• Journal of KIISE:Databases
• /
• v.37 no.5
• /
• pp.275-284
• /
• 2010

GPUs are stream processors based on multi-cores, which can process large data with a high speed and a large memory bandwidth. Furthermore, GPUs are less expensive than multi-core CPUs. Recently, usage of GPUs in general purpose computing has been wide spread. The CUDA architecture from Nvidia is one of efforts to help developers use GPUs in their application domains. In this paper, we propose techniques to parallelize a skyline algorithm which uses a simple nested loop structure. In order to employ the CUDA programming model, we apply our optimization techniques to make our skyline algorithm fit into the performance restrictions of the CUDA architecture. According to our experimental results, we improve the original skyline algorithm by 80% with our optimization techniques.

• Geophysics and Geophysical Exploration
• /
• v.21 no.4
• /
• pp.213-219
• /
• 2018

In this study, we simulated 3D wave propagation modeling using a Xeon Phi x200 processor and compared the parallel computation performance with that using a Xeon CPU. Unlike the 1st generation Xeon Phi coprocessor codenamed Knights Corner, the 2nd generation x200 Xeon Phi processor requires no additional communication between the internal memory and the main memory since it can run an operating system directly. The Xeon Phi x200 processor can run large-scale computation independently, with the large main memory and the high-bandwidth memory. For comparison of parallel computation, we performed the modeling using the MPI (Message Passing Interface) and OpenMP (Open Multi-Processing) libraries. Numerical examples using the SEG/EAGE salt model demonstrated that we can achieve 2.69 to 3.24 times faster modeling performance using the Xeon Phi with a large number of computational cores and high-bandwidth memory compared to that using the 12-core CPU.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1035-1045
• /
• 2015

Recent studies in Big Data Analysis are showing promising results, utilizing the main memory for rapid data processing. In-memory computing technology can be highly advantageous when used with high-performing servers having tens of gigabytes of RAM with multi-core processors. The constraint in network in these infrastructure can be lessen by combining in-memory technology with distributed parallel processing. This paper discusses the research in the aforementioned concept applying to a test taxi hailing application without disregard to its underlying RDBMS structure. The application of IMDG technology in the application's backend API without restructuring the database schema yields 6 to 9 times increase in performance in data processing and throughput. Specifically, the change in throughput is very small even with increase in data load processing.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.840-845
• /
• 2015

In recent years, Big Data has been a topic of great interest for the production and operation work of offshore plants as well as for enterprise resource planning. The ability to predict future equipment performance based on historical results can be useful to shuttling assets to more productive areas. Specifically, a centrifugal compressor is one of the major piece of equipment in offshore plants. This machinery is very dangerous because it can explode due to failure, so it is necessary to monitor its performance in real time. In this paper, we present stream data processing architecture that can be used to compute the performance of the centrifugal compressor. Our system consists of two major components: a virtual tag stream generator and a real-time data stream manager. In order to provide scalability for our system, we exploit a parallel programming approach to use multi-core CPUs to process the massive amount of stream data. In addition, we provide experimental evidence that demonstrates improvements in the stream data processing for the centrifugal compressor.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.11-18
• /
• 2021

The small radio frequency tracking radar is a tracking system with a radio frequency sensor that identifies a target through all-weather radio frequency signal processing for a target and searches, detects and tracks the target for the major target. In this paper, we describe the development of a board equipped with TMS320C6678 and XILINX FPGA (Field Programmable Gate Array), a high-speed multi-core DSP that acquires target information through all-weather radio frequency and identifies a target through real-time signal processing. We propose DSP-FPGA combination architecture for DSP and FPGA selection and signal processing, and also explain the design of SRIO for high-speed data transmission.

• Design & Manufacturing
• /
• v.15 no.2
• /
• pp.42-48
• /
• 2021

In this paper, when manufacturing large/multi-mold parts (more than 30 core parts),A mold manufacturing (tolerance) management system was established through design-processing linkage.The mold manufacturing (tolerance) management system is a design-based measurement shape/measurement position determination system, M/C processing-linked measurement drive system,It is composed of four parts: CAD-linked measurement result analysis system and manager mold part quality management system.In addition, the constructed system was applied to the field and the effect of system construction was evaluated by comparing it with the existing process.As a result of the evaluation, the measurement precision is within 0.02mm, and the time it takes to measure after the end of processing is shorter than that of the existing process.(12 hours → 2 hours) It was shortened to 16.7%.In addition, it was confirmed that the time required for reprocessing after measurement was reduced by 25% (4 hours → 1 hour) compared to the existing process.

• The KIPS Transactions:PartC
• /
• v.15C no.2
• /
• pp.93-102
• /
• 2008

The network weather map and bandwidth time-series graph are popularly used to understand the current and past traffic condition of NSP, ISP, and enterprise networks. These systems collect traffic performance data from a SNMP agent running on the network devices such as routers and switches, store the gathered information into a DB, and display the network performance status in the form of a time-series graph or a network weather map using Web user interface. Most of current enterprise networks are constructed in the form of a hierarchical tree-like structure with multi-Gbps Ethernet links, which is quietly different from the national or world-wide backbone network structure. This paper focuses on the network weather map for current enterprise network. We start with the considering points in developing a network weather map system suitable for enterprise network. Based on these considerings, this paper proposes the best way of using SNMP in constructing a network weather map system. To prove our idea, we designed and developed a network weather map system for our campus network, which is also described in detail.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.8
• /
• pp.261-270
• /
• 2014

As Internet traffic increases recently, much effort has been put on improving the performance of a web server. In addition to hardware side solutions such as replacement by high-end hardware or expansion of the number of servers, there are software side solutions to improve performance. Recent studies on these software side solutions have been actively performed. In this paper, we identify performance degradation problems occurring in a conventional TCP networking reception process and propose a way to solve them. We improve performance by combining three kinds of existing methods for Linux Networking Performance Improvement and two kinds of newly proposed methods in this paper. The three existing methods include 1) an allocation method of a packet flow to a core in a multi-core environment, 2) ITR(Interrupt Throttle Rate) method to control excessive interrupt requests, and 3) sk_buff data structure recycling. The two newly proposed methods are fd data structure recycling and epoll_event data structure recycling. Through experiments in a web server environment, we verify the effect of our two proposed methods and its combination with the three existing methods for performance improvement, respectively. We use three kinds of web servers: a simple web server, Lighttpd generally used in Linux, and Apache. In a simple web server environment, fd data structure recycling and epoll_event data structure recycling bring out performance improvement by about 7 % and 6%, respectively. If they are combined with the three existing methods, performance is improved by up to 40% in total. In a Lighttpd and an Apache web server environment, the combination of five methods brings out performance improvement by up to 36% and 20% in total, respectively.

• Journal of dental hygiene science
• /
• v.13 no.4
• /
• pp.487-492
• /
• 2013

This study aimed to illuminate the correlatives between the surface processing of Zirconia core and the shear bond strength. The specimens were made by precipitating for two minutes in color liquid and drying to produce a colored Zirconia core following the manufacturer's instructions. The specimens were divided into 4 subgroups according to the surface treatment-sandblasted+liner treatment, SLT group; sandblasted treatment, ST group; liner treatment, LT group; non treatment (control), NT group. The specimens were put on the device with regard to ISO/TS 11405, then tested the shear bond strength with 1 mm shearing speed per minute using the Instron multi-purpose tester. The collected data was analysed by one way ANOVA and t-test. After applying the liner and sandblast to the Zirconia core, shear bond strength value were SLT (23.19 MPa), ST (21.17 MPa), LT (20.53 MPa) and NT (16.46 MPa) in the order. There was a significant difference in the surface roughness between NT and ST group (p<0.001), and in the compressive shear bond strength between NT and SLT group (p<0.05). Therefore, sandblasted plus liner treatment on pre-sintered substructure increased the bond strength of veneering ceramic, compared with other surface treatments.