Energy and thermal models for simulation of workload and resource management in computing systems
PBN-AR
Instytucja
Instytut Chemii Bioorganicznej Polskiej Akademii Nauk
Informacje podstawowe
Główny język publikacji
en
Czasopismo
SIMULATION MODELLING PRACTICE AND THEORY
ISSN
1569-190X
EISSN
1878-1462
Wydawca
ELSEVIER SCIENCE BV
DOI
Rok publikacji
2015
Numer zeszytu
Strony od-do
40-54
Numer tomu
58, Part 1
Identyfikator DOI
Liczba arkuszy
Autorzy
(liczba autorów: 4)
Pozostali autorzy
+ 2
Słowa kluczowe
en
Simulations
Thermal models
Energy-efficiency
Data centers
Streszczenia
Język
en
Treść
Abstract In the recent years, we have faced the evolution of high-performance computing (HPC) systems towards higher scale, density and heterogeneity. In particular, hardware vendors along with software providers, HPC centers, and scientists are struggling with the exascale computing challenge. As the density of both computing power and heat is growing, proper energy and thermal management becomes crucial in terms of overall system efficiency. Moreover, an accurate and relatively fast method to evaluate such large scale computing systems is needed. In this paper we present a way to model energy and thermal behavior of computing system. The proposed model can be used to effectively estimate system performance, energy consumption, and energy-efficiency metrics. We evaluate their accuracy by comparing the values calculated based on these models against the measurementshttps://pbn-ms.opi.org.pl/pbn-report-web/pages/work/addEditArticle.xhtml?referrer=/pages/report/viewPBNUAR.xhtml&institutionId=291&publicationId=56936b2281067928399e2ca5# obtained on real hardware. Finally, we show how the proposed models can be applied to workload scheduling and resource management in large scale computing systems by integrating them in the DCworms simulation framework.
Cechy publikacji
ORIGINAL_ARTICLE
Inne
System-identifier
670338
CrossrefMetadata from Crossref logo
Cytowania
Liczba prac cytujących tę pracę
Brak danych
Referencje
Liczba prac cytowanych przez tę pracę
Brak danych