CXL Device Reassignment with Error Record Transfer Across Hosts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Dynamic reassignment of Compute Express Link (CXL) devices between multiple host systems introduces challenges for system-level reliability and fault management in high-performance computing environments.

Innovation Solution

A mechanism for reassigning CXL devices between hosts while maintaining fault awareness by retrieving and transferring error records using management controllers and firmware-managed storage, ensuring seamless fault context transfer across host boundaries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If CXL devices are dynamically reassigned between multiple host systems to maximize utilization and flexibility, then resource utilization and system flexibility are improved, but system-level reliability and fault management become more difficult

Engineering Contradiction:

Improvedevice reassignment flexibilityVSAvoidsystem-level reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies preliminary action by retrieving error records from the first host's firmware-managed storage before the CXL device is reassigned to the second host. The management controller triggers a firmware routine to obtain diagnostic information in advance, ensuring fault context is transferred proactively rather than reactively. This prevents loss of fault awareness during dynamic reassignment while maintaining system flexibility.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If CXL devices are dynamically reassigned between multiple host systems, then resource utilization is improved, but fault management and error tracking become more complex

Engineering Contradiction:

Improveresource utilizationVSAvoidfault management complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a management controller as an intermediary component that coordinates fault information transfer during device reassignment. The management controller receives reassignment notifications, triggers firmware routines to retrieve error records, and facilitates communication between the first and second hosts. This intermediary approach simplifies fault management by centralizing the coordination of diagnostic information transfer.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent implements feedback mechanisms where the management controller receives notifications about CXL device reassignment events, triggers appropriate firmware routines to retrieve and transfer error records, and ensures fault context is maintained. This feedback loop enables continuous monitoring and tracking of device status across host boundaries, making fault management more manageable despite dynamic reassignment.

Inventive Principle:

Principle #23Feedback

3Speed

If CXL devices are reassigned without transferring error records, then reassignment speed is improved, but fault awareness is lost and silent failures may occur

Engineering Contradiction:

Improvereassignment speedVSAvoidfault context loss

Core Design Contradiction:

SpeedVSLoss of information

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250363068A1Apparatus and first and second management controllers

Publication Date: 2025.11.27 INTEL CORP

AI summary

Provided is an apparatus comprising interface circuitry, machine-readable instructions and processing circuitry to execute the machine-readable instructions. The machine-readable instructions include instructions to receive a request to reassign a CXL device from a first host to a second host. The machine-readable instructions include instructions to transmit, to a first management controller of the first host, a request for retrieving an error record of the CXL device. The machine-readable instructions include instructions to receive, from the first management controller, the error record. The machine-readable instructions include instructions to transmit, to a second management controller of a second host, a request for storing the error record of the CXL device. The machine-readable instructions include instructions to bind the CXL device to the second host after receiving a confirmation indicating successful storing of the error record at the second host.