Exploring Cross-layer power management for PGAS applications on the SCC platform

Technological limitations and power constraints are resulting in high-performance parallel computing architectures that are based on large numbers of high-core-count processors. Commercially available processors are now at 8 and 16 cores and experimental platforms, such as the many-core Intel Single-chip Cloud Computer (SCC) platform, provide much higher core counts. These trends are presenting new sets of challenges to HPC applications including programming complexity and the need for extreme energy efficiency.In this work, we first investigate the power behavior of scientific PGAS application kernels on the SCC platform, and explore opportunities and challenges for power management within the PGAS framework. Results obtained via empirical evaluation of Unified Parallel C (UPC) applications on the SCC platform under different constraints, show that, for specific operations, the potential for energy savings in PGAS is large; and power/performance trade-offs can be effectively managed using a cross-layerapproach. We investigate cross-layer power management using PGAS language extensions and runtime mechanisms that manipulate power/performance tradeoffs. Specifically, we present the design, implementation and evaluation of such a middleware for application-aware cross-layer power management of UPC applications on the SCC platform. Finally, based on our observations, we provide a set of recommendations and insights that can be used to support similar power management for PGAS applications on other many-core platforms.

Nitrogen metabolism in Zucker rats is affected by moderate reduction, but not by moderate incerase in dietary protein

Marked changes in the content of protein in the diet affects the rat"s pattern of growth, but there is not any data on the effects to moderate changes. Here we used a genetically obese rat strain (Zucker) to examine the metabolic modifications induced to moderate changes in the content of protein of diets, doubling (high-protein (HP): 30%) or halving (low-protein (LP): 8%) the content of protein of reference diet (RD: 16%). Nitrogen, energy balances, and amino acid levels were determined in lean (L) and obese (O) animals after 30 days on each diet. Lean HP (LHP) animals showed higher energy efficiency and amino acid catabolism but maintained similar amino acid accrual rates to the lean RD (LRD) group. Conversely, the lean LP (LLP) group showed a lower growth rate, which was compensated by a relative increase in fat mass. Furthermore, these animals showed greater efficiency accruing amino acids. Obesity increased amino acid catabolism as a result of massive amino acid intake; however, obese rats maintained protein accretion rates, which, in the OHP group, implied a normalization of energy efficiency. Nonetheless, the obese OLP group showed the same protein accretion pattern as in lean animals (LLP). In the base of our data, concluded that the Zucker rats accommodate their metabolism to support moderates increases in the content of protein in the diet, but do not adjust in the same way to a 50% decrease in content of protein, as shown by an index of growth reduced, both in lean and obese rats.

Secure Dynamic MANET On-demand (SEDYMO) Routing Protocol

This paper describes the state of the art of secure ad hoc routing protocols and presents SEDYMO, a mechanism to secure a dynamic multihop ad hoc routing protocol. The proposed solution defeats internal and external attacks usinga trustworthiness model based on a distributed certification authority. Digital signatures and hash chains are used to ensure the correctness of the protocol. The protocol is compared with other alternatives in terms of security strength, energy efficiency and time delay. Both computational and transmission costs are considered and it is shown that the secure protocol overhead is not a critical factor compared to the high network interface cost.

Una interpretación de los cambios de uso del suelo desde el punto de vista del metabolismo social agrario. La comarca catalana del Vallès, 1853-2004

El paisaje puede ser visto como la expresión territorial del metabolismo que cualquier sociedad mantiene con los sistemas naturales que la sustentan. Uno de los caminos para comprender cómo y por qué la intervención humana cambia la configuración del territorio consiste en analizar los flujos energéticos del intercambio metabólico de la economía con su entorno ambiental, y en identificar los impactos ecológicos que se imprimen en él. Este trabajo busca verificar, mediante la contabilidad del metabolismo social, y el empleo diacrónico de diversos índices desarrollados por la ecología del paisaje, que el enorme incremento de energía externa empleada por los sistemas agrarios tras la “revolución verde”, y la drástica reducción de su eficiencia, están estrechamente relacionados con los cambios de uso del suelo que han degradado considerablemente los tradicionales paisajes agrarios en mosaico del Mediterráneo. El recurso a flujos biofísicos externos, y el abandono del manejo integrado del territorio, han comportado una pérdida de la estructura funcional de la matriz territorial y de su conectividad ecológica. Los resultados obtenidos en cinco municipios de la comarca catalana del Vallès corroboran la estrecha relación existente durante los últimos 150 años entre la eficiencia energética y territorial, y el estado ecológico del paisaje.