John R. Rice

Purdue University West Lafayette | Purdue ·  Department of Computer Science

HCF of turbomachinery blading is a significant design problem because fatigue failures can result from resonant vibratory stresses sustained over a relatively short time. Fatigue failure result from a combination of steady stress, vibratory stress, and material imperfections. However, the size of microscopic imperfections is difficult to control. H...

We consider computations associated with data parallel iterative solvers used for the numerical solution of Partial Differential Equations (PDEs). The mapping of such computations into load balanced tasks requiring minimum synchronization and communication is a difficult combinatorial optimization problem. Its optimal solution is essential for the...

There are many practical situations in which, by policy, software is supposed to run on a specific hardware instance. This is not only useful to combat piracy, but also in national security situations, such as a battlefield loss of critical technology, where it is paramount that an enemy be unable to rehost the system on a different set of (possibl...

The combination of the recent advances in computational and distributed sensor network technologies provide a unique opportunity for focused efforts on high confidence modelling and simulation of multiphysics systems. Responding to this opportunity, we present in this paper the architecture of a data-driven environment for multiphysics applications...

We describe a protocol to solve the problem of comparing fingerprints without actually exchanging them. We extend this to private verification where the verifier does not obtain fingerprint information. We show that no substantial information is leaked to the other party even during multiple protocol runs and present evaluation results from a proto...

The design architecture of a multidisciplinary problem-solving environment (MPSE) for supporting an efficient prediction capability for the response of continuous interacting systems under multiphysics conditions is presented. The system will be referred to as a Data Driven Environment for Multiphysics Applications (DDEMA) and will be primarily dif...

The focus of this paper is the application and extension of the knowledge discovery in databases process [5] developed in PYTHIA recommender system, to analyze the behavior of a DOE ASCI application/hardware pairs in the context of POEMS project[4]. The POEMS project has built a library of models for modeling scalable architectures like those in th...

In this paper we present the design of a multidisciplined problem solving environment (MPSE) for supporting an ecient pre- diction capability for the response of multiscale interdisciplinary con- tinuous interacting systems. This design takes into consideration infor- mation technologies, coupled multiphysics sciences, and data-driveness to steer a...

The method of lines is a widely used algorithm for solving parabolic partial differential equations that could benefit greatly from implementation on Grid computing environments. This paper outlines the issues involved in executing method-of-lines codes on a Grid and in developing model-driven adaptive control strategies for these codes. We have de...

Gas turbine engines are very complex (with 20–40,000 parts) and have extreme operating conditions. The important physical phenomena take place on scales from 10–100 microns to meters. A complete and accurate dynamic simulation of an entire engine is enormously demanding. Designing a complex system, like a gas turbine engine, will require fast, accu...

We outline the design of a recommendation system (MyPYTHIA) implemented as a Web portal. MyPYTHIA's design objectives include evaluating the quality and performance of scientific software on Grid platforms, creating knowledge about which software and computational services should be selected for solving particular problems, selecting parameters of...

In this paper we define a knowledge discovery in databases (KDD) methodology to automatically generate metadata (i.e., knowledge rules) from software/machine pair performance databases. This metadata can be used to characterize the computational behavior of various classes of software or machines. The core and the most computationally intensive par...

Complex problems, whether scientific or engineering, are most often solved today by utilizing public domain or commercial libraries or some form of problem solving environment. The task of "selecting" the best software for a targeted application or computation is often difficult and sometimes even intractable. We have proposed an approach for deali...

We describe the design and implementation of GAUSS — an online algorithm selection system for numerical quadrature. Given a quadrature problem and performance constraints on its solution, GAUSS selects the best (or nearly best) algorithm. GAUSS uses inductive logic programming to generalize a database of performance data; this produces high-level r...

Model-based control utilizes performance models of applications to choose performant system configurations for execution of applications. The performance models used in this research separate specification of the software system from specification of the execution environment so that model-based control can select software configurations for a give...

Introduction This paper presents an extension and application of the algorithm in [2]. We refer to this algorithm as FIXEDKNOT. FIXEDKNOT is for the computation of least-squares approximations on finite point sets by cubic polynomial splines with fixed knots. The algorithm presented here incorporates FIXEDKNOT and treats the knots as variables. The...

This paper presents an algorithm for the computation of the least-squares approximation to a given function u by cubic splines with a given fixed set of knots. But since the successful use of splines for purposes of "smoothly" approximating a given set of data depends strongly on the proper placement of the knots, the algorithm is written so as to...

Two simple interface relaxation techniques for solving elliptic differential equations are considered. A theoretical analysis is carried out at the differential level and "optimal" relaxation parameters are obtained for model problems. A comprehensive experimental numerical study for 1- and 2-dimensional problems is also presented. We present a com...

We investigate the outsourcing of numerical and scientific computations using the following framework: A customer who needs computations done but lacks the computational resources (computing power, appropriate software, or programming expertise) to do these locally would like to use an external agent to perform these computations. This currently ar...

In this paper we review the current state of the problem solving environment (PSE) field and make projections for the future. First we describe the computing context, the definition of a PSE and the goals of a PSE. The state-of-the-art is summarized along with the principal components and paradigms for building PSEs. The discussion of the future is...

this paper, we describe the PYTHIA-II architecture and its use as an RS for PDE software

The POEMS project is creating an environment for end-to-end performance modeling of complex parallel and distributed systems, spanning the domains of application software, runtime and operating system software, and hardware architecture. Toward this end, the POEMS framework supports composition of component models from these different domains into...

The simulation and modeling of complex physical systems often involves many components because (1) the physical system itself has components of differing natures, (2) parallel computing strategies require many (somewhat independent) components, and (3) existing simulation software applies only to simpler geometrical shapes and physical situations....

The simulation and modeling of complex physical systems often involves many components because (i) the physical system itself has components of differing natures, (ii) parallel computing strategies require many (somewhat independent) components, and (iii) existing simulation software applies only to simpler geometrical shapes and physical situation...

this document, we describe the initial design of a generic MPSE framework based on a network of computational agents assuming a net-centric run-time support environment. Moreover, we present the realization of this framework for designing a prototype MPSE (GasTurbnLab) for supporting simulations needed for the design of efficient gas turbine engine...

Often scientists need to locate appropriate software for their problems and then select from among many alternatives. We have previously proposed an approach for dealing with this task by processing performance data of the targeted software. This approach has been tested using a customized implementation referred to as PYTHIA. This experience made...

s Mathematical software libraries were introduced in the 1960s to support the reuse of high quality software as a means of transferring numerical analysis and algorithmic expertise to practitioners. Specialized journals, conferences, software repositories (e.g., ACM CALGO, Netlib), and commercial libraries (i.e., IMSL, NAG) were established to supp...

The POEMS project is creating an environment for end-to-end performance modeling of complex parallel and distributed systems, spanning the domains of application software, runtime and operating system software, and hardware architecture. Towards this end, the POEMS framework supports composition of component models from these different domains. The...

The simulation of complex physical systems often involves solving a large system of partial differential equations (PDEs). We discuss how solving such a system of PDEs can be done by splitting a domain into several sub-domains and creating of a network of PDE solvers. In such a network several agents are used to: (a) control the execution of indivi...

Rapid advances in modern networking technologies and commodity high performance computing systems are leading the field of computing in a new paradigm referred to as network-based computing (NC). This paradigm views a large number of geographically distributed computer resources such as PCs, workstations, Symmetric Multi-processors (SMP) and Massiv...

Problem Solving Environments (PSEs) are very high level software environments that provide all the facilities needed for handling some class of problems. It is clear that building PSEs is a costly endeavor both in terms of the person-years required and the diversity of knowledge and expertise required. This paper describes the Purdue PSE Kernel (PP...

The Internet offers scientists round the world access to high-powered problem- solving environments. With Purdue’s Net PELLPACK, they can solve complex partial differential equations with common Web browsers that support Java applets. This chapter presents the architecture of a PSE server and identifies the associated research issues.

Researchers from several universities, national laboratories, software companies, and government funding agencies participated in the 1998 Scientific Integrated Development Environments for Knowledge, Information, and Computing Workshop. This meeting summarized the state-of-the-art in the area of Problem-Solving Environments (PSEs) for scientific a...

As the reader would have discovered by now, the field of PSEs is sufficiently wide and open to make it impractical to compile and print a comprehensive bibliography that would be restricted to any reasonable page limits. Paraphrasing Jonathon Green4, the nature of bibliography compilation, whether in fonn or content, brings with it decisions, and w...

Very often scientists are faced with the task of locating appropriate solution software for their problems and then selecting from among many alternatives. In #Houstis et al. 1991# we had proposed an approach for dealing with this task by #processing# performance data of the targeted software. The validation of the approach is de# scribed in #Weera...

The POEMS project is creating an environment for endto -end performance modeling of complex parallel and distributed systems, spanning the domains of application software, runtime and operating system software, and hardware architecture. To enable end-to-end modeling of large-scale applications and systems, the POEMS framework is designed to compos...

this article is that agent-based computing provides important advantages for scientific computing. We present our ideas in the context of a particular application, the simulation of gas turbine engines. This application is typical in that it involves an enormously complex device of great economic importance, one whose design is continually evolving...

Computational science's driving force has been and will continue to be the steady and rapid growth in available raw computing power. This growth exceeds anything else witnessed in the history of technology. The challenge for the 21st Century is to exploit properly this enormous potential. Several fairly obvious directions of development can (and do...

The enormous amount of data that can be collected in any performance evaluation study of a complex system indicates the need for methodologies and systems capable of analyzing, fusing and reducing high-dimensional data spaces with very high speed. In this paper, we devise and present an adaptation of the Knowledge Discovery in Databases (KDD) frame...

An adaptive procedure, based on Automatic Differentiation, for estimating "good" values for the relaxation paramaters for general multi-dimensional problems is proposed.

In this paper we present a paradigm for simulating complex systems. Such systems, typically found in Scientific and Engineering domains (simulating an engine, designing an airplane wing), involve multiple physical phenomena with complicated geometry. The computational techniques we propose use cooperating agents. Our focus in this paper will be on...

Introduction to MPSEs Computational modeling in the (near) future will operate at the scale of entire physical systems. These systems will have many components that have different shapes, obey different physical laws, and interact with each other through geometric and physical interfaces. The design of an entire physical system requires that these...

The process of prototyping is part of every scientific inquiry, product design, and learning activity. Economic realities require fast, accurate prototyping using knowledge and computational models from multiple disciplines in science and engineering [l, 3, 15, 47, 491. Thus rapid multidisciplinary problem solving orprototyping is a new grand chall...

This paper presents the software architecture and implementation of the problem solving environment (PSE) PELLPACK for modeling physical objects described by partial differential equations (PDEs). The scope of this PSE is broad as PELLPACK incorporates many PDE solving systems and some of these, in turn, include several specific PDE solving methods...

. In this study we analyze a non-overlapping domain decomposition method for the solution of elliptic Partial Differential Equation (PDE) problems. This domain decomposition method involves the solution of Dirichlet and Neumann PDE problems on each subdomain, coupled with smoothing operations on the interfaces of the subdomains. The convergence ana...

In this study we analyze a nonoverlapping domain decomposition method for the solution of elliptic Partial Differential Equation (PDE) problems. This domain decomposition method involves the solution of Dirichlet and Neumann PDE problems on each subdomain, coupled with smoothing operations on the interfaces of the subdomains. The convergence analys...

A population of eight non-overlapping domain decomposition methods for solving Elliptic Differential Equations viewed and formulated as iterated interface relaxation procedures is considered. A comprehensive review of the underlying mathematical ideas and the computational characteristics is given. The existing theoretical results are also reviewed...

The Internet offers scientists around the world access to high-powered problem-solving environments (PSEs). With Purdue University's Net Pellpack PSE server, they can solve complex partial differential equations with common World Wide Web browsers that support Java applets

Challenges and opportunities are evident for the evolving technology of problem-solving environments (PSE). One such area is the integration of multiple interacting applications. The growth of computational power and networking suggests that computational science will shift from the single physical-model design to the design of a whole physical sys...

Advances in wired and wireless networking technologies are making networked computing the most common form of high performance computing. Similarly, software like Mosaic and Netscape have not only unified the networked computing landscape, but they have made it available to the masses in a simple, machine independent way. These developments are cha...

In this paper we investigate the impact of the data partitioning on the performance of parallel iterative solvers, for very large PDE problems, on distributed memory MIMD (DM-MIMD) machines. Our goal is to minimize the local synchronization time required for the parallel processing of such computations. We succeed by : (i) partitioning any two (or...

The new economic realities require the rapid prototyping of manufactured artifacts and rapid solutions to problems with numerous interrelated elements. In the SoftLab project, we investigate the issues involved in the design and implementation of a virtual laboratory that simulates and controls the functionality of a wet/dry prototyping laboratory....

The evolution of the Internet into the Global Information Infrastructure (GII) is impacting many institutions of life in general, and, the way we view computing in particular. This future computational and communication infrastructure will allow computing everywhere. Learning and training simulators will be part of any classroom and laboratory. The...

Electronic protoyping is becoming a part of every scientific inquiry and product design, and is the focus of research in the new scientific field of Computational Science and Engineering. The new grand challenge here is the rapid prototyping of manufactured artifacts and the rapid solution to problems with numerous interrelated elements. This, in t...

Both hardware power and algorithm power are predicted to increase over the next decade or two. These powers provide the opportunity to attack new domains of scientific applications as well as to make strong progress in current application areas, and have to be delivered by software systems. Programming these systems will be the essential challenge...

Participants from academia, industry, and government were brought together to examine the issues and activities in education, employment, and research and development during the first IEEE Computer Society Workshop on Computational Science and Engineering (CSE). Discussions during the conference addressed such issues as developments in using the Wo...

This paper describes the //ELLPACK networked computing service that we have made available through the World Wide Web. //ELLPACK is a problem solving environment

Rapid advances in High Performance Computing (HPC) and the Internet are heralding a paradigm shift to network-- based scientific software servers, libraries, repositories and problem solving environments. According to this new paradigm, vital pieces of software and information required for a computation are distributed across a network and need to...

Computational Science is an interdisciplinary field that addresses all aspects of science and engineering that utilize computing as their main tool. One important research issue in computational science is the selection of appropriate algorithms for solving particular problems. In other words, given a problem and some performance objectives (speed,...

Problem Solving Environments (PSEs) interact with the user in a language "natural " to the associated discipline, and provide a high level abstraction of the underlying, computationally complex, model. The knowledge based system, PYTHIA, addresses the problem of (parameter, algorithm) pair selection within a scientific computing domain assuming som...

In this paper, we propose two new neuro-fuzzy schemes, one for classification and one for clustering problems. The classification scheme is based on Simpson's fuzzy min-max method (1992, 1993) and relaxes some assumptions he makes. This enables our scheme to handle mutually nonexclusive classes. The neuro-fuzzy clustering scheme is a multiresolutio...

In this paper we present a paradigm for simulating complex phenomena which may involve multiplephysical phenomena and complicated geometry. The computational structure is of cooperating agentsand much of the proposed methodology is widely applicable, but the focus in this paper is on phenomenamodeled by partial differential equations (PDE). The com...

In this paper we present a paradigm for simulating complex phenomena which may involve multiple physical phenomena and complicated geometry. The computational structure is of cooperating agents and much of the proposed methodology is widely applicable, but the focus in this paper is on phenomena modeled by partial differential equations (PDE). The...

An abstract is not available.

. In this paper we present the convergence analysis of iterative schemes for solving linear systems resulting from discretizing multidimensional linear second order elliptic partial differential equations (PDEs) defined in a hyper-parallelepipedOmega and subject to Dirichlet boundary conditions on some faces ofOmega and Neumann on the others, using...

The convergence rate of a numerical procedure based on Schwarz Alternating Method (SAM) for solving elliptic boundary value problems (BVPs) depends on the selection of the so-called interface conditions applied on the interior boundaries of the overlapping subdomains. It has been observed that the weighted mixed interface conditions (), controlled...

In this paper, we introduce a new agglomerative clustering algorithm in which each pattern cluster is represented by a collection of fuzzy hyperboxes. Initially, a number of such hyperboxes are calculated to represent the pattern samples. Then, the algorithm applies multi-resolution techniques to progressively “combine” these hyperboxes in a hierar...

Systems with interacting agents are now being proposed to solve many problems grouped together under the "distributed problem solving" umbrella. For such systems to work properly, it is necessary that agents learn from their environment and adapt their behaviour accordingly. We investigate such systems in the context of scientific computing. The ph...

A typical computing environment for solving Grand Challenge Problems consists of a high performance graphics workstation acting as a front-end, connected to a variety of remote supercomputers. A Problem Solving Environment (PSE) is a system of programs designed to assist a scientist in solving his/her problems without detailed understanding of para...

In the “problem-solving environments” that will one day free scientists and engineers from many algorithmic and computing details, computational intelligence techniques such as neural networks and fuzzy logic can help automate the choice of the best solution methods. Classifying the problems, illustrated in this article by using partial differentia...

Software libraries encapsulate problem solving power and problem solving environments (PSEs) give users painless access to problem solving power. Thus libraries and PSEs are inextricably linked. This workshop explored the state-of-the-art in these two areas and their interdependence. A few application areas (e.g., linear algebra) have a rather simp...

this report was partially supported by Grant CCR-90-24549 from the National Science Foundation. This is a report to the National Science Foundation and other agencies; it is not a report by or of the National Science Foundation or any other agency.

Problem solving using complex mathematical models of physical phenomena requires expert knowledge in a variety of fields of computer science, such as parallel computing and numerical methods. SciAgents is a problem-solving environment to allow these models to become truly easy to use for the application scientists, much like PC-based systems. It is...

In this paper, we introduce a new agglomerative clustering algorithm in which each pattern cluster is represented by a collection of fuzzy hyperboxes. Initially, a number of such hyperboxes are calculated to represent the pattern samples. Then, the algorithm applies multi-resolution techniques to progressively "combine" these hyperboxes in a hierar...