High-Performance Computing (HPC) in the cloud has reached the mainstream and is currently a hot topic in the research community and the industry. The attractiveness of cloud for HPC is the capability to run large applications on powerful, scalable hardware without needing to actually own or maintain this hardware. In this paper, we conduct a detailed comparison of HPC applications running on three cloud providers, Amazon EC2, Microsoft Azure and Rackspace. We analyze three important characteristics of HPC, deployment facilities, performance and cost efficiency and compare them to a cluster of machines.For the experiments, we used the well-known NAS parallel benchmarks as an example of general scientific HPC applications to examine the computational and communication performance. Our results show that HPC applications can run efficiently on the cloud. However, care must be taken when choosing the provider, as the differences between them are large. The best cloud provider depends on the type and behavior of the application, as well as the intended usage scenario. Furthermore, our results show that HPC in the cloud can have a higher performance and cost efficiency than a traditional cluster, up to 27% and 41%, respectively. C OpenMP, MPI LU Lower and Upper Triangular Regular communication Fortran OpenMP, MPI MG Multigrid Regular communication Fortran OpenMP, MPI SP Scalar Pentadiagonal Floating point performance Fortran OpenMP, MPI UA Unstructured Adaptive Irregular communication Fortran OpenMP B. Machines
Abstract-Currently, parallel platforms based on large scale hierarchical shared memory multiprocessors with NonUniform Memory Access (NUMA) are becoming a trend in scientific High Performance Computing (HPC). Due to their memory access constraints, these platforms require a very careful data distribution. Many solutions were proposed to resolve this issue. However, most of these solutions did not include optimizations for numerical scientific data (array data structures) and portability issues. Besides, these solutions provide a restrict set of memory policies to deal with data placement. In this paper, we describe an user-level interface named Memory Affinity interface (MAi) 1 , which allows memory affinity control on Linux based cache-coherent NUMA (ccNUMA) platforms. Its main goals are, fine data control, flexibility and portability. The performance of MAi is evaluated on three ccNUMA platforms using numerical scientific HPC applications, the NAS Parallel Benchmarks and a Geophysics application. The results show important gains (up to 31%) when compared to Linux default solution.
Objective: Although studies have shown an association between poor sleep and chronotype with psychiatric problems in young adults, few have focused on identifying multiple concomitant risk factors. Methods: We assessed depressive symptoms (Beck Depression Inventory [BDI]), circadian typology (Morningness-Eveningness Questionnaire [MEQ]), sleep quality (Pittsburgh Sleep Quality Index [PSQI]), perceived stress (Perceived Stress Scale [PSS]), social rhythm (Social Rhythm Metrics [SRM]), and salivary cortisol (morning, evening and night, n=37) in 236 men (all 18 years old). Separate analyses were conducted to understand how each PSQI domain was associated with depressive symptoms. Results: Depressive symptoms were more prevalent in individuals with higher perceived stress (prevalence ratio [PR] = 6.429, p o 0.001), evening types (PR = 2.58, p o 0.001) and poor sleepers (PR = 1.808, p = 0.046). Multivariate modeling showed that these three variables were independently associated with depressive symptoms (all p o 0.05). The PSQI items subjective sleep quality and sleep disturbances were significantly more prevalent in individuals with depressive symptoms (PR = 2.210, p = 0.009 and PR = 2.198, p = 0.008). Lower levels of morning cortisol were significantly associated with higher depressive scores (r =-0.335; p = 0.043). Conclusion: It is important to evaluate multiple factors related to sleep and chronotype in youth depression studies, since this can provide important tools for comprehending and managing mental health problems.
RESUMO.-A cinomose canina é uma doença viral e afeta principalmente os sistemas respiratório, gastrintestinal e nervoso. Neste trabalho foram analisados os achados patológicos e imuno-histoquímicos de 54 cães com cinomose de um total de 760 cães necropsiados no período de julho de 2006 a outubro de 2007. As lesões macroscó-picas observadas foram caracterizadas por corrimento ocular e nasal mucopurulentas, hiperqueratose dos coxins digitais, pulmões avermelhados e não colapsados, atrofia do timo, conteúdo intestinal diarréico e placas de Peyer proeminentes. Os achados histológicos caracterizavamse principalmente por pneumonia intersticial, rarefação linfóide, desmielinização da substância branca, manguitos perivasculares e corpúsculos de inclusão intranucleares e intracitoplasmáticos, que se localizam principalmente na mucosa do estômago, epitélios da bexiga, brônquios e bronquíolos, pelve renal, coxins digitais, pálpebra, orelha e tonsila no sistema nervoso central e em células mononucleares dos linfonodos, baço e tonsilas. Os tecidos foram marcados pela técnica imuno-histoquímica utilizan- Canine distemper is a viral disease that affects mainly respiratory, gastrointestinal and nervous system. The present study analyzes pathologic and immunohistochemical findings in 54 dogs with canine distemper of a total of 760 canine necropsies performed from July 2006 to October 2007. The gross lesions were characterized by mucopurulent oculonasal discharge, hyperkeratosis of footpads, red and not collapsed lungs, thymic atrophy, watery intestinal content, hyperemia and enlarged Peyer's patches. The histological findings were characterized by interstitial pneumonia, lymphoid depletion, white matter demyelization, perivascular cuffs and intracytoplasmatic and intranuclear inclusion bodies located in epithelial cells of gastric mucosa, urinary bladder, bronchial, renal pelvis, footpads, eyelid, skin of the ear, tonsil, central nervous system and mononuclear cells in lymph nodes, spleen, and tonsils. Viral antigen was detected by an immunohistochemical procedure using a mouse monoclonal anti-canine distemper antibody. The footpads were the more constantly (67.4% of the cases) immunolabeled tissue, followed by stomach with 62.7%. Immunohistochemistry was demonstrated to be a useful tool for the study of viral antigen distribution in distemper affected dogs as well as it indicated which is the best tissue to be examined in order to confirm a suspected case of canine.INDEX TERMS: Canine diseases, distemper, immunohistochemistry.
Despite emerging evidence that disruption in circadian rhythms may contribute to the pathophysiology of psychiatric disorders, there is a significant knowledge gap on the rhythmicity of psychological symptoms. Here, we aimed at investigating the rhythmicity of mood symptoms in individuals at risk for psychiatric disorders. 391 Brazilian and 317 Spanish participants completed the Self-Reporting Questionnaire-20 for non-psychotic mental disorders; the Mood Rhythm Instrument was used to assess rhythmicity of mood symptoms and the Munich ChronoType Questionnaire to assess sleep patterns. We found that the rhythmicity of specific mood-related symptoms and behaviors, particularly pessimism and motivation to exercise, were associated with being at risk for psychiatric disorders, even after controlling for sleep timing, sleep deficit, and season of data collection. We also found that the peak of some mood symptoms and behaviors were different between individuals at high vs. low risk for psychiatric disorders, with specific differences between countries. These results are consistent with previous research showing that circadian misalignment is associated with higher risk for mental health conditions. These findings also suggest that lifestyle changes preventing circadian misalignment might be useful to reduce the risk of psychiatric disorders, where cultural differences must be taken into account.
The circadian perspective seems to provide promising insight into childhood obesity, but this aspect needs to be further explored.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.