arXiv subjects

Miguel Correia

Publications and source records attributed to Miguel Correia.

39 records · Page 3Linked to original sources

arXiv2019

Black holes, gravitational waves and fundamental physics: a roadmap

The grand challenges of contemporary fundamental physics---dark matter, dark energy, vacuum energy, inflation and early universe cosmology, singularities and the hierarchy problem---all involve gravity as a key component. And of all gravitational phenomena, black holes stand out in their elegant simplicity, while harbouring some of the most remarkable predictions of General Relativity: event horizons, singularities and ergoregions. The hitherto invisible landscape of the gravitational Universe is being unveiled before our eyes: the historical direct detection of gravitational waves by the LIGO-Virgo collaboration marks the dawn of a new era of scientific exploration. Gravitational-wave astronomy will allow us to test models of black hole formation, growth and evolution, as well as models of gravitational-wave generation and propagation. It will provide evidence for event horizons and ergoregions, test the theory of General Relativity itself, and may reveal the existence of new fundamental fields. The synthesis of these results has the potential to radically reshape our understanding of the cosmos and of the laws of Nature. The purpose of this work is to present a concise, yet comprehensive overview of the state of the art in the relevant fields of research, summarize important open problems, and lay out a roadmap for future progress.

gr-qc↗

arXiv2018

PCIe Hot Plug support standardization challenges in ATCA

Throughout the last decade, the Advanced Telecommunications Computing Architecture (ATCA) solidified its position as one of the main switched-based crate standards for advanced Physics instrumentation, offering not only highly performant characteristics in data throughput, channel density or power supply/dissipation capabilities, but also special features for high availability (HA), required for latest and upcoming large-scale endeavours, as is the case of ITER. Hot Swap is one of the main HA features in ATCA, allowing for Boards to be replaced in a crate (Shelf), without powering off the whole system. Platforms using the Peripheral Component Interconnect Express (PCIe) protocol on the Fabric Interface must be complemented, at the software level, with the PCIe Hot Plug native feature, currently not specified for the ATCA form-factor. From a customised Hot Plug support implementation for ATCA Node Boards, the paper presents an implementation extension for Hub Boards, allowing Hot Plug of PCIe switching devices, without causing bus enumeration problems. This paper further addresses the main issues concerning an eventual standardization of PCIe Hot Plug support in ATCA, such as the implementability of Hot Plug Elements and the generation and management of Hot Plug Events, aiming to stimulate the discussion within the PICMG community towards a long overdue standardized solution for Hot Plug in ATCA.

physics.ins-det↗

arXiv2015

Medusa: An Efficient Cloud Fault-Tolerant MapReduce

Applications such as web search and social networking have been moving from centralized to decentralized cloud architectures to improve their scalability. MapReduce, a programming framework for processing large amounts of data using thousands of machines in a single cloud, also needs to be scaled out to multiple clouds to adapt to this evolution. The challenge of building a multi-cloud distributed architecture is substantial. Notwithstanding, the ability to deal with the new types of faults introduced by such setting, such as the outage of a whole datacenter or an arbitrary fault caused by a malicious cloud insider, increases the endeavor considerably. In this paper we propose Medusa, a platform that allows MapReduce computations to scale out to multiple clouds and tolerate several types of faults. Our solution fulfills four objectives. First, it is transparent to the user, who writes her typical MapReduce application without modification. Second, it does not require any modification to the widely used Hadoop framework. Third, the proposed system goes well beyond the fault-tolerance offered by MapReduce to tolerate arbitrary faults, cloud outages, and even malicious faults caused by corrupt cloud insiders. Fourth, it achieves this increased level of fault tolerance at reasonable cost. We performed an extensive experimental evaluation in the ExoGENI testbed, demonstrating that our solution significantly reduces execution time when compared to traditional methods that achieve the same level of resilience.

cs.DC↗