어서 슈퍼컴퓨터와 같은 고성능을 가지도록 만들어진 시스템이다. 이런 클러스터 컴퓨팅 환경에서 효율적인 스케줄링은 그 성능에 직접적인 영향을 주는 요소이다. 이런 시스템에서 완전한 동시 스케줄링(Coscheduling)은 서로 교환해야하는 정보가 많아지기 때문에 그 구현이 어렵다. 이 상황에서 메시지를 기다리는 정보와 메시지의 도착 정보를 이용해서 즉 단지 그 노드(Node) 자체의 정보만을 이용해 동시 스케줄링의 효과를 구현할 수 있다. 그리고 이것을 이용한 알고리즘 중에 주기적 추진(Periodic Boost(PB))이 있다. 이 논문에서는 주기적 추진에 휴리스틱을 이용하du 더 효과적인 스케줄링을 할 수 있는 알고리즘을 소개한다. 그리고 이 휴리스틱의 효과를 검증하기 위해서 클러스터 노드 2개를 이용해서 실험을 했다. 실험은 계산대 통신 비율(Communication-to-Computation ratio)을 변화시켜가면서 총 수행시간을 측정하고, 서로 통신하는 양이 다른 프로세스를 섞어서 그 성능을 실험한 결과 휴리스틱이 주기적 추진(PB)에서 불필요하게 낭비되는 자원을 효율적으로 사용할 수 있음을 알 수 있었다.