Island-Based Network Flow Processor Scalability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network processors, such as the Intel IXP2800, face limitations in scalability and efficiency due to rigid architectures that do not effectively manage packet processing and memory access across multiple processing units, leading to bottlenecks in handling high-speed packet traffic.
Innovation Solution
The island-based network flow processor (IB-NFP) integrated circuit features a configurable mesh data bus with crossbar switches and distributed credit FIFO structures, allowing for flexible partitioning of functional circuitry into rectangular islands with a staggered layout, enabling efficient communication and resource management across multiple islands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a rigid architecture with fixed bus structure is used, then device complexity is reduced, but productivity decreases due to bottlenecks in handling high-speed packet traffic
Solution Approach 1:
The functional circuitry is partitioned into rectangular islands that are organized in a staggered fashion, with each island containing a portion of the mesh data bus. This segmentation allows multiple islands to perform simultaneous reads and writes across the configurable mesh data bus, thereby increasing packet processing throughput while managing complexity through modular organization
Solution Approach 2:
The mesh data bus is made configurable rather than fixed, allowing the system to adapt its structure dynamically. The bus can be configured to enable simultaneous access by multiple islands, transforming the rigid architecture into a flexible one that can optimize packet processing paths based on traffic requirements
2Productivity
If multiple processing units are added to increase processing power, then productivity improves, but device complexity increases due to rigid architecture limitations
Solution Approach 1:
The mesh data bus structure is designed to be universal and scalable, allowing additional processing islands to be added to the system. Each island follows the same rectangular structure with integrated bus portions, enabling seamless expansion of processing power while maintaining architectural consistency and avoiding rigidity
Solution Approach 2:
Each rectangular island contains a nested structure where functional circuitry is integrated with portions of the mesh data bus. This nesting allows processing units to be added in a hierarchical manner, with each new island integrating into the existing mesh structure without disrupting the overall architecture
3Productivity
If functional circuitry is partitioned into rectangular islands with staggered layout, then productivity increases through simultaneous operations, but device complexity increases due to mesh bus configuration
Solution Approach 1:
Each rectangular island is designed with local quality, containing its own portion of the mesh data bus and crossbar switch configured for its specific needs. This local configuration allows each island to perform operations independently while contributing to the overall simultaneous operations capability of the system
Data Source
AI summary
The functional circuitry of a network flow processor is partitioned into a number of rectangular islands. The islands are disposed in rows. A configurable mesh data bus extends through the islands. A first island includes a first memory and a first data bus interface. A second island includes a processor, a second memory, and a second data bus interface. The processor can issue a command for a target memory to do an action. If a field in the command has a first value then the target memory is the first memory, whereas if the field has a second value then the target memory is in the second memory. The command format is the same, regardless of whether the target memory is local or remote. If the target memory is remote, then a data bus bridge adds destination information before putting the command onto the global configurable mesh data bus.