Dual Relationship Hash Structure for Non-Volatile Memory Efficiency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The inefficiencies in memory structures built for conventional DRAM technology when used in non-volatile memories (NVMs) due to hardware architecture differences lead to suboptimal performance in NVMs.

Innovation Solution

The implementation of dual relationship-based hash structures, which involve creating multiple layers of storage components where at least one layer shares storage components with another, partitioning these components into slots, and configuring status value spaces for efficient storage and retrieval operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional DRAM memory structures are used in NVMs, then hardware architecture compatibility is maintained, but storage efficiency and performance deteriorate due to hardware architecture differences

Engineering Contradiction:

Improvehardware architecture compatibilityVSAvoidstorage efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The hash table is divided into multiple levels (primary hash table and secondary hash tables), where each level handles different aspects of storage. This segmentation allows the system to optimize for NVM characteristics while maintaining DRAM-compatible access patterns, resolving the contradiction between hardware compatibility and storage efficiency

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a multi-level hierarchical structure that adds a vertical dimension to the traditional flat hash table. By organizing storage components across multiple levels with different capacities, the system achieves better storage efficiency for NVMs while preserving the essential hash table interface for DRAM compatibility

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If traditional hash table structures are used, then implementation simplicity is maintained, but resizing operations become computationally expensive

Engineering Contradiction:

Improveimplementation simplicityVSAvoidresizing computational cost

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The patent pre-allocates multiple levels of storage components during table creation, preparing the hierarchical structure in advance. This preliminary action enables efficient resizing by simply activating or deactivating pre-configured levels rather than performing expensive reallocation operations, reducing both computational cost and time loss

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The multi-level hash table structure allows dynamic adjustment of storage capacity by selectively using different levels. When resizing is needed, the system can dynamically transition between levels without complete rehashing, maintaining implementation simplicity while dramatically reducing resizing computational cost

Inventive Principle:

Principle #15Dynamics

3Stability of the object's composition

If storage components are dedicated to single layers, then layer independence is maintained, but storage efficiency deteriorates due to unused capacity in each layer

Engineering Contradiction:

Improvelayer independenceVSAvoidstorage efficiency

Core Design Contradiction:

Stability of the object's compositionVSProductivity

Solution Approach 1:

Storage components are designed to serve multiple levels universally. Each storage component can be shared across different levels of the hash table hierarchy, allowing the same physical storage to fulfill multiple logical roles. This multi-functionality achieves high storage efficiency while maintaining layer independence through logical separation

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Productivity

If NVM-specific structures are implemented, then storage efficiency improves, but hardware architecture compatibility with DRAM deteriorates

Engineering Contradiction:

Improvestorage efficiencyVSAvoidhardware architecture compatibility

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The multi-level hash table structure acts as an intermediary layer between the DRAM-compatible interface and the NVM-optimized storage backend. It translates DRAM-style access patterns into NVM-efficient storage operations, achieving both hardware compatibility and improved storage efficiency simultaneously

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11500815B2Dual relationship-based hash structure for non-volatile memory technology

Publication Date: 2022.11.15 EMC IP HLDG CO LLC

AI summary

Methods, apparatus, and processor-readable storage media for implementing dual relationship-based hash structures for non-volatile memory technology are provided herein. An example computer-implemented method includes generating a hash storage structure by: creating multiple layers of storage components, wherein a first layers comprise a first number of storage components and at least a second layer comprises at least a second number of storage components less than the first number of storage components; configuring the at least a second layer to share at least a portion of the storage components therein with at least a portion of the storage components in the first layer; partitioning each of the storage components in each of the multiple layers into multiple portions; configuring a respective status value space for each of the multiple portions of each of the storage components in the multiple layers; and implementing the hash storage structure in at least one storage system.