• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.33-41
• /
• 2014

This paper presents an effective memory access method for a high-speed data transfer on mobile systems using a direct memory access controller that considers the characteristics of a multi-port memory controller. The direct memory access controller has an integrated channel management function to control multiple direct memory access channels. The channels are physically separated and operate independently from each other. Experimental results show that the proposed direct memory access method improves the transfer performance by up to 72% and 69% on read and write transfer cycles, respectively. The total number of transfer cycles of the proposed method is 63% less than in a commercial method under 4-channel access.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.501-504
• /
• 2000

근본적으로 방대한 양의 실시간 연산을 요구하는 영상 신호처리, 소나, 레이다와 같은 시스템에서는 시스템의 성능을 최대화하기 위해 병렬 신호처리 시스템의 사용이 불가피하다. 본 논문은 방대한 양의 데이터를 실시간으로 처리할수 있는 병렬 신호처리보드를 설계 및 구현하였다. 이 보드는 DSP칩간의 통신과 보드간의 통신이 가능하며, DSP칩이 마스터가 되어 EMIF(External Memory Interface Port)포트를 통해 다른 DSP칩의 지역메모리를 액세스 할수 있다. 또한 외부의 호스트 프로세서가 보드 내의 DSP칩에 프로그램을 다운로딩 할수 있다. 보드간의 통신은 PCI 버스를 통하여 이루어지며, DSP칩간의 통신과 DSP칩과 그의 지역메모리와의 통신은 지역버스를 통해 직접적으로 이루어진다. 보드에서 가장 핵심인 DSP-to-PCI제어기는 하드웨어 언어인 VHDL로 설계하였으며, 시뮬레이션 환경은 Synopsys ＆ ALTERA MaxplusⅡ를 사용하여 검증하였으며, 최종적으로 CPLD(Complex Programable Logic Device)칩을 사용하여 구현하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.2
• /
• pp.88-97
• /
• 1990

In this paper, DPA bus is proposed for implementation of MC 68000 based tightly-coupled multiprocessor system. The DPMC and arbiter are designed that the local memory of each PE can accept memory request both from a local processor and from the system bus. The performance of the proposed system bus is evaluated by Stochastic Petri Net(SPN) system modeling. The processing power, the efficiency, and the utilization of system bus are simulated for various load factors.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.1
• /
• pp.29-42
• /
• 1999

은행이나 증권시장 혹은 통신 분야와 같은 온라인 트랜잭션처리 (OLTP) 응용 분야들이 계속 증가하고 있으며 그 규모와 복잡성은 매년 405에서 50% 이상 증가하고 있는 것으로 평가되고 있다. 이러한 복잡한 OLTP 응용분야들은 한 대의 개인용 컴퓨터나 워크스테이션으로는 처리가 불가능하며, 슈퍼 컴퓨터나 MPP와 같은 고성능의 컴퓨터를 이용하는 경우에는 방대한 예산이 소요될 것이다. 본 논문에서는 데이터를 공유하는 워크스테이션 클러스터에서 트랜잭션을 병렬로 처리할 수 있는 고성능 트랜잭션처리 시스템인 PHLOX를개발한다. PHLOX는 네트워크 파일 시스템을 이용하여 데이터를 공유함으로써 확장성이 뛰어나며 각 워크스테이션의 메모리 버퍼간에 직접 데이터 전송을 지원함으로써 디스크 액세스빈도수를 줄일 수 있다는 장점을 갖는다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.26 no.2
• /
• pp.99-107
• /
• 2006

Magnetic nondestructive testing is very useful far detecting a crack on the surface or near of the surface of the ferromagnetic materials. The distribution of the magnetic flux leakage (DMFL) on a specimen has to be obtained quantitatively to evaluate the crack. The magnetic camera is proposed to obtain the DMFL at the large lift-off. The magnetic camera consists of a magnetic source, magnetic lens, analog to digital converters (ADCs), interface, and computer. The magnetic leakage fields or the distorted magnetic fields from the object, which are concentrated on the magnetic lens, are converted to analog electrical signals tv arrayed small magnetic sensors. These analog signals are converted to digital signals by the ADCs, and are stored, imaged, and processed by the interface and computer. However the magnetic camera has limitations with respect to converting and switching speed, full range and resolution, direct memory access (DMA), temporary storage speed and volume because common ADCs were used. Improved techniques, such as those that introduce the operational amplifier (OP-Amp), amplify the signal, reduce the connection line, and use the low pass filter (LPF) to increase the signal to noise ratio are necessary. This paper proposes the exclusive embedded ADC including OP-Amp, LPF, microprocessor and DMA circuit for the magnetic camera to satisfy the conditions mentioned above.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.3
• /
• pp.127-143
• /
• 2022

Recently, many attempts to run numerical ocean models in cloud computing environments have been tried actively. A cloud computing environment can be an effective means to implement numerical ocean models requiring a large-scale resource or quickly preparing modeling environment for global or large-scale grids. Many commercial and private cloud computing systems provide technologies such as virtualization, high-performance CPUs and instances, ether-net based high-performance-networking, and remote direct memory access for High Performance Computing (HPC). These new features facilitate ocean modeling experimentation on commercial cloud computing systems. Many scientists and engineers expect cloud computing to become mainstream in the near future. Analysis of the performance and features of commercial cloud services for numerical modeling is essential in order to select appropriate systems as this can help to minimize execution time and the amount of resources utilized. The effect of cache memory is large in the processing structure of the ocean numerical model, which processes input/output of data in a multidimensional array structure, and the speed of the network is important due to the communication characteristics through which a large amount of data moves. In this study, the performance of the Regional Ocean Modeling System (ROMS), the High Performance Linpack (HPL) benchmarking software package, and STREAM, the memory benchmark were evaluated and compared on commercial cloud systems to provide information for the transition of other ocean models into cloud computing. Through analysis of actual performance data and configuration settings obtained from virtualization-based commercial clouds, we evaluated the efficiency of the computer resources for the various model grid sizes in the virtualization-based cloud systems. We found that cache hierarchy and capacity are crucial in the performance of ROMS using huge memory. The memory latency time is also important in the performance. Increasing the number of cores to reduce the running time for numerical modeling is more effective with large grid sizes than with small grid sizes. Our analysis results will be helpful as a reference for constructing the best computing system in the cloud to minimize time and cost for numerical ocean modeling.