다중 메모리 뱅크 구조를 위한 고속의 자료 할당 기법

조정훈(JEONGHUN CHO),백윤흥(YUNHEUNG PAEK),최준식(JUNSIK CHOI) 한국정보과학회 2003 한국정보과학회 학술발표논문집 Vol.30 No.2Ⅰ

Virtually every digital signal processors(DSPs) support on-chip multi- memory banks that allow the processor to access multiple words of data from memory in a single instruction cycle. Also, all existing fixed-point DSPs have irregular architecture of heterogeneous register which contains multiple register files that arc distributed and dedicated to different sets of instructions. Although there have been several studies conducted to efficiently assign data to multi-memory banks, most of them assumed processors with relatively simple, homogeneous general-purpose registers. Therefore, several vendor-provided compilers for DSPs were unable to efficiently assign data to multiple data memory banks, thereby often failing to generate highly optimized code for their machines. This paper presents an algorithm that helps the compiler to efficiently assign data to multi- memory banks. Our algorithm differs from previous work in that it assigns variables to memory banks in separate, decoupled code generation phases, instead of a single, tightly-coupled phase. The experimental results have revealed that our decoupled algorithm greatly simplifies our code generation process; thus our compiler runs extremely fast, yet generates target code that is comparable in quality to the code generated by a coupled approach.

유헬스 환경에서 센서네트워크의 안정성 보장을 위한 소프트웨어 플랫폼

정민우,조정훈,Jung, Min Woo,Cho, Jeonghun 대한임베디드공학회 2012 대한임베디드공학회논문지 Vol.7 No.5

The rises of the life index quality together with the medical technology improvement lead to a longer life expectancy. Then a better health care program, especially for elderly, is needed. The common health problems facing those senior citizens are changed from acute diseases to chronic diseases, such as diabetes, hypertension. Then u-Health takes center stage in medical industry. Although u- Health medical device manufacturers have been improving their instruments, these instruments still rely on proprietary technologies without fixed platform. Even if the interface has been provided by the manufacturer, there is no widely-accepted uniform data model to access data of various u-Health devices. IEEE 11073 is a standard attempting to unify the interfaces of all medical devices. In this paper we have proposed a conversion software platform that assures interoperability among medical devices for ubiquitous sensor network. This module uses in order to develop a standard platform of medical system.

이동 목표물의 효율적인 위치 추정을 위한 파티클 필터 신호 처리의 GPU 기반 가속화

김성섭,조정훈,박대진,Kim, Seongseop,Cho, Jeonghun,Park, Daejin 대한임베디드공학회 2017 대한임베디드공학회논문지 Vol.12 No.5

Time of difference of arrival (TDOA) method using passive sonar sensor array has normally been used to estimate the location of a concealed moving target in underwater environment. Particle filter has been introduced for effective target estimation for non-Gaussian and nonlinear systems. In this paper, we propose a GPU-based acceleration of target position estimation using particle filter and propose efficient embedded system and software architecture. For the TDOA measurement from the passive sonar sensor, we use the generalized cross correlation phase transform (GCC-PHAT) method to obtain the correlation coefficient of the signal using FFT and we try to accelerate the calculation of GCC-PHAT based TDOA measurements using FFT with GPU CUDA. We also propose parallelization method of the target position estimation algorithm using the GPU CUDA to update the state of each particle for the target position estimation using the measured values. The target estimation algorithm was verified using Matlab and implemented using GPU CUDA. Then, we realized the proposed signal processing acceleration system using NVIDIA Jetson TX1 as the target board to analyze in terms of the execution time. The execution time of the algorithm is reduced by 55% to the CPU standalone-operation on the target board. Experiment results show that the proposed architecture is a feasible solution in terms of high-performance and area-efficient architecture.

멀티 코어와 GPU 결합 구조를 이용한 DEVS 기반 대규모 하이브리드 시스템 모델링 시뮬레이션의 가속화

김성섭,조정훈,박대진,Kim, Seongseop,Cho, Jeonghun,Park, Daejin 한국시뮬레이션학회 2018 한국시뮬레이션학회 논문지 Vol.27 No.3

이산 사건 시스템 명세 (DEVS)를 이용한 하이브리드 시스템 시뮬레이션은 IoT 기반 Smart factory의 최적 동작을 위한 파라미터 추출 등 멀티 레벨 모델 계층을 포함한 복잡계 시스템의 해석에서 중요한 도구로 사용되고 있다. 하이브리드 시스템은 연속 시간 시스템과 이산 사건 시스템의 특성을 모두 포함하고 있어 그 복잡성으로 인해 결과를 얻기 위해 많은 시간을 필요로 한다. 본 연구에서는 멀티 코어와 GPU가 결합된 이기종 컴퓨터 구조를 이용한 DEVS 기반 대규모 하이브리드 시스템 시뮬레이션의 가속화를 제안한다. 제안하는 멀티 코어-GPU 상호 결합 시뮬레이션 실행 플랫폼을 사용하여 상대적으로 많은 순간 전력을 소모하지만 실행 시간 측면에서 빠른 시뮬레이션이 오히려 전체 에너지 소모 측면에서 장점을 가지는 것을 보여주고자 한다. 이를 위해 대규모 모델의 수평적/수직적 상호 결합된 DEVS 기반 하이브리드 시스템을 시뮬레이션 하였고 효과적인 시뮬레이션을 위한 하드웨어의 조합, 동작 파라미터 변경에 따른 성능 향상을 전력 소모 관점에서 분석하였다. Discrete event system specification (DEVS) has been used in many simulations including hybrid systems featuring both discrete and continuous behavior that require a lot of time to get results. Therefore, in this study, we proposed the acceleration of a DEVS-based hybrid system simulation using multi-cores and GPUs tightly coupled computing. We analyzed the proposed heterogeneous computing of the simulation in terms of the configuration of the target device, changing simulation parameters, and power consumption for efficient simulation. The result revealed that the proposed architecture offers an advantage for high-performance simulation in terms of execution time, although more power consumption is required. With these results, we discovered that our approach is applicable in hybrid system simulation, and we demonstrated the possibility of optimized hardware distribution in terms of power consumption versus execution time via experiments in the proposed architecture.

TTCN-3를 이용한 네트워크 기반 임베디드 소프트웨어 테스팅 환경 구축

채호창,김수림,조정훈,이성훈,Chae, Hochang,Jin, Xiulin,Cho, Jeonghun,Lee, Seonghun 대한임베디드공학회 2010 대한임베디드공학회논문지 Vol.5 No.1

It is highly requested that the more complicated embedded software is used for high performance and multiple functions of the systems. This is inevitably increasing the errors. Therefore the embedded software testing is getting important recently. There are not general testing methods which are able to be applied for any embedded systems, but via this research, we introduce a testing method which is based on TTCN-3, a testing standard, for embedded systems. A testing environment for network-based embedded software is implemented with considering the features of TTCN-3 testing which is based on message exchange. The testing environment has two additional parts with TTCN-3 test system, the network analyzer to access the network-based systems and the communication interface which is suggested for embedded systems in previous work, and we have implemented the whole testing environment with interacting these two parts. In addition to the normal testing domain, called single node testing as a unit testing of V-model, we suggest another concept to test multiple nodes in network. It could be achieved by adding keywords such as supervisor and object which are describing the feature of TTCN-3 testing component and generating the TTCN-3 Executable code which contains new keywords. The testing has done for embedded software which is based on CAN network and the demonstration of the testing environment has been shown in this paper.

사물-사람 간 개인화된 상호작용을 위한 음향신호 이벤트 감지 및 Matlab/Simulink 연동환경

이상현,김탁곤,조정훈,박대진,Lee, Sanghyun,Kim, Tag Gon,Cho, Jeonghun,Park, Daejin 대한임베디드공학회 2015 대한임베디드공학회논문지 Vol.10 No.4

Most IoT-related approaches have tried to establish the relation by connecting the network between things. The proposed research will present how the pervasive interaction of eco-system formed by touching the objects between humans and things can be recognized on purpose. By collecting and sharing the detected patterns among all kinds of things, we can construct the environment which enables individualized interactions of different objects. To perform the aforementioned, we are going to utilize technical procedures such as event-driven signal processing, pattern matching for signal recognition, and hardware in the loop simulation. We will also aim to implement the prototype of sensor processor based on Arduino MCU, which can be integrated with system using Arduino-Matlab/Simulink hybrid-interoperation environment. In the experiment, we use piezo transducer to detect the vibration or vibrates the surface using acoustic wave, which has specific frequency spectrum and individualized signal shape in terms of time axis. The signal distortion in time and frequency domain is recorded into memory tracer within sensor processor to extract the meaningful pattern by comparing the stored with lookup table(LUT). In this paper, we will contribute the initial prototypes for the acoustic touch processor by using off-the-shelf MCU and the integrated framework based on Matlab/Simulink model to provide the individualization of the touch-sensing for the user on purpose.

제어흐름 에러 탐지를 위한 분리형 시그니처 모니터링 기법

최기호,박대진,조정훈,Choi, Kiho,Park, Daejin,Cho, Jeonghun 대한임베디드공학회 2018 대한임베디드공학회논문지 Vol.13 No.5

Control flow errors are caused by the vulnerability of memory and result in system failure. Signature-based control flow monitoring is a representative method for alleviating the problem. The method commonly consists of two routines; one routine is signature update and the other is signature verification. However, in the existing signature-based control flow monitoring, monitoring target application is tightly combined with the monitoring code, and the operation of monitoring in a single thread is the basic model. This makes the signature-based monitoring method difficult to expect performance improvement that can be taken in multi-thread and multi-core environments. In this paper, we propose a new signature-based control flow monitoring model that separates signature update and signature verification in thread level. The signature update is combined with application thread and signature verification runs on a separate monitor thread. In the proposed model, the application thread and the monitor thread are separated from each other, so that we can expect a performance improvement that can be taken in a multi-core and multi-thread environment.

범용 개발 보드를 이용한 차량용 소프트웨어 테스트 시스템 개발

금대현,홍재승,진성호,조정훈,Kum, DaeHyun,Hong, JaeSeung,Jin, SungHo,Cho, JeongHun 대한임베디드공학회 2012 대한임베디드공학회논문지 Vol.7 No.1

Recently automotive software has been more complex and needs to be reduced its development time. Software testing of its functionalities and performance should be conducted in an early development phase to reduce time to market and the development cost. Software functional testing can be performed through simulating the hardware, but it is not guaranteed that evaluation of real-time performance using simulation has enough accuracy. Real-time performance can be precisely evaluated with hardware-in-the-loop simulation, but it costs time and effort to set up hardware for testing. In this paper, we suggest a testing system that can evaluate functional requirements and real time properties with a general-purpose development board in the early development phase. In addition, we improve reusability of the testing system through modularized and layered architecture. With the proposed testing system we can contribute to building reliable testing system at low cost without difficulty.

FMI 기반 가상 ECU 시뮬레이션 정보 교환 기법 제안

김형래(Hyeongrae Kim),조정훈(Jeonghun Cho) 한국통신학회 2023 한국통신학회 학술대회논문집 Vol.2023 No.6

모델 기반 평가 방법을 이용한 평가 항목 생성에 관한 연구

손인식 ( Insick Son ),조정훈 ( Jeonghun Cho ),한갑수 ( Kabsu Han ),백윤흥 ( Yunheung Paek ),이진용 ( Jinyong Lee ) 한국정보처리학회 2013 한국정보처리학회 학술대회논문집 Vol.20 No.2

모델 기반 평가 방법은 블랙박스 테스트의 한 종류로 평가 항목의 생성과 평가 항목의 실행이 모델 기반 평가 도구를 통하여 자동으로 이루어지는 평가 방법이다. 자동차 지능형 헤드램프의 AFLS/ADB 를 대상으로 무작위 평가 생성 기법과 T-method 평가 생성 기법을 이용 하여 평가 항목을 생성하고 비교해 보았으며 Vector CANoe 를 사용하여 시뮬레이션을 구성하고 CAPL 을 이용하여 스크립트를 작성하고 평가하여 나온 평가 보고서를 확인 하였다.