CPU Core State Migration to Spare Core

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Modern processors face downtime and processing delays when a core enters an inoperable state, requiring resets, power cycles, or physical replacements, which can be time-consuming and disruptive.

Innovation Solution

The method involves detecting when a core stops committing instructions, disabling it from further processing, and transferring its data to a spare core, allowing the spare core to resume processing the instructions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a core enters an inoperable state and requires reset or power cycle to recover, then the core can resume processing, but system downtime and processing delays increase

Engineering Contradiction:
Improvecore recovery capabilityVSAvoidsystem downtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-positions a spare core in standby mode before the primary core fails. When the primary core enters an inoperable state, the spare core is already prepared to immediately take over processing tasks, eliminating the downtime associated with reset or power cycle operations. This preliminary preparation of backup resources directly resolves the contradiction between ensuring core recovery capability and minimizing system downtime.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If a core is reset to exit stalled state, then the core can continue execution, but other processor cores waiting on output experience delays

Engineering Contradiction:
Improvecore execution continuityVSAvoidprocessor throughput
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent creates a copy of the processor state from the inoperable core and transfers it to a spare core. This copying mechanism allows the spare core to assume the exact execution context of the failed core, enabling other cores that were waiting on output to continue receiving data without delays. The state copy ensures execution continuity while maintaining processor throughput, resolving the contradiction between core reliability and system productivity.

Inventive Principle:
Principle #26Copying

3Reliability

If physical damage occurs to a core, then the core must be replaced, but system downtime extends until replacement is complete

Engineering Contradiction:
Improvesystem operational statusVSAvoidsystem unavailability
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent maintains a spare core in standby mode as a pre-prepared replacement resource. When physical damage occurs to the primary core, the system can immediately switch to the spare core without waiting for replacement or repair operations. This preliminary preparation of backup hardware eliminates system unavailability time while ensuring continuous operational status, directly resolving the contradiction between maintaining system reliability and minimizing downtime during hardware replacement.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12277041B2Method for migrating CPU state from an inoperable core to a spare core
Publication Date: 2025.04.15 ORACLE INT CORP
  • US12277041B2 patent drawing
  • US12277041B2 patent drawing
  • US12277041B2 patent drawing

AI summary

An apparatus is disclosed in which the apparatus may include a plurality of cores, including a first core, a second core and a third core, and circuitry coupled to the first core. The first core may be configured to process a plurality of instructions. The circuitry may be may be configured to detect that the first core stopped committing a subset of the plurality of instructions, and to send an indication to the second core that the first core stopped committing the subset. The second core may be configured to disable the first core from further processing instructions of the subset responsive to receiving the indication, and to copy data from the first core to a third core responsive to disabling the first core. The third core may be configured to resume processing the subset dependent upon the data.