Turbo Write Buffer Segmentation for Fast NVMe Storage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current storage devices face limitations in achieving fast write and read operations, particularly in nonvolatile memory systems, where existing technologies do not efficiently utilize buffer areas to enhance performance.

Innovation Solution

A storage device architecture that includes a nonvolatile memory device with distinct areas for turbo write and read operations, managed by a memory controller, which prioritizes data storage and movement between these areas to optimize performance through a turbo write buffer and user storage buffer configuration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a single buffer area is used for both turbo write and normal write operations, then device complexity is reduced, but write speed performance deteriorates

Engineering Contradiction:
Improvewrite speedVSAvoidbuffer area configuration
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The nonvolatile memory device is divided into multiple buffer areas (first buffer area and second buffer area) with different write speed capabilities. The first buffer area is configured for turbo write operations with higher write speeds, while the second buffer area is configured for normal write operations. This segmentation allows the system to achieve high write speeds when needed without compromising overall device complexity management.

Inventive Principle:
Principle #1Segmentation

2Productivity

If multiple buffer areas are implemented for different write speeds, then write speed performance is improved, but device complexity increases

Engineering Contradiction:
Improvewrite speedVSAvoidbuffer area configuration
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The memory controller dynamically selects which buffer area to use based on the write operation requirements. For turbo write operations, the controller directs data to the first buffer area, while for normal write operations, it uses the second buffer area. This dynamic allocation strategy enables the system to achieve high write speeds when needed while managing complexity through intelligent control rather than static configuration.

Inventive Principle:
Principle #15Dynamics

3Productivity

If data is preferentially written to the first buffer area for turbo operations, then turbo write performance is improved, but storage capacity utilization deteriorates

Engineering Contradiction:
Improveturbo write performanceVSAvoidstorage capacity utilization
Core Design Contradiction:
ProductivityVSQuantity of substance

Solution Approach 1:

The system implements partial action by providing a first buffer area specifically for turbo write operations rather than making the entire buffer area suitable for both turbo and normal operations. This allows the first buffer area to be optimized for high-speed writes, while the second buffer area handles normal writes, ensuring that storage capacity is efficiently utilized across different operation types without compromising turbo performance.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3772063A1Memory device including plurality of buffer areas for supporting fast write and fast read and storage device including the same
Publication Date: 2021.02.03 SAMSUNG ELECTRONICS CO LTD
  • EP3772063A1 patent drawingFigure 1
  • EP3772063A1 patent drawingFigure 2
  • EP3772063A1 patent drawingFigure 3

AI summary

A storage device includes a nonvolatile memory device that includes a first region including memory cells configured to store n-bit data and a second region including memory cells configured to store m-bit data and a memory controller, where n and m are natural numbers and n is less than m. The first region includes a first area and a second area, and the second region includes a third area. The memory controller is configured to perform one of a turbo write operation on the first area or the second area and a normal write operation on the third area, and configured to perform one of a turbo read operation on the first area or the second area and a normal read operation on the third area.