Earticle

최근 프로세서의 집적도는 급속도로 발전하고 있으나 클락 스피드는 증가하지 않는 대신에 프로세서 내의 코어 수가 늘어나고 있는 실정으로 프로그래밍 속도 향상을 위한 방법에 대한 연구가 필수적이라 할 수 있다. 이에 본 논문에서는 현재 연산 가속화를 위해 사용되는 매니 코어 프로세서의 대표적인 인텔 제온 파이의 성능 분석을 위하여 퀀텀 에스프레소를 활용하였다. 또한 제온 파이에서 MPI 실행시 랭크의 수를 변화시키면서 성능 벤치마킹 을 수행하여 하드웨어적인 성능 특성을 연구하였다. 그 결과 물리 코어가 57개인 제온파이 프로세서의 하나의 코어 당 4개의 작업을 처리할 때 가장 좋은 성능을 나타내고 있으며, 물리 코어 하나에 MPI 랭크수를 4개 이상 확장하면 성능향상이 거의 일어나지 않는다. 이러한 융합 기술을 통하여 퀀텀 에스프레소의 성능 향상과 제온 파이의 하드웨 어적인 특성을 확인할 수 있다.

Recently the degree of integration of processor and developed rapidly. However, clock speed is not increased, a situation that increases the number of cores in the processor. In this paper, we analyze the performance of a typical Intel Xeon Phi of many core process used for the current operation accelerate. Utilizing the Quantum ESPRESSO, which was calculated using the FFTW library. By varying the number of ranks in MPI when running the benchmarks the performance Xeon Phi. The result shows a good performance in the handling of four job on one physical core. However, four or more to expand the number of MPI Rank is degraded. Through this convergence it was found to improve the performance of Quantum ESPRESSO. It is possible to check the hardware characteristics of the Xeon Phi.

It has been recognized as an important issue to design optimally a firm's logistics network for minimizing logistics cost and maximizing customer service. It is, however, not easy to get an optimal solution by analyzing trade-off of cost factors, dynamic and interdependent characteristics in the logistics network decision making. Although there has been some developments in a system which helps decision making for logistics analysis, it is true that there is no system for enterprise-wise's on-site support and methodical logistics decision. Specially, E-biz process along with information technology has been made dramatic advance in a various industries, there has been much need for practical education closely resembles on-site work. The software developed by this study materializes efficient algorithm suggested by recent studies in key topics of logistics such as location and allocation problem, traveling salesman problem, and vehicle routing problem and transportation and distribution problem. It also supports executing a variety of experimental design and analysis in a way of the most user friendly based on Java. In the near future, we expect that it can be extended to integrated supply chain solution by adding decision making in production in addition to a decision in logistics.

Recently, research using artificial neural networks has further expanded the field of neural network optimization and automatic structuring from improving inference accuracy. The performance of the machine learning algorithm depends on how the hyperparameters are configured. Open-source hyperparameter optimization software can be an important step forward in improving the performance of machine learning algorithms. In this paper, we review open-source hyperparameter optimization softwares.

This paper discusses the efficiency optimization for mobile application. By adopting reconfigurable software architecture, a dynamic reschedule method is proposed. Modeling the overheads of single operation, the uncertainty caused by control structure is represented with experienced data and branch prediction. Several criteria are proposed considering different situation.

The costs of finding and correcting software defects have been the most expensive activity in software development. The accurate prediction of defect‐prone software modules can help the software testing effort, reduce costs, and improve the software testing process by focusing on fault-prone module. Recently, static code attributes are used as defect predictors in software defect prediction research, since they are useful, generalizable, easy to use, and widely used. However, two common aspects of data quality that can affect performance of software defect prediction are class imbalance and noisy attributes. In this research, we propose the combination of particle swarm optimization and bagging technique for improving the accuracy of the software defect prediction. Particle swarm optimization is applied to deal with the feature selection, and bagging technique is employed to deal with the class imbalance problem. The proposed method is evaluated using the data sets from NASA metric data repository. Results have indicated that the proposed method makes an impressive improvement in prediction performance for most classifiers.

Computer software has gradually become an indispensable elements in many aspects of our daily lives and an important factor in numerous systems. In recent years, it is not unusual that the software cost is more than the hardware cost in many situations. In addition to the costs of developing software, the repair cost resulting from the software failures are even more significant. In this paper, a cost model with warranty cost, time to remove each fault detected in the software system, and delivery delay cost is developed. We use a software reliability model based on non-homogeneous Poisson process (NHPP). We discuss the optimal release policies to minimize the expected total software cost. Numerical examples are provided to illustrate the results.

Building programming unwavering quality development models means software reliability growth models (SRGM) for evaluating in the feeling of foreseeing the product dependability speaks to an incredible test for programming testing designers in the product commercial ventures. Being able to foresee or gauge the quantity of flaws in the product amid improvement and testing procedure helps altogether in indicating/registering the product discharge day into the business sector and in overseeing venture assets (i.e. individuals and money).There are different routines to appraise the parameters of programming unwavering quality development models, for example, Subterranean insect state enhancement and Molecule swarm improvement means particle swarm optimization (PSO). We to investigate the upsides of utilizing PSO to better model the product dependability expectation process.

For a multiprocessor System-on-Chip (MPSoC) to achieve high performance via parallelism, we must consider how to partition a given application into different components and map the components onto multiple processors. In this paper, we propose a software pipeline-based partitioning method with cyclic dependent task management and communication optimization. During task partitioning, simultaneously considering computation load balance and communication optimization can cause interference, which leads to performance loss. To address this issue, we formulate their constraints and apply an integer linear programming approach to find an optimal partitioning result - one that requires a trade-off between these two factors. Experimental results on a reconfigurable MPSoC platform demonstrate the effectiveness of the proposed method, with 20% to 40% performance improvements compared to a traditional software pipeline-based partitioning method.

Vinalines is actually known as not only one of Vietnam's state-sponsored economic giants but also the largest shipowner by tonnage in Vietnamese shipping industry. Therefore, a question of how to improve business performance of the corporation is always received deep attention by Vietnamese government, specially after the seriously economic scandal of Vinalines in a last few years. Among development strategies, the study focuses on short-term one in which Vinalines is recommended to restructure its own fleet in order to optimize performance of fleet operation and minimize costs while meeting the customer's shipping demand in near future. The first section is of introduction. Via method of statistical data analysis, section 2 brings to readers a panorama about the development profile and the current situation of development of Vinalines. In section 3, the authors use linear programming for setting a cost-minimization model optimizing Vinalines fleet structure based on available statistics and forecast information by Vinalines. The optimization problem is solved by applying AIMMS software in section 4. Finally, some conclusions and proposals by authors for the development of Vinalines are given.

Experimental software data capturing the essence of software projects (expressed e.g., in terms of their complexity and development time) have been a subject of intensive modeling. In this study, we introduce a new category of Hybrid Fuzzy Neural Networks (gHFNN) and discuss their comprehensive design methodology. The gHFNN architecture results from highly synergistic linkages between Fuzzy Neural Networks (FNN) and Polynomial Neural Networks (PNN). We develop a rule-based model consisting of a number of "if-then" statements whose antecedents are formed in the input space and linked with the consequents (conclusion pats) formed in the output space. In this framework, FNNs contribute to the formation of the premise part of the overall network structure of the gHFNN. The consequences of the rules are designed with the aid of genetically endowed PNNs. The experiments reported in this study deal with well-known software data such as the NASA dataset. In comparison with the previously discussed approaches, the proposed self-organizing networks are more accurate and yield significant generalization abilities.

광 디스크 드라이브에서의 서보 제어시스템에는 광 픽업에서 발생된 레이저 빔을 디스크 기록면의 데이터 트랙에 정확히 위치시키기 위한 제어 계를 갖고 있다. 광 디스크의 고배속화에 따른 외란의 주파수 대역의 증가에 따라 더욱 더 높은 샘플링 주파수로 레이저 빔의 위치 제어를 필요로 하게 되고, 여러 가지 알고리즘의 증가로 인해 DSP의 연산 부담은 증가하게 된다. 본 논문에서는 서보 제어에 필요한 알고리즘의 최적화된 하드웨어/소프트웨어 시스템을 구현하고 이를 이용한 실험 결과를 제시한다.

구조최적설계는 구조물의 성능 개선을 추구하며, 항공 및 자동차의 설계 등에서 사용된다. 최근에는 구조최적설계를 위한 상용 소프트웨어들이 잘 개발되어 있기 때문에 산업 분야에서 쓰임이 활발해지는 추세이다. 본 연구에서는 구조최적설계 상용 소프트웨어 중에서 많이 사용되는 Genesis, MSC. Nastran과 OptiStruct에 대해 성능 비교 연구를 수행한다. 최적설계의 관점에서 소프트웨어 성능은 설계결과의 우수성과 수행에 소요된 CPU 시간으로 평가할 수 있다. 치수최적설계, 형상최적설계와 위상최적설계에 대하여, 구조 예제들을 풀이한다. 공정한 비교를 위하여 구조최적설계의 수행 환경과 방법은 동일하게 통일한다. 또한 최적설계 결과를 분석하고 각 소프트웨어의 성능과 특징에 대해 토의한다.

Structural optimization is widely accepted in industrial fields. Structural optimization pursues improved performance of the structures. Recently, structural optimization is actively utilized due to the well-developed commercial design software systems. Three popular commercial structural optimization systems are investigated and compared. They are MSC.Nastran, Genesis and OptiStruct. The performance of the systems is analyzed based on the quality of the optimum solution and the computational time. Linear static response size, shape and topology optimizations are explored and compared with some test examples. For fair comparison, the systems are run in the same environment and the optimization parameters affecting the performance are unified. The optimization results are analyzed and the performances and characteristics of each software system are discussed.

Theories for optimal design and optimization algorithms have long been well developed. In industries, however, they are not well practiced. To make them work for industry, a new philosophy is necessary and an integration of various software systems required. A review of the history in the aspect of optimal design software is made and a newly developed code DS-Structure is introduced.

본 논문에서는 PC 기반 지상파 DMB(Terrestrial Digital Multimedia Broadcasting, T-DMB) 수신기를 위한 SW 최적화에 대해 설명한다. 이 수신기는 PC 외부에 지상파 DMB 신호를 안테나로 수신하여 복조하고 채널 복호하는 프론트 엔드(front-end) 수신 모듈을 이용, USB를 통하여 RS(Reed-Solomon) 부호화된 MPEG-2 TS(Transport Stream) 데이터를 읽어 들여 RS 복호, TS 역다중화, 비디오 복호, 오디오 복호 등의 SW 처리 과정을 거쳐 디스플레이 상에 수신 내용을 표시하게 된다. 본 논문에서는 저사양 PC에서도 T-DMB를 수신할 수 있도록 H.264/MPEG-4 AVC(Advanced Video Coding) 복호 과정을 최적화한 결과에 대해 설명한다.