• Publications
  • Influence
Private IaaS Clouds: A Comparative Analysis of OpenNebula, CloudStack and OpenStack
TLDR
The goal is to make a comparative analysis of OpenNebula, OpenStack and CloudStack tools, evaluating their differences on support for flexibility and resiliency and evaluating these three cloud tools when they are deployed using a mutual hypervisor (KVM) for discovering new empirical insights. Expand
SPar: A DSL for High-Level and Productive Stream Parallelism
TLDR
SPar is introduced, an internal C++ Domain-Specific Language (DSL) that supports the development of classic stream parallel applications and uses standard C++ attributes to introduce a number of new features. Expand
Minimizing Communication Overheads in Container-based Clouds for HPC Applications
TLDR
This work proposes the aggregation of Network Interface Cards (NICs) in a ready-to-use integration with the OpenNebula cloud manager using Linux containers and highlights that the implementation of NIC aggregation improves network performance in terms of throughput and latency. Expand
A High-Level DSL for Geospatial Visualizations with Multi-core Parallelism Support
TLDR
This work presents a novel Domain-Specific Language (DSL), which focuses on large data geovisualizations, and takes advantage of multi-core parallelism to speed-up data pre-processing abstractly. Expand
Providing high‐level self‐adaptive abstractions for stream parallelism on multicores
TLDR
A self‐adaptive regulation of the degree of parallelism to provide higher‐level abstractions is proposed and Flexibility is provided to programmers with two new self‐ Adaptive strategies, one is for performance experts, and the other abstracts the need to set a performance goal. Expand
Higher-Level Parallelism Abstractions for Video Applications with SPar
TLDR
Assessment of SPar’s programming language and its performance in traditional video applications demonstrates that SPar maintains the sequential code structure, is less code intrusive, and provides higherlevel programming abstractions without introducing notable performance losses. Expand
Stream parallelism with ordered data constraints on multi-core systems
TLDR
A new implementation technique designed to be easily integrated with any of the existing C++ parallel programming frameworks that support stream parallelism is proposed, first implemented and studied using SPar, the authors' high-level domain-specific language for stream Parallelism. Expand
Improving the Network Performance of a Container-Based Cloud Environment for Hadoop Systems
TLDR
The results prove that the approach adds minimal overhead in cloud environment as well as increases throughput and reduces latency, and demonstrates a suitable alternative for running Hadoop applications, reducing completion times up to 33.73%. Expand
High-Level and Productive Stream Parallelism for Dedup, Ferret, and Bzip2
TLDR
The results demonstrate that SPar improves productivity and provides the necessary features to achieve similar performances compared to the state-of-the-art, as well as discussing SPar’s programmability advantagesCompared to the frameworks in terms of productivity and structured parallel programming. Expand
The NAS Benchmark Kernels for Single and Multi-Tenant Cloud Instances with LXC/KVM
TLDR
A comparative performance evaluation of scientific applications with single and multi-tenancy cloud instances using KVM and LXC virtualization technologies under private cloud conditions has shown that applications running on LXC-based cloud instances outperform KVM- based cloud instances. Expand
...
1
2
3
4
5
...