Asymptotic Studies of Large Distributed systems with Failures by Philippe Robert (Inria, Paris)
Asymptotic Studies of Large Distributed systems with Failures by Philippe Robert (Inria, Paris)
– October 19, 2017
Asymptotic Studies of Large Distributed systems with Failures
The qualitative behavior of a large scale storage network of non reliable file servers is investigated. In such systems a fraction of the processing capacity can be used to duplicate files on new servers when necessary. Due to random losses, with probability 1 all files will be lost eventually if no new files are added. The main question in this context is of understanding the relation between the durability of the system and the parameters of the network: the duplication capacity, the failure rate, the duplication factor and the average load of a node. Different scalings via mean-field limits or stochastic averaging can be used to study the eventual decay of these networks. They will be reviewed and discussed. An analysis of placement algorithms will be also presented.
On-line speed scaling minimizing expected energy consumption for real-time tasks, by Stephan Plassart (Polaris)
– September 28, 2017
We present a Markov Decision Process (MDP) approach to compute the optimal on-line speed scaling policy to minimize the energy consumption of a processor executing a finite or infinite set of jobs with real-time constraints. The policy is computed off-line but used on-line. We provide several qualitative properties of the optimal policy: monotonicity with respect to the jobs parameters, comparison with on-line deterministic algorithms. Numerical experiments show that our proposition performs well when compared with off-line optimal solutions and out-performs on-line solutions oblivious to statistical information on the jobs.
Seminar Takai Kennouche : LTE/WiFi Coexistence: a WiFi interference-evasion approach
– October 9, 2017
LTE/WiFi Coexistence: a WiFi interference-evasion approach
Abstract
The growing spectrum crunch has motivated exploratory efforts in the use of LTE in the 5GHz ISM bands for downlink traffic. However, this paradigm raises concerns of fair sharing of the spectrum and the adverse impact of scheduled LTE frames on Wi-Fi Packet Success Rates (PSR). To address this issue, we propose an interference-evasion mechanism that allows Wi-Fi devices to survive LTE transmissions without any cooperation between these two different standards. Different from existing approaches, we argue that the simple use of Almost Blank Subframes (ABS) within the LTE standard offering short channel access windows overestimates opportunities for Wi-Fi. The pilots embedded in the ABS not only interfere with Wi-Fi but also adversely impact the carrier sensing function. E-Fi mitigates this problem through a two-fold approach. It uses a combination of (i) Wi-Fi Direct with packet relaying and (ii) classical distributed coordination function to reach distant nodes. Second, it ensures load balancing for both Wi-Fi uplink and downlink traffic with high PSR by creating node-groups with dedicated contention-based medium access intervals. Our approach is validated by comprehensive simulation and experimental results that indicate significantly higher throughput in our approach compared to classical Wi-Fi.
Asymptotic Studies of Large Distributed systems with Failures by Philippe Robert (Inria, Paris)
– October 19, 2017
Asymptotic Studies of Large Distributed systems with Failures
The qualitative behavior of a large scale storage network of non reliable file servers is investigated. In such systems a fraction of the processing capacity can be used to duplicate files on new servers when necessary. Due to random losses, with probability 1 all files will be lost eventually if no new files are added. The main question in this context is of understanding the relation between the durability of the system and the parameters of the network: the duplication capacity, the failure rate, the duplication factor and the average load of a node. Different scalings via mean-field limits or stochastic averaging can be used to study the eventual decay of these networks. They will be reviewed and discussed. An analysis of placement algorithms will be also presented.
Association dans les réseaux WiFi, par Isabelle Guerin (Lyon)
– October 26, 2017
Les déploiements de réseaux WiFi denses permettent à une station d’avoir le choix entre plusieurs points d’accès lors de la connexion au réseau WiFi, améliorant ainsi la couverture radio, la qualité des liens radio et facilitant la mobilité. En contrepartie, la densité des points d’accès peut générer plus d’interférences et de contention, ce qui peut amener à une baisse du débit global puisque ces points d’accès doivent partager un nombre limité de canaux. Le retour à une gestion centralisée des réseaux WiFi offre l’opportunité d’une optimisation globale de l’usage de la ressource radio et donc de réduire les problèmes soulevés lors d’un partage intensif de cette dernière.
Dans cet exposé, je vous montrerai, qu’en modifiant l’étape d’association dans les réseaux WiFi (qui est dans les interfaces WiFi actuelles basée sur le RSSI -Received Signal Strength Indicator-), il est possible d’améliorer le débit global du réseau ainsi que l’équité entre les stations.
Detecting Performance Outliers for Task-based HPC Applications in multi-[CPU|GPU|Node] clusters By Lucas Schnorr (Porto Allegre)
– November 16, 2017
Detecting Performance Outliers for Task-based HPC Applications in
multi-[CPU|GPU|Node] clusters
Programming paradigms in High-Performance Computing have
been shifting towards task-based models which are capable of
adapting readily to heterogeneous and scalable
supercomputers. Detecting performance outliers in such environments
is particularly difficult because it must consider architecture
heterogeneity and variability. In this work we present how we have
employed a very simple performance model to highlight task outliers
of the well-known tiled-based dense Cholesky factorization running
on top of StarPU-MPI, a runtime for task-based applications. Such
work has been integrated into our visualization framework based on the
R programming language and the tidyverse meta-package. Experiments
have been conducted in a controlled environment using the Chifflet
cluster at Lille, part of the Grid'5000 infrastructure, using up to
eight nodes, each one equipped with 28 cores and two GPUs. The
preliminary results, derived from collected traces, indicate that
explicit binding for the MPI and GPU-managing threads, within
StarPU, alleviate the issue, leading to performance gains.
Convergence d’algorithme de non regret, Amélie Heliou (Polaris)
– November 30, 2017
Les algorithmes de non-regret sont souvent utilisés dans les jeux répétés où les joueurs ont peu d’information sur le jeu auquel ils jouent. Ces algorithmes garantissent que le regret de chaque joueur est sous-linéaire. La moyenne temporelle des stratégies choisies en suivant un algorithme de non-regret converge dans l’ensemble des équilibres corrélés. Cependant cela ne donne aucune information sur la convergence de la séquence de stratégies.
Nous nous sommes intéressés à la question « est-ce que la sequence de stratégie obtenue pas un algorithme de non regret converge vers un équilibre de Nash? ».
Dans cet exposé, je présenterai un algorithme de non regret appelé Hedge qui est une version d’algorithmes à poids exponentiels. En particulier, je discuterai la convergence des séquences de stratégies obtenues par Hedge en utilisant deux types d’informations accessibles aux joueurs.
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.
