-
公开(公告)号：KR100392817B1
公开(公告)日：2003-07-28
申请号：KR1020010047498
申请日：2001-08-07
IPC: H04L12/44
Abstract: PURPOSE: A parallel demultiplexing system for mass switching and a method therefor are provided to perform a high-speed mass communication by connecting cells as a tree structure, distributing each cell to a sub-path in parallel using a tree traversal method, inserting a link for indicating a sub-path of a next cell into a header of the cell, transmitting the cell through a plurality of sub-paths, and reassembling the cell in parallel. CONSTITUTION: A parallel cell distributing unit(210) segments inputted data into a plurality of cells, connects a plurality of cells as an M-way tree in which a leader cell is root, and distributes each cell to sub-paths in parallel using a certain tree traversal method. The parallel cell distributing unit(210) inserts a link for indicating a sub-path of a next transmission cell into a header of the cell, and transmits each cell to the sub-path. A parallel cell assembly unit(220) stores the cell transmitted from each sub-path in a cell queue according to sub-paths, analyzes the link inserted into the header of each cell, reassembles the cell in parallel according to the analyzed result, and transmits the reassembled cell.
Abstract translation: 目的：提供了一种用于批量切换的并行解复用系统及其方法，用于通过将单元连接为树结构来执行高速大量通信，使用树遍历方法将每个单元并行分配到子路径，插入链路 用于将下一个小区的子路径指示到小区的报头中，通过多个子路径发送该小区，并且并行地重组该小区。 组成：并行信元分配单元（210）将输入的数据分割成多个信元，将多个信元作为以引导信元为根的M路树连接，并将每个信元并行地分配给子路径，使用 某种树遍历方法。 并行信元分配单元（210）将用于指示下一个传输信元的子信道的链路插入信元的信头中，并且将每个信元传送到子信道。 并行信元组装单元（220）根据子路径将从每个子路径发送的信元存储在信元队列中，分析插入到每个信元的信头中的链路，根据分析结果并行地重组该信元，以及 传输重组的小区。
-
公开(公告)号：KR1020030013158A
公开(公告)日：2003-02-14
申请号：KR1020010047498
申请日：2001-08-07
IPC: H04L12/44
Abstract: PURPOSE: A parallel demultiplexing system for mass switching and a method therefor are provided to perform a high-speed mass communication by connecting cells as a tree structure, distributing each cell to a sub-path in parallel using a tree traversal method, inserting a link for indicating a sub-path of a next cell into a header of the cell, transmitting the cell through a plurality of sub-paths, and reassembling the cell in parallel. CONSTITUTION: A parallel cell distributing unit(210) segments inputted data into a plurality of cells, connects a plurality of cells as an M-way tree in which a leader cell is root, and distributes each cell to sub-paths in parallel using a certain tree traversal method. The parallel cell distributing unit(210) inserts a link for indicating a sub-path of a next transmission cell into a header of the cell, and transmits each cell to the sub-path. A parallel cell assembly unit(220) stores the cell transmitted from each sub-path in a cell queue according to sub-paths, analyzes the link inserted into the header of each cell, reassembles the cell in parallel according to the analyzed result, and transmits the reassembled cell.
Abstract translation: 目的：提供用于质量切换的并行解复用系统及其方法，用于通过将小区连接为树结构来执行高速大规模通信，使用树遍历方法将每个小区并行地分配到子路径，插入链路 用于将下一个小区的子路径指示到小区的头部，通过多个子路径发送小区，并且并行重新组合小区。 构成：并行单元分配单元（210）将输入的数据分割成多个单元，将多个单元作为前导单元为根的M方向树连接，并且将每个单元并行地分配给子路径 某些树遍历方法。 并行单元分配单元（210）将用于指示下一个传输小区的子路径的链路插入到小区的首部，并将每个小区发送到子路径。 并行单元组合单元（220）根据子路径将从每个子路径发送的小区存储在小区队列中，分析插入每个小区的报头中的链路，根据分析结果并行重新组合小区，以及 传输重新组装的单元。
-
公开(公告)号：KR1020060061746A
公开(公告)日：2006-06-08
申请号：KR1020050021413
申请日：2005-03-15
Applicant: 한국전자통신연구원
IPC: H04L12/28
Abstract: 1. 청구범위에 기재된 발명이 속한 기술분야
본 발명은 다수의 공유 저장장소를 이용한 효율적인 스위칭 장치 및 그 방법에 관한 것임.
2. 발명이 해결하려고 하는 기술적 과제
본 발명은 다수의 저장장소를 공유함으로써 확장이 용이하고, 저장장소에 한번 저장되어 출력되므로 전력소모가 적을 뿐만 아니라 균일분포 및 비균일분포 트래픽에 대하여 출력큐 스위치 구조와 같은 성능을 제공할 수 있는 스위칭 장치 및 그 방법을 제공하는데 그 목적이 있음.
3. 발명의 해결방법의 요지
본 발명은, 다수의 입력포트로 입력되는 자료를 다수의 출력포트로 전달하기 위한 스위칭 장치에 있어서, 외부 기기로부터 입력되는 자료의 출력포트를 읽어 출력포트로의 출력시간을 결정하기 위한 출력시간 결정 수단; 상기 출력시간 결정 수단에 연결되어 자료의 출력포트별로 가능한 자료 출력시간을 관리하기 위한 출력시간 관리 수단; 상기 출력시간 결정 수단으로부터의 자료 출력시간을 이용하여 자료 출력시간 위치가 비어있는 저장장소(memory bank)를 선택하기 위한 저장장소 선택 수단; 상기 저장장소 선택 수단에 연결되어 저장장소의 출력시간별 이용정보를 관리하기 위한 저장장소 이용정보 관리 수단; 상기 출력시간 결정 수단과 상기 저장장소 선택 수단의 결과를 이용하여 선택 및 결정된 상기 저장장소(memory bank)의 출력시간 위치로 전송자료를 전달하기 위한 연결 수단; 상기 연결 수단에 연결되어 상기 출력시간 결정 수단과 상기 저장장소 선택 수단의 결과를 이용하여 선택 및 결정된 상기 저장장소(memory bank)의 출력시간 위치에 자료를 저장하고, 다수의 분산 공유 저장장소를 출력될 시간( )에 따라 구분하여 관리하며, 현재 출력시간( )에 해당하는 저장장소들의 전송자료들을 읽어 출력하기 위한 공유 저장 수단; 및 상기 공유 저장 수단의 현재 출력시간( )에 해당하는 출력자료들을 입력받아 자료의 출력포트 정보를 읽어 해당하는 출력포트로 전달하기 위한 출력포트 연결 수단을 포함함.
4. 발명의 중요한 용도
본 발명은 스위칭 시스템 또는 네트워크 시스템 등에 이용됨.
다수의 분산된 저장장소, 공유 저장장소, 스위칭 장치, 출력시간 결정, 저장장소 선택, 균일분포 트래픽, 비균일분포 트래픽, 출력큐 스위치 구조 성능-
公开(公告)号：KR100419609B1
公开(公告)日：2004-02-25
申请号：KR1020010066715
申请日：2001-10-29
IPC: H04L12/863
Abstract: PURPOSE: A cell and packet scheduling device of a switching system is provided to convert non-uniform traffic into uniform traffic for applying to a scheduler, so as to furnish scheduling throughput similar to the throughput of an output buffer in the non-uniform traffic as well as in the uniform traffic. CONSTITUTION: A transfer request re-alignment part(110) re-aligns transfer request signals of a switch uniformly by ports. A cell and packet scheduler(120) receives the aligned transfer requests from the transfer request re-alignment part(110), to decide an output port not to generate input and output collision and output transfer accept signals. A transfer accept re-alignment part(130) re-aligns the transfer accept signals outputted from the cell and packet scheduler to original states(120). And a re-alignment state management part(140) decides the re-alignment state of the transfer request re-alignment part(110) and the transfer accept re-alignment part(130), according to ratio of scheduler services by ports of a switching system.
Abstract translation: 目的：提供一种交换系统的信元和分组调度设备，用于将非均匀业务量转换为统一业务量以便应用于调度器，从而提供类似于非均匀业务量中的输出缓冲器的吞吐量的调度吞吐量，作为 以及统一的交通。 组成：传输请求重新对齐部分（110）通过端口一致地重新对齐交换机的传输请求信号。 单元和分组调度器（120）从传输请求重新对齐部分（110）接收对齐的传输请求，以确定输出端口不产生输入和输出冲突并输出传输接受信号。 传送接受重新对齐部分（130）将从单元和分组调度器输出的传送接受信号重新对准到原始状态（120）。 并且，重新对齐状态管理部分（140）根据基于端口的调度器服务的比率来决定传送请求重新对齐部分（110）和传送接受重新对齐部分（130）的重新对齐状态 交换系统。
-
公开(公告)号：KR1020040001007A
公开(公告)日：2004-01-07
申请号：KR1020020036062
申请日：2002-06-26
Applicant: 한국전자통신연구원
IPC: H04L12/28
Abstract: PURPOSE: A demultiplexing device for supporting QoS(Quality of Service) and COS(Class of Service) in a switch system and a method therefor are provided to improve embodying complexity by using a switch, which supports the QoS and the CoS, as a detailed transmission path. CONSTITUTION: A transmission data distribution unit(210) receives transmission data, classifies the received transmission data according to the flow of transmission data with the order relation of transmission, and distributes the classified transmission data. A transmission data transmitting unit(230) having a plurality of detailed paths transmits the transmission data distributed in the transmission data distribution unit(210). A transmission data assembling unit(220) reassembles frames according to the order relation of the transmission data transmitted from the transmission data transmitting unit(230).
Abstract translation: 目的：提供一种用于支持交换机系统中的QoS（服务质量）和COS（服务等级）的解复用设备及其方法，以通过使用支持QoS和CoS的交换机作为详细的方式来提高体现复杂性 传输路径。 构成：发送数据分发单元（210）接收发送数据，根据发送数据的发送数据的流向对所接收的发送数据进行分类，分发发送数据。 具有多个详细路径的发送数据发送单元（230）发送分发在发送数据分配单元（210）中的发送数据。 发送数据组合单元（220）根据从发送数据发送单元（230）发送的发送数据的顺序关系重新组合帧。
-
Patent Agency Ranking
公开(公告)号：KR1020030034905A
公开(公告)日：2003-05-09
申请号：KR1020010066715
申请日：2001-10-29
IPC: H04L12/863
CPC classification number: H04L47/6215 , H04L47/6275 , H04L49/30
Abstract: PURPOSE: A cell and packet scheduling device of a switching system is provided to convert non-uniform traffic into uniform traffic for applying to a scheduler, so as to furnish scheduling throughput similar to the throughput of an output buffer in the non-uniform traffic as well as in the uniform traffic. CONSTITUTION: A transfer request re-alignment part(110) re-aligns transfer request signals of a switch uniformly by ports. A cell and packet scheduler(120) receives the aligned transfer requests from the transfer request re-alignment part(110), to decide an output port not to generate input and output collision and output transfer accept signals. A transfer accept re-alignment part(130) re-aligns the transfer accept signals outputted from the cell and packet scheduler to original states(120). And a re-alignment state management part(140) decides the re-alignment state of the transfer request re-alignment part(110) and the transfer accept re-alignment part(130), according to ratio of scheduler services by ports of a switching system.
Abstract translation: 目的：提供交换系统的小区和分组调度设备，将非均匀流量转换为统一流量，以应用于调度器，从而提供类似于非均匀流量中输出缓冲区吞吐量的调度吞吐量，如 就像在统一的交通。 构成：转移请求重新对准部分（110）通过端口将移动请求信号均匀地重新对齐。 小区和分组调度器（120）从传送请求重新对准部分（110）接收对齐的传送请求，以决定不产生输入和输出冲突和输出传送接受信号的输出端口。 转移接受重新对准部分（130）将从小区和分组调度器输出的传送接受信号重新对齐到原始状态（120）。 并且重新对准状态管理部件（140）根据调度器服务按照端口的比例来决定转移请求重新对准部分（110）和转移接受重新对准部分（130）的重新对准状态 切换系统
-
公开(公告)号：KR1020020059115A
公开(公告)日：2002-07-12
申请号：KR1020000087661
申请日：2000-12-31
IPC: H04Q3/52
Abstract: PURPOSE: An apparatus and method for high speed and small area switch cell scheduling is provided to reduce the latency by making the latency increased logN or N times and to switch many input/output ports by installing a scheduler to make the area increased NlogN or N times. CONSTITUTION: An apparatus for high speed and small area switch cell scheduling is comprised of an input request rotator(1010), a scheduler main processor(1020), and an input accept rotator. The input request rotator(1010) receives each input port's scheduling request, executes rotation as much as a priority value, and provides it to the scheduler core(1020). The scheduler main processor(1020) receives the rotated scheduling request of the input request rotator(1010) under a fixed priority and provides a scheduling result to the input accept rotator. The input accept rotator executes reverse rotation for the scheduling result provided from the scheduler main processor(1020) according to a priority value and provides the reverse rotated scheduling result to each output port.
Abstract translation: 目的：提供一种用于高速和小区域交换机调度的设备和方法，通过使延迟增加logN或N次来减少等待时间，并通过安装调度程序来切换许多输入/输出端口，使区域增加NlogN或N 倍。 构成：用于高速和小区域切换单元调度的装置包括输入请求旋转器（1010），调度器主处理器（1020）和输入接受旋转器。 输入请求旋转器（1010）接收每个输入端口的调度请求，执行与优先级值一样多的旋转，并将其提供给调度器核心（1020）。 调度器主处理器（1020）以固定优先级接收输入请求旋转器（1010）的旋转调度请求，并向输入接受旋转器提供调度结果。 输入接受旋转器根据优先级值对从调度器主处理器（1020）提供的调度结果执行反向旋转，并向每个输出端口提供反向旋转调度结果。
-
公开(公告)号：KR100317123B1
公开(公告)日：2001-12-24
申请号：KR1019990047540
申请日：1999-10-29
IPC: H04L12/28
Abstract: 본발명은두 개이상의입력이동시에하나의출력장치에대해데이터통신을요구할때 공유통신선로를공정하게중재하는선형시스톨릭라운드로빈스케줄러및 그의스케줄링방법에관한것이다. 이러한선형시스톨릭라운드로빈스케줄러는, 각클라이언트들의요청신호들을조합하여 N×N의 2차원요청매트릭스를만드는요청매트릭스생성수단과; 상기 2차원요청매트릭스를입력받아입력포트별각 출력포트들에대한요청신호들을추출하여우선순위순으로재배열하는요청배열생성수단; 상기우선순위순으로재배열된 1차원요청배열중 우선순위순으로하나의요청신호를출력포트정보와함께출력하는 N단의요청신호전파수단들; 쌍을이루는요청신호전파수단으로부터상기요청신호와출력포트정보를입력받고전단의프로세싱수단으로부터요청허가결과를입력받아, 상기요청신호에대한요청허가여부를결정하여후단의프로세싱수단에게전파하는 N단의프로세싱수단들; 및해당라운드로빈스케줄링사이클에서요청허가된상호독립적인입력포트들정보와출력포트들정보를출력하는수집수단을포함한것을특징으로한다.
-
公开(公告)号：KR1020010039236A
公开(公告)日：2001-05-15
申请号：KR1019990047540
申请日：1999-10-29
IPC: H04L12/28
CPC classification number: H04L47/6225 , H04L49/101 , H04L49/30
Abstract: PURPOSE: A linear systolic Round-Robin scheduler and its scheduling method are provided to implement a simple circuit structure having an excellent modularity for many shared communication links and perform a 2-dimensional Round-Robin scheduling of a high throughput by scheduling at a high speed many shared communication links with a small circuit size. CONSTITUTION: A Round Rover(310) outputs an output Round Robin seed address(o-seed) which is increased by 1 every Round-Robin scheduling cycle and an input Round-Robin seed address(i-seed) which is increased by 1 every Nth Round-Robin scheduling cycle. A request matrix register block(320) reads a request data of an input port to every output port by one time and propagates it to a rotation block(330). The rotation block(330) rotates the request signals read by line unit every Round-robin scheduling cycle from the request matrix register block(320) by using the output Round-Robin seed address. The rotated request signals are propagated to request propagation blocks(341,342,343). Processing elements(344,345,346) are respectively connected to each request propagation blocks(341,342,343) to form pairs. The request signals propagated from the rotation block(330) are propagated from the first request propagation block(341) to the nth request propagation block(343). In this respect, in each propagation block, the request signals are propagated in a pipeline as the uppermost bit is rotated by single bits to the lowermost bit. An aggregator block(350) is positioned at the end of the overall pipeline stage. The aggregator block(350) determines a use allowance of every input shafted communication link and output shared communication link selected by each pipeline stage and each Round-Robin cycles, and generates a data for configuring a space division switching.
Abstract translation: 目的：提供一种线性收缩循环调度器及其调度方法，以实现对许多共享通信链路具有出色模块性的简单电路结构，并通过高速调度执行高吞吐量的二维Round-Robin调度 许多共享的通信链路具有小的电路大小。 组合：轮回（310）输出一个输出轮回种子地址（o-seed），每个循环轮询调度周期增加1，而输入的Round-Robin种子地址（i-seed）每增加1个 第N轮回调度周期。 请求矩阵寄存器块（320）将输入端口的请求数据读取到每个输出端口一次，并将其传播到旋转块（330）。 旋转块（330）通过使用输出的Round-Robin种子地址从请求矩阵寄存器块（320）旋转每循环调度周期的线路单元读取的请求信号。 旋转的请求信号被传播到请求传播块（341,342,343）。 处理元件（344,345,346）分别连接到每个请求传播块（341,342,343）以形成对。 从旋转块（330）传播的请求信号从第一请求传播块（341）传播到第n个请求传播块（343）。 在这方面，在每个传播块中，当最高比特以单个比特旋转到最低比特时，请求信号在流水线中传播。 聚合器块（350）位于整个流水线阶段的末端。 聚合器块（350）确定每个输入轴通信链路的使用余量和由每个流水线级选择的每个循环循环的输出共享通信链路，并且生成用于配置空分切换的数据。
-
公开(公告)号：KR1020050019266A
公开(公告)日：2005-03-03
申请号：KR1020030056919
申请日：2003-08-18
Applicant: 한국전자통신연구원
CPC classification number: H04L49/60 , H04J3/0691 , H04J3/1611
Abstract: PURPOSE: A TDM/IP data integrated switching system and a method thereof are provided to simultaneously switch all packet-type data using a fixed-length packet switch by converting TDM/EoS(Ethernet over SDH)-mixed data, received from a SONET/SDH network, into the same format as packet data, received from an IP/Ethernet network. CONSTITUTION: A TDM/IP data integrated switching system(200) comprises a TDM/EoS data processor(300), an IP/Ethernet data processor(400), a fixed-length packet switch(500), and a control/timing driver(600). The TDM/EoS data processor(300) comprises an input TDM/EoS data processor(310) and an output TDM/EoS data processor(320). The input TDM/EoS data processor(310) comprises an input data classification part(311), an input EoS data processing part(312), an input TDM data processing part(313), and an input data multiplexer(314). The input data classification part(311) classifies TDM/EoS-mixed data, received from a SONET/SDH network, into TDM data and EoS data. The input EoS data processing part(312) packetizes the classified EoS data through demultiplexing, EoS protocol processing, Ethernet frame processing, and packet header creation. The input TDM data processing part(313) packetizes the classified TDM data through demultiplexing, data alignment, and packet header creation. The input data multiplexer(314) receives packetized data from the input EoS data processing part(312) and multiplexes them.
Abstract translation: 目的：提供一种TDM / IP数据集成交换系统及其方法，通过转换从SONET / EOS接收的TDM / EoS（Ethernet over SDH）混合数据，同时切换所有分组型数据，使用固定长度的分组交换机， SDH网络与从IP /以太网接收的分组数据格式相同。 构成：TDM / IP数据集成交换系统（200）包括TDM / EoS数据处理器（300），IP /以太网数据处理器（400），固定长度分组交换机（500）和控制/定时驱动器 （600）。 TDM / EoS数据处理器（300）包括输入TDM / EoS数据处理器（310）和输出TDM / EoS数据处理器（320）。 输入TDM / EoS数据处理器（310）包括输入数据分类部分（311），输入EoS数据处理部分（312），输入TDM数据处理部分（313）和输入数据多路复用器（314）。 输入数据分类部（311）将从SONET / SDH网络接收的TDM / EoS混合数据分类为TDM数据和EoS数据。 输入EoS数据处理部分（312）通过解复用，EoS协议处理，以太网帧处理和分组报头创建对分类的EoS数据进行打包。 输入TDM数据处理部分（313）通过解复用，数据对准和分组报头创建对分类的TDM数据进行分组。 输入数据多路复用器（314）从输入的EoS数据处理部分（312）接收分组数据，并对其进行复用。
-
-
-
-
-
-
-
-
-
Search Results
21
records
(took 0.03 seconds)
