Interference from GPU System Service Requests

Basu, Arkaprava and Greathouse, Joseph L and Venkataramani, Guru and Vesely, Jan (2018) Interference from GPU System Service Requests. In: 2018 IEEE International Symposium on Workload Characterization, IISWC 2018, 30 September - 2 October 2018, Raleigh; United States, pp. 179-190.

PDF Int_Sym_Wor_Cha_179_2018.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Heterogeneous systems combine general-purpose CPUs with domain-specific accelerators like GPUs. Recent heterogeneous system designs have enabled GPUs to request OS services, but the domain-specific nature of accelerators means that they must rely on the CPUs to handle these requests. Such system service requests can unintentionally harm the performance of unrelated CPU applications. Tests on a real heterogeneous processor demonstrate that GPU system service requests can degrade contemporaneous CPU application performance by up to 44% and can reduce energy efficiency by limiting CPU sleep time. The reliance on busy CPU cores to perform the system services can also slow down GPU work by up to 18%. This new form of interference is found only in accelerator-rich heterogeneous designs and may be exacerbated in future systems with more accelerators. We explore mitigation strategies from other fields that, in the face of such interference, can increase CPU and GPU performance by over 20% and 2 x, respectively, and CPU sleep time by 4.8 x. However, these strategies do not always help and offer no performance guarantees. We therefore describe a technique to guarantee quality of service to CPU workloads by dynamically adding backpressure to GPU requests.

Item Type:	Conference Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	Copyright belongs to Institute of Electrical and Electronics Engineers Inc
Keywords:	Energy efficiency;Program processors;Quality of service;Graphics processing unit
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	16 Apr 2019 06:50
Last Modified:	16 Apr 2019 06:50
URI:	http://eprints.iisc.ac.in/id/eprint/62307

Actions (login required)

View Item