• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.350-352
• /
• 2011

마이크로 프로세서의 퍼포먼스 카운터는 프로그램의 병목 현상을 분석할 수 있는 중요한 도구이다. 퍼포먼스 카운터를 사용하면 다양한 이벤트의 출현 빈도를 성능의 저하 없이 정확하게 측정할 수 있다는 장점이 있다. 특히 퍼포먼스 카운터는 현재 널리 사용되고 있는 멀티코어 프로세서의 성능을 분석하는데 유효하다. 본 논문에서는 인텔 네할렘 프로세서의 확장된 퍼포먼스 카운터를 이용하여 멀티코어 프로세서의 성능을 분석하는 기법을 소개하고자 한다. 본 논문에서는 네할렘 아키텍쳐를 적용한 인텔 Xeon 시리즈 프로세서와 SPEC CPU 2006벤치마크를 이용하여 성능을 분석한다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.6
• /
• pp.23-33
• /
• 1996

The exploitation of locality of reference in shared memory NUMA multiprocessors is one of the improtant problems in parallel processing today. In this paper, we propose a revised hardeare reference counter to help operating system to manage locality. In contrast to the previous one, the value of counter can abe adjusted dynamically and periodically to adapt the page replication policy to the various memory reference patterns of processors. We use execution-driven simulation of real applications to evaluate the effectiveness of our adjustable DELAY counter. Our main conclusijon is that by using the adjustable DELAY counter the t normalized average memory access costs and the variance of them become smaller for most applications than the previous one and more robust memory management policies can be provided for the operating systems.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.221-230
• /
• 2020

Supercomputer that shares limited resources to multiple users needs a way to optimize the execution of application. For this, it is useful for system administrators to get prior information and hint about the applications to be executed. In most high-performance computing system operations, system administrators strive to increase system productivity by receiving information about execution duration and resource requirements from users when executing tasks. They are also using profiling techniques that generates the necessary information using statistics such as system usage to increase system utilization. In a previous study, we have proposed a scheduling optimization technique by developing a hardware performance counter-based profiling technique that enables characterization of applications without further understanding of the source code. In this paper, we constructed a profiling testbed cluster to support optimal execution of the supercomputer and experimented with the scalability of the profiling method to analyze application characteristics in the built cluster environment. Also, we experimented that the profiling method can be utilized in actual scheduling optimization with scalability even if the application class is reduced or the number of nodes for profiling is minimized. Even though the number of nodes used for profiling was reduced to 1/4, the execution time of the application increased by 1.08% compared to profiling using all nodes, and the scheduling optimization performance improved by up to 37% compared to sequential execution. In addition, profiling by reducing the size of the problem resulted in a quarter of the cost of collecting profiling data and a performance improvement of up to 35%.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 1998.12a
• /
• pp.471-481
• /
• 1998

피승수를 승수로 곱하는 곱셈연산은 승수에 대한 많은 부분곱을 더하기 때문에 본질적으로 느린 연산이다. 특히, 큰 수를 사용하는 암호 프로세서에서는 매우 빠른 곱셈기가 요구된다. 현재까지 느린 연산의 개선책으로 radix 4, radix 8, 또는 radix 16의 변형 부스 알고리즘을 사용하여 부분곱의 수를 줄이려는 연구와 더불어 Wallace tree나 병렬 카운터를 사용하여 부분곱의 합을 빠르게 연산하는 방법이 연구되어 왔다. 본 논문에서는 암호 프로세서용 64$\times$64 비트 곱셈기를 구현하는데 있어서, 고속의 곱셈을 위하여 고속의 병렬 카운터를 제안하였으며, radix 4의 변형 부스 알고리즘을 이용하여 부분합을 만들고 부분합의 덧셈은 제안한 카운터를 사용하였다. 64$\times$64 비트 곱셈기를 구현함에 있어서 본 논문에서 제안된 카운터를 이용하는 것이 속도 면에서 Wallace scheme또는 Dadda scheme을 적용하여 구현하는 것 보다 31% 정도, Mehta의 카운터를 적용하여 구현하는 것 보다 21% 정도 개선되었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.106-108
• /
• 2020

대부분의 최신 마이크로 프로세서에서 사용 가능한 하드웨어 퍼포먼스 카운터는 시스템과 어플리케이션의 상태를 모니터링, 분석 및 최적화하는 다양한 용도로 폭넓게 사용되고 있다. 적은 오버헤드로 시스템의 가장 기본적인 정보를 수집할 수 있기 때문에 다양한 분야에서 활용이 가능하다. 이러한 퍼포먼스 카운터는 리눅스에 내장되어 있는 퍼프 이벤트를 통하여 수집 할 수 있는데 클러스터 시스템에서는 단일 노드에서와는 다른 방법을 사용하여 이벤트를 수집해야 한다. 본 연구에서는 클러스터 시스템에서 하드웨어 퍼포먼스 카운터를 수집하는 방법과 오버헤드에 대하여 연구하여 카운터의 활용을 지원하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.974-977
• /
• 2007

본 논문은 성능 카운터를 이용하여 Intel XScale 마이크로아키텍쳐 기반의 Marvell PXA320 프로세서에 대한 성능 모니터링을 구현하였다. Windows CE 운영체제 환경의 응용프로그램에 대하여 DVFS 구성에 따른 각각의 벤치마크를 측정하였고, 성능 이벤트에 따른 성능 카운터 값을 측정 하였다. 성능 모니터링으로 측정된 데이터를 기반으로 DVFS 기법을 위한 스케줄링이 가능하다.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.456-477
• /
• 2022

The purpose of this study is to provide basic data on practical intervention strategies that many people with disabilities can empower in the future by analyzing the experiences in which people with disabilities were empowered through Encounter group counseling program focusing on people with physical disabilities and brain lesions, who account for 50% of all people with disabilities. The research questions were: First, did people with disabilities get empowerment experiences through an Encounter group counseling program? Second, what kind of empowerment experiences did people with disabilities begin to have through the program? In this study, a focus group interview was conducted with the participants of the program to qualitatively evaluate the empowerment experiences from the Encounter group program. The participants were people with physical disabilities and brain lesions experiencing Encounter group counseling programs at the self-reliance center in Seoul from 2015 to 2019. As a result of the analysis, 7 components, and 17 sub-components were derived, which were grouped into three themes: 1) restoring self relationship 2) forming new relationship with others, and 3) realizing a sense of solidarity with society. The research results were discussed considering the impact of the Encounter program on personal, interpersonal, and social empowerment of people with disabilities and finally, limitations of the study and suggestions for follow-up studies were presented.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.88-95
• /
• 1994

This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration. Two neural networks were developed to forecast daily evapotranspiration of the rice crop with back-propagation and counter-propagation algorithm. The neural network trained by back-propagation algorithm with delta learning rule is a three-layer network with input, hidden, and output layers. The other network with counter-propagation algorithm is a four-layer network with input, normalizing, competitive, and output layers. Training neural networks was conducted using daily actual evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity, and pan evaporation. During the training, neural network parameters were calibrated. The trained networks were applied to a set of field data not used in the training. The created response of the back-propagation network was in good agreement with desired values and showed better performances than the counter-propagation network did. Evaluating the neural network performance indicates that the back-propagation neural network may be applied to the estimation of evapotranspiration of the rice crop. This study does not provide with a conclusive statement as to the ability of a neural network to evapotranspiration estimating. More detailed study is required for better understanding and evaluating the behavior of neural networks.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.149-157
• /
• 2011

Passive tags are inferior to active tags in processing efficiency, so they have difficulty in largevolume processing. The proposed protocol reduces the volume of computation in passive tags and, at the same time, improves authentication for enhanced safety and security. That is, different from existing RFID protocols that return the same value even if an error happens when the reader reads a tag, the improved RFID security protocol returns a new value using a re-counter and processes the computation part of a tag in the reader or in a back.end system. Even if the information of a tag is acquired by an malicious way, it is not actual information but encrypted information that is not usable. In addition, even if tag information is read in sequence, it is changed in each read, so the protocol is safe from Location Tracking.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.137-147
• /
• 2008

Recently, Power and thermal management are becoming major concerns in computer system design. The energy efficiency is an important attribute of the mobile and embedded systems. Today's powerful mobile processors needs more energy and longer battery life. Many research has been focused to reduce energy consumption for the mobile processors.In this paper, performance monitoring system for the Power-management techniques is implemented for Intel's XScale microarchitecture-based Marvell PXA320 processor on Windows CE platform. It also provides software interface for changing DVFS configuration. Performance and power consumption are measured for benchmark programs through performance counter value and voltage/current measurements on LabVIEW platform. By using the developed monitoring system, it is possible for dynamic power management to track processor's workload and to determine the actual power consumption.