Column-Aware Memory Scrambling for Balanced Power and Wear

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing memory architectures face challenges in adapting column-based I/O operations due to row-based scrambling schemes, leading to inefficient power consumption and uneven wear on bit locations, which are not addressed by existing technologies such as US2009/0323942A1, US2012/0265928A1, US2013/0018934A1, US2016/0321000A1, US2018/0074791A1, US2019/0227808A1, WO2009/088920A1, and US2017/090764A1.

Innovation Solution

Implementing column-aware scrambling and descrambling techniques using a linear function of row and column indices, specifically through a linear-feedback shift register (LFSR) function, allowing simultaneous scrambling and descrambling of data in columns without executing row-based algorithms per entry, thereby optimizing power consumption and wear distribution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If row-based scrambling schemes are used, then scrambling functionality is provided, but column-based I/O operations become inefficient and power consumption becomes uneven

Engineering Contradiction:
Improvecolumn-based I/O operation supportVSAvoidpower consumption efficiency
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent applies local quality by making the scrambling scheme adaptive to the specific I/O operation type. Column-aware scrambling detects whether a column-based I/O operation is being performed and applies the appropriate scrambling method (column-based vs. row-based) locally to that operation, rather than universally applying row-based scrambling to all operations.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements dynamics by making the scrambling behavior dynamic and context-dependent. The scrambling scheme dynamically switches between row-based and column-based approaches based on the detected operation type, allowing the system to adapt its scrambling strategy in real-time to match the I/O operation being performed.

Inventive Principle:
Principle #15Dynamics

2Adaptability or versatility

If row-based scrambling schemes are used, then scrambling functionality is provided, but wear distribution on bit locations becomes uneven

Engineering Contradiction:
Improvecolumn-based I/O operation supportVSAvoidwear distribution uniformity
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies local quality by making the scrambling scheme adaptive to the specific I/O operation type. Column-aware scrambling detects whether a column-based I/O operation is being performed and applies the appropriate scrambling method (column-based vs. row-based) locally to that operation, rather than universally applying row-based scrambling to all operations.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent applies parameter changes by modifying the scrambling parameters (scrambler seed, scrambler polynomial) based on the detected operation type. When column-based I/O is detected, the system changes the scrambling parameters to those optimized for column operations, ensuring uniform wear distribution specific to the column access pattern.

Inventive Principle:
Principle #35Parameter changes

3Ease of manufacture

If row-based scrambling schemes are used, then simple scrambling implementation is achieved, but simultaneous column-based scrambling and descrambling is inefficient

Engineering Contradiction:
Improvescrambling implementation simplicityVSAvoidcolumn operation throughput
Core Design Contradiction:
Ease of manufactureVSProductivity

Solution Approach 1:

The patent applies segmentation by dividing the scrambling implementation into distinct column-based and row-based pathways. The column-aware scrambling logic segments the operation flow to detect column-based I/O operations and route them through the optimized column scrambling path, which enables simultaneous scrambling and descrambling operations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamics by making the scrambling behavior dynamic and context-dependent. The scrambling scheme dynamically switches between row-based and column-based approaches based on the detected operation type, allowing the system to adapt its scrambling strategy in real-time to match the I/O operation being performed.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3910481B1Technologies for performing column architecture-aware scrambling
Publication Date: 2025.08.27 INTEL CORP
  • EP3910481B1 patent drawingFigure 1
  • EP3910481B1 patent drawingFigure 2
  • EP3910481B1 patent drawingFigure 3~4

AI summary

Technologies for scrambling functions in a column-addressable memory architecture includes a device having a memory and a circuitry. The memory includes a matrix storing individually addressable bit data, and the matrix is formed by rows and columns. The circuitry is to receive a request to perform a write operation of one or more bit values to one of the columns. The circuitry is further to determine a scrambler state at each location of the column, the location corresponding to a respective row and column index. The scrambler state is indicative of a function used to determine a value at the respective column location. Each of the bit values is scrambled as a function of the scrambler state for the respective column location and written thereto.