• 한국인쇄학회지
• /
• 제19권2호
• /
• pp.1-11
• /
• 2001

As for the sheet fed offset printing machine, the research and development of the speedup and multi-color for little rod are done. A charge per one offset printing machine became high year, and all kinds of control device became attach. Under this situation to need, many studies of printability of paper and ink are done. In particular improvement of surface strength of printing paper with speedup is needed. The use of non-wood paper and soybean printing paper with speedup is needed. The use of non-wood paper and soybean printing ink had been increased, study of those printability are important for printing development. From the viewpoint of quality and print important for printing development. From the viewpoint of quality and print productivity, the digital printing machine became lo on the introduction in Japan for the present.

• 전자공학회논문지B
• /
• 제28B권12호
• /
• pp.75-82
• /
• 1991

We proposed an optimal parallel implementation of an optimization neural network with linear increase of speedup by using multicomputer system and presented performance analysis model of the system. We extracted the temporal-and the spatial-parallelism from the optimization neural network and constructed a parallel pipeline processing model using the parallelism in order to achieve the maximum speedup and efficiency on the CSP architecture. The results of the experiments for the TSP using the Transputer system, show that the proposed system gives linear increase of speedup proportional to the size of the optimization neural network for more than 140 neurons, and we can have more than 98% of effeciency upto 16-node system.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.2
• /
• pp.399-403
• /
• 2006

Software-based GNSS receivers have the great advantage in flexibility compared with conventional receivers. But it has some problems to processing IF level Signal RAW data, need long time to process long term data and TTFF is long because the process is too slow. So this time, we concentrated on the signal acquisition, and examined the speedup technique. Using this technique, the acquisition was speedup dramatically, and signal-to-noise ratio was improved.

• 전자공학회논문지CI
• /
• 제44권3호
• /
• pp.81-89
• /
• 2007

MPI(message passing interface) 기반 PC 클러스터 상에서 병렬분산 GHT(generalized Hough transform)를 모델화하고 시간 분석하여 고속화 구현하였다. 파이프라인 방송(pipelined broadcast) 통신방식과 누산기 배열(accumulator array) 분할 처리정책을 사용함으로써 통신부담을 최대한 줄였고, 전체 처리 과정에 걸쳐 통신과 계산처리를 시간 중첩시켜 구현함으로써 최대한의 속도제고를 하였다. 100 Mbps Ethernet 스위치를 이용하여 MPI 기반 PC 클러스터를 구현하고 제안한 병렬분산 GHT를 실험하여 선형에 가까운 속도 제고율 (speedup)을 확인하였다.

• Nuclear Engineering and Technology
• /
• 제49권6호
• /
• pp.1165-1171
• /
• 2017

The traditional form of parallelism in Monte Carlo particle transport simulations, wherein each individual particle history is considered a unit of work, does not lend itself well to data-level parallelism. Event-based algorithms, which were originally used for simulations on vector processors, may offer a path toward better utilizing data-level parallelism in modern computer architectures. In this study, a simple model is developed for estimating the efficiency of the event-based particle transport algorithm under two sets of assumptions. Data collected from simulations of four reactor problems using OpenMC was then used in conjunction with the models to calculate the speedup due to vectorization as a function of the size of the particle bank and the vector width. When each event type is assumed to have constant execution time, the achievable speedup is directly related to the particle bank size. We observed that the bank size generally needs to be at least 20 times greater than vector size to achieve vector efficiency greater than 90%. When the execution times for events are allowed to vary, the vector speedup is also limited by differences in the execution time for events being carried out in a single event-iteration.

• 인터넷정보학회논문지
• /
• 제5권6호
• /
• pp.1-10
• /
• 2004

A web robot is a software that has abilities of tracking and collecting web documents on the Internet(l), The performance scalability of recent web robots reached the limit CIS the number of web documents on the internet has increased sharply as the rapid growth of the Internet continues, Accordingly, it is strongly demanded to study on the performance scalability in searching and collecting documents on the web. 'Design of web robot based on Multi-Agent to speed up documents collection ' rather than 'Sequentially executing Web Robot based on the existing Fork-Join method' and the results of analysis on its performance scalability is presented in the thesis, For collection speedup, a Multi-Agent based web robot performs the independent process for inactive URL ('Dead-links' URL), which is caused by overloaded web documents, temporary network or web-server disturbance, after dividing them into each agent. The agents consist of four component; Loader, Extractor, Active URL Scanner and inactive URL Scanner. The thesis models a Multi-Agent based web robot based on 'Amdahl's Law' to speed up documents collection, introduces a numerical formula for collection speedup, and verifies its performance improvement by comparing data from the formula with data from experiments based on the formula. Moreover, 'Dynamic URL Partition algorithm' is introduced and realized to minimize the workload of the web server by maximizing a interval of the web server which can be a collection target.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1997년도 춘계 학술대회 발표집
• /
• pp.9-9
• /
• 1997

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2230-2234
• /
• 2003

This paper proposes a distributed simulator for general control system in CEMTool. Systems can be described by SIMTool likes the simulink in Matlab. For distributed simulation, we can seperate any system into several parallel subsystems in SIMTool. The number of parallel subsystem can be determined by the system's property. After seperation, parallel simulator will do initialization, one-step-ahead simulation, block-distribution and ordering and so on. Finally, simulator will create independent C codes and executive files for each subsystem. The whole system is fulfilled by several PCs, and each PC executes one subsystem. There are communications among these subsystem using reflective memory or ethernet. We have made several experiments, and the 5-stand cold rolling mill control system is our main target. The result of parallel simulation has shown effective speedup in comparison with one pc simulation.

• Journal of applied mathematics & informatics
• /
• 제3권2호
• /
• pp.217-234
• /
• 1996

This report introduces a faster parallel LU decomposi-tion algorithm that gives a speedup almost equal to the number of nodes used. The new algorithm takes an advantage of an important C feature that lays out a matrix using a row major scheme and is based on the currently widely used LU decomposition algorithm with one major modification to eliminate most of the communication overhead. Empirical results are included in this report. For example solving a dense matrix that contains 100,000,000 elements gives a speedup of 50 when executed on 50 nodes of an intel Paragon in parallel.

• 한국시뮬레이션학회논문지
• /
• 제4권2호
• /
• pp.1-16
• /
• 1995

The performance of a computer system depends on the system architecture and workload, and the high performance required in many applications can be achieved by the scalability of the system architecture and workload. This paper presents scalable workload, a performance metric of scalable speedup and hierarchical modeling for the scalable computer system as well as the development of the object-oriented simulator spmplC++ Which is an advanced C++ version of the discrete event-driven simulation environment smplE. In addition, this paper presents two examples of applying scalable speedup, hierarchical modeling and simulator smplC++ to analyze the performance effect of the sclcbility in a multiprocessor system and a network-based client/server system.