{MArk}: Exploiting cloud services for {Cost-Effective},{SLO-Aware} machine learning inference serving

C Zhang, M Yu, W Wang, F Yan - 2019 USENIX Annual Technical …, 2019 - usenix.org
The advances of Machine Learning (ML) have sparked a growing demand of ML-as-a-
Service: developers train ML models and publish them in the cloud as online services to …

Patterns in the chaos—a study of performance variation and predictability in public iaas clouds

P Leitner, J Cito - ACM Transactions on Internet Technology (TOIT), 2016 - dl.acm.org
Benchmarking the performance of public cloud providers is a common research topic.
Previous work has already extensively evaluated the performance of different cloud …

Performance evaluation of heterogeneous cloud functions

K Figiela, A Gajek, A Zima, B Obrok… - Concurrency and …, 2018 - Wiley Online Library
Summary Cloud Functions, often called Function‐as‐a‐Service (FaaS), pioneered by AWS
Lambda, are an increasingly popular method of running distributed applications. As in other …

Benchmarking heterogeneous cloud functions

M Malawski, K Figiela, A Gajek, A Zima - Euro-Par 2017: Parallel …, 2018 - Springer
Abstract Cloud Functions, often called Function-as-a-Service (FaaS), pioneered by AWS
Lambda, are an increasingly popular method of running distributed applications. As in other …

Exploiting spot and burstable instances for improving the cost-efficacy of in-memory caches on the public cloud

C Wang, B Urgaonkar, A Gupta, G Kesidis… - Proceedings of the …, 2017 - dl.acm.org
In order to keep the costs of operating in-memory storage on the public cloud low, we devise
novel ideas and enabling modeling and optimization techniques for combining conventional …

Enabling cost-effective, slo-aware machine learning inference serving on public cloud

C Zhang, M Yu, W Wang, F Yan - IEEE Transactions on Cloud …, 2020 - ieeexplore.ieee.org
The remarkable advances of Machine Learning (ML) have spurred an increasing demand
for ML-as-a-Service on public cloud: developers train and publish ML models as online …

Estimating cloud application performance based on micro-benchmark profiling

J Scheuner, P Leitner - 2018 IEEE 11th International …, 2018 - ieeexplore.ieee.org
The continuing growth of the cloud computing market has led to an unprecedented diversity
of cloud services. To support service selection, micro-benchmarks are commonly used to …

Using burstable instances in the public cloud: Why, when and how?

C Wang, B Urgaonkar, N Nasiriani… - Proceedings of the ACM on …, 2017 - dl.acm.org
Amazon EC2 and Google Compute Engine (GCE) have recently introduced a new class of
virtual machines called" burstable" instances that are cheaper than even the smallest …

Scheduling bag-of-tasks in clouds using spot and burstable virtual machines

L Teylo, L Arantes, P Sens… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Cloud providers offer several types of Virtual Machines (VMs) in diverse markets, with
different guarantees in terms of availability and reliability. Among them, the most popular …

Burstable instances for clouds: Performance modeling, equilibrium analysis, and revenue maximization

Y Jiang, M Shahrad, D Wentzlaff… - IEEE/ACM …, 2020 - ieeexplore.ieee.org
Leading cloud providers recently introduced a new instance type named burstable instances
to better match the time-varying workloads of tenants and further reduce their costs. In the …