Hub-Based Interconnection Network Using Parallel-Headerless TDMA Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing networks face high latency due to resource contention in switches, particularly when heavily loaded, leading to packet buffering or discarding, which is costly and inefficient.
Innovation Solution
A hub-based network architecture where data is transferred between processing nodes through a central hub, with data written and read at different speeds based on node proximity and data volume, using point-to-point electrical signaling and time slots to manage communication delays and optimize data routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If switches are used for interconnection in cloud computing networks, then cost is reduced and availability is improved, but latency increases significantly when the network is heavily loaded due to resource contention
Solution Approach 1:
The network communication is segmented into discrete time slots, with each node assigned specific time slots for transmitting data to specific destinations. This segmentation eliminates resource contention by ensuring that only one node transmits to a particular destination at any given time slot, thereby reducing latency while maintaining high data transfer efficiency through full-duplex communication capabilities.
2Adaptability or versatility
If data is written into hub slots at different speeds based on node proximity and data volume, then data transfer flexibility is improved, but synchronization difficulty increases
Solution Approach 1:
The hub operates with periodic write and read phases at standardized speeds. Data from nodes at different distances is accommodated by scheduling writes during designated write phases and reads during designated read phases, with the hub buffer absorbing timing variations. This periodic operation maintains synchronization simplicity while allowing flexible data transfer adaptation to different node distances and data volumes.
Data Source
AI summary
Embodiments of the present disclosure generally relate to a cloud computing network, or datacenter network, and a method of transferring information among processing nodes in a cloud computing network or datacenter. The network may include a hub that is coupled to a plurality of nodes so that data is transferred between nodes through the hub. Data from different nodes may be written into a slot within the hub, read, and then written into a slot within the destination node. Due to the proximity of the nodes to the hub, or even due to the amount of data to be written, the data may be written at different clock phases. The read may occur one or more clock cycles after the data has been written into the hub.