Registro de fallos en accesos a caché (L2) del Pentium 4 mediante performance counters

Nuestro proyecto intentará conseguir la contabilización de los fallos en los accesos a caché de segundo nivel (L2) de un determinado proceso, para lo que trataremos de habilitar los contadores de rendimiento del Pentium 4, configurarlos para obtener la información buscada de acuerdo a los eventos a monitorizar y, por último, obtener esta información y dejarla adisposición de la aplicación de usuario que la requiera.

A multi-resource load balancing algorithm for cloud cache systems

With the advent of cloud computing model, distributed caches have become the cornerstone for building scalable applications. Popular systems like Facebook [1] or Twitter use Memcached [5], a highly scalable distributed object cache, to speed up applications by avoiding database accesses. Distributed object caches assign objects to cache instances based on a hashing function, and objects are not moved from a cache instance to another unless more instances are added to the cache and objects are redistributed. This may lead to situations where some cache instances are overloaded when some of the objects they store are frequently accessed, while other cache instances are less frequently used. In this paper we propose a multi-resource load balancing algorithm for distributed cache systems. The algorithm aims at balancing both CPU and Memory resources among cache instances by redistributing stored data. Considering the possible conflict of balancing multiple resources at the same time, we give CPU and Memory resources weighted priorities based on the runtime load distributions. A scarcer resource is given a higher weight than a less scarce resource when load balancing. The system imbalance degree is evaluated based on monitoring information, and the utility load of a node, a unit for resource consumption. Besides, since continuous rebalance of the system may affect the QoS of applications utilizing the cache system, our data selection policy ensures that each data migration minimizes the system imbalance degree and hence, the total reconfiguration cost can be minimized. An extensive simulation is conducted to compare our policy with other policies. Our policy shows a significant improvement in time efficiency and decrease in reconfiguration cost.

Trends Of CPU, GPU and FPGA for high-performance computing

Floating-point computing with more than one TFLOP of peak performance is already a reality in recent Field-Programmable Gate Arrays (FPGA). General-Purpose Graphics Processing Units (GPGPU) and recent many-core CPUs have also taken advantage of the recent technological innovations in integrated circuit (IC) design and had also dramatically improved their peak performances. In this paper, we compare the trends of these computing architectures for high-performance computing and survey these platforms in the execution of algorithms belonging to different scientific application domains. Trends in peak performance, power consumption and sustained performances, for particular applications, show that FPGAs are increasing the gap to GPUs and many-core CPUs moving them away from high-performance computing with intensive floating-point calculations. FPGAs become competitive for custom floating-point or fixed-point representations, for smaller input sizes of certain algorithms, for combinational logic problems and parallel map-reduce problems. © 2014 Technical University of Munich (TUM).

A shared-disk parallel cluster file system

Dissertação apresentada para obtenção do Grau de Doutor em Informática Pela Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia

A system’s approach to cache hierarchy-aware decomposition of data-parallel computations

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Estudi / implementació de la Qualitat de Servei en els entorns de xarxa i CPU

En aquest treball final de carrera es realitza estudi, així com la implementació, de la QoS (Quality of Service) en els entorns de xarxa i CPU sota el sistema operatiu Linux. L'objectiu és garantir uns determinats amples de banda, així com reservar porcions de CPU a través del nucli del S.O., per determinades aplicacions. D'aquesta manera es podrà obtenir una execució més eficient d'aquestes aplicacions.

Que cache l'agenda caché [What is behind the hidden agenda?]

The physicians often forget to ask their patients if they would like to discuss other complaints or topics. It is sometimes quite difficult to explore the patient's complaints; while the physicians tend to focus on the immediate problem, the patients may have not only one, but several hidden agendas during a visit. In a caring relation there is a clear advantage to clarify the implicit. The search for the hidden agenda is to improve the care of i) biomedical problems ii) the social quest presented to the physicians. The sentence "Oh, by the way, doctor..." should not be only understood as an information but also as a relational expression and a reaction to the imminent separation from the physician.

Que cache l'hypertension arterielle masquée? [What is behind masked hypertension?]

In approximately 10% of adults, ambulatory blood pressures recorded during everyday activities or selfmeasured blood pressures are abnormally elevated whereas office blood pressures are in a normal range. This type of blood pressure behavior, known as masked hypertension, is associated with an increased cardiovascular risk. It may be pertinent to search for the presence of masked hypertension in individuals having sometimes elevated, sometimes normal office blood pressures, as well as in very high risk patients and in patients requiring an optimal blood pressure control, such as for instance in those with diabetes or nephropathy.