Processor Settings API for Adaptive Job Scheduling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing job scheduling systems in data centers often fail to efficiently utilize computing resources, leading to suboptimal use of time and resources for job execution.

Innovation Solution

A processor management system that uses an application programming interface (API) to configure processors based on job characteristics, such as performance preferences and priorities, to optimize resource allocation and scheduling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional job scheduling is used based on priority levels, then jobs can be scheduled according to importance, but computing resources are not efficiently utilized

Engineering Contradiction:

Improvejob execution efficiencyVSAvoidresource allocation flexibility

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts processor settings (clock frequency, voltage, power states) based on real-time job characteristics and system conditions. The job scheduler continuously monitors and reconfigures processor parameters during job execution, transforming static scheduling into adaptive dynamic resource management that optimizes both productivity and adaptability

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The invention changes multiple processor parameters simultaneously (frequency, voltage, power state, core allocation) based on job requirements. By adjusting these parameters in combination rather than using fixed priority levels, the system achieves efficient resource utilization while maintaining flexibility to handle diverse job types

Inventive Principle:

Principle #35Parameter changes

2Use of energy by moving object

If processor settings are fixed, then system stability is maintained, but computing resource efficiency is reduced

Engineering Contradiction:

Improvepower consumption efficiencyVSAvoidprocessor configuration complexity

Core Design Contradiction:

Use of energy by moving objectVSDevice complexity

Solution Approach 1:

The system implements feedback loops where processor performance metrics and power consumption data are continuously monitored and fed back to the job scheduler. This feedback enables automatic adjustment of processor settings to optimize power efficiency while managing complexity through closed-loop control rather than manual configuration

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The processor management system automatically configures and adjusts processor settings without external intervention. The job scheduler autonomously monitors system state, selects appropriate processor configurations, and applies optimizations, enabling the system to self-manage its own resource allocation and power efficiency

Inventive Principle:

Principle #25Self-service

3Productivity

If processor settings are customized for each job, then performance is optimized, but system complexity increases

Engineering Contradiction:

Improvejob performanceVSAvoidscheduling system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of job characteristics when jobs are submitted to the scheduler. By pre-configuring processor settings based on job type and requirements before execution begins, the system optimizes performance without adding runtime complexity, as the configuration work is done in advance

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250321750A1Application programming interface to identify settings to configure a processor

Publication Date: 2025.10.16 NVIDIA CORP

AI summary

Apparatuses, systems, and techniques to perform an application programming interface (API) to identify processor settings to be used when performing one or more software workloads. As an example, one or more processors comprising one or more circuits perform an API to identify processor settings to be used to configure processors assigned to perform a software workload based, at least in part, on one or more processors to be used.