TheSPoT: Thermal Stress-Aware Power and Temperature Management for Multiprocessor Systems-on-Chip

Abstract

Abstract-Thermal stress including temperature gradients in time and space, as well as thermal cycling, influences lifetime reliability and performance of modern Multiprocessor Systemson-Chip (MPSoCs). Conventional power and temperature management techniques considering the peak temperature/power consumption do not provide a comprehensive solution to avoid high spatial and temporal thermal variations. This work presents TheSPoT, a novel multi-level thermal stress-aware power and thermal management approach for MPSoCs. At the top level, core consolidation and deconsolidation is performed based on peak temperature, thermal stress, and power consumption constraints. These constraints are also used at the next level, where operating frequencies are determined. At this level we obtain optimal core frequencies by solving a convex optimization problem. However, thereafter, to reduce the runtime overhead in large MPSoCs, we alternatively propose to use a fast heuristic algorithm. The efficacy of the proposed approaches in reducing the thermal cycles and temporal/spatial temperature gradients is evaluated by comparing the results with the state-of-the-art methods. The evaluation performed on 4-core, 8-core, and 16-core MPSoCs, using PARSEC benchmarks, reveals a considerable reduction in thermal stress. For the 8-core MPSoC case study, on average, for the proposed heuristic(optimal) approach, the mean time to failure improved by 47(35) % compared to the state-of-the-art techniques with only 6(4) % performance degradation. Also, our simulations show that TheSPoT is more efficient in thermal stress reduction when more heterogeneous workloads are used.

P‐EdgeCoolingMode: an agent‐based performance aware thermal management unit for DVFS enabled heterogeneous MPSoCs

“…This approach was implemented on Sniper multicore simulator [21] and was able to reduce spatial and temporal thermal gradients by 7% and 18% respectively when compared to the work in [19]. In another work by Iranfar et al [22], the researchers proposed a multi-tier hierarchical thermal stress-aware power and temperature management framework for MPSoCs, where the methodology used similar convex optimization solution in multi-layer to improve mean time to failure (MTTF) * . The effectiveness of this methodology is again proved based on simulations performed on Sniper multicore simulator.…”

Enhancing Two-Phase Cooling Efficiency through Thermal-Aware Workload Mapping for Power-Hungry Servers

“…Chan et al [18] propose a thermal management framework with respect to fan speed impact on performance and its energy cost. TheSPoT [19] proposes thermal-aware workload migration scheme for MPSoCs. Authors in [9] address thermal-aware workload balancing policies for MPSoCs.…”

Dynamic Energy and Thermal Management of Multi-core Mobile Platforms: A Survey

“…Additionally, the variety of the workloads, which could be processed at the same time, may cause large temporal heat generation/dissipation leading to temporal thermal gradients (TTGs) at a single point on the chip. In the meantime, STGs, TTGs and thermal cycles lead to reduced performance and reliability of the system over the period of time [10]. If there is an increase of 10°C to 20°C for metallic structures then the lifetime reliability may decrease up to 16 times, thus, optimizing thermal behaviour of such mobile platforms is very important.…”