Image Processor Block Packing Direction for Lower Memory Access

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing demand for high-resolution video images and high frame rates leads to increased data storage and memory access in image processing apparatuses, resulting in reduced processing performance and increased power consumption.

Innovation Solution

An image processor divides image data into blocks, compresses each block, and determines a packing direction for storage based on data size and start address, reducing memory access by packing blocks to the left or right of storage areas, thereby optimizing storage and retrieval operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If image data is compressed and stored in memory, then data storage capacity is improved, but power consumption increases due to compression and decompression operations

Engineering Contradiction:
Improvedata storage capacityVSAvoidpower consumption
Core Design Contradiction:
Quantity of substanceVSUse of energy by moving object

Solution Approach 1:

The image processor performs compression operations before storing data in memory, preparing the data in advance in a compressed state. This preliminary compression reduces the total volume of data that needs to be stored and transferred, ultimately reducing power consumption during read/write operations despite the initial compression energy cost

Inventive Principle:
Principle #10Preliminary action

2Productivity

If the amount of data to be stored in memory increases, then high-resolution and high frame rate image processing is improved, but processing performance degrades due to memory access limitations

Engineering Contradiction:
Improveimage processing throughputVSAvoidprocessing speed
Core Design Contradiction:
ProductivityVSSpeed

Solution Approach 1:

The image processor divides image data into multiple data blocks and processes them independently. Each block can be compressed, stored, and retrieved separately, allowing parallel processing and reducing memory access bottlenecks. This segmentation enables high-resolution and high frame rate processing by breaking down large data volumes into manageable units that can be handled more efficiently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts the compression level and data block size based on processing requirements. By changing parameters such as compression ratio and block dimensions, the system optimizes the balance between data storage efficiency and processing speed, maintaining high productivity while minimizing memory access delays

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If the number of memory accesses increases, then data retrieval flexibility is improved, but power consumption increases

Engineering Contradiction:
Improvedata retrieval flexibilityVSAvoidpower consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The image processor determines the packing direction of compressed data blocks in advance, before actual memory write operations. By pre-calculating the optimal storage layout based on anticipated retrieval patterns, the system reduces the need for subsequent memory reorganization operations, thereby reducing power consumption while maintaining retrieval flexibility

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11417026B2Operating method of image processor with varying packing directions, image processing apparatus with varied packing directions, and operating method of the image processing apparatus with the varied packing directions
Publication Date: 2022.08.16 SAMSUNG ELECTRONICS CO LTD
  • US11417026B2 patent drawing
  • US11417026B2 patent drawing
  • US11417026B2 patent drawing

AI summary

An operating method of an image processor includes dividing image data into a plurality of data blocks and compressing each of the plurality of data blocks. The operating method also includes determining a packing direction as a determined packing direction, in which a corresponding compressed data block of a plurality of compressed data blocks is to be stored, based on a data size of the corresponding compressed data block and a start address of a storage area where the corresponding compressed data block is to be stored among a plurality of storage areas of a memory. Each of the plurality of compressed data blocks is packed in a corresponding storage area among the plurality of storage areas of the memory based on the determined packing direction.