• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.286-288
• /
• 2003

본 논문에서는 real-time환경에서 abnormal task를 자동 검출하여 시스템 overload 및 오 동작을 사전에 검출할 수 있는 방안을 제안한다. 본 논문에서 제안한 방안은 context switching이 발생하는 시점에서 각task들의 cpu 점유율 및 context switching 횟수를 분석하여 비정상적으로 높은 cpu 점유율을 가지는 task와 과도한 context switching을 일으켜 시스템에 overload를 주는 task들을 자동으로 검출한다. 이들 이용하여 신뢰성 있는 real-time시스템 설계 및 구현을 지원할 수 있다.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.564-569
• /
• 2013

The current embedded devices are growing rapidly in the multi-core, and these demand fast boot time. But method of previous boot uses core only one. The method includes parallel techniques and modification of CPU Frequency policy. Parallel methods, after analyzing the Android boot process with analysis tool, applied to location where a lot of CPU operation. CPU Frequency policy is modified for high performance of core. The proposed method was applied to S5PV310 dual core and Exynos4412 quad core embedded system. As a result of the experiment, we found that the proposed method makes boot time fast about 20.71% and 31.34% in dual core and quad core environment as compared with the previous method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.43-48
• /
• 2022

With the recent performance improvement of mobile devices as well as the emergence of various applications, not only interactive tasks but also real-time tasks are rapidly increasing. As real-time tasks have deadline requirements, resource management policies used in the conventional time-sharing systems have limitations in satisfying real-time constraints. In this paper, we examine how to efficiently manage resources while satisfying the constraints of real-time tasks through end-to-end resource management of CPU, memory, and storage when interactive and real-time tasks are executed concurrently on a mobile device. Instead of suggesting complicated resource management policies, we focus on examining the basic concepts necessary for each resource management. Specifically, we first look at basic policies such as assigning dedicated CPU cores for real-time tasks, allocating a certain working set of real-time tasks in memory, and using fast storage without context switch in I/O. We then consider how these basic policies can be adopted efficiently.

• Journal of Biomedical Engineering Research
• /
• v.41 no.3
• /
• pp.128-137
• /
• 2020

Cardiac electrophysiology studies often use simulation to predict how cardiac will behave under various conditions. To observe the cardiac tissue movement, it needs to use the high--resolution heart mesh with a sophisticated and large number of nodes. The higher resolution mesh is, the more computation time is needed. To improve computation speed and performance, parallel processing using multi-core processes and network computing resources is performed. In this study, we compared the computational speeds of CPU parallelization and GPU parallelization in virtual heart simulation for efficiently calculating a series of ordinary differential equations (ODE) and partial differential equations (PDE) and determined the optimal CPU and GPU parallelization architecture. We used 2D tissue model and 3D ventricular model to compared the computation performance. Then, we measured the time required to the calculation of ODEs and PDEs, respectively. In conclusion, for the most efficient computation, using GPU parallelization rather than CPU parallelization can improve performance by 4.3 times and 2.3 times in calculations of ODEs and PDE, respectively. In CPU parallelization, it is best to use the number of processors just before the communication cost between each processor is incurred.

• Journal of Korea Game Society
• /
• v.9 no.2
• /
• pp.135-142
• /
• 2009

Mesh denoising is a method to remove noise applying various filters. However, those methods usually spend much time since filtering is performed on CPU. Because GPU is specialized for floating point operations and faster than CPU, real-time processing for complex operations is possible. Especially mesh denoising is adequate for GPU parallel processing since it repeats the same operations for vertices or triangles. In this paper, we propose mesh denoising algorithm based on bilateral filtering using GPU parallel processing to reduce processing time. It finds neighbor triangles of each vertex for applying bilateral filter, and computes its normal vector. Then it performs bilateral filtering to estimate new vertex position and to update its normal vector.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.757-759
• /
• 2005

일반적인 렌더링 방식은 응용$\rightarrow$기하$\rightarrow$래스터화로 진행되는 렌더링 파이프라인 상에서 진행된다. 그래픽 카드의 발전으로 기하 단계의 연산을 GPU가 담당함에 따라 CPU의 연산을 줄여 CPU가 많은 연산을 할 수 있게 되었다. 그러나 이 같은 분배로 인해 CPU와 GPU가 서로 끝나기를 기다리는 병목현상이 발생하게 되었다. 이러한 병목 현상은 효율적인 렌더링을 저해하는 요인이다. 본 연구의 목적은 CPU와 GPU의 병렬처리 과정에서 발생하는 병목현상을 줄여 실시간 렌더링에서 그래픽 출력을 더욱 빠르게 하는데 있다. 이를 위해 본 논문에서는 그래픽 출력 과정 중 CPU 와 GPU 사이에서 하드웨어적으로 처리되고 있는 동기적 처리 과정을 소프트웨어적인 기법을 이용하여 비동기적으로 처리함으로써 성능을 향상시킬 수 있음을 말하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.1
• /
• pp.170-176
• /
• 2009

The efficiently power management is an important requirement traditionally in the mobile communication system which uses battery as their power source. Especially, it has been emphasized in the most devices, which has to provide high performance and various functions with an extended operating time. In this article, the adaptive power management technique for the core CPU unit in Embedded systems used widely for the mobile system thanks to its advantage on power consumption and physical size, is proposed.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.9
• /
• pp.1239-1244
• /
• 2001

The Virtual Interface Architecture (VIA) is usually suggested as a new standard high-performance communication of the cluster systems. However the VIA specification aims for platform independence, the current Intel VI Provider Library (VIPL) design favors systems with Intel architecture processors running the Windows operating system (OS). This paper aims for clarifying the guesstion problem of VIA and VIPL in the newtrul time of CPU Architecture and OS further more, It suggests the solution aiming the communication in the other CPU or OS

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.358-367
• /
• 2017

Advanced Driver Assistance Systems(ADAS), such as Front Collision Warning System (FCWS) are currently being developed. FCWS require high processing speed because it must operate in real time while driving. In addition, a low-power system is required to operate in an automobile embedded system. In this paper, FCWS is implemented in CPU-FPGA architecture in embedded system to enable real-time processing. The lane detection enabled the use of the Inverse Transform Perspective (IPM) and sliding window methods to operate at fast speed. To detect the vehicle, a Convolutional Neural Network (CNN) with high recognition rate and accelerated by parallel processing in FPGA is used. The proposed architecture was verified using Intel FPGA Cyclone V SoC(System on Chip) with ARM-Core A9 which operates in low power and on-board FPGA. The performance of FCWS in HD resolution is 44FPS, which is real time, and energy efficiency is about 3.33 times higher than that of high performance PC enviroment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8B
• /
• pp.736-744
• /
• 2006

For the handhold devices, minimizing repetitive CPU operations such as multiplications is a major factor for their performances. In this paper, we propose efficient algorithms for finding similar sequences from streaming time-series data such as stock prices, network traffic data, and sensor network data. First, we formally define the problem of similar subsequence matching from streaming time-series data, which is called the stream sequence matching in this paper. Second, based on the window construction mechanism adopted by the previous subsequence matching algorithms, we present an efficient window-based approach that minimizes CPU operations required for stream sequence matching. Third, we propose a notion of window MBR and present two stream sequence matching algorithms based on the notion. Fourth, we formally prove correctness of the proposed algorithms. Finally, through a series of analyses and experiments, we show that our algorithms significantly outperform the naive algorithm. We believe that our window-based algorithms are excellent choices for embedded stream sequence matching in handhold devices.