Modeling power consumption in multicore CPUs with multithreading and frequency scaling

D. Cerotti; M. Gribaudo; P. Piazzolla; R. Pinciroli; G. Serazzi

doi:10.1007/978-3-319-22635-4_7

Modeling power consumption in multicore CPUs with multithreading and frequency scaling

D. Cerotti
, M. Gribaudo
, P. Piazzolla
, R. Pinciroli
, G. Serazzi

Risultato della ricerca: Capitolo in libro/report/atti di convegno › Contributo a conferenza › peer review

Abstract

The rapid growth of energy requirements in large data-center has motivated several research projects focusing on the reduction of power consumption. Several techniques have been studied to tackle this problem, and most of them require simple power models to estimate the energy consumption starting from known system parameters. It has been proven that the CPU is the component of a server that is most responsible for its total power consumption: for this reason several power models focusing on this resource has been developed. However, only a few accounts for standard CPU features like dynamic frequency scaling and hyperthreading, which can have a significant impact on the estimation accuracy. In this paper, we present the results from a set of experiments focusing on these CPU features, and we propose a simple power model able to provide accurate power estimates by taking them into account.

Lingua originale	Inglese
Titolo della pubblicazione ospite	Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015
Editor	Omer H. Abdelrahman, Erol Gelenbe, Gokce Gorbil, Ricardo Lent
Editore	Springer Verlag
Pagine	81-90
Numero di pagine	10
ISBN (stampa)	9783319226347
DOI	https://doi.org/10.1007/978-3-319-22635-4_7
Stato di pubblicazione	Pubblicato - 2015
Pubblicato esternamente	Sì
Evento	30th International Symposium on Computer and Information Sciences, ISCIS 2015 - London, United Kingdom Durata: 21 set 2015 → 24 set 2015

Serie di pubblicazioni

Nome	Lecture Notes in Electrical Engineering
Volume	355
ISSN (stampa)	1876-1100
ISSN (elettronico)	1876-1119

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	30th International Symposium on Computer and Information Sciences, ISCIS 2015
Paese/Territorio	United Kingdom
Città	London
Periodo	21/09/15 → 24/09/15

OSS delle Nazioni Unite

Questo processo contribuisce al raggiungimento dei seguenti obiettivi di sviluppo sostenibile

SDG 7 Energia pulita e accessibile

Accesso al documento

10.1007/978-3-319-22635-4_7

Altri file e collegamenti

Link to publication in Scopus

Cita questo

Cerotti, D., Gribaudo, M., Piazzolla, P., Pinciroli, R., & Serazzi, G. (2015). Modeling power consumption in multicore CPUs with multithreading and frequency scaling. In O. H. Abdelrahman, E. Gelenbe, G. Gorbil, & R. Lent (Edd.), Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015 (pagg. 81-90). (Lecture Notes in Electrical Engineering; Vol. 355). Springer Verlag. https://doi.org/10.1007/978-3-319-22635-4_7

Cerotti, D. ; Gribaudo, M. ; Piazzolla, P. et al. / Modeling power consumption in multicore CPUs with multithreading and frequency scaling. Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015. curatore / Omer H. Abdelrahman ; Erol Gelenbe ; Gokce Gorbil ; Ricardo Lent. Springer Verlag, 2015. pagg. 81-90 (Lecture Notes in Electrical Engineering).

@inproceedings{42dc2348db4e44fb980ff96e3445fd77,

title = "Modeling power consumption in multicore CPUs with multithreading and frequency scaling",

abstract = "The rapid growth of energy requirements in large data-center has motivated several research projects focusing on the reduction of power consumption. Several techniques have been studied to tackle this problem, and most of them require simple power models to estimate the energy consumption starting from known system parameters. It has been proven that the CPU is the component of a server that is most responsible for its total power consumption: for this reason several power models focusing on this resource has been developed. However, only a few accounts for standard CPU features like dynamic frequency scaling and hyperthreading, which can have a significant impact on the estimation accuracy. In this paper, we present the results from a set of experiments focusing on these CPU features, and we propose a simple power model able to provide accurate power estimates by taking them into account.",

author = "D. Cerotti and M. Gribaudo and P. Piazzolla and R. Pinciroli and G. Serazzi",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 30th International Symposium on Computer and Information Sciences, ISCIS 2015 ; Conference date: 21-09-2015 Through 24-09-2015",

year = "2015",

doi = "10.1007/978-3-319-22635-4\_7",

language = "English",

isbn = "9783319226347",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "81--90",

editor = "Abdelrahman, \{Omer H.\} and Erol Gelenbe and Gokce Gorbil and Ricardo Lent",

booktitle = "Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015",

address = "Germany",

}

Cerotti, D, Gribaudo, M, Piazzolla, P, Pinciroli, R & Serazzi, G 2015, Modeling power consumption in multicore CPUs with multithreading and frequency scaling. in OH Abdelrahman, E Gelenbe, G Gorbil & R Lent (edd.), Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015. Lecture Notes in Electrical Engineering, vol. 355, Springer Verlag, pagg. 81-90, 30th International Symposium on Computer and Information Sciences, ISCIS 2015, London, United Kingdom, 21/09/15. https://doi.org/10.1007/978-3-319-22635-4_7

Modeling power consumption in multicore CPUs with multithreading and frequency scaling. / Cerotti, D.; Gribaudo, M.; Piazzolla, P. et al.
Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015. a cura di / Omer H. Abdelrahman; Erol Gelenbe; Gokce Gorbil; Ricardo Lent. Springer Verlag, 2015. pag. 81-90 (Lecture Notes in Electrical Engineering; Vol. 355).

Risultato della ricerca: Capitolo in libro/report/atti di convegno › Contributo a conferenza › peer review

TY - GEN

T1 - Modeling power consumption in multicore CPUs with multithreading and frequency scaling

AU - Cerotti, D.

AU - Gribaudo, M.

AU - Piazzolla, P.

AU - Pinciroli, R.

AU - Serazzi, G.

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2015

Y1 - 2015

N2 - The rapid growth of energy requirements in large data-center has motivated several research projects focusing on the reduction of power consumption. Several techniques have been studied to tackle this problem, and most of them require simple power models to estimate the energy consumption starting from known system parameters. It has been proven that the CPU is the component of a server that is most responsible for its total power consumption: for this reason several power models focusing on this resource has been developed. However, only a few accounts for standard CPU features like dynamic frequency scaling and hyperthreading, which can have a significant impact on the estimation accuracy. In this paper, we present the results from a set of experiments focusing on these CPU features, and we propose a simple power model able to provide accurate power estimates by taking them into account.

AB - The rapid growth of energy requirements in large data-center has motivated several research projects focusing on the reduction of power consumption. Several techniques have been studied to tackle this problem, and most of them require simple power models to estimate the energy consumption starting from known system parameters. It has been proven that the CPU is the component of a server that is most responsible for its total power consumption: for this reason several power models focusing on this resource has been developed. However, only a few accounts for standard CPU features like dynamic frequency scaling and hyperthreading, which can have a significant impact on the estimation accuracy. In this paper, we present the results from a set of experiments focusing on these CPU features, and we propose a simple power model able to provide accurate power estimates by taking them into account.

UR - https://www.scopus.com/pages/publications/84945897828

U2 - 10.1007/978-3-319-22635-4_7

DO - 10.1007/978-3-319-22635-4_7

M3 - Conference contribution

AN - SCOPUS:84945897828

SN - 9783319226347

T3 - Lecture Notes in Electrical Engineering

SP - 81

EP - 90

BT - Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015

A2 - Abdelrahman, Omer H.

A2 - Gelenbe, Erol

A2 - Gorbil, Gokce

A2 - Lent, Ricardo

PB - Springer Verlag

T2 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015

Y2 - 21 September 2015 through 24 September 2015

ER -

Cerotti D, Gribaudo M, Piazzolla P, Pinciroli R, Serazzi G. Modeling power consumption in multicore CPUs with multithreading and frequency scaling. In Abdelrahman OH, Gelenbe E, Gorbil G, Lent R, editor, Information Sciences and Systems 2015 - 30th International Symposium on Computer and Information Sciences, ISCIS 2015. Springer Verlag. 2015. pag. 81-90. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-3-319-22635-4_7

Modeling power consumption in multicore CPUs with multithreading and frequency scaling

Abstract

Serie di pubblicazioni

???event.eventtypes.event.conference???

OSS delle Nazioni Unite

Accesso al documento

Altri file e collegamenti

Fingerprint

Cita questo