Connection State Compression Using Block-Sector Bitmap Encoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In connection-oriented network architectures, the limited system memory bandwidth restricts the efficient storage and retrieval of connection states, particularly when using off-chip memory like DRAM, which can become a bottleneck in system performance.

Innovation Solution

A method and system for compressing connection state information by partitioning input bitmaps into blocks and sectors, generating block and sector information sequences, and encoding sectors using run-length encoding or raw formats to minimize bandwidth requirements for storage and retrieval.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If connection state data is stored in system memory without compression, then data integrity and accessibility are maintained, but memory bandwidth consumption increases

Engineering Contradiction:
Improvedata integrityVSAvoidmemory bandwidth consumption
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The connection state bitmap is divided into multiple blocks, and each block is further divided into sectors. This segmentation allows the system to process and compress data in manageable units, applying different compression strategies to different segments based on their characteristics.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies run-length encoding to transform the representation of connection state data. By encoding sequences of identical bits (0s or 1s) as length-value pairs, the system changes the parameter representation from individual bits to compressed tuples, significantly reducing the amount of data that needs to be stored and transmitted while maintaining complete information for reconstruction.

Inventive Principle:
Principle #35Parameter changes

2Loss of energy

If connection state data is compressed using run-length encoding, then memory bandwidth consumption is reduced, but processing complexity increases

Engineering Contradiction:
Improvememory bandwidth consumptionVSAvoidprocessing complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

By dividing the bitmap into blocks and sectors, the patent limits the scope of run-length encoding to smaller, manageable units. This segmentation reduces the complexity of processing each individual block while maintaining overall compression effectiveness across the entire connection state data structure.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The run-length encoding process automatically identifies and compresses sequences of identical bits without requiring complex external processing. The encoding algorithm itself serves to both analyze and compress the data, reducing the need for additional processing steps and simplifying the overall system architecture.

Inventive Principle:
Principle #25Self-service

3Quantity of substance

If off-chip memory is used to store connection states, then storage capacity is increased, but system performance becomes bottlenecked by memory bandwidth

Engineering Contradiction:
Improvestorage capacityVSAvoidsystem performance
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The patent applies run-length encoding to dramatically reduce the amount of data that needs to be transferred between off-chip memory and the processing units. By transforming the data representation from uncompressed bitmaps to compressed encoded sequences, the system maintains large storage capacity while minimizing the bandwidth requirements for memory access, thereby eliminating the performance bottleneck.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4300830A1Data compression engine
Publication Date: 2024.01.03 GOOGLE LLC
  • EP4300830A1 patent drawingFigure 1
  • EP4300830A1 patent drawingFigure 2
  • EP4300830A1 patent drawingFigure 3

AI summary

Compressing connection state information for a network connection including receiving an input bitmap having a sequence of bits describing transmit states and receive states; partitioning the input bitmap into a plurality of equal size blocks; partitioning each of the blocks into a plurality of equal sized sectors; generating a block valid sequence indicating the blocks having at least one bit set; generating, for each block having at least one bit set, a sector information sequence, the sector information sequence indicating, for the corresponding block, the sectors that have at least one bit set and an encoding type for each sector; and generating one or more symbols by encoding each sector that has at least one bit set.