Paging tradeoffs in distributed-shared-memory multiprocessors

Massively parallel processors have begun using commodity operating systems that support demand-paged virtual memory. To evaluate the utility of virtual memory, we measured the behavior of seven shared-memory parallel application programs on a simulated distributed-shared-memory machine. Our results (1) confirm the importance of gang CPU scheduling, (2) show that a page-faulting processor should spin rather than invoke a parallel context switch, (3) show that our parallel programs frequently touch most of their data, and (4) indicate that memory, not just CPUs, must be gang scheduled. Overall, our experiments demonstrate that demand paging has limited value on current parallel machines because of the applications' synchronization and memory reference patterns and the machines' high page-fault and parallel context-switch overheads.An earlier version of this paper was presented at Supercomputing '94.This work is supported in part by NSF Presidential Young Investigator Award CCR-9157366; NSF Grants MIP-9225097, CCR-9100968, and CDA-9024618; Office of Naval Research Grant N00014-89-J-1222; Department of Energy Grant DE-FG02-93ER25176; and donations from Thinking Machines Corporation, Xerox Corporation, and Digital Equipment Corporation.     

Higher-order schemes for the Laplace transformation method for parabolic problems

In this paper we solve linear parabolic problems using the three stage noble algorithms. First, the time discretization is approximated using the Laplace transformation method, which is both parallel in time (and can be in space, too) and extremely high order convergent. Second, higher-order compact schemes of order four and six are used for the the spatial discretization. Finally, the discretized linear algebraic systems are solved using multigrid to show the actual convergence rate for numerical examples, which are compared to other numerical solution methods.     

Unified computational methods for regression analysis of zero-inflated and bound-inflated data

Bounded data with excess observations at the boundary are common in many areas of application. Various individual cases of inflated mixture models have been studied in the literature for bound-inflated data, yet the computational methods have been developed separately for each type of model. In this article we use a common framework for computing these models, and expand the range of models for both discrete and semi-continuous data with point inflation at the lower boundary. The quasi-Newton and EM algorithms are adapted and compared for estimation of model parameters. The numerical Hessian and generalized Louis method are investigated as means for computing standard errors after optimization. Correlated data are included in this framework via generalized estimating equations. The estimation of parameters and effectiveness of standard errors are demonstrated through simulation and in the analysis of data from an ultrasound bioeffect study. The unified approach enables reliable computation for a wide class of inflated mixture models and comparison of competing models.     

Robustness of design for the testing of lack of fit and for estimation in binary response models

Experimentation in scientific or medical studies is often carried out in order to model the ‘success’ probability of a binary random variable. Experimental designs for the testing of lack of fit and for estimation, for data with binary responses depending upon covariates which can be controlled by the experimenter, are constructed. It is supposed that the preferred model is one in which the probability of the occurrence of the target outcome depends on the covariates through a link function (logistic, probit, etc.) evaluated at a regression response — a function of the covariates and of parameters to be estimated from the data, once gathered. The fit of this model is to be tested within a broad class of alternatives over which the regression response varies. To this end, the problem is phrased as one of discriminating between the preferred model and the class of alternatives. This, in turn, is a hypothesis testing problem, for which the asymptotic power of the test statistic is directly related to the Kullback-Leibler divergence between the models, averaged over the design. ‘Maximin’ designs, which maximize (through the design) the minimum (among the class of alternative models) value of this power together with a measure of the efficiency of the parameter estimates are also constructed. Several examples are presented in detail; two of these relate to a medical study of fluoxetine versus a placebo in depression patients. The method of design construction is computationally intensive, and involves a steepest descent minimization routine coupled with simulated annealing.     

The Effects of Survey Administration on Disclosure Rates to Sensitive Items Among Men: A Comparison of an Internet Panel Sample with a RDD Telephone Sample

Research using Internet surveys is an emerging field, yet research on the legitimacy of using Internet studies, particularly those targeting sensitive topics, remains under-investigated. The current study builds on the existing literature by exploring the demographic differences between Internet panel and RDD telephone survey samples, as well as differences in responses with regard to experiences of intimate partner violence perpetration and victimization, alcohol and substance use/abuse, PTSD symptomatology, and social support. Analyses indicated that after controlling for demographic differences, there were few differences between the samples in their disclosure of sensitive information, and that the online sample was more socially isolated than the phone sample. Results are discussed in terms of their implications for using Internet samples in research on sensitive topics.     

Assessing the state of software in a large enterprise

To be relevant to the goals of an enterprise, an industrial software engineering research organization must identify problems of interest to, and find solutions that have an impact on, the software development organizations within the company. Using a systematic measurement program both to identify the problems and assess the impact of solutions is key to satisfying this need. Avaya has had such a program in place for about seven years. Every year we produce an annual report known as the State of Software in Avaya that describes software development trends throughout the company and that contains prioritized recommendations for improving Avaya’s software development capabilities. We start by identifying the goals of the enterprise and use the goal-question-metric approach to identify the measures to compute. The result is insight into the enterprise’s problems in software development, recommendations for improving the development process, and problems that require research to solve. We will illustrate the process with examples from the Software Technology Research Department in Avaya Labs whose purpose is to improve the state of software development and know it. “Know it” means that improvement should be subjectively evident and objectively quantifiable. “Know it” also means that one must be skilled at identifying the data sources, performing the appropriate analyses to answer the questions of interest, and validating that the data are accurate and appropriate for the purpose. Examples will include how and why we developed a measure of software quality that appeals to customers, how and why we are studying the effectiveness of distributed software development, and how and why we are helping development organizations to adopt iterative development methods. We will also discuss how we keep the company and the department apprised of the current strengths and weaknesses of software development in Avaya through the publication of the annual State of Software in Avaya Report. Our purpose is both to provide a model for assessment that others may emulate, based on seven years of experience, and to spotlight analyses and conclusions that we feel are common to software development today.     

Implementation and analysis of multigrid schemes with finite elements for elliptic optimal control problems

The detailed implementation and analysis of a finite element multigrid scheme for the solution of elliptic optimal control problems is presented. A particular focus is in the definition of smoothing strategies for the case of constrained control problems. For this setting, convergence of the multigrid scheme is discussed based on the BPX framework. Results of numerical experiments are reported to illustrate and validate the optimal efficiency and robustness of the performance of the present multigrid strategy.     

Bryophyte cover estimation in a boreal black spruce forest using airborne lidar and multispectral sensors

Bryophytes are the dominant ground cover vegetation layer in many boreal forests and in some of these forests the net primary production of bryophytes exceeds the overstory. Therefore it is necessary to quantify their spatial coverage and species composition in boreal forests to improve boreal forest carbon budget estimates. We present results from a small exploratory test using airborne lidar and multispectral remote sensing data to estimate the percentage of ground cover for mosses in a boreal black spruce forest in Manitoba, Canada. Multiple linear regression was used to fit models that combined spectral reflectance data from CASI and indices computed from the SLICER canopy height profile. Three models explained 63-79% of the measured variation of feathermoss cover while three models explained 69-92% of the measured variation of sphagnum cover. Root mean square errors ranged from 3-15% when predicting feathermoss, sphagnum, and total moss ground cover. The results from this case study warrant further testing for a wider range of boreal forest types and geographic regions.     

Boundary Detection in Particle‐based Fluids

This paper presents a novel method to detect free‐surfaces on particle‐based volume representation. In contrast to most particle‐based free‐surface detection methods, which perform the surface identification based on physical and geometrical properties derived from the underlying fluid flow simulation, the proposed approach only demands the spatial location of the particles to properly recognize surface particles, avoiding even the use of kernels. Boundary particles are identified through a Hidden Point Removal (HPR) operator used for visibility test. Our method is very simple, fast, easy to implement and robust to changes in the distribution of particles, even when facing large deformation of the free‐surface. A set of comparisons against state‐of‐the‐art boundary detection methods show the effectiveness of our approach. The good performance of our method is also attested in the context of fluid flow simulation involving free‐surface, mainly when using level‐sets for rendering purposes.