Inline Decode String Compare Micro-Operations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional string operations in computing environments, such as those using the z/Architecture, often require known string lengths and rely on microcode for instructions like Move String (MVST) and Compare Logical String (CLST), leading to increased latency and reduced performance due to microcode processing and boundary checks.

Innovation Solution

Implementing a computer program product that decodes instructions into sequences of operations to perform string operations without microcode processing, eliminating loops and boundary checks, allowing for concurrent processing of characters within specified memory boundaries, thereby reducing latency and improving system performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional string operations use microcode processing, then they can handle variable length termination semantics, but processing latency increases and system performance decreases

Engineering Contradiction:

Improvevariable length termination semanticsVSAvoidprocessing latency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent replaces microcode processing with a sequence of micro-operations that are executed directly in the instruction stream. This substitution eliminates the need to enter and exit microcode processing modes, thereby reducing processing latency while maintaining the ability to handle variable length termination semantics through the micro-operations sequence.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If string operations include boundary checks, then memory safety is ensured, but processing efficiency decreases due to additional checks and potential loops

Engineering Contradiction:

Improvememory safetyVSAvoidprocessing efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent segments the string operation into a sequence of micro-operations that process data in fixed-size chunks (e.g., 16 bytes at a time). Each micro-operation handles a specific portion of the data, and the sequence naturally manages boundary conditions through the segmented approach, eliminating the need for explicit boundary checks and loops while maintaining memory safety.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent loads data in fixed-size chunks that may extend beyond the actual string boundary. By using excessive action (loading more data than strictly necessary), the patent simplifies the processing logic and eliminates boundary checks, as the micro-operations can safely process the loaded data without needing to verify exact boundary conditions.

Inventive Principle:

Principle #16Partial or excessive action

3Adaptability or versatility

If looping instructions are used for string operations, then variable length strings can be processed, but system performance is reduced due to loop overhead

Engineering Contradiction:

Improvevariable length string processingVSAvoidsystem performance

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent segments the string processing into a sequence of micro-operations that collectively handle variable length strings without requiring a looping instruction. Each micro-operation processes a fixed portion of the data, and the sequence naturally adapts to variable length through the micro-operations themselves, eliminating loop overhead and improving system performance.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10564965B2Compare string processing via inline decode-based micro-operations expansion

Publication Date: 2020.02.18 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Compare string processing via inline decode-based micro-operations expansion. An instruction, which is to perform a compare string operation, is decoded. The decoding provides a sequence of operations to perform the compare string operation. The sequence of operations includes a first load to boundary operation to load a first set of data up to a specified boundary of memory and a second load to boundary operation to load a second set of data. The first set of data and the second set of data are loaded as part of the compare string operation.