Automated Network-on-Chip Layout Generation via Grid Projection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The complexity of designing efficient Network-on-Chip (NoC) layouts for System-on-Chips (SoCs) with user-specified topological constraints is challenging due to scalability limitations and sub-optimal designs resulting from manual processes, which often lead to inefficient interconnect architectures.

Innovation Solution

An automated method for generating optimal NoC layouts by projecting NoC elements onto a grid layout based on user-specified topological information, enabling selective enabling and disabling of routers, nodes, and links to minimize turns and optimize resource usage, while allowing for traffic mapping and configuration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual design methods are used for NoC layouts, then design flexibility is maintained, but design efficiency and optimality deteriorate

Engineering Contradiction:

Improvedesign efficiencyVSAvoiddesign complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs automatic NoC layout generation where the design tool itself carries out the layout optimization process without requiring manual intervention. The automated algorithm projects application nodes onto a grid, determines optimal router placements, and generates the complete NoC layout, making the design process self-executing and highly efficient

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical design processes with an automated computational system. Instead of designers manually placing routers and configuring connections, a software algorithm automatically performs the layout generation by projecting application nodes onto a grid and determining optimal router placements based on traffic patterns and topological constraints

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If traditional manual design processes are used, then design control is maintained, but layout optimality and performance deteriorate

Engineering Contradiction:

Improvelayout optimalityVSAvoiddesign time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary projection of application nodes onto a grid layout before final router placement. By pre-determining the positions of application nodes and their traffic patterns, the system prepares the foundation for optimal router placement, ensuring that the final layout is both optimal and generated quickly without iterative manual adjustments

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces time-consuming manual design iterations with an automated algorithm that quickly computes the optimal NoC layout. The system substitutes manual trial-and-error design processes with a computational approach that directly generates optimized layouts based on application node projections and traffic analysis

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If manual NoC layout design is performed, then customization is possible, but resource utilization and scalability deteriorate

Engineering Contradiction:

ImprovescalabilityVSAvoidinterconnect complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system provides a universal automated design framework that can handle various NoC configurations, topologies, and application types through a single integrated tool. The same core algorithm that projects nodes onto a grid can be applied to different application scenarios, making the design process scalable and adaptable without requiring separate manual design procedures for each case

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces manual customization processes with an automated system that adapts to different requirements through algorithmic configuration. Instead of manually redesigning NoC layouts for different scalability requirements, the system uses automated projection and placement algorithms that can be configured to generate layouts suitable for various scales and complexities

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10050843B2Generation of network-on-chip layout based on user specified topological constraints

Publication Date: 2018.08.14 INTEL CORP

AI summary

In an aspect, the present disclosure provides a method that comprises automatic generation of a NoC from specified topological information based on projecting NoC elements of the NoC onto a grid layout. In an aspect, the specified topological information, including specification of putting constraints on positions/locations of NoC elements and links thereof, can be input by a user in real space, and can then be projected on the grid layout.