Single Architected Compression Instruction Using History Buffer

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing computing environments face inefficiencies in compression and decompression operations due to the need for multiple primitive software instructions, which increase program complexity and require task switches to I/O devices, leading to reduced performance.

Innovation Solution

A single architected instruction is used on a general-purpose processor to perform compression and decompression functions, utilizing a circular buffer for history storage, which reduces program complexity and eliminates the need for task switches by processing data within the processor.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple primitive software instructions are used to perform compression and decompression operations, then the operations can be performed on general-purpose processors, but the program complexity increases and execution time is extended

Engineering Contradiction:
Improvecompatibility with general-purpose processorsVSAvoidprogram complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple primitive software instructions into a single specialized compression/decompression instruction. This single instruction integrates the functionality of numerous individual instructions, reducing program complexity while maintaining compatibility with general-purpose processor architectures through standardized instruction set integration.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The invention creates a universal compression instruction that can perform both compression and decompression operations within a single instruction framework. This multi-functional instruction eliminates the need for separate instruction sequences for different compression tasks, reducing overall program complexity while maintaining versatility.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If multiple primitive software instructions are used to perform compression and decompression operations, then the operations can be performed, but the execution time is extended due to increased number of instructions

Engineering Contradiction:
Improveoperational capabilityVSAvoidexecution time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent combines multiple sequential instructions into a single integrated compression/decompression instruction. This merging reduces the total number of instruction cycles required, directly decreasing execution time while preserving the complete operational capability of the original multi-instruction sequence.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The instruction performs preliminary setup and configuration internally within the processor execution unit, eliminating the need for multiple separate instructions to prepare and execute compression operations. This preliminary action is embedded within the single instruction, reducing overall execution time.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If task switches are performed to I/O devices for compression and decompression operations, then specialized processing can be utilized, but the performance is reduced due to task switching overhead

Engineering Contradiction:
Improvespecialized processing capabilityVSAvoidprocessing performance
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent introduces an intermediary execution unit within the processor that handles compression and decompression operations. This intermediary component provides specialized processing capabilities while remaining integrated within the processor architecture, eliminating the need for task switches to external I/O devices and maintaining high processing performance.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The invention merges specialized compression processing capabilities directly into the processor's execution pipeline. By combining general-purpose processing with specialized compression functionality in a unified execution unit, the system achieves specialized processing performance without the overhead of task switching to separate I/O devices.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3918470B1Compression/decompression instruction specifying a history buffer to be used in the compression/decompression of data
Publication Date: 2024.10.16 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • EP3918470B1 patent drawingFigure 1A~1B
  • EP3918470B1 patent drawingFigure 2
  • EP3918470B1 patent drawingFigure 3A~3F

AI summary

An instruction to perform a function of a plurality of functions is obtained. The instruction is a single architected instruction of an instruction set architecture that complies to an industry standard for compression. The instruction is executed, and the executing includes performing the function specified by the instruction. The performing includes, based on the function being a compression function or a decompression function, transforming state of input data between an uncompressed form of the input data and a compressed form of the input data to provide a transformed state of data accessing. During performing the function, history relating to the function is accessed. The history is to be used in transforming the state of input data between the uncompressed form and the compressed form.