Data analytics for energy-efficient clouds: design, implementation and evaluation

Altomare, Albino; Cesario, Eugenio; Vinci, Andrea

doi:10.1080/17445760.2018.1448931

Cited by 13 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the following, we initially assume α = 0.2 (i.e., BRAM contributes to 0.2 1+0.2 of critical path delay [32]) and β = 0.4 (i.e., BRAM power initially is ∼ 25% of device total power [28]). Figures 4,5,6 demonstrates the efficiency of different voltage scaling schemes under varying workloads, applications' critical paths ('α's), and applications' power characteristics (i.e., β, the ratio of memory to chip power). Prop means the proposed approach that simultaneously determines Vcore and V bram , core-only is the technique that only scales Vcore [25], [24], and bram-only is similar to [28].…”

Section: Motivational Analysismentioning

confidence: 99%

“…Data centers are expected to provide the required QoS of users while the size of the incoming workload varies temporally. Typically, the size of the workload is less than 30% of the users' expected maximum, directly translating to the fact that servers run at less than 30% of their maximum capacity [5]. Several works have attempted to tackle the underutilization in FPGA clouds by leveraging the concept of virtual machines to minimize the amount of required resources and turn off the unused resources [18].…”

Section: Introductionmentioning

confidence: 99%

“…The huge power consumption of cloud data centers has several adverse consequences [5]: (i) operational cost of cloud servers obliges the providers to rise the price of services, (ii) high power consumption increases the working temperature which leads to a significant reduction in the system reliability as well as the data center lifetime, and (iii) producing the energy required for cloud servers emits an enormous amount of environmentally hostile carbon dioxide. Therefore, improving the power efficiency of cloud servers is a critical obligation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Workload-Aware Opportunistic Energy Efficiency in Multi-FPGA Platforms

Salamat

Khaleghi

Imani

et al. 2019

2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

View full text Add to dashboard Cite

The continuous growth of big data applications with high computational and scalability demands has resulted in increasing popularity of cloud computing. Optimizing the performance and power consumption of cloud resources is therefore crucial to relieve the costs of data centers. In recent years, multi-FPGA platforms have gained traction in data centers as lowcost yet high-performance solutions particularly as acceleration engines, thanks to the high degree of parallelism they provide. Nonetheless, the size of data centers workloads varies during service time, leading to significant underutilization of computing resources while consuming a large amount of power, which turns out as a key factor of data center inefficiency, regardless of the underlying hardware structure. In this paper, we propose an efficient framework to throttle the power consumption of multi-FPGA platforms by dynamically scaling the voltage and hereby frequency during runtime according to prediction of, and adjustment to the workload level, while maintaining the desired Quality of Service (QoS). This is in contrast to, and more efficient than, conventional approaches that merely scale (i.e., power-gate) the computing nodes or frequency. The proposed framework carefully exploits a pre-characterized library of delay-voltage, and power-voltage information of FPGA resources, which we show is indispensable to obtain the efficient operating point due to the different sensitivity of resources w.r.t. voltage scaling, particularly considering multiple power rails residing in these devices. Our evaluations by implementing state-of-the-art deep neural network accelerators revealed that, providing an average power reduction of 4.0×, the proposed framework surpasses the previous works by 33.6% (up to 83%).

show abstract

Section: Motivational Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Workload-Aware Opportunistic Energy Efficiency in Multi-FPGA Platforms

Salamat

Khaleghi

Imani

et al. 2019

2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

View full text Add to dashboard Cite

show abstract

“…Adding quantum resources to the typical Cloud/Edge architecture can help to solve hard problems for which quantum algorithms promise to offer a computational speedup in the coming years; specifically, optimization problems and machine learning problems. Currently, resource management algorithms are used in the Cloud layer to determine the assignment and scheduling of processes on the nodes of a Cloud data center [46], [47]. With the inclusion of quantum platforms, two novel research avenues have been opened in this context: (i) on the one hand, resource management algorithms are needed to assign and schedule specific parts of the computation on quantum hardware; (ii) on the other hand, there are chances that such algorithms, applied to any layer of the architecture, can be executed more efficiently on quantum hardware than on classical computers.…”

Section: A Reference Architecturementioning

confidence: 99%

Quantum Computing Management of a Cloud/Edge Architecture

Mastroianni

Scarcello

Vinci

2023

Proceedings of the 20th ACM International Conference on Computing Frontiers

Self Cite

View full text Add to dashboard Cite

1 Modern Cloud/Edge architectures need to orchestrate multiple layers of heterogeneous computing nodes, including pervasive sensors/actuators, distributed Edge/Fog nodes, centralized data centers and quantum devices. The optimal assignment and scheduling of computation on the different nodes is a very difficult problem, with NP-hard complexity. In this paper, we explore the possibility of solving this problem with variational quantum algorithms, which can become a viable alternative to classical algorithms in the near future. In particular, we compare the performances, in terms of success probability, of two algorithms, i.e., Quantum Approximate Optimization Algorithm (QAOA) and Variational Quantum Eigensolver (VQE). The simulation experiments, performed for a set of simple problems, show that the VQE algorithm ensures better performances when it is equipped with appropriate circuit ansatzes that are able to restrict the search space. Moreover, experiments executed on real quantum hardware show that the execution time, when increasing the size of the problem, grows much more slowly than the trend obtained with classical computation, which is known to be exponential.Index Terms-quantum computing, cloud/edge computing, resource assignment I. INTRODUCTIONCloud/Edge architectures are required to include and integrate heterogeneous types of computing devices, with very different capabilities and characteristics, ranging from pervasive sensors and actuators and mobile devices to personal computers, local servers and Cloud data centers. This complex architecture is sometimes referred to as a "continuous computing" platform [1]-[4], and is the subject of intense research aiming to achieve a judicious allocation of computational, storage, and network resources to meet the demands of modern applications. A skillful resource allocation involves the strategic distribution of resources to the different layers, in order to deliver desired outcomes efficiently. This problem encompasses multiple dimensions, including cost-effectiveness, energy efficiency, security, and scalability, and its solution becomes increasingly intricate [5], [6].Recent research in this area is inspired by machine learning and AI-driven decision-making algorithms, which aim to adapt resource allocation strategies to the evolving needs of diverse workloads. Indeed, efficiency, latency, and privacy issues foster

show abstract

“…In the third paper [3], Altomare et al present a data mining approach to improve consolidation of virtual machines in Cloud systems. Consolidation of virtual machines is one of the most used and wellstudied strategies to reduce the energy consumption in large data centres.…”

mentioning

confidence: 99%