Adaptive power shifting for power-constrained heterogeneous systems
Visualitza/Obre
Cita com:
hdl:2117/367517
Tipus de documentArticle
Data publicació2023-03-01
EditorInstitute of Electrical and Electronics Engineers (IEEE)
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
ProjecteMont-Blanc 2020 - Mont-Blanc 2020, European scalable, modular and power efficient HPC processor (EC-H2020-779877)
UPC-COMPUTACION DE ALTAS PRESTACIONES VIII (AEI-PID2019-107255GB-C22)
BSC - COMPUTACION DE ALTAS PRESTACIONES VIII (AEI-PID2019-107255GB-C21)
UPC-COMPUTACION DE ALTAS PRESTACIONES VIII (AEI-PID2019-107255GB-C22)
BSC - COMPUTACION DE ALTAS PRESTACIONES VIII (AEI-PID2019-107255GB-C21)
Abstract
The number and heterogeneity of compute devices, even within a single compute node, has been steadily on the rise. Since all systems must operate under a power cap, the number of discrete devices that can run simultaneously at their highest frequency is limited by the globally-imposed power cap. Current systems incorporate a centralized power management unit that statically controls the distribution of power among the devices within the node. However, such static distribution policies are unaware of the dynamic utilization profile across the devices, which leads to unfair power allocations that end up degrading system throughput performance. The problem is particularly acute in the presence of heterogeneity since type-specific performance-boost capabilities cannot be leveraged via utilization-agnostic static power allocations. This paper proposes Adaptive Power Shifting for multi-accelerator heterogeneous systems (APS), a technique that leverages system utilization information to dynamically allocate and re-distribute power budgets across multiple discrete devices. Democratizing the power allocation based on dynamic needs results in dramatic speedup over a need-agnostic static allocation. We use APS in a real OpenPOWER compute node with 2 CPUs and 4 GPUs to demonstrate the value of on-demand, equitable power allocations. Overall, the proposed solution increases performance with respect to two state-of-the-art techniques by up to 14.9% and 13.8%.
CitacióOrtega, C. [et al.]. Adaptive power shifting for power-constrained heterogeneous systems. "IEEE transactions on computers", 1 Març 2023, vol. 72, núm. 3, p. 627-640.
ISSN0018-9340
Versió de l'editorhttps://ieeexplore.ieee.org/abstract/document/9773997
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
main.pdf | 4,615Mb | Visualitza/Obre |