Subscription Matching Accelerator for Content Routing Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content routing technologies face scalability issues in handling large numbers of XPath subscriptions due to inefficient algorithms and lack of hardware implementation optimization, leading to suboptimal performance in matching XML documents.
Innovation Solution
A highly scalable content-routing method utilizing specialized hardware, such as ASICs or FPGAs, with an optimized NFA tree approach for evaluating value-based and nested predicates, enabling efficient subscription matching across content routers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If software-based algorithms are used for subscription matching, then implementation complexity is reduced, but processing speed and scalability deteriorate
Solution Approach 1:
The patent replaces software-based algorithmic processing with a hardware accelerator that uses specialized circuitry (FPGA/ASIC) to perform subscription matching. The hardware accelerator includes a finite state machine and lookup tables that directly process XML documents against subscription criteria, eliminating the need for complex software algorithms and achieving gigabit-per-second throughput.
2Device complexity
If existing content routing technologies are used, then system simplicity is maintained, but scalability to large numbers of subscriptions deteriorates
Solution Approach 1:
The patent segments the content router functionality by introducing a separate hardware accelerator module that handles subscription matching independently from the main routing processor. This accelerator contains specialized components including a finite state machine for parsing XML and lookup tables for efficient pattern matching, allowing the system to scale to large numbers of subscriptions without increasing overall system complexity.
3Ease of manufacture
If generic hardware platforms are used, then ease of manufacture is improved, but performance for specialized matching tasks deteriorates
Solution Approach 1:
The patent employs a reconfigurable hardware platform (FPGA) that can be dynamically configured for different subscription matching workloads. The hardware accelerator includes programmable finite state machines and lookup tables that can be adapted to handle various XML document structures and subscription criteria, providing high-performance specialized matching while maintaining flexibility for different applications.
Data Source
AI summary
A method of matching subscriptions to published documents in a content-routed network involves receiving subscription information, receiving published documents, storing the subscription information and the published documents in memory, instructing an accelerator of the locations in memory of the published documents, transferring portions of the stored published documents from the memory to the accelerator on an as-needed basis, providing the subscription information to the accelerator, and processing the portions in the accelerator to perform subscription matching in the accelerator independently of other functions in the content-router. The accelerator preferably includes a pipeline. In this way, efficiently highly scalable subscription matching can be performed efficiently on a very large number of subscriptions.