http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김종문,이병권,정회경,Kim, Jong-Moon,Lee, Byung-Kwon,Jung, Hoe-Kyung 한국정보통신학회 2013 한국정보통신학회논문지 Vol.17 No.5
본 논문에서는 모바일 디스플레이장치에 필요한 MDDI(Mobile Display Digital Interface) 프로토콜 패킷생성방법을 소프트웨어로 구현하는 것을 제안한다. 최소한의 하드웨어 구성을 가지며, 소프트웨어를 이용하여 MDDI 프로토콜 패킷을 생성한다. 이의 구현을 위해 고속 마이크로프로세와 FPGA(Field-Programmable Gate Array)로 하드웨어를 설계하였다. 소프트웨어로 생성한 패킷은 FPGA를 통해 LVDS(Low-Voltage Differential Signaling) 신호로 변환되어 출력된다. 제안하는 방식의 장점은 다양한 패킷을 소프트웨어로 쉽게 만들 수 있다는 것이다. 단점은 패킷전송에 걸리는 시간이 기존에 제안된 방식보다 빠르지 않았다. 이는 향후 개선되어야 할 과제로 남았다. In this study, we propose how th implement a MDDI(Mobile Display Digital Interface) protocol packet generation method in software. MDDI protocol is widely used in mobile display device. MDDI protocol packets are generated by software within micro processor. This method needs the minimum hardware configuration. In order to implementation of this method, we design a hardware platform with a high performance microprocessor and a FPGA. The packets generated by software within microprocessor are converted into LVDS signals, and transmitted by hardware within FPGA. This study suggests the benefits of the way how software can easily create a variety of packet. But, this proposed method takes more time in packet transmission compared to the traditional method. This weakness remains as a future challenge, which can be soon improved.
대규모 신경망 시뮬레이션을 위한 칩상 학습가능한 단일칩 다중 프로세서의 구현
김종문,송윤선,김명원 대한전자공학회 1996 전자공학회논문지-B Vol.b33 No.2
In this paper we describe designing and implementing a digital neural chip and a parallel neural machine for simulating large scale neural netsorks. The chip is a single-chip multiprocessor which has four digiral neural processors (DNP-II) of the same architecture. Each DNP-II has program memory and data memory, and the chip operates in MIMD (multi-instruction, multi-data) parallel processor. The DNP-II has the instruction set tailored to neural computation. Which can be sed to effectively simulate various neural network models including on-chip learning. The DNP-II facilitates four-way data-driven communication supporting the extensibility of parallel systems. The parallel neural machine consists of a host computer, processor boards, a buffer board and an interface board. Each processor board consists of 8*8 array of DNP-II(equivalently 2*2 neural chips). Each processor board acn be built including linear array, 2-D mesh and 2-D torus. This flexibility supports efficiency of mapping from neural network models into parallel strucgure. The neural system accomplishes the performance of maximum 40 GCPS(giga connection per second) with 16 processor boards.