Core and Uncore Joint Frequency Scaling Strategy

dc.contributor.author Gordon, Mark
dc.contributor.author Sosonkina, Masha
dc.contributor.author Westheimer, Bryce
dc.contributor.author Gordon, Mark
dc.contributor.department Chemistry
dc.contributor.department Ames National Laboratory
dc.date.accessioned 2022-03-01T21:21:36Z
dc.date.available 2022-03-01T21:21:36Z
dc.date.issued 2018-12
dc.description.abstract Energy-proportional computing is one of the foremost constraints in the design of next generation exascale systems. These systems must have a very high FLOP-per-watt ratio to be sustainable, which requires tremendous improvements in power efficiency for modern computing systems. This paper focuses on the processor—as still the biggest contributor to the power usage—by considering both its core and uncore power subsystems. The uncore describes those processor functions that are not handled by the core, such as L3 cache and on-chip interconnect, and contributes significantly to the total system power. The uncore frequency scaling (UFS) capability has been available to the user since the Intel Haswell processor generation. In this paper, performance and power models are proposed to use both the UFS and dynamic voltage and frequency scaling (DVFS) to reduce the energy consumption in parallel applications. Then, these models are incorporated into a runtime strategy that performs processor frequency scaling during parallel application execution. The strategy can be implemented at the kernel/firmware level, which makes it suitable for improving the energy efficiency of exascale design. Experiments on a 20-core Haswell-EP machine using the quantum chemistry application GAMESS and NAS benchmark resulted in up to 24% energy savings with as little as 2% performance loss.
dc.description.comments This article is published as Sundriyal, Vaibhav, Masha Sosonkina, Bryce Westheimer, and Mark Gordon. "Core and uncore joint frequency scaling strategy." Journal of Computer and Communications 6, no. 12 (2018): 184-201. DOI: 10.4236/jcc.2018.612018. Copyright 2022 by authors and Scientific Research Publishing Inc. Attribution 4.0 International (CC BY 4.0). Posted with permission.
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/ywAbGqnv
dc.language.iso en_US
dc.publisher Scientific Research Publishing Inc.
dc.source.uri https://doi.org/10.4236/jcc.2018.612018 *
dc.subject.keywords NAS Benchmarks
dc.title Core and Uncore Joint Frequency Scaling Strategy
dc.type Article
dspace.entity.type Publication
relation.isAuthorOfPublication 1a5927c0-5a5f-440e-86e0-9da8dc6afda0
relation.isOrgUnitOfPublication 42864f6e-7a3d-4be3-8b5a-0ae3c3830a11
relation.isOrgUnitOfPublication 25913818-6714-4be5-89a6-f70c8facdf7e
File
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2018-GordonMark-CoreUncore.pdf
Size:
1.18 MB
Format:
Adobe Portable Document Format
Description:
Collections