No abstract

This paper presents an energy efficiency and I/O performance analysis of low-power architectures when compared to conventional architectures, with the goal of studying the viability of using them as storage servers. Our results show that despite the fact the power demand of the storage device amounts for a small fraction of the power demand of the whole system, significant increases in power demand are observed when accessing the storage device. We investigate the access pattern impact on power demand, looking at the whole system and at the storage device by itself, and compare all tested configurations regarding energy efficiency. Then we extrapolate the conclusions from this research to provide guidelines for when considering the replacement of traditional storage servers by low-power alternatives. We show the choice depends on the expected workload, estimates of power demand of the systems, and factors limiting performance. These guidelines can be applied for other architectures than the ones used in this work.

As large-scale parallel platforms are deployed to comply with the increasing performance requirements of scientific applications, a new concern is getting the attention of the HPC community: the power consumption. In this paper, we aim at evaluating the viability of using low-power architectures as file systems servers in HPC environments, since processing power is of less importance for these servers. We present a performance and energy efficiency study of such low-power servers when compared to conventional architectures. Our results indicate that the low-power alternative could be a viable choice to save energy by up to 85% while not compromising on performance, specially for read-intensive workloads. We show the low-power server provides 7 times more energy efficiency to the system while running a real application from the seismic wave propagation field.

Resumo-Técnicas automáticas de identificação da doença oculares são muito importantes no campo da oftalmologia. As técnicas convencionais de identificação de doenças da retina são baseadas em observações manuais dos componentes da retina (discoóptico, mácula, vasos etc.) e são altamente suscetíveis e propensas a erros. Daí, a necessidade de técnicas automáticas que eliminem esses inconvenientes. Apesar de todos os avanços, os sistemas de identificação dos componentes da retina, ainda não podem ser utilizados na prática por causa da enorme diversidade de imagens. Em particular, imagens muito degradadas por patologias possuem muitos artefatos que dificultam a tarefa de detecção. Neste artigo, apresentamos uma proposta de aplicação de algoritmos de aprendizado de máquina na identificação de retinas patológicas. Dessa forma, um sistema automático de auxílio ao diagnóstico poderá identificar quais imagens deverão ter uma atenção maior do médico especialista. Palavras-chaveaprendizagem de máquina, imagens de retina, diagnóstico auxiliado por computador Abstract-Automated techniques for identification of eye disease are very important in the field of ophthalmology. Conventional techniques for the identification of retinal disease are based on manual observations of the components of the retina (the optic disc, macula, vessels, etc..) And are highly susceptible and prone to errors. Hence, there is a necessity for automated techniques that eliminate these drawbacks. Despite all the advances, the systems for identifying the components of the retina, still can not be used in practice because of the large diversity of images. In particular, images degraded by pathology has too many artifacts that complicate the task of detection. This paper presents a proposal for application of machine learning algorithms to identify pathological retinas. Thus, the computer-aided diagnosis system can identify which images should have a greater attention of the specialist doctor.