IP Addressable Memory Blocks for Scalable Shared Memory

Solution Overview

Problem

Current systems for shared memory among networked devices are limited by high latency and low throughput, as they rely on traditional hard disk storage for page faults, which can lead to inefficient CPU usage and reduced system performance.

Innovation Solution

The implementation of IP addressable memory blocks using IPv6 and Remote Direct Memory Access (RDMA) over Converged Ethernet (RoCEv2) enables direct memory access across the network, leveraging Border Gateway Protocol (BGP) for scalable memory allocation and management, allowing applications to access remote memory with low latency and high throughput.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional hard disk storage is used for page faults, then memory sharing among networked devices is enabled, but latency increases and throughput decreases

Engineering Contradiction:

Improvememory sharing capabilityVSAvoidlatency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical hard disk storage system with a network-based direct memory access system using RoCEv2 and RDMA technology. This substitution eliminates the mechanical limitations of hard disks by using network infrastructure to directly access remote memory, achieving latency comparable to or better than local memory while enabling shared memory across networked devices.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary network layer with specific protocols (RoCEv2, RDMA) that mediates between the application's memory access requests and the physical memory locations. This intermediary enables efficient memory sharing by providing standardized access mechanisms while maintaining low latency through direct memory access bypassing traditional storage bottlenecks.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If traditional hard disk storage is used for page faults, then memory sharing is achieved, but throughput is reduced

Engineering Contradiction:

Improvememory sharing capabilityVSAvoidthroughput

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces the mechanical hard disk storage system with a network-based direct memory access system using RoCEv2 and RDMA technology. This substitution eliminates the mechanical limitations of hard disks by using network infrastructure to directly access remote memory, achieving latency comparable to or better than local memory while enabling shared memory across networked devices.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary network layer with specific protocols (RoCEv2, RDMA) that mediates between the application's memory access requests and the physical memory locations. This intermediary enables efficient memory sharing by providing standardized access mechanisms while maintaining low latency through direct memory access bypassing traditional storage bottlenecks.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If IPv4 addressing is used, then network connectivity is provided, but memory scalability is limited due to address space constraints

Engineering Contradiction:

Improvenetwork connectivityVSAvoidmemory scalability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent changes the addressing parameter from IPv4's 32-bit address space to IPv6's 128-bit address space. This parameter change provides sufficient address space to directly address any arbitrary byte in memory on 64-bit systems, enabling memory addressable by IP to scale with modern memory capacities while maintaining network connectivity.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11675510B2Systems and methods for scalable shared memory among networked devices comprising IP addressable memory blocks

Publication Date: 2023.06.13 ZHAO XIAOLIANG

AI summary

Systems and methods for scalable shared memory among networked devices comprising IP addressable memory blocks is disclosed. The disclosed systems and methods comprise a communications network, one or more memory lending devices, each comprising one or more allocated and/or available uniformly sized blocks of memory remotely lendable over the communications network, wherein each of the one or more blocks of memory are uniquely addressable over the communications network using an Internet Protocol (IP) destination address. The systems and methods comprise further comprise at least one memory borrowing device comprising one or more remote blocks of memory allocated (loaned) thereto, wherein the at least one memory borrowing device is configured to individually access each of the one or more remote blocks of memory allocated thereto over the communications network using a unique Internet Protocol (IP) destination address.