Resource allocation is a well-known problem, with a large number of research contributions towards efficient utilisation of the massive hardware parallelism using various exact and heuristic approaches.We address the problem of optimising resources usage on deeply heterogeneous platforms in the context of HPC systems running multiple applications with different quality of service levels. Our approach manages the partitioning within a single heterogeneous node aiming at serving as many critical applications as possible while leaving to the upper levels of runtime resource management the decision to preempt resources or to launch the critical application on a different node. We investigate predictive allocation algorithms, allowing to serve up to 20% more high priority requests when using a moving average or machine learning prediction model vs baseline without prediction.

Prediction-based partitions evaluation algorithm for resource allocation

Pupykina A.;Agosta G.
2020-01-01

Abstract

Resource allocation is a well-known problem, with a large number of research contributions towards efficient utilisation of the massive hardware parallelism using various exact and heuristic approaches.We address the problem of optimising resources usage on deeply heterogeneous platforms in the context of HPC systems running multiple applications with different quality of service levels. Our approach manages the partitioning within a single heterogeneous node aiming at serving as many critical applications as possible while leaving to the upper levels of runtime resource management the decision to preempt resources or to launch the critical application on a different node. We investigate predictive allocation algorithms, allowing to serve up to 20% more high priority requests when using a moving average or machine learning prediction model vs baseline without prediction.
2020
Parallel Computing: Technology Trends
978-1-64368-071-2
978-1-64368-070-5
High Performance Computing
Memory management
NUMA Shared Memory
Prediction
Resource management
File in questo prodotto:
File Dimensione Formato  
ParCo19_Pupykina_Agosta.pdf

accesso aperto

Descrizione: Article
: Publisher’s version
Dimensione 753.54 kB
Formato Adobe PDF
753.54 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1141048
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact