A Multiformalism-Based Model for Performance Evaluation of Green Data Centres

Although the coexistence of ARM and INTEL technologies in green data centres is technically feasible, significant challenges exist that must be addressed. These challenges stem from the differences in instruction sets and power consumption between the two processor architectures. While ARM processor...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2023-05, Vol.12 (10), p.2169
Main Authors: Barbierato, Enrico, Manini, Daniele, Gribaudo, Marco
Format: Article
Language:English
Subjects:
Analysis
Bottlenecks
Data centers
Emission standards
Energy efficiency
High performance computing
Machine learning
Microprocessors
Performance evaluation
Performance indices
Portable computers
Power
Power consumption
Power management
Processor architecture
Processors
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although the coexistence of ARM and INTEL technologies in green data centres is technically feasible, significant challenges exist that must be addressed. These challenges stem from the differences in instruction sets and power consumption between the two processor architectures. While ARM processors are known for their energy efficiency, INTEL processors tend to consume more power. Consequently, evaluating the performance of hybrid architectures can be a complex task. The contributions of this article consist of (i) a multiformalism-based model of a data centre, providing a natural and convenient approach to the specification process and performance analysis of a realistic scenario and (ii) a review of the performance indices, including the choice of one architecture over another, power consumption, the response time, and request loss, according to different policies. As a result, the model aims to address issues such as system underutilization and the need to estimate the optimal workload balance, thereby providing an effective solution for evaluating the performance of hybrid hardware architectures.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12102169