Heterogeneous Multi-Core Processor Thermal Management via Workload Reallocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Portable computing devices (PCDs) face thermal management challenges due to limited space, where heterogeneous processing components require efficient thermal energy management without impacting performance, as existing methods like shutting down components can render devices inoperable and affect quality of service (QoS).
Innovation Solution
A method and system that monitor temperature readings of individual processing cores in a heterogeneous multi-core processor, track workloads, and allocate or reallocate workloads based on comparative analysis of performance curves to manage thermal energy generation, optimizing power consumption and preventing overheating.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Temperature
If workload is reallocated across heterogeneous processing cores based on performance curve comparison, then thermal energy generation is managed efficiently, but system complexity increases due to monitoring and analysis requirements
Solution Approach 1:
The system continuously monitors temperature readings from multiple processing cores and uses this feedback to dynamically compare performance curves and reallocate workloads. Temperature sensors provide real-time data to the thermal management system, which adjusts workload distribution based on current thermal conditions and core performance characteristics, creating a closed-loop control system that manages thermal energy generation effectively.
Solution Approach 2:
The heterogeneous multi-core processor performs self-thermal-management by automatically monitoring its own core temperatures, comparing performance curves of different cores, and reallocating workloads without external intervention. The system uses internal temperature sensors and built-in performance curve data to make autonomous decisions about workload distribution, reducing the need for complex external thermal management hardware.
2Temperature
If workload is dynamically reallocated based on temperature and performance curves, then thermal management improves, but processing speed may be impacted due to workload switching overhead
Solution Approach 1:
Performance curves for each processing core are pre-characterized and stored in memory, capturing the relationship between workload levels and temperature generation for each core. When thermal management is needed, the system queries these pre-computed curves rather than performing real-time thermal analysis, significantly reducing the computational overhead and time required for workload reallocation decisions.
Solution Approach 2:
The workload allocation system dynamically adjusts the balance between thermal management and processing speed based on current system conditions. When thermal thresholds are not exceeded, workloads remain on active cores to maintain processing speed. When temperatures approach critical levels, the system dynamically switches workloads to cooler cores or reduces workload intensity, optimizing the trade-off between thermal management and processing throughput in real-time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Various embodiments of methods and systems for controlling and/or managing thermal energy generation on a portable computing device that contains a heterogeneous multicore processor are disclosed. Because individual cores in a heterogeneous processor may exhibit different processing efficiencies at a given temperature, thermal mitigation techniques that compare performance curves of the individual cores at their measured operating temperatures can be leveraged to manage thermal energy generation in the PCD by allocating and/or reallocating workloads among the individual cores based on the performance curve comparison.