Multi-processor Flash Storage with Dedicated RAM and Bus Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current Flash-based storage systems face performance bottlenecks due to single processor management over a shared bus, leading to slower data management speeds and limited scalability for robust systems, as well as RAM and bus contentions that hinder high-performance operations.

Innovation Solution

A distributed architecture for Flash storage devices with multiple microprocessor units, each having dedicated RAM and bus connections to Flash configurations, managed by a dataflow controller to optimize access and reduce contention, allowing for independent operation and improved performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single processor manages Flash storage over a shared bus, then device complexity is reduced, but data management speed and scalability deteriorate

Engineering Contradiction:
Improveprocessor architectureVSAvoiddata management speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent divides the single processor into multiple microprocessor units (MPUs), each capable of independently managing Flash storage operations. This segmentation allows parallel processing of data management tasks, thereby increasing data management speed while distributing the complexity across multiple simpler units rather than one complex processor.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-dimensional processing model (one processor) to a multi-dimensional parallel processing architecture. Multiple MPUs operate simultaneously on different data blocks, utilizing temporal and spatial parallelism to enhance throughput without proportionally increasing bus complexity.

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

2Device complexity

If a shared bus is used for processor access to Flash memory, then device complexity is reduced, but bus contention and performance degradation occur

Engineering Contradiction:
Improvebus architectureVSAvoidperformance consistency
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The shared bus architecture is segmented into multiple dedicated buses, with each MPU having its own private bus connection to Flash memory. This eliminates bus contention by providing multiple independent data pathways, ensuring consistent performance even under high utilization conditions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a bus arbitration mechanism that acts as an intermediary to manage access requests from multiple MPUs to the Flash memory. This mediator coordinates bus usage to prevent conflicts and maintain reliable performance across the system.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Device complexity

If RAM is shared among multiple processors, then device complexity is reduced, but RAM contention and data management speed deteriorate

Engineering Contradiction:
Improvememory architectureVSAvoiddata management speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The shared RAM is divided into dedicated memory regions assigned to each MPU. Each microprocessor unit has its own private RAM space for storing data blocks and management information, eliminating contention while maintaining overall system coherence through coordinated access protocols.

Inventive Principle:
Principle #1Segmentation

4Quantity of substance

If Flash memory is written frequently, then data storage capacity is improved, but mean time before failure deteriorates

Engineering Contradiction:
Improvestorage capacityVSAvoidmean time before failure
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The Flash memory is divided into multiple data blocks that can be independently managed. When one block becomes full or worn, the system can switch to another block, distributing write operations across multiple segments. This extends the overall lifespan of the Flash memory while maintaining full storage capacity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements a wear-leveling strategy where Flash blocks are discarded (marked as full or worn) and later recovered (erased and reused) in a rotated fashion. This allows the system to continuously utilize full storage capacity while distributing wear evenly across all blocks, thereby extending mean time before failure.

Inventive Principle:
Principle #34Discarding and recovering

Data Source

PatentUS7882320B2Multi-processor flash memory storage device and management system
Publication Date: 2011.02.01 INTELLECTUAL VENTURES II LLC
  • US7882320B2 patent drawing
  • US7882320B2 patent drawing
  • US7882320B2 patent drawing

AI summary

A data storage device has a host controller interface, a plurality of microprocessor units each having a portion of random access memory (RAM) dedicated thereto, a plurality of Flash device configurations each having dedicated bus connections to individual ones or multiples of the microprocessor units, and a dataflow controller accessible to the host controller interface for managing access to the Flash device configurations.