DeadPool: Performance Deadline Based Frequency Pooling and Thermal Management Agent in DVFS Enabled MPSoCs

Abstract

High operating temperature and frequent thermal cycles in a multi-processor system-on-chip, which is now popularly utilized in mobile/Edge devices, harm the overall lifespan and reliability of such devices. In this paper, we propose an intelligent software agent that works alongside other resource mapping and partitioning mechanism in order to monitor and reduce the operating temperature of the system by regulating the operating frequency of the CPU cores while catering for performance constraint at the same time. Our proposed approach, DeadPool thermal management agent, is able to reduce the overall operating temperature of the system by 24.21% and reduce thermal cycle by 67.42% at the most when compared to the state-of-the-art methods.

CPU-GPU-Memory DVFS for Power-Efficient MPSoC in Mobile Cyber Physical Systems

“…Power-saving mechanisms within performance constraints utilizing DVFS capabilities on heterogeneous MPSoCs have been considered in many studies [4][5][6]13,14,[24][25][26][27][28][29][30][31][32][33][34][35][36]. Given the fact that power consumption in a heterogeneous MPSoC can be significantly affected by big CPUs, LITTLE CPUs, GPUs and memory, most of the published studies have proposed power-saving approaches utilizing DVFS of different aforementioned components of the MPSoC but have not considered performing DVFS on all these components to achieve more reduced power consumption while catering to performance constraints.…”

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

“…However, majority of the studies are focused on many-core (more than 16 cores) general purpose processors and Network-onchips (NoCs) on contrary to multi-core mobile platforms. Techniques in [9], [39], [40] are solely focused on optimizing thermal behaviour during runtime on mobile platforms. Note that this section covers approaches considering only thermal management but not both thermal and energy management that are provided in the next section.…”

“…Dey et al [40] presented a dynamic thermal management technique using frequency scaling to meet the performance deadline of the executing application. This technique maps the operating frequency of the cores to a temperature while executing an application and uses the mapping to select the appropriate frequency to cater for the performance deadline while keeping the operating temperature lower than the threshold.…”

Temporal Motionless Analysis of Video using CNN in MPSoC

“…For our traffic categorization experimentation we are using the same dataset used in [3], [7]. Hardware setup: We have implemented the methodology on an Odroid-XU4 [16], [23], which employs Exynos 5422 MPSoC [24], [25], [26] used in popular Samsung Note phones and phablets. Experimental Results: To categorize traffic we chose four pre-Trained CNN models, which were trained on millions of ImageNet images, for our validation.…”