公开(公告)号：US20210334143A1

公开(公告)日：2021-10-28

申请号：US17221086

申请日：2021-04-02

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Daeub KIM ,  Jongtae SONG ,  Ji Wook YOUN ,  Joon Ki LEE ,  Kyeong-Eun HAN

IPC: G06F9/50

Abstract: A system for cooperation of disaggregated computing resources interconnected through an optical circuit, and a method for cooperation of disaggregated resources are disclosed. Functional block devices such as a processor block, an accelerator block, and a memory fabric block exist at a remote location, and these three types of remote functional block devices are interconnected and interoperated in a specific program to perform a cooperative computation and processing process. Accordingly, the system shares data and information of a memory existing in each block through optical signal interconnection that provides low-latency, fast processing, and wide bandwidth, and maintains cooperation and memory coherency.

公开(公告)号：US20180262437A1

公开(公告)日：2018-09-13

申请号：US15607931

申请日：2017-05-30

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Kyeong-Eun HAN ,  Jongtae SONG ,  Daeub KIM ,  Chansung PARK ,  Sun Me KIM ,  Ji Wook YOUN

IPC: H04L12/875 ,  H04L12/863 ,  G06F9/48

Abstract: A scheduling method for switching including receiving an allocation request for a time slot from input nodes to which the time slot is not allocated, receiving property information of at least one of virtual output queues (VOQs) in which data received by the input nodes is stored, determining a transmission priority of the VOQs for transmission of the data stored in the VOQs based on the received property information of the VOQs, determining input nodes to which the time slot is to be allocated using outputter arbiters for output nodes corresponding to the VOQs, allocating the time slot to the determined input nodes, and updating elements used to allocate the time slot with respect to input nodes for which the allocating of the time slot is completed and output nodes for which the allocating of the time slot is completed.

公开(公告)号：US20140078918A1

公开(公告)日：2014-03-20

申请号：US13952948

申请日：2013-07-29

Applicant: Electronics and Telecommunications Research Institute

Inventor： Kyeong-Eun HAN ,  Sun-Me KIM ,  Jong-Hyun LEE

IPC: H04L12/861

CPC classification number: H04L49/90 ,  H04L12/12 ,  H04L41/0833 ,  H04L47/30 ,  H04L49/9047 ,  Y02D50/40 ,  Y02D50/42

Abstract: Provided are a power-saving apparatus and method for multi-lane-based Ethernet, which allow a multi-lane-based Ethernet apparatus to improve energy-conserving efficiency while minimizing the deterioration of the performance of a network. The power-saving apparatus includes: a multi-lane communication unit configured to distribute an input communication packet between a plurality of transmission lanes, photoelectrically convert the input communication packet and transmit the photoelectrically-converted communication packet; a multi-buffer unit configured to comprise one or more buffers, store the input communication packet in each active buffer and transmit the input communication packet to the multi-lane communication unit; and a control unit configured to monitor the multi-buffer unit, compare the size of memory space in use of the multi-buffer unit with a predefined threshold and switch the one or more buffers to an active or inactive state based on the results of the comparison.

Abstract translation: 提供了一种用于多通道以太网的节电装置和方法，其允许基于多通道的以太网设备提高节能效率，同时最小化网络性能的恶化。 省电装置包括：多通道通信单元，被配置为在多个传输通道之间分配输入通信分组，对所输入的通信分组进行光电转换并发送光电转换的通信分组; 配置为包括一个或多个缓冲器的多缓冲器单元，将输入通信分组存储在每个主动缓冲器中，并将输入的通信分组发送到多通道通信单元; 以及控制单元，被配置为监视所述多缓冲单元，将所述多缓冲单元的使用中的存储器空间的大小与预定义的阈值进行比较，并且基于所述多缓冲单元的结果将所述一个或多个缓冲器切换到活动或非活动状态 比较。