Calvin J. Ribbens

Hybrid Computing-Where HPC meets grid and Cloud Computing

We introduce a hybrid High Performance Computing (HPC) infrastructure architecture that provides predictable execution of scientific applications, and scales from a single resource to multiple resources, with different ownership, policy, and geographic locations. We identify three paradigms in the evolution of HPC and high-throughput computing: owner-centric HPC (traditional), Grid computing, and Cloud computing. After analyzing the synergies among HPC, Grid and Cloud computing, we argue for an architecture that combines the benefits of these technologies. We call the building block of this architecture, Elastic Cluster. We describe the concept of Elastic Cluster and show how it can be used to achieve effective and predictable execution of HPC workloads. Then we discuss implementation aspects, and propose a new distributed information system design that combines features of distributed hash tables and relational databases.

Multiple-dislocation emission from the crack tip in the ductile fracture of Al

Abstract This paper presents the results of a large-scale atomistic simulation study of the process of emission of multiple dislocations in Al. We use embedded-atom method potentials based on ab-initio data and molecular statics and dynamics techniques to study the configuration of the crack tip as the dislocation emission process evolves. In the configuration studied, the crack is oriented in a {111}-type plane with a [110]-type crack front and the dislocations are emitted in adjacent inclined {111}-type planes. The dislocations are Shockley partials and they form a twinned region. The number of dislocations emitted increases with increasing applied stress intensity and is limited if the dislocations are not allowed to reach their equilibrium positions The shielding effect of the emitted dislocations decreases the total stress intensity factor at the crack tip but also causes a net decrease in the mode-II stress intensity factor projected on the slip plane of the emitted dislocations. Most importantly, this lower stress intensity along the slip plane limits the emission of new dislocations and, after a number of dislocations are emitted, the crack advances by cleavage for several lattice periods. The process is then repeated, resulting in a combined dislocation emission–crack propagation process. These results suggest a mechanism for the brittle-to-ductile transition that depends strongly on dislocation mobility and pinning behaviour.

Computational study of a nonhierarchical decomposition algorithm

Optimizing the design of complex ground and flight vehicles involves multiple disciplines and multilayered computer codes stitched together from mostly incompativle disciplinary codes. The application of established, large-scale, optimization algorithms to the complete model is nearly impossible. Hierarchical decompositions are inappropriate for these types of problems and do not parallelize well. Sobieszczanski-Sobieski has proposed a nonhierarchical decomposition strategyfor nonlinear constrained optimization that is naturally parallel. Despite some successes on engineering problems, the algorithm as originally proposed fails on simple two-dimensional quadratic programs. This paper demonstrates the failure of the algorithm for quadratic programs and suggests a number of possible modifications.

Pattern-based sparse matrix representation for memory-efficient SMVM kernels

Pattern-based Representation (PBR) is a novel approach to improving the performance of Sparse Matrix-Vector Multiply (SMVM) numerical kernels. Motivated by our observation that many matrices can be divided into blocks that share a small number of distinct patterns, we generate custom multiplication kernels for frequently recurring block patterns. The resulting reduction in index overhead significantly reduces memory bandwidth requirements and improves performance. Unlike existing methods, PBR requires neither detection of dense blocks nor zero filling, making it particularly advantageous for matrices that lack dense nonzero concentrations. SMVM kernels for PBR can benefit from explicit prefetching and vectorization, and are amenable to parallelization. We present sequential and parallel performance results for PBR on two current multicore architectures, which show that PBR outperforms available alternatives for the matrices to which it is applicable.

ReSHAPE: A Framework for Dynamic Resizing and Scheduling of Homogeneous Applications in a Parallel Environment

A traditional application scheduler running on a parallel cluster only supports static scheduling where the number of processors allocated to an application remains fixed throughout the lifetime of the job. Due to unpredictability in job arrival times and varying resource requirements, static scheduling can result in idle system resources thereby decreasing the overall system throughput. In this paper we present a prototype framework called ReSHAPE, which supports dynamic resizing of parallel MPI applications executed on distributed memory platforms. The framework includes a scheduler that supports resizing of applications, an API to enable applications to interact with the scheduler, and a library that makes resizing viable. Applications executed using the ReSHAPE scheduler framework can expand to take advantage of additional free processors or can shrink to accommodate a high priority application, without getting suspended. Experimental results show that the ReSHAPE framework can improve individual job turn-around time and overall system throughput.

WBCSim: A Prototype Problem Solving Environment for Wood-Based Composites Simulations

Abstract. This paper describes a computing environment named WBCSim that is intended to increase the productivity of wood scientists conducting research on wood-based composite materials. WBCSim integrates Fortran 77-based simulation codes with a graphical front end, an optimization tool, and a visualization tool. WBCSim serves as a prototype for the design, construction and evaluation of larger scale problem solving (computing) environments. Several different wood-based composite material simulations are supported. A detailed description of the prototype’s software architecture and a typical scenario of use are presented. The system converts output from the simulations to the Virtual Reality Modeling Language (VRML) for visualizing simulation results.

Steady Viscous Flow in a Trapezoidal Cavity

The flow in a trapezoidal cavity (including the rectangular and triangular cavities) with one moving wall is studied numerically by finite differences with special treatment in the corners. It is found that streamlines and vorticity distributions are sensitive to geometric changes. The mean square law for core vorticity is valid for the rectangle but ceases to be valid for the triangular cavity.

Mining and visualizing recommendation spaces for elliptic PDEs with continuous attributes

In this paper we extend previous work in mining recommendation spaces based on symbolic problem features to PDE problems with continuous-valued attributes. We identify the research issues in mining such spaces, present a dynamic programming algorithm form the data-mining literature, and describe how a priori domain metaknowledge can be used to control the complexity of induction. A visualization aid for continuous-valued recommendation spaces is also outlined. Two case studies are presented to illustrate our approach and tools: (i) a comparison of an iterative and a direct linear system solver on nearly singular problems, and (ii) a comparison of two iterative solvers on problems posed on nonrectangular domains. Both case studies involve continuously varying problem and method parameters which strongly influence the choice of best algorithm in particular cases. By mining the results from thousands of PDE solves, we can gain valuable insight into the relative performance of these methods on similar problems.

Interactive ELLPACK: an interactive problem-solving environment for elliptic partial differential equations

ELLPACK is a versatile, very high-level language for solving elliptic partial differential equations.Solving elliptic problems with ELLPACK typically involves a process in which one repeatedlycomputes a solution, analyzes the results, and modifies the solution technique. Although this processis best suited for an interactive environment, ELLPACK itself is batch oriented. With this in mind,we have developed Interactive ELLPACK, an extension of ELLPACK that provides true interactiveelliptic problem solving by allowing the user to interactively build grids, choose solution methods,and analyze computed results. Interactive ELLPACK features a sophisticated interface with window-ing, color graphics output, and graphics input.

Programming environments for multidisciplinary Grid communities

As the power of computational Grids increases, there is a corresponding need for better usability for large and diverse communities. The focus in this paper is on supporting multidisciplinary communities of scientists and engineers. We discuss requirements for Grid computing environments (GCEs) in this context, and describe several core support technologies developed to meet these requirements. Our work extends the notion of a programming environment beyond the compile–schedule–execute paradigm, to include functionality such as collaborative application composition, information services, and data and simulation management. Systems designed for five different applications communities are described. These systems illustrate common needs and characteristics arising in multidisciplinary communities and motivate a high‐level design framework for building GCEs that meet those needs. Copyright