• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.479-485
• /
• 2013

Virtualization is a promising approach to consolidating multiple online services onto a smaller number of computing resources. A virtualized server environment allows computing resources to be shared among multiple performance isolated platforms called virtual machines. Through server virtualization software, applications servers are encapsulated into VMs, and deployed with APIs on top generalized pools of CPU and memory resources. Networking and security have been moved to a software abstraction layer that transformed computing, network virtualization. And it paves the way for enterprise to rapidly deploy networking and security for any application by creating the virtual network. Stochastic reward net (SRN) is an extension of stochastic Petri nets which provides compact modeling facilities for system analysis. In this paper, we develop SRN model of network virtualization based on virtual switch. Measures of interest such as switching delay and throughput are considered. These measures are expressed in terms of the expected values of reward rate functions for SRNs. Numerical results are obtained according to the virtual switch capacity and number of active VMs.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.564-571
• /
• 2017

The burst loading of a pre-created cache-image is an effective method to reduce the instruction cache misses in the early stage of the program execution. It is useful to alleviate the performance degradation as well as the energy inefficiency, which is induced by the concentrated cold misses at the instruction cache. However, there are some defects, including software overhead on the compiler and installer. Furthermore, there are several mismatches as a result of the dynamic properties for specific applications. This paper addresses these issues and proposes a cache-image maintenance/recreation policy that can conduct dynamic management using a hardware-assisted method. The results of the simulation show that the proposed method can maintain the cache-image with a proper size and validity.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.105-112
• /
• 2018

As data size increase, a single database is not enough to serve current volume of tasks. Since data is partitioned and stored into multiple databases, analysis should also support parallelism in order to increase efficiency. However, traditional analysis requires data to be transferred out of database into nodes where analytic service is performed and user is required to know both database and analytic framework. In this paper, we propose an efficient way to perform K-means clustering algorithm inside the distributed column-based database and relational database. We also suggest an efficient way to optimize K-means algorithm within relational database.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.1051-1058
• /
• 2024

In semiconductors for AI, Computing in Memory (CIM) integrates computation and memory to minimize data movement and reduce processing bottlenecks, thereby improving performance. In AI tasks that handle large amounts of data, CIM is gaining attention as a key technology that optimizes the performance of AI systems by improving power efficiency and enabling faster computation. In this paper, a new CIM architecture for AI semiconductors is proposed. The proposed architecture can perform MAC operations by controlling the width of the transistor and the pulse width of the control signal, and can be implemented in a smaller area than the existing architecture.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.498-509
• /
• 2001

Collaborative systems allow users, who may be far removed from each other geographically, to do collaborative work such as 3D animation, computer game, and industrial design in a single virtual space. This paper describes our experience to develop a collaborative system framework that aims at expanding the some functions of a stand-alone visual modeling tool, called 3D Studio Max, into those of the distributed collaborative working environments. The paper mainly deals with design and implementation of a 3D shared-object Plug-In with respect to the 3D Studio Max Plug-In Software Development Kit in the distributed collaborative system developed by the authors. There are two major functions of the proposed scheme; one is to write 3D object-information to the shared memory after extracting it from the 3D Studio Max, the other is to create 3D objects after retrieving them from the shared memory. Also, the proposed scheme provides a simple way of storing 3D objects that have variable size, by means of shared memory which located in between the collaborative system clients and 3D studio Max. One of the remarkable virtures of the Plug-In is to reduce a considerable amount of shared object data which in consequence can mitigate the network overhead. This can be achieved by the fact that the system is able to extract a minimum amount of 3D objects that are required to transmit. Also, using the proposed scheme, user can facilitate 3D Studio Max into distributed collaborative working environments. This, in consequence give many benefits such as saving time as well as eliminating space constraints in the course of 3D modeling when we are under industrial design process.

• Transactions on Semiconductor Engineering
• /
• v.2 no.4
• /
• pp.33-40
• /
• 2024

Recent advancements in computing-in-memory (CIM) have enabled substantial energy efficiency by leveraging charge-domain operations and multi-bit input mechanisms. However, earlier designs still suffer from elevated power consumption and often compromise computation signal-to-noise ratio (SNR) to enhance energy efficiency. In this study, we introduce a CIM processor optimized for energy efficiency and accuracy in multi-bit input/weight-parallel operations, featuring four main innovations: (1) a 10T2C sign-magnitude cell that utilizes voltage-capacitance-ratio (VCR) decoding for 5-bit analog inputs with only two supply voltage levels, (2) a charge reuse technique for the computation word line (CWL) to lower input driver power requirements, (3) a signal-amplifying noise-canceling voltage-to-time converter (SANC-VTC) to boost SNR, and (4) a distribution-aware time-to-digital converter (DA-TDC) aimed at reducing ADC power consumption. The proposed CIM processor, implemented in 28 nm CMOS technology with a 1.25 mm² footprint, achieves a power consumption of 4.44 mW and an energy efficiency of 332 TOPS/W, reaching a benchmark accuracy of 72.43% (tested on ImageNet with ResNet50, 5-bit input/5-bit weight).

• KIISE Transactions on Computing Practices
• /
• v.21 no.12
• /
• pp.774-779
• /
• 2015

In this paper, we present the design and implementation of a large-scale qualitative spatial reasoner using Apache Spark, an in-memory high speed cluster computing environment, which is effective for sequencing and iterating component reasoning jobs. The proposed reasoner can not only check the integrity of a large-scale spatial knowledge base representing topological and directional relationships between spatial objects, but also expand the given knowledge base by deriving new facts in highly efficient ways. In general, qualitative reasoning on topological and directional relationships between spatial objects includes a number of composition operations on every possible pair of disjunctive relations. The proposed reasoner enhances computational efficiency by determining the minimal set of disjunctive relations for spatial reasoning and then reducing the size of the composition table to include only that set. Additionally, in order to improve performance, the proposed reasoner is designed to minimize disk I/Os during distributed reasoning jobs, which are performed on a Hadoop cluster system. In experiments with both artificial and real spatial knowledge bases, the proposed Spark-based spatial reasoner showed higher performance than the existing MapReduce-based one.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.1
• /
• pp.19-30
• /
• 2012

The context aware service is the service to provide useful information to the users by recognizing surroundings around people who receive the service via computer based on computing and communication, and by conducting self-decision. But CAS(Context Awareness System) shows the weak point of small-scale context awareness processing capacity due to restricted mobile function under the current mobile environment, memory space, and inference cost increment. In this paper, we propose a mobile cloud context system with using Google App Engine based on PaaS(Platform as a Service) in order to get context service in various mobile devices without any subordination to any specific platform. Inference design method of the proposed system makes use of knowledge-based framework with semantic inference that is presented by SWRL rule and OWL ontology and Jess with rule-based inference engine. As well as, it is intended to shorten the context service reasoning time with mapping the regular reasoning of SWRL to Jess reasoning engine by connecting the values such as Class, Property and Individual which are regular information in the form of SWRL to Jess reasoning engine via JessTab plug-in in order to overcome the demerit of queries reasoning method of SparQL in semantic search which is a previous reasoning method.

• Journal of KIISE
• /
• v.42 no.8
• /
• pp.998-1009
• /
• 2015

In recent years, there has been a growing interest in RDFS Inference to build a rich knowledge base. However, it is difficult to improve the inference performance with large data by using a single machine. Therefore, researchers are investigating the development of a RDFS inference engine for a distributed computing environment. However, the existing inference engines cannot process data in real-time, are difficult to implement, and are vulnerable to repetitive tasks. In order to overcome these problems, we propose a method to construct an in-memory distributed inference engine that uses a parallel graph structure. In general, the ontology based on a triple structure possesses a graph structure. Thus, it is intuitive to design a graph structure-based inference engine. Moreover, the RDFS inference rule can be implemented by utilizing the operator of the graph structure, and we can thus design the inference engine according to the graph structure, and not the structure of the data table. In this study, we evaluate the proposed inference engine by using the LUBM1000 and LUBM3000 data to test the speed of the inference. The results of our experiment indicate that the proposed in-memory distributed inference engine achieved a performance of about 10 times faster than an in-storage inference engine.