Memory Management via Data Migration Across Computing Resources

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The limited memory capacity of dedicated computing resources leads to performance degradation when processing tasks require greater storage space, necessitating data exchange between internal and external memory, resulting in increased time and overhead.

Innovation Solution

A method for managing memories by determining the access speed of computing resources, selecting a target resource with a higher access speed, and migrating data from a slower memory to a faster one, optimizing data storage and processing efficiency across multiple computing resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data is stored in external memory to expand storage capacity, then memory capacity is increased, but data access speed decreases

Engineering Contradiction:
Improvememory capacityVSAvoiddata access speed
Core Design Contradiction:
Quantity of substanceVSSpeed

Solution Approach 1:

The patent segments memory resources into multiple memory pools associated with different computing resources. Data is divided and stored across these segmented memory pools, allowing the system to select optimal storage locations that balance capacity and access speed requirements.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of memory management by creating a multi-dimensional memory pool structure where data can be stored across different computing resources and memory locations. This dimensional expansion allows the system to optimize both capacity and access speed by selecting appropriate dimensions for data placement.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If data is exchanged between internal and external memory, then storage flexibility is improved, but processing time increases

Engineering Contradiction:
Improvestorage flexibilityVSAvoidprocessing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-allocation and pre-positioning data in optimal memory locations before computing tasks execute. The memory management system proactively manages data placement, predicting future access patterns and positioning data in high-speed memory pools in advance, thereby reducing actual processing time during task execution.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a memory management system as an intermediary between computing resources and memory pools. This intermediary intelligently mediates data exchange operations, optimizing the balance between storage flexibility and access speed by selecting appropriate memory pools and managing data movement efficiently.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If data is migrated between memory pools, then data access efficiency is improved, but system complexity increases

Engineering Contradiction:
Improvedata access efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent creates a universal memory management framework that handles multiple computing resources and various memory pool types through a unified interface and set of operations. This universal approach simplifies the system by providing consistent data migration and access mechanisms across diverse hardware configurations, reducing overall system complexity despite the multi-pool architecture.

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

Data Source

PatentUS11106500B2Managing memories of computing resources based on data access speeds
Publication Date: 2021.08.31 EMC IP HLDG CO LLC
  • US11106500B2 patent drawing
  • US11106500B2 patent drawing
  • US11106500B2 patent drawing

AI summary

A method, apparatus and computer program product for managing memories of computing resources is disclosed. In the method, a computing task processed by a first computing resource in a group of computing resources is determined. In response to a second memory of a second computing resource other than the first computing resource in the group of computing resources being allocated to the computing task, a second access speed with which the first computing resource accesses the second memory is determined. A target computing resource is selected from the group of computing resources based on an access speed with which the first computing resource accesses a target memory of the target computing resource, where the access speed is higher than the second access speed. At least one part of data in the second memory is migrated to the target memory.