A5067736038- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Parallel Computing and Optimization Techniques
- Magnetic confinement fusion research
- Cloud Computing and Resource Management
- Advanced Data Storage Technologies
- Superconducting Materials and Applications
- Software Engineering and Design Patterns
- Simulation Techniques and Applications
- Fusion materials and technologies
- Model-Driven Software Engineering Techniques
- Meteorological Phenomena and Simulations
- Software Engineering Research
- Ionosphere and magnetosphere dynamics
- Advanced Software Engineering Methodologies
- Advanced Optimization Algorithms Research
- Structural Analysis of Composite Materials
- Advanced Control Systems Optimization
- Logic, programming, and type systems
- Advanced Surface Polishing Techniques
- Numerical methods for differential equations
- Computational Fluid Dynamics and Aerodynamics
- Advanced Database Systems and Queries
- Research Data Management Practices
- Laser-Plasma Interactions and Diagnostics
Lawrence Livermore National Laboratory
2007-2019
Oak Ridge National Laboratory
2014
Sandia National Laboratories
2014
Washington State University Vancouver
2014
University of Alabama
2014
University of Edinburgh
2014
Pacific Northwest National Laboratory
2014
Engineering Software Research and Development (United States)
2014
National Technical Information Service
2001
Office of Scientific and Technical Information
2001
The Common Component Architecture (CCA) provides a means for software developers to manage the complexity of large-scale scientific simulations and move toward plug-and-play environment high-performance coputing. In computing context, component models also promote collaboration using independently developed software, thereby allowing particular individals or groups focus on aspects greatest interest them. CCA supports parallel distributed coputing as well local connections between components...
Abstract The Common Component Architecture (CCA) is a component model for high‐performance computing, developed by grass‐roots effort of computational scientists. Although the CCA usable with CORBA‐like distributed‐object components, its main purpose to set forth high‐performance, parallel computing. Traditional models are not well suited performance and massive parallelism. We outline design pattern model, discuss our strategy language interoperability, describe development tools we...
High-performance scientific applications are usually built from software modules written in multiple programming languages. This raises the issue of language interoperability which involves making calls between languages, converting basic types, and bridging disparate models. Babel provides a feature-rich, extensible, high-performance solution to problem currently supporting C, C++, FORTRAN 77, Fortran 90/95, 2003/2008, Python, Java. supports object-oriented features interface semantics with...
The title of this article refers to Rudolph Flesch's famous 1955 book, "Why Johnny Can't Read", which called attention a nationwide decline in reading ability. Here, the author wants talk about another situation an important ability is lacking: create significant, portable scientific software. discusses some reasons problem exists and suggests approaches solving it that seem promising.
Computational chemists are using Common Component Architecture (CCA) technology to increase the parallel scalability of their application ten-fold. Combustion researchers publishing science faster because CCA manages software complexity for them. Both solver and meshing communities in SciDAC converging on community interface standards as a direct response novel level interoperability that presents. Yet, there is much more do before component becomes mainstream computational science. This...
Babel is a high-performance, n-way language interoperability tool for the HPC community that now includes support distributed computing via remote method invocation (RMI). We describe design and implementation of RMI, including its specification in our scientific interface definition (SIDL), modifications to Babel's code generators, third-party wire protocols. RMI's programming model consistency, functional capabilities, runtime performance are compared context with COM, CORBA, grid/Web...
Coupling separately developed codes offers an attractive method for increasing the accuracy and fidelity of computational models. Examples include earth sciences fusion integrated modeling. This paper describes Framework Application Core-Edge Transport Simulations (FACETS).
FACETS (Framework Application for Core-Edge Transport Simulations), is now in its third year. The team has developed a framework concurrent coupling of parallel computational physics use on Leadership Class Facilities (LCFs). In the course last year, tackled many difficult problems moving to parallel, integrated modeling by developing algorithms coupled systems, extracting legacy applications as components, modifying them run LCFs, and improving performance all components. development abides...
This special issue contains extensions of the best papers from 2013 International Workshop on Software Engineering for Computational Science and Engineering. In addition to summaries included articles, this introduction also a summary workshop discussion.
FACETS (Framework Application for Core-Edge Transport Simulations), now in its second year, has achieved first coupled core-edge transport simulations. In the process, a number of accompanying accomplishments were achieved. These include new parallel core component, wall improvements edge and source components, framework coupling all this together. result an interdisciplinary collaboration among computational physics, computer scientists, applied mathematicians on team.
The FACETS (Framework Application for Core-Edge Transport Simulations) project began in January 2007 with the goal of providing core to wall transport modeling a tokamak fusion reactor. This involves coupling previously separate computations core, edge, and regions. Such is primarily through connection regions lower dimensionality. has started developing component-based framework bring together models each these In first year, model will be 1 ½ dimensional (1D across flux surfaces coupled 2D...
Coupling separately developed codes offers an attractive method for increasing the accuracy and fidelity of computational models. Examples include earth sciences fusion integrated modeling. This paper describes Framework Application Core-Edge Transport Simulations (FACETS).
Coupled simulations of core and edge transport in the DIII-D shot number 118897, after L-H transition but before first localized mode (ELM), are presented. For plasma transport, a set one dimensional equations solved using FACETS:Core solver. The fluxes this region calculated GLF23 anomalous model Chang-Hinton neoclassical model. two-dimensional UEDGE code. Fluxes use static diffusivity profiles based on an interpretive analysis experimental profiles. Simulations used to study range validity...
High-performance computing (HPC) is having a profound impact on scientific discovery and engineering in variety of areas, researchers are beginning to demonstrate how HPC can problems energy grid planning operations. Contemporary supercomputers perform over 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">15</sup> floating point operations per second have more than 1.4 petabytes memory - roughly 5 orders magnitude greater commodity PC...
We report our effort in engineering a high performance remote method invocation (RMI) mechanism for the Common Component Architecture (CCA). This provides highly efficient and easy-to-use distributed computing CCA, enabling CCA applications to effectively leverage parallel systems accelerate computations. work is built on previous of Babel RMI. language interoperability tool that used scientific application writers share, reuse, compose from software components written different programming...
The Carbon Capture Simulation Initiative (CCSI) project has developed and deployed scientific infrastructure called the CCSI Toolset. Toolset provides state-of-the-art computational modeling simulation tools to accelerate commercialization of carbon capture technologies from discovery development, demonstration, ultimately widespread deployment hundreds power plants. have potential dramatically reduce emissions end users in industry with a comprehensive, integrated suite leading-edge,...