• 기술사
• /
• 제22권3호
• /
• pp.5-13
• /
• 1989

A major problem of stopwatch time study is how to do for the accurate and consistent performance rating, which is one of the critical variables to determine the accuracy of work measurement and should be still dependent upon time observer's judgement. Therefore the time observer's ability for the performance rating is very important, and must be improved by correct training method and procedure. This paper developed a new benchmark and benchmark-observation method for the effective performance rating training of assembling and machining operations. The trainees' ability in the accuracy and consistency of the performance rating ,improved significantly after being trained by subject method. The percentage improvement in rating accuracy and consistency values was 34.7% and 49% respectively. In addition, benchmark-practice method for the performance rating training is not significant, so it is proofed that the skill of a certain operation is not important for the improvement of the rating ability.

• 한국정보처리학회논문지
• /
• 제7권7호
• /
• pp.1997-2007
• /
• 2000

This paper presents a new benchmark for object-relational database systems, which are regarded as the next-generation database system. This benchmark has been developed to evaluate system performance peculiar to object-relational database systems. The design philosophy, test databases, an test queries of the benchmark are presented. This benchmark features scaleability, use of a synthesized database only, and a query-oriented evaluation. We have implemented his benchmark with two commerical object-relational database systems and the experimental results are also reported.

• Journal of Information Technology Applications and Management
• /
• 제12권2호
• /
• pp.29-43
• /
• 2005

The paper presents the EBORD (Extended Benchmark for Object-Relational Databases) benchmark, which is an extension of the BORD benchmark for object-relational databases. The EBORD benchmark is developed to evaluate the database common functions that should be supported in modern database systems. Besides the 36 test queries already defined in the BORD benchmark, totally 22 test queries in five categories are newly defined in order to measure the index-relevant performance issues and database import capabilities. The EBORD benchmark also features scalability, use of a synthesized database, and a query-oriented evaluation. In order to show the feasibility of the proposed benchmark, we implement it with two commercial database systems. The experimental results and analyses are also reported.

• 한국컴퓨터정보학회논문지
• /
• 제15권8호
• /
• pp.1-11
• /
• 2010

데이터스트림 관리시스템(DSMS)의 많은 응용분야에서는 단순한 실시간 스트림 데이터의 효율적인 처리뿐만 아니라 기존의 DBMS와 결합하여 데이터마이닝이나 데이터웨어하우징 같은 고급 서비스를 사용자에게 제공하는 것을 요구하고 있다. 본 논문에서는 고급 서비스를 위하여 DSMS와 DBMS를 결합한 시스템의 성능평가를 위한 도구를 개발하였다. 기존 연구 개발된 대표적인 DSMS와 DBMS를 결합하여 네트워크 모니터링 스트림 데이터를 기반으로 통합된 시스템의 성능평가를 수행하였다. 통합된 시스템의 평가를 위하여 JAVA로 통합 시스템 성능 평가 툴을 개발하였으며, 개발 된 툴을 이용하여 DSMS(STREAM, Coral8)와 DBMS(MySQL, Oracle10g)를 결합한 시스템의 성능평가를 수행하였다

• 한국IT서비스학회지
• /
• 제5권3호
• /
• pp.99-108
• /
• 2006

Public institutions are considering adoption of open-source software in the process of information projects. However, there doesn't exist reliable information about an adoption process for open-source software. Performance and stability problems of this software also persist, as a result, current open-source software is not widely used. As a software market and industry grows, Benchmark test has been performed more often than before in order to help customers understand and select the most appropriate product among myriad similar ones. It is certain that more objective and trustful data evidence should be obtained by way of utilizing the procedures and methods of Benchmark Test in decision making process for selecting an open-source software. For this research, Benchmark test was applied as a way of demonstrating performance verification of an open-source software in the public institutions. It is certain that more objective and trustful data evidence should be obtained by way of utilizing the procedures and methods of Benchmark Test in decision making process for selecting an open-source software. It also introduces a case study of a information system, which selected and implemented open-source software, in order to confirm the validity of this research. This research will serve as a guideline to adopt open-source software in governments as well as public institutions.

• 정보과학회 논문지
• /
• 제43권4호
• /
• pp.411-418
• /
• 2016

최근 낸드 플래시 메모리가 널리 보급됨에 따라 기존 파일 시스템의 한계를 보완하고 낸드 플래시 메모리의 장점을 활용하기 위한 파일 시스템 연구가 활발히 진행되고 있다. 이렇게 제안된 파일 시스템들에 대해서는, 일반적으로 벤치마크를 통해 성능 측정이 이루어진다. 서버나 모바일 환경에서 실제 시스템의 성능 측정이 어려울 경우, 벤치마크는 측정하고자 하는 실제 시스템에 대한 직접적인 성능 측정 대신 워크로드를 통해 재현된 환경에서 소프트웨어적 성능 측정을 가능하게 한다. 이 때, 성능 측정 환경이 실제 시스템이 아니기 때문에 측정하는 시스템 환경에 따라서 일정하지 않은 성능 측정 결과를 보인다. 이에 본 논문에서는 파일 시스템의 성능을 측정하는데 흔히 사용되는 벤치마크 중에서 Filebench를 이용하여 여러 가지 시스템 환경에 따른 성능 측정 결과를 살펴보고 측정 결과의 변동이 생기는 원인을 알아본다. 실험 결과, 캐시 내부에 벤치마크 I/O 외의 성능 측정에 불필요한 I/O가 많이 발생할수록 벤치마크의 성능 측정 결과가 떨어지는 것을 확인하였다. 또한 fsync 동작이 포함된 백그라운드 I/O를 동작시키는 경우에는 최대 98.2%의 성능 저하가 발생하는 것을 확인하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권1호
• /
• pp.180-186
• /
• 2021

In cloud computing service it is important to share the system resource among multiple instances according to user requirements. In particular, the issue of efficiently distributing I/O resources across multiple instances is paid attention due to the rise of emerging data-centric technologies such as big data and deep learning. However, it is difficult to evaluate the I/O resource distribution of a Linux container, which is one of the core technologies of cloud computing, since conventional I/O benchmarks does not support features related to container management. In this paper, we propose a new I/O performance benchmarking framework that can easily evaluate the resource distribution of Linux containers using existing I/O benchmarks by supporting container-related features and integrated user interface. According to the performance evaluation result with trace-replay benchmark, the proposed benchmark framework has induced negligible performance overhead while providing convenience in evaluating the I/O performance of multiple Linux containers.

• 전자공학회논문지CI
• /
• 제42권5호
• /
• pp.1-8
• /
• 2005

SPEC CPU2000은 CPU의 성능 측정에 중점을 둔 벤치마크 프로그램으로서 표준화에 대한 노력을 바탕으로 산학계에 널리 사용되고 있으나, 하드웨어 측면에서의 특성 분석은 미비하였다. 본 논문에서는 컴퓨터 시스템의 중요한 구성 요소 중 하나인 CPU 주파수 속도의 변화에 따른 SPEC CPU2000 벤치마크의 성능 변화를 고찰하였다. x86 구조 기반의 단일 프로세서 시스템에서 CPU 주파수 속도를 제외한 다른 구성요소를 일정하게 유지하면서 SPEC CPU2000 벤치마크 프로그램의 성능을 측정함으로써 SPEC CPU2000 벤치마크 프로그램의 특성을 시스템적 측면에서 해석하였다. 실험을 통하여 SPEC CPU2000은 CPU 주파수 속도의 변화에 대하여 유연한 성능분석이 가능하도록 개별 벤치마크 프로그램의 CPU 주파수 의존도가 고르게 분포되어 있음을 알 수 있었으며, SPEC CPU2000에 대한 시스템적 측면의 해석을 제공함으로써 SPEC CPU2000을 사용하는 연구, 개발에 있어서 기반 자료로 사용될 것으로 기대된다.

• 대한임베디드공학회논문지
• /
• 제14권1호
• /
• pp.51-61
• /
• 2019

There are strict evaluation processes before using new processors to satellites. Engineers evaluate processors from various viewpoints including specification, development environment, and cost. From a viewpoint of computation power, manufacturers provide benchmark results with processors, and engineers decide which processors are adequate to their satellites by comparing the benchmark results with requirements of their satellites. However, the benchmark results depends on a test environment of manufacturers, and it is quite difficult to achieve similar performance in a target environment. Therefore, it is necessary to evaluate the processors in the target environment. This paper compares performance of a processor, AT697F/LEON2, in software testbed (STB) with three development boards of XC2V/LEON3, GR712RC/LEON3, and GR740/LEON4. Seven benchmark functions of Dhrystone, Stanford, Coremark, Whetstone, Flops, NBench, and MiBench are selected. Results are analyzed with hardware and software properties: hardware properties of core architecture, number of cores, cache, and memory; and software properties of build options and compilers. Based on the analysis, this paper describes a guideline for choosing processors for next generation satellites.

• 한국항공운항학회지
• /
• 제23권2호
• /
• pp.69-74
• /
• 2015

We propose a rigorous and practical methodology to evaluate the performance of symbolic manipulation program such as Mathematica, Maple, and Maxima. First, we demonstrate an inverse method to construct the benchmark problems of an initial value problems. The benchmark problems associated with the discrete version of the Chebyshev polynomials provide a rigorous and objective measure to evaluate the performance of symbolic manipulation programs. We compare three symbolic manipulation programs, which are Mathematica, Maple and Maxima, using this methodology. The computation time, the used memory and the perturbation terms are chosen for comparison parameters.