Task Execution Management Optimizing Cache Hit Rates

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing task scheduling techniques reduce cache hit rates when the ratio of data capacity to cache size is high, even if tasks with overlapping memory access regions are continuously executed.

Innovation Solution

A task execution management system that divides tasks based on cache size and classifies them by data reference ranges, determining an execution order within groups to optimize cache usage and maintain a high cache hit rate.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If tasks with overlapping memory access regions are continuously executed, then task processing efficiency is improved, but cache hit rate deteriorates when data capacity to cache size ratio is high

Engineering Contradiction:

Improvetask processing efficiencyVSAvoidcache hit rate

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent divides tasks into multiple subtasks based on cache size, ensuring that each subtask's data access pattern fits within the cache capacity. This segmentation prevents cache overflow and maintains high cache hit rates while still allowing continuous execution of multiple subtasks, thereby resolving the contradiction between processing efficiency and cache performance

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent dynamically adjusts task execution parameters by dividing tasks according to cache size and determining optimal execution orders. By changing the granularity of task execution from whole tasks to cache-sized subtasks, the system maintains both high processing efficiency and cache hit rates

Inventive Principle:

Principle #35Parameter changes

2Reliability

If tasks are divided and classified by data reference ranges, then cache efficiency is improved, but system complexity increases

Engineering Contradiction:

Improvecache efficiencyVSAvoidtask management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments tasks into subtasks with defined data reference ranges that correspond to cache sizes. This segmentation provides a systematic approach to managing task complexity while improving cache efficiency, as each subtask can be independently managed and executed

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different execution strategies to different groups of subtasks based on their data reference ranges. By classifying subtasks into groups and determining execution orders specific to each group, the system optimizes cache efficiency locally for each group while maintaining overall system manageability

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11556377B2Storage medium, task execution management device, and task execution management method

Publication Date: 2023.01.17 FUJITSU LTD

AI summary

A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process includes acquiring first multiple tasks; dividing each task in the first multiple tasks in accordance with a cache size; classifying second multiple tasks in accordance with a range of data to be referred to at a time of execution of each task in the second multiple tasks that have been obtained by the dividing; and determining an execution order of tasks in a group for each group that has been obtained by the classifying.