Multi-Packet Sliding Window Scheduling for Input-Queued Switches
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing switching algorithms for input-queued crossbar switches struggle to compute high-quality matchings in a short time frame, leading to suboptimal throughput and queueing delays, particularly in high-speed networking environments.
Innovation Solution
A sliding window scheduling method and system, such as SW-QPS and SW-iSLIP, that utilize bitmap operators and distributed parallelization hardware to achieve O(1) time complexity per matching computation, enabling efficient packet scheduling through queue-proportional sampling and first-fit-accepting policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional switching algorithms are used to compute matchings, then high-quality matchings can be achieved, but the time complexity is too high to complete computation within a short time slot
Solution Approach 1:
The patent segments the matching computation into multiple iterations, where each iteration refines the matching solution. The algorithm performs a series of proposal and acceptance phases, breaking down the complex O(N^2) computation into smaller O(N) steps that can be executed within the time slot constraint while progressively improving matching quality.
Solution Approach 2:
The patent uses preliminary action by pre-computing availability information and queue lengths before the matching computation. Input ports prepare proposal messages with pre-calculated data, and output ports pre-process acceptance criteria, allowing the actual matching algorithm to run faster within the time slot by working with pre-prepared information.
2Loss of time
If switching algorithms are optimized for fast computation, then time complexity is reduced, but the quality of matchings deteriorates resulting in suboptimal throughput and queueing delays
Solution Approach 1:
The patent implements feedback mechanisms where output ports send acceptance messages back to input ports based on their buffer status and matching preferences. This feedback loop allows the system to adjust and improve matchings iteratively, achieving high-quality results that maximize throughput while maintaining fast computation through the structured proposal-acceptance protocol.
Solution Approach 2:
The patent introduces dynamics by allowing the matching computation to adapt during the time slot based on real-time queue conditions. The algorithm dynamically adjusts which packets are matched and in what order, rather than using a static predetermined scheme, enabling the system to respond to changing traffic patterns and maintain high throughput.
3Ease of operation
If a one-to-one matching is computed for each time slot, then packet routing is controlled, but the scheduling efficiency is insufficient to handle high-speed networking environments
Solution Approach 1:
The patent merges multiple scheduling decisions into a single coordinated matching computation. By combining the proposal generation from multiple input ports and the acceptance decisions from multiple output ports into a unified iterative process, the system achieves both fine-grained control over individual packet routing and high overall scheduling efficiency suitable for high-speed networks.
Data Source
AI summary
An exemplary sliding window scheduling method and system are disclosed. The exemplary sliding window scheduling method and system can schedule multiple packets in a given scheduling frame with a sliding window scheduling frame. The scheduling operation can be performed using bitmap operators and can achieve a lowest time complexity of O(1) per matching computation and per port using distributed parallelization hardware. The exemplary sliding window scheduling method and system can be performed in the context of a queue-proportional scheduler (QPS) as well as iSLIP. In alternative embodiments, the SW-QPS operation can be performed in a batching window rather than in a sliding window.