• 한국통신학회논문지
• /
• 제30권2B호
• /
• pp.1-10
• /
• 2005

빠른 데이터 처리를 위하여 기존에는 소프트웨어방식으로 구현되었던 TCP/IP를 고속의 하드웨어로 구현함에 있어, TCP/IP 하드웨어와 외부 블록간의 통신을 중계하는 블록인 Host Interface를 구현하였다. Host Interface는 TCP/IP 하드웨어와 외부 블록의 중간에 위치하여 외부 블록과의 통신을 위해 AMBA AHB 규약을 따른다. Host Interface는 내부의 Command/Status Register를 통하여 CPU와 TCP/IP 하드웨어 간의 명령, 상태, 헤더 정보 등을 전달하는데 이 때에는 AMBA AHB의 Slave로서 동작한다. Data Flow를 위해서 Host Interface는 AMBA AHB의 Master로서 동작하는데, 데이터 흐름의 방향에 따라 Data flow는 데이터를 수신하는 Receive flow와 데이터를 패킷으로 만들어 보내는 Transmit Flow로 나된다. Rx Flow의 경우, UDP 블록이나 TCP Buffer로부터 받은 데이터를 내부의 작은 RxFIFO를 통해 외부 RxRAM에 써서 CPU가 읽어갈 수 있도록 하고, Tx Flow의 경우에는 외부 TxRAM에서 전송할 데이터를 읽어 와서 TxFIFO를 거쳐 UDP Buffer나 TCP Buffer에 씀으로써 패킷을 만들어 보내도록 한다. 외부 RAM의 액세스에는 Command/Status Register에 위치한 Buffer Descriptor의 정보를 이용하게 된다. Host Interface는 이러한Data Flow의 원활한 흐름을 위해서 여러 세부 기능들을 수행하게 된다. Host Interface의 기능을 검증하기 위하여 여러 testcase들이 수행되었으며, 0.18 마이크론 기술을 사용하여 synthesis한 결과, 내부의 Command/Status Register와 FIFO를 모두 포함하여 약 173K 게이트가 소요됨을 보았다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 II
• /
• pp.855-858
• /
• 2003

TCP/IP 를 포함하는 데이터 네트워킹 프로토콜을 구현함에 있어, 기존에는 소프트웨어 방식으로 구현되었던 모듈들을 하드웨어로 구현하는 프로젝트를 수행하면서, CPU 와 하드웨어 모듈과의 통신을 중계하는 모듈을 구현하였다. 본 논문에서는 TCP/IP 하드웨어와 CPU 와의 통신을 위한 Host Interface 의 기능에 대해 다루고 구현 방식을 Control flow와 Data flow의 입장에서 설명하였다. 우선, Host Interface 의 기능을 설명하고 Host Interface 의 입출력 신호를 정의하였다. Host Interface에서 이루어지는 CPU와 하드웨어 모듈간의 통신을 제어정보 흐름과 데이터정보 흐름으로 나누고 제어흐름을 위해서는 Command/Status Register 를 두었고, 데이터 흐름을 위해서는 CPU와 데이터 RAM 사이에 FIFO 를 두어 데이터의 흐름이 신속히 이루어지도록 하였다. 끝으로 Host Interface 와 주변 모듈들간의 통신에 대한 Testcases에 대해서도 다루었다.

• IMMUNE NETWORK
• /
• 제13권5호
• /
• pp.163-167
• /
• 2013

The dynamics of the virus-host interface in the response to respiratory virus infection is not well-understood; however, it is at this juncture that host immunity to infection evolves. Respiratory viruses have been shown to modulate the host response to gain a replication advantage through a variety of mechanisms. Viruses are parasites and must co-opt host genes for replication, and must interface with host cellular machinery to achieve an optimal balance between viral and cellular gene expression. Host cells have numerous strategies to resist infection, replication and virus spread, and only recently are we beginning to understand the network and pathways affected. The following is a short review article covering some of the studies associated with the Tripp laboratory that have addressed how respiratory syncytial virus (RSV) operates at the virus-host interface to affects immune outcome and disease pathogenesis.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권2호
• /
• pp.97-103
• /
• 2017

정규표현식 패턴 매칭을 고속으로 수행하기 위하여 하드웨어 기반의 정규표현식 매칭 회로들이 제시되었으며, 특히 보통 프로세서처럼 정규표현식에 대한 프로그램을 실행하여 패턴 매칭을 수행하는 정규표현식 프로세서가 제시되었다. 정규표현식 프로세서가 패턴 매칭을 수행하기 위해서는 명령어 메모리에 정규표현식 패턴에 대한 명령어가, 데이터 메모리에는 매칭 대상이 되는 데이터가 미리 저장되어야 한다. 정규표현식 프로세서를 호스트의 보조프로세서로 사용하려면 호스트에서 정규표현식 프로세서의 명령어 메모리와 데이터 메모리를 초기화하는 기능을 제공해야 하며 이를 위한 호스트 인터페이스가 필요하다. 본 논문에서는 Altera사의 DE1-SoC 보드에서 호스트와 정규표현식 프로세서 간의 인터페이스를 설계하였고, 이를 사용하기 위한 응용 프로그램 인터페이스도 구현하였다. 응용 프로그램에서 응용프로그램 인터페이스를 사용하여 정규표현식 프로세서를 이용한 패턴 매칭을 수행하여 호스트 인터페이스의 동작을 확인하였다.

• Journal of Plant Biology
• /
• 제36권3호
• /
• pp.285-292
• /
• 1993

Cellular compatibility in the self-parasitism of Cuscuta australis R. Brown was studied at the ultrastructural level. The front cells of the haustorium penetrated the host stems independently grew within the host tissues and transformed into elongate, filamentous hyphae. Each hyphal cells contained a large nucleus and dense cytoplasm with abundant cell organelles. Multilamellar structures were contained in the cytoplasm and cell walls of the penetrating hyphal cells. When the hyphal cells did not yet invade the host cells, the middle lamella and the fused cellulosic cell walls of the two partners at the host-parasite interface were preserved well. As the invasion of the parasitic hyphal cells progressed, however, the middle lamella was not found at the interface and the host cell walls and plasma membranes were partially broken down. A hyphal cell penetrated deeply into the host cell had a more darkly stained cytoplasm with numerous of cell organelles. In the host cells attacked by the hyphal cells the limiting membranes of plastids were broken down and several vesicles were arrayed near the cell walls. No plasmodesmatal connections between the host and parasite cell walls were found; however, half-plasmodesmata were observed frequently on the side of the hyphal cell walls. These results suggested that the compatibility response in the self-parasitism of Cuscuta was expressed by cell walls, not by plasmodesmata, between the host and the parasite cells.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권2호
• /
• pp.27-35
• /
• 2021

NAND flash memory-based SSD needs an internal software, Flash Translation Layer(FTL) to provide traditional block device interface to the host because of its physical constraints, such as erase-before-write and large erase block. However, because useful host-side information cannot be delivered to FTL through the narrow block device interface, SSDs suffer from a variety of problems such as increasing garbage collection overhead, large tail-latency, and unpredictable I/O latency. Otherwise, the new type of SSD, open-channel SSD exposes the internal structure of SSD to the host so that underlying NAND flash memory can be managed directly by the host-level FTL. Especially, I/O data classification by using host-side information can achieve the reduction of garbage collection overhead. In this paper, we propose a new scheme to reduce garbage collection overhead of open-channel SSD by separating the journal from other file data for the journaling filesystem. Because journal has different lifespan with other file data, the Write Amplification Factor (WAF) caused by garbage collection can be reduced. The proposed scheme is implemented by modifying the host-level FTL of Linux and evaluated with both Fio and Filebench. According to the experiment results, the proposed scheme improves I/O performance by 46%~50% while reducing the WAF of open-channel SSDs by more than 33% compared to the previous one.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1836-1839
• /
• 2005

We have developed Ethernet based real-time communication systems called "Vnet/IP" for DCS which is the control system for process automation. This paper describes the features and the technologies of the ASIC which is utilized in the communication interface hardware for Vnet/IP. Vnet/IP has been developed for mission-critical communications. Hence it has real-time feature, high reliability and precise time synchronization capability. At the same time, it is able to deal with standard protocols without influence on mission-critical communications. The communication interface hardware has a host interface and dual redundant network interfaces. The host interface can be chosen PCI-bus or R-bus which is the proprietary internal bus developed for the high reliable redundant controller. Each network interface is a RJ45 connection with 1Gbps maximum in compliance with IEEE802.3.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.665-668
• /
• 2003

In this paper, we have designed and implemented the RAID controller board which connects to the host computer with serial ATA interface and connects to the disks with parallel ATA interface. Serial ATA interface is proposed to overcome the design limitation of parallel ATA while enabling the storage interface to scale with the slowing media rate demands for PC platforms. Serial ATA is to replace parallel ATA with the compatibility with existing operating systems and drivers, adding performance headroom for years to come. It Moreover, serial ATA provides even faster transfer rate of 150 Mbytes/s which is larger than that of current parallel ATA. The RAID controller board designed in this paper combines up to 4 disks with parallel ATA interface, and connects to PC host computer with serial ATA interface. We have implemented RAID controller using Verilog HDL language with FPGA chip. The RAID controller supports RAID level 0 and 1 functionality. Experimently, the average read/write performance of parallel ATA interface is about 30 Mbytes/s. Therefore, when 4 parallel disks is connected to the RAID controller board, we can get almost full throughput of serial ATA protocol using the RAID level 0 configuration with 4 disks.

• Journal of Information Processing Systems
• /
• 제4권4호
• /
• pp.133-144
• /
• 2008

Clusters have become a popular alternative for building high-performance parallel computing systems. Today's high-performance system area network (SAN) protocols such as VIA and IBA significantly reduce user-to-user communication latency by implementing protocol stacks outside of operating system kernel. However, emerging parallel applications require a significant improvement in communication latency. Since the time required for transferring data between host memory and network interface (NI) make up a large portion of overall communication latency, the reduction of data transfer time is crucial for achieving low-latency communication. In this paper, Eager Data Transfer (EDT) mechanism is proposed to reduce the time for data transfers between the host and network interface. The EDT employs cache coherence interface hardware to directly transfer data between the host and NI. An EDT-based network interface was modeled and simulated on the Linux-based, complete system simulation environment, Linux/SimOS. Our simulation results show that the EDT approach significantly reduces the data transfer time compared to DMA-based approaches. The EDTbased NI attains 17% to 38% reduction in user-to-user message time compared to the cache-coherent DMA-based NIs for a range of message sizes (64 bytes${\sim}$4 Kbytes) in a SAN environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.414-420
• /
• 2005

The ShortStack Micro Server enables any product that contains a microcontroller or microprocessor to quickly and inexpensively become a networked, Internet-accessible device. The ShortStack Micro Server provides a simple way to add LonWorks networking to new or existing smart devices. . It implements the LonTalk protocol and provides the physical interface with the LonWorks communication. The ShortStack host processor can be an 8, 16, or 32-bit microprocessor or microcontrollers. The ShortStack API and driver typically require about 4kbytes of program memory on the host processor and less than 200 bytes of RAM. The interface between host processor and the ShortStack Micro Server may be a Serial Communication Interface (SCI). The LonWorks control module with a high performance is developed, which is composed of the 8 bit PIC Microprocessor for host processor and the smart neuron chip for the ShortStack Micro Server. This intelligent control board is verified as proceeding the various function tests from experimental system with an boost pump and inverter driving systems. It is also confirmed that the developed control module provides stably 0-10VDC linear signal to the input signal of inverter driving system for varying the induction motor speed. Thus, the experimental results show that the fabricating intelligent board carried out very well the various functions in the wide operating ranges of boost pump system. This developed control module expect to apply to industrial fields to require the comparatively exact control and monitoring such as multi-motor driving system with inverter, variable air volume system and the boost pump water supply systems.