Universal PCIe Port for Flexible Blade Server Interconnects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing blade server chassis configurations are inflexible, leading to wasted resources and high costs due to limited slot configurations, which restrict the ability to independently scale and update server components, as they often require new chassis for added components and cannot easily accommodate different types of component cards.

Innovation Solution

A universal PCI Express (PCIe) port is introduced, allowing for symmetric acceptance of PCIe connections as both hosts and endpoints, enabling virtualization and decoupling of server components, allowing for independent scaling and configuration of hosts and I/O devices across a common infrastructure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If specialized hardware is used in the interconnect fabric to provide dedicated slots for specific component types, then communication performance and reliability are improved, but adaptability and flexibility are worsened

Engineering Contradiction:
Improvecommunication reliabilityVSAvoidslot configuration flexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The interconnect fabric is designed with universal slots that can accommodate any component type through a standardized interface. Each slot is equipped with detection circuitry that automatically identifies the inserted component and configures the appropriate communication protocol, enabling a single slot to serve multiple functions for different component types without requiring specialized hardware for each component category.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The interconnect fabric employs dynamic configuration capabilities where communication parameters, bandwidth allocation, and protocol selection are adjusted in real-time based on the detected component type. This dynamic adaptation allows the system to maintain optimal performance for each component while using a standardized physical interface, resolving the contradiction between specialized performance and general compatibility.

Inventive Principle:
Principle #15Dynamics

2Stability of the object's composition

If fixed slot configurations are implemented for specific component types, then system stability and performance optimization are improved, but adaptability and resource utilization are worsened

Engineering Contradiction:
Improvesystem stabilityVSAvoidcomponent configuration flexibility
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary detection and configuration actions when a component is inserted into a slot. The interconnect fabric automatically detects the component type, pre-configures the appropriate communication parameters, and establishes the optimal data path before normal operation begins. This preliminary setup ensures system stability while accommodating various component types without requiring fixed configurations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The interconnect fabric dynamically changes communication parameters such as data rate, protocol type, and bandwidth allocation based on the detected component characteristics. This parameter adaptation allows the system to maintain stable operation for each specific component type while using a universal slot interface, effectively resolving the contradiction between stability and adaptability.

Inventive Principle:
Principle #35Parameter changes

3Speed

If dedicated interconnect fabric hardware is used for each component type, then communication performance is improved, but device complexity and cost are worsened

Engineering Contradiction:
Improvecommunication speedVSAvoidinterconnect fabric complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent merges multiple specialized communication paths into a single unified interconnect fabric with dynamic routing capabilities. Instead of having separate dedicated hardware for each component type, the system combines all communication functions into one fabric that uses intelligent switching and protocol adaptation to achieve component-specific performance at a fraction of the complexity cost.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The interconnect fabric introduces an intermediary layer of protocol translation and adaptive routing between the universal slot interface and the actual communication channels. This intermediary mechanism enables high-speed communication tailored to each component type without requiring dedicated hardware for each component, thereby reducing overall system complexity while maintaining performance.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Reliability

If components are tightly coupled to specific chassis slots, then system reliability is improved, but ease of operation and scalability are worsened

Engineering Contradiction:
Improvesystem reliabilityVSAvoidcomponent scalability
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system segments the coupling between components and chassis by introducing a standardized interface layer that decouples the physical slot from the logical component assignment. This segmentation allows components to be independently inserted, removed, or replaced without affecting system reliability, as the interconnect fabric automatically reconfigures to maintain stable connections for all active components.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3042297B1Universal PCI express port
Publication Date: 2018.05.23 CISCO TECHNOLOGY INC
  • EP3042297B1 patent drawingFigure 1
  • EP3042297B1 patent drawingFigure 2
  • EP3042297B1 patent drawingFigure 3

AI summary

Methods and systems are disclosed herein for providing a universal PCIe port. In one example, the same port is configured to accept a PCIe connection as a host or an endpoint symmetrically. Downstream transactions towards an endpoint can be intercepted and a virtual address in the downstream transaction can be translated to a local address using a mapping. The downstream transactions can be forwarded to the endpoint using the local address instead of the virtual address. For endpoints that share the same local address with multiple hosts, a reverse lookup may be provided to determine which one of the hosts a local address corresponds when forwarding upstream transactions. PCIe over Ethernet is provided as one embodiment for allowing remote PCIe endpoints to be associated with a local host transparently.