PCI-Express Scheduling Table Remapping for Compact Selection Engine
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industry-standard scheduling tables, such as those defined in the PCI-Express specification, impose restrictions on constructing high-speed and efficient scheduling circuitry for managing bandwidth allocation in data processing systems, leading to inefficient resource utilization and increased costs.
Innovation Solution
A data processing device with a first scheduling table for public access and a second, privately maintained scheduling table with a different data structure, allowing for a more compact and flexible selection engine to manage data stream selection, mimicking the public schedule while optimizing resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a protocol-specified scheduling table with a fixed data structure is used, then protocol compliance is maintained, but the complexity of constructing high-speed selection circuits increases and resource utilization becomes inefficient
Solution Approach 1:
The patent creates a copy of the protocol-specified scheduling table (first scheduling table) and maintains another copy with a different data structure (second scheduling table). The selection engine reads from the second scheduling table while presenting protocol-compliant scheduling decisions based on the first scheduling table, thus copying the protocol interface while using a more efficient internal structure.
Solution Approach 2:
The patent introduces a translation or mapping mechanism that acts as an intermediary between the protocol-specified scheduling table and the internally optimized scheduling table. This intermediary layer allows the system to comply with protocol requirements while utilizing a more efficient data structure for actual scheduling decisions.
2Reliability
If a protocol-specified scheduling table with a fixed data structure is used, then protocol compliance is maintained, but the bandwidth allocation efficiency decreases
Solution Approach 1:
The patent maintains a copy of the protocol-specified scheduling table for external compliance while using a different, more efficient data structure for internal bandwidth allocation decisions. This allows the system to present protocol-compliant scheduling behavior while achieving superior bandwidth allocation efficiency through the alternative data structure.
Solution Approach 2:
The patent changes the data structure parameters of the scheduling table from the protocol-specified format to a more efficient format. By modifying how scheduling information is stored and organized (parameter changes), the system achieves better bandwidth allocation efficiency while maintaining protocol compliance through appropriate translation.
3Productivity
If a more flexible scheduling data structure is used, then resource utilization improves and circuit complexity reduces, but protocol compliance may be compromised
Solution Approach 1:
The patent copies the protocol-specified scheduling table to maintain the required interface and compliance, while simultaneously maintaining a second scheduling table with a more flexible data structure for internal use. This dual-copy approach allows the system to benefit from improved resource utilization through the flexible structure while preserving protocol compliance through the standardized interface.
Solution Approach 2:
The patent segments the scheduling table functionality into separate components: one portion handles protocol compliance (first scheduling table) and another portion handles optimized internal scheduling (second scheduling table). This segmentation allows each component to be optimized independently for its specific purpose.
Data Source
AI summary
Public scheduling tables of PCI-Express network devices are remapped into private scheduling tables having different data structures. The private scheduling tables enable the construction of parallel-processing selection engines (ones with look-ahead selection capabilities) that are more compact in size than would have been possible with use of the data structures of the public scheduling tables. In one embodiment, residual weight values are re-shuffled so as to move each winner of an arbitration round away from a winner's proximity bar by a distance corresponding to an initial weight assigned to the winner. The initial weight can be proportional to the reciprocal of a bandwidth allocation assigned to each data source.