A generalized software framework for accurate and efficient management of performance goals
(2013) 13th International Conference on Embedded Software, EMSOFT 2013 In 2013 Proceedings of the International Conference on Embedded Software, EMSOFT 2013- Abstract
A number of techniques have been proposed to provide runtime performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE's generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86... (More)
A number of techniques have been proposed to provide runtime performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE's generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86 systems and a simulated 128-core system, each with different components governing power and performance tradeoffs. Our experimental results show that PTRADE provides generality while meeting performance goals with low error and close to optimal power consumption.
(Less)
- author
- Hoffmann, Henry ; Maggio, Martina LU ; Santambrogio, Marco D. ; Leva, Alberto and Agarwal, Anant
- organization
- publishing date
- 2013
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Adaptive systems, Power-aware computing, Self-aware computing
- host publication
- 2013 Proceedings of the International Conference on Embedded Software, EMSOFT 2013
- series title
- 2013 Proceedings of the International Conference on Embedded Software, EMSOFT 2013
- article number
- 6658597
- publisher
- IEEE Computer Society
- conference name
- 13th International Conference on Embedded Software, EMSOFT 2013
- conference location
- Montreal, QC, Canada
- conference dates
- 2013-09-29 - 2013-10-04
- external identifiers
-
- scopus:84892654929
- ISBN
- 9781479914432
- DOI
- 10.1109/EMSOFT.2013.6658597
- project
- Cloud Control
- Power Control for Computing Infrastructures
- language
- English
- LU publication?
- yes
- additional info
- Copyright: Copyright 2019 Elsevier B.V., All rights reserved.
- id
- d49458eb-dde1-439b-ad62-730e2c109d2d
- date added to LUP
- 2021-03-22 11:09:02
- date last changed
- 2022-02-09 05:43:08
@inproceedings{d49458eb-dde1-439b-ad62-730e2c109d2d, abstract = {{<p>A number of techniques have been proposed to provide runtime performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE's generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86 systems and a simulated 128-core system, each with different components governing power and performance tradeoffs. Our experimental results show that PTRADE provides generality while meeting performance goals with low error and close to optimal power consumption.</p>}}, author = {{Hoffmann, Henry and Maggio, Martina and Santambrogio, Marco D. and Leva, Alberto and Agarwal, Anant}}, booktitle = {{2013 Proceedings of the International Conference on Embedded Software, EMSOFT 2013}}, isbn = {{9781479914432}}, keywords = {{Adaptive systems; Power-aware computing; Self-aware computing}}, language = {{eng}}, publisher = {{IEEE Computer Society}}, series = {{2013 Proceedings of the International Conference on Embedded Software, EMSOFT 2013}}, title = {{A generalized software framework for accurate and efficient management of performance goals}}, url = {{http://dx.doi.org/10.1109/EMSOFT.2013.6658597}}, doi = {{10.1109/EMSOFT.2013.6658597}}, year = {{2013}}, }