Enhancing ARM-based Compute Core Performance using Task Priority and Proximity-Induced Thermal Thresholds in Heterogeneous Core Architecture

View at publisher Summarise with VIRAT
Authors: Suranjan Chakraborty, Chintakunta Ratna Kumari, Nitesh Jain, Vishnu Vardhan Kasiliya Sudarsan, Mallikarjunan M
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Modern microprocessors featuring multi-core, multi-cluster CPU architectures incorporate multiple digital thermal sensors in heterogeneous cores, positioned within micrometer-scale proximity. Under high computational load, localized temperature elevation in an active core induces significant thermal coupling effects in adjacent cores, necessitating proactive thermal management. Experimental evaluation reveals that ARM-architecture based processors demonstrate up to a 200% temperature rise in neighboring cores that remain idle, underscoring the critical impact of spatial thermal interactions.The proposed solution establishes a "Proximity-Induced" thermal threshold for each compute core, dynamically governed by task priority. Prior to a core attaining its thermal limit, adjacent cores executing lower-priority tasks are proactively transitioned to reduced power states. This preemptive strategy mitigates premature thermal escalation in cores executing high-priority task, resulting in an observed increase of more than 30% in additional thermal headroom.

Fields of Study & Subjects

Parallel Computing and Optimization Techniques Real-Time Systems Scheduling Low-power high-performance VLSI design

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–6
Publication date
3 February 2026
Language
EN