Prediction-Based Power-Performance Adaptation of Multithreaded Scientific Codes

Computing has recently reached an inflection point with the introduction of multicore processors. On-chip thread-level parallelism is doubling approximately every other year. Concurrency lends itself naturally to allowing a program to trade performance for power savings by regulating the number of active cores; however, in several domains, users are unwilling to sacrifice performance to save power. We present a prediction model for identifying energy-efficient operating points of concurrency in well-tuned multithreaded scientific applications and a runtime system that uses live program analysis to optimize applications dynamically. We describe a dynamic phase-aware performance prediction model that combines multivariate regression techniques with runtime analysis of data collected from hardware event counters to locate optimal operating points of concurrency. Using our model, we develop a prediction-driven phase-aware runtime optimization scheme that throttles concurrency so that power consumption can be reduced and performance can be set at the knee of the scalability curve of each program phase. The use of prediction reduces the overhead of searching the optimization space while achieving near-optimal performance and power savings. A thorough evaluation of our approach shows a reduction in power consumption of 10.8 percent, simultaneous with an improvement in performance of 17.9 percent, resulting in energy savings of 26.7 percent.

Individual and Public-Program Adaptation: Coping with Heat Waves in Five Cities in Canada

Heat Alert and Response Systems (HARS) are currently undergoing testing and implementation in Canada. These programs seek to reduce the adverse health effects of heat waves on human health by issuing weather forecasts and warnings, informing individuals about possible protections from excessive heat, and providing such protections to vulnerable subpopulations and individuals at risk. For these programs to be designed effectively, it is important to know how individuals perceive the heat, what their experience with heat-related illness is, how they protect themselves from excessive heat, and how they acquire information about such protections. In September 2010, we conducted a survey of households in 5 cities in Canada to study these issues. At the time of the survey, these cities had not implemented heat outreach and response systems. The study results indicate that individuals' recollections of recent heat wave events were generally accurate. About 21% of the sample reported feeling unwell during the most recent heat spell, but these illnesses were generally minor. Only in 25 cases out of 243, these illnesses were confirmed or diagnosed by a health care professional. The rate at which our respondents reported heat-related illnesses was higher among those with cardiovascular and respiratory illnesses, was higher among younger respondents and bore no relationship with the availability of air conditioning at home. Most of the respondents indicated that they would not dismiss themselves as

Determination of the Tolman length in the improved Derjaguin-Broekhoff-de Boer theory for capillary condensation of ethanol in mesoporous thin films by ellipsometric porosimetry

Ethanol adsorption-desorption isotherms on well-organized mesoporous silica and titania films with hexagonal pores structure were studied by ellipsometric porosimetry. The mesopore volume Was calculated from the change of the effective refractive index at the end points of the isotherm. An improved Derjaguin-Broekhoff-de Boer (IDBdB) model for cylindrical pores is proposed for the determination of the pore size. In this model, the disjoining pressure isotherms were obtained by measuring the thickness of the ethanol film on a non-porous film with the same chemical composition. This approach eliminates uncertainties related to the application of the statistical film thickness determined via t-plots in previous versions of the DBdB model. The deviation in the surface tension of ethanol in the mesopores from that of a flat interface was described by the Tolman parameter in the Gibbs-Tolman-Koening-Buff equation. A positive value of the Tolman parameter of 0.2 nm was found from the fitting of the desorption branch of the isotherms to the experimental data obtained by Low Angle X-ray Diffraction (LA-XRD) and Transmission Electron Microscopy (TEM) measurements in the range of pore diameters between 2.1 and 8.3 nm. (C) 2009 Elsevier Inc. All rights reserved.

Role of the plasma scale length in the harmonic generation from solid targets

We have investigated the generation of high harmonics from the interaction of 150 fsec, 790 nm, and 395 nm laser pulses with solid targets. Experiments are presented that demonstrate a strong dependence of the conversion efficiency on the temporal pulse shape and the resulting density scale length (L/lambda) of the preformed plasma. The highest conversion efficiencies are achieved for short density scale lengths (L/lambda less than or equal to 0.4), which result from high contrast ratio pulse interactions. [S1063-651X(98)50211-5].

Assessing length of stay and associated characteristics of geriatric patients in Northern Ireland

The effective provision of care for the elderly is becoming increasingly more difficult. This is due to the rising proportion of elderly in the population, increasing demands placed on the health services and the financial strain placed on an already stretched economy. The research presented in this paper uses three different models to represent the length of stay distribution of geriatric patients admitted to one of the six key acute hospitals in Northern Ireland and various patient characteristics associated with their respective length of stay. The accurate modelling of bed usage within wards would enable hospital managers to prepare patient discharge packages and rehabilitation services in advance. The models presented within the paper include a Cox proportional hazards model, a Bayesian network with a discrete variable to represent length of stay and a special conditional phase-type model (C-Ph) with a connecting outcome node. This research demonstrates the new efficient fitting algorithm employed for Coxian phase-type distributions while updating C-Ph models for recent elderly patient data.