15 Hits in 7.1 sec

Scalable Data Management of the Uintah Simulation Framework for Next-Generation Engineering Problems with Radiation [chapter]

Sidharth Kumar, Alan Humphrey, Will Usher, Steve Petruzza, Brad Peterson, John A. Schmidt, Derek Harris, Ben Isaac, Jeremy Thornock, Todd Harman, Valerio Pascucci, Martin Berzins
2018 Lecture Notes in Computer Science  
This paper focuses on data management related problems faced by the Uintah simulation framework at a production scale of 260K processes.  ...  The need to scale next-generation industrial engineering problems to the largest computational platforms presents unique challenges.  ...  The authors would like to thank the Intel Parallel Computing Centers program. We would like to thank all those involved with Uintah past and present.  ... 
doi:10.1007/978-3-319-69953-0_13 fatcat:lodqec3lujdxrmd3qphlmds7cq

Investigating applications portability with the Uintah DAG-based runtime system on PetaScale supercomputers

Qingyu Meng, Alan Humphrey, John Schmidt, Martin Berzins
2013 Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '13  
The Uintah framework for example, solves a broad class of large-scale problems on structured adaptive grids using fluid-flow solvers coupled with particle-based solids methods.  ...  for solving challenging multiscale multi-physics engineering problems on some of the largest and most powerful computers available today.  ...  What distinguishes Uintah from these efforts is the use of very large scale parallelism and the use of these techniques in a very general purpose computational PDEs framework for challenging engineering  ... 
doi:10.1145/2503210.2503250 dblp:conf/sc/MengHSB13 fatcat:g36u5ewh7na3zgdem377ztrqdm

Extending the Uintah Framework through the Petascale Modeling of Detonation in Arrays of High Explosive Devices

Martin Berzins, Jacqueline Beckvermit, Todd Harman, Andrew Bezdjian, Alan Humphrey, Qingyu Meng, John Schmidt, Charles Wight
2016 SIAM Journal on Scientific Computing  
The Uintah software framework for the solution of a broad class of fluid-structure interaction problems has been developed by using a problem-driven approach that dates back to its inception.  ...  These improvements enabled scalable runs for the target problem and provided the capability to model the transition to detonation.  ...  The task then puts its results into a new data warehouse for the next time step. The new data warehouse at the end of one step becomes the old data warehouse for the next time step.  ... 
doi:10.1137/15m1023270 fatcat:5f7bs5eks5hu3oue3l7hjzeoze

A survey of high level frameworks in block-structured adaptive mesh refinement packages

Anshu Dubey, Ann Almgren, John Bell, Martin Berzins, Steve Brandt, Greg Bryan, Phillip Colella, Daniel Graves, Michael Lijewski, Frank Löffler, Brian O'Shea, Erik Schnetter (+2 others)
2014 Journal of Parallel and Distributed Computing  
We look at their high-level frameworks, and their approach to dealing with the advent of radical changes in hardware architecture.  ...  Some have stayed focused on specific domain areas, others have pursued a more general functionality, providing the building blocks for a larger variety of applications.  ...  for simulation of turbulent reacting flows with participating media radiation.  ... 
doi:10.1016/j.jpdc.2014.07.001 fatcat:uhzy4q53jfb3bjldz2tbl533jy

Large Scale Parallel Solution of Incompressible Flow Problems Using Uintah and Hypre

J. Schmidt, M. Berzins, J. Thornock, T. Saad, J. Sutherland
2013 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing  
The Uintah Software framework was developed to provide an environment for solving fluid-structure interaction problems on structured adaptive grids on large-scale, long-running, data-intensive problems  ...  The weak scalability of Uintah and hypre is addressed for particular examples when applied to an incompressible flow problem relevant to combustion applications.  ...  We would like to thank all those previously involved with Uintah and TACC, NICS and Oak Ridge for access to large numbers of cores.  ... 
doi:10.1109/ccgrid.2013.10 dblp:conf/ccgrid/SchmidtBTSS13 fatcat:v3b5ryn5zbaqvhjz7s72iwqcpi

DAG-Based Software Frameworks for PDEs [chapter]

Martin Berzins, Qingyu Meng, John Schmidt, James C. Sutherland
2012 Lecture Notes in Computer Science  
This approach is not yet widely used in the large-scale multi-core parallel computing of complex systems of partial differential equations.  ...  The task-based approach to software and parallelism is well-known and has been proposed as a potential candidate, named the silver model, for exascale software.  ...  , over the next decade has led to a discussion of task-based approaches as potential candidates for exascale software over the next decade. For example, the Silver model, [?]  ... 
doi:10.1007/978-3-642-29737-3_37 fatcat:q5fw4vfs4nh2rkgbzhifwuabfu

Using hybrid parallelism to improve memory use in the Uintah framework

Qingyu Meng, Martin Berzins, John Schmidt
2011 Proceedings of the 2011 TeraGrid Conference on Extreme Digital Discovery - TG '11  
The Uintah Software framework was developed to provide an environment for solving fluid-structure interaction problems on structured adaptive grids on large-scale, long-running, data-intensive problems  ...  Uintah uses a combination of fluid-flow solvers and particle-based methods for solids together with a novel asynchronous task-based approach with fully automated load balancing.  ...  of Utah's Center for the Simulation of Accidental Fires and Explosions (C-SAFE) and funded by the Department of Energy, subcontract No.  ... 
doi:10.1145/2016741.2016767 fatcat:6bvq5ib56jbvlamqshzv7yduim

Systematic Debugging of Concurrent Systems Using Coalesced Stack Trace Graphs [chapter]

Diego Caminha B. de Oliveira, Zvonimir Rakamarić, Ganesh Gopalakrishnan, Alan Humphrey, Qingyu Meng, Martin Berzins
2015 Lecture Notes in Computer Science  
Conventional debuggers, while good at presenting details at the problem-site (e.g., crash), often omit contextual information to identify the root causes of the bug.  ...  In this paper, we detail CSTGs through case studies in the context of Uintah where unexpected behaviors caused by different versions of software or occurring across different time-steps of a system (e.g  ...  Driving Example: Uintah HPC Framework Uintah serves as a non-trivial test-bed for our work, given its complexity and continuing development both in terms of applications and in terms of parallel scalability  ... 
doi:10.1007/978-3-319-17473-0_21 fatcat:7hlmep2wtjcodoi5bfe4n5ixe4

JAUMIN: a programming framework for large-scale numerical simulation on unstructured meshes

Qingkai Liu, Zeyao Mo, Aiqing Zhang, Zhang Yang
2019 CCF Transactions on High Performance Computing  
Based on this framework, serial codes are only required to be written for large-scale parallel application suitable for modern supercomputers with tens of thousands of CPU cores.  ...  Domain-specific programming frameworks are usually effective to simplify the development of large-scale applications on supercomputers.  ...  The data for a physical quantity on a single patch is managed by a patch data object. With a patch data object, users can access all the values of a physical quantity on the patch.  ... 
doi:10.1007/s42514-019-00001-z fatcat:eqsqtsicp5efranlodrempqxdu

D7.2.1 A Report on the Survey of HPC Tools and Techniques

Michael Lysaght, Bjorn Lindi, Vit Vondrak, John Donners, Marc Tajchman
2013 Zenodo  
We summarize our findings separately by topic: Programming Interfaces and Standards, Debuggers and Profilers, Scalable Libraries and Algorithms and I/O Management Techniques.  ...  he objective of PRACE-3IP Work Package 7 (WP7) 'Application Enabling and Support' is to provide applications enabling support for HPC applications codes which are important for European researchers to  ...  with data management for virtual functions.  ... 
doi:10.5281/zenodo.6575492 fatcat:grwigpxd7naifbzo6w67w4glrm

Large-scale distributed runtime system for dag-based computational framework

Qingyu Meng
The Uintah framework, for example, solves a broad class of large-scale problems on structured adaptive grids using fluid-flow solvers coupled with particle-based solids methods.  ...  These changes pose formidable challenges for applications code to attain scalability.  ...  The Uintah framework provides a general purpose component-based environment for large-scale science and engineering simulations including fluid-structure interaction problems though a combination of fluid-flow  ... 
doi:10.26053/0h-jz2j-bm00 fatcat:76v7krlnb5bztmdxo4zyjhavu4

The scalability of parallel adaptive mesh refinement within Uintah

Justin Paul Luitjens
Finally, the scalability of AMR simulations as a whole using these algorithms is tested within the Uintah computational framework.  ...  In addition, a scalable space-filling curve generation algorithm for dynamic load balancing is also presented.  ...  ACKNOWLEDGEMENTS The funding for the work within was provided by DOE-B524196, NSF-OCI-  ... 
doi:10.26053/0h-rwc3-1n00 fatcat:wu4fvd6x3faj5pf2gb2f7waxoe

Parallel PDE-Based Simulations Using the Common Component Architecture [chapter]

Lois Curfman McInnes, Benjamin A. Allan, Robert Armstrong, Steven J. Benson, David E. Bernholdt, Tamara L. Dahlgren, Lori Freitag Diachin, Manojkumar Krishnan, James A. Kohl, J. Walter Larson, Sophia Lefantzi, Jarek Nieplocha (+4 others)
Lecture Notes in Computational Science and Engineering  
the reuse of software for parallel mesh manipulation, discretization, linear algebra, integration, optimization, and parallel data redistribution.  ...  A goal of componentbased software engineering in such large-scale simulations is to help manage this complexity by enabling better interoperability among various codes that have been independently developed  ...  with the National Aeronautics and Space Administration.  ... 
doi:10.1007/3-540-31619-1_10 fatcat:5poo3qaygbflxp2lejwym6usqu

Special Report 3: A Study of China's Technology Revolution [chapter]

Song Zifeng, Nigel Dickens
2020 Multi-scale Quantitative Diagenesis and Impacts on Heterogeneity of Carbonate Reservoir Rocks  
Energy is a key driver of social development. The energy transition correlates strongly with social and economic reform.  ...  The Implications of Energy Technology Revolution It is extremely rare for innovations to be evenly distributed across time and space.  ...  and user data with monitoring, protection, control and management of the power distribution network.  ... 
doi:10.1007/978-3-030-40154-2_4 fatcat:sa7dq5qksvg5bfgt6gz3mxrjqa

Parallel distributed, reciprocal monte carlo radiation in coupled, large eddy combustion simulations

Isaac L. Hunsaker
In this work, a new model was developed in which reciprocal monte carlo radiation was coupled with a turbulent, large-eddy simulation combustion model.  ...  A technique wherein domain patches are stitched together was implemented to allow for scalable parallelism. The combustion model runs in parallel on a decomposed domain.  ...  To create a mesh with multiple refinement levels, framework and data management adjustments have been made to the ARCHES component.  ... 
doi:10.26053/0h-5d17-5700 fatcat:tmb7g34vabdkhbbmg3gzfrva6e