A report on the Sisal language project
Journal of Parallel and Distributed Computing - Special issue: data-flow processing
SCIRun: a scientific programming environment for computational steering
Supercomputing '95 Proceedings of the 1995 ACM/IEEE conference on Supercomputing
Simulating accidental fires and explosions
Computing in Science and Engineering
Computational Steering Software Systems and Strategies
IEEE Computational Science & Engineering
Toward a Common Component Architecture for High-Performance Scientific Computing
HPDC '99 Proceedings of the 8th IEEE International Symposium on High Performance Distributed Computing
Uintah: A Massively Parallel Problem Solving Environment
HPDC '00 Proceedings of the 9th IEEE International Symposium on High Performance Distributed Computing
Parallel components for PDEs and optimization: some issues and experiences
Parallel Computing - Special issue: Advanced environments for parallel and distributed computing
On the Role and Place of Computation in Science and Engineering
Computing in Science and Engineering
Gauss: A Framework for Verifying Scientific Computing Software
Electronic Notes in Theoretical Computer Science (ENTCS)
Integrating teaching and research in HPC: experiences and opportunities
ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part II
Hi-index | 0.00 |
We describe the Uintah Computational Framework (UCF), a set of software components and libraries that facilitate the simulation of Partial Differential Equations (PDEs) on Structured AMR (SAMR) grids using hundreds to thousands of processors. The UCF uses a non-traditional approach to achieving parallelism, employing an abstract taskgraph representation to describe computation and communication. This representation has a number of advantages that affect the performance of the resulting simulation. We demonstrate performance of the system on a solid mechanics algorithm, two different Computational Fluid-Dynamics (CFD) algorithms, and coupled CFD/solids algorithms. We illustrate the performance of the UCF for jobs requiring up to 2000 processors.