Veröffentlichungen "Korch, Matthias"

2023

Bartel, Silas ; Korch, Matthias:
Generation of logic designs for efficiently solving ordinary differential equations on field programmable gate arrays.
In: Software : Practice and Experience. Bd. 53 (2023) Heft 1 . - S. 27-52.
ISSN 1097-024X
DOI: https://doi.org/10.1002/spe.3043

2022

Hacker, Oliver ; Korch, Matthias ; Seiferth, Johannes:
A Motivating Case Study on Code Variant Selection by Reinforcement Learning.
In: Varbanescu, Ana-Lucia ; Bhatele, Abhinav ; Luszczek, Piotr ; Marc, Baboulin (Hrsg.): High Performance Computing : Proceedings. - Cham : Springer , 2022 . - S. 293-312 . - (Lecture Notes in Computer Science ; 13289 )
ISBN 978-3-031-07312-0
DOI: https://doi.org/10.1007/978-3-031-07312-0_15

2021

Korch, Matthias ; Werner, Tim:
An in-depth introduction of multi-workgroup tiling for improving the locality of explicit one-step methods for ODE systems with limited access distance on GPUs.
In: Concurrency and Computation. Bd. 33 (2021) Heft 11 . - e6016.
ISSN 1532-0634
DOI: https://doi.org/10.1002/cpe.6016

Alappat, Christie L. ; Seiferth, Johannes ; Hager, Georg ; Korch, Matthias ; Rauber, Thomas ; Wellein, Gerhard:
YaskSite : Stencil Optimization Techniques Applied to Explicit ODE Methods on Modern Architectures.
In: Lee, Jae W. ; Soffa, Mary Lou ; Zaks, Ayal (Hrsg.): 2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO) : Proceedings. - Piscataway, NJ , 2021 . - S. 174-186
ISBN 978-1-7281-8613-9
DOI: https://doi.org/10.1109/CGO51591.2021.9370316

2020

Korch, Matthias ; Raithel, Philipp ; Werner, Tim:
Implementation and Optimization of a 1D2V PIC Method for Nonlinear Kinetic Models on GPUs.
In: 2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing : PDP 2020 ; Proceedings. - Piscataway, NJ : IEEE , 2020 . - S. 30-37
ISBN 978-1-7281-6582-0
DOI: https://doi.org/10.1109/PDP50117.2020.00012

Korch, Matthias ; Werner, Tim:
Improving locality of explicit one-step methods on GPUs by tiling across stages and time steps.
In: Future Generation Computer Systems. Bd. 102 (2020) . - S. 889-901.
ISSN 0167-739X
DOI: https://doi.org/10.1016/j.future.2019.07.075

Korch, Matthias ; Werner, Tim:
Multi-workgroup Tiling to Improve the Locality of Explicit One-Step Methods for ODE Systems with Limited Access Distance on GPUs.
In: Wyrzykowski, Roman ; Deelman, Ewa ; Dongarra, Jack ; Karczewski, Konrad (Hrsg.): Parallel Processing and Applied Mathematics : 13th International Conference, PPAM 2019 ; Revised Selected Papers. Part I. - Cham : Springer , 2020 . - S. 3-12 . - (Lecture Notes in Computer Science ; 12043 )
ISBN 978-3-030-43229-4
DOI: https://doi.org/10.1007/978-3-030-43229-4_1

Seiferth, Johannes ; Korch, Matthias ; Rauber, Thomas:
Offsite Autotuning Approach : Performance Model Driven Autotuning Applied to Parallel Explicit ODE Methods.
In: Sadayappan, Ponnuswamy ; Chamberlain, Bradford L. ; Juckeland, Guido ; Ltaief, Hatem (Hrsg.): High Performance Computing. - Cham : Springer , 2020 . - S. 370-390 . - (Lecture Notes in Computer Science ; 12151 )
ISBN 978-3-030-50743-5
DOI: https://doi.org/10.1007/978-3-030-50743-5_19

2019

Scherg, Markus ; Seiferth, Johannes ; Korch, Matthias ; Rauber, Thomas:
Performance Prediction of Explicit ODE Methods on Multi-Core Cluster Systems.
In: Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering. - New York, NY : ACM , 2019 . - S. 139-150
ISBN 978-1-4503-6239-9
DOI: https://doi.org/10.1145/3297663.3310306

2018

Korch, Matthias ; Werner, Tim:
Accelerating explicit ODE methods on GPUs by kernel fusion.
In: Concurrency and Computation. Bd. 30 (2018) Heft 18 . - e4470.
ISSN 1532-0634
DOI: https://doi.org/10.1002/cpe.4470

Seiferth, Johannes ; Alappat, Christie L. ; Korch, Matthias ; Rauber, Thomas:
Applicability of the ECM Performance Model to Explicit ODE Methods on Current Multi-core Processors.
In: Yokota, Rio ; Weiland, Michèle ; Keyes, David ; Trinitis, Carsten (Hrsg.): High Performance Computing. - Cham : Springer , 2018 . - S. 163-183
ISBN 978-3-319-92040-5
DOI: https://doi.org/10.1007/978-3-319-92040-5_9

Korch, Matthias ; Werner, Tim:
Exploiting Limited Access Distance for Kernel Fusion Across the Stages of Explicit One-Step Methods on GPUs.
In: 2018 30th International Symposium on Computer Architecture and High Performance Computing : proceedings. - Piscataway, NJ : IEEE , 2018 . - S. 148-157
ISBN 978-1-5386-7769-8
DOI: https://doi.org/10.1109/CAHPC.2018.8645892

2017

Korch, Matthias ; Werner, Tim:
Efficient GPU-based Smoothed Particle Hydrodynamics.
2017
Veranstaltung: PARNUM 2017 , 19.-21. Apr. 2017 , Waischenfeld, Deutschland.
(Veranstaltungsbeitrag: Workshop , Vortrag )

2016

Korch, Matthias ; Rauber, Thomas ; Stachowski, Matthias ; Werner, Tim:
Influence of locality on the scalability of method- and system-parallel explicit peer methods.
In: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems. - Piscataway, NJ : IEEE , 2016 . - S. 685-694
ISBN 978-83-60810-90-3
DOI: https://doi.org/10.15439/2016F464

2014

Kalinnik, Natalia ; Korch, Matthias ; Rauber, Thomas:
Online auto-tuning for the time-step-based parallel solution of ODEs on shared-memory systems.
In: Journal of Parallel and Distributed Computing. Bd. 74 (2014) Heft 8 . - S. 2722-2744.
ISSN 0743-7315
DOI: https://doi.org/10.1016/j.jpdc.2014.03.006

2013

Ferber, Marvin ; Kalinnik, Natalia ; Korch, Matthias ; Prell, Andreas ; Rauber, Thomas ; Witzgall, Matthias:
MAP : Mobile Assistance Platform with a VM Type Selection Ability.
In: Proceedings of the 19th IEEE International Conference on Parallel and Distributed Systems 2013 : ICPADS. - New York : ACM , 2013 . - S. 448-449
ISBN 978-1-4799-2081-5
DOI: https://doi.org/10.1109/ICPADS.2013.79

Korch, Matthias ; Ramming, Tobias ; Rein, Gerhard:
Parallelization of particle-in-cell codes for nonlinear kinetic models from mathematical physics.
In: International Conference on Parallel Processing, The 42nd Annual Conference ICPP 2013 : Proceedings ; 1 - 4 October 2013 Lyon, France. - Los Alamitos, CA : IEEE , 2013 . - S. 523-529
ISBN 978-0-7695-5117-3
DOI: https://doi.org/10.1109/ICPP.2013.65

2012

Korch, Matthias ; Kulbe, Julien ; Scholtes, Carsten:
Diamond-Like Tiling Schemes for Efficient Explicit Euler on GPUs.
In: 11th International Symposium on Parallel and Distributed Computing (ISPDC), 2012 : proceedings. - Piscataway, NJ : IEEE , 2012 . - S. 259-266
ISBN 978-1-4673-2599-8
DOI: https://doi.org/10.1109/ISPDC.2012.42

Korch, Matthias:
Exploiting Limited Access Distance of ODE Systems for Parallelism and Locality in Explicit Methods.
In: Algoritmy 2012 : proceedings of contributed papers and posters. - Bratislava : Slovak University of Technology , 2012 . - S. 250-260
ISBN 978-80-227-3742-5

Korch, Matthias:
Locality Improvement of Data-Parallel Adams-Bashforth Methods through Block-Based Pipelining of Time Steps.
In: Kaklamanis, Christos ; Papatheodorou, Theodore ; Spirakis, Paul G. (Hrsg.): Euro-Par 2012 Parallel Processing : Proceedings. - Berlin : Springer , 2012 . - S. 563-574 . - (Lecture Notes in Computer Science ; 7484 )
ISBN 978-3-642-32820-6
DOI: https://doi.org/10.1007/978-3-642-32820-6_56

2011

Korch, Matthias ; Rauber, Thomas ; Scholtes, Carsten:
Memory-Intensive Applications on a Many-Core Processor.
In: IEEE 13th International Conference on High Performance Computing and Communications (HPCC) : Proceedings. - Los Alamitos, CA : IEEE , 2011 . - S. 126-134
ISBN 978-0-7695-4538-7
DOI: https://doi.org/10.1109/HPCC.2011.26

Kalinnik, Natalia ; Korch, Matthias ; Rauber, Thomas:
Dynamic Selection of Implementation Variants of Sequential Iterated Runge-Kutta Methods with Tile Size Sampling.
In: ICPE'11 : Proceedings of the 2nd AMC/SPEC International Conference on Performance Engineering. - New York : ACM , 2011 . - S. 189-200
ISBN 978-1-4503-0519-8
DOI: https://doi.org/10.1145/1958746.1958775

Kalinnik, Natalia ; Korch, Matthias ; Rauber, Thomas:
An efficient time-step-based self-adaptive algorithm for predictor-corrector methods of Runge-Kutta type.
In: Journal of Computational and Applied Mathematics. Bd. 236 (2011) Heft 3 . - S. 394-410.
ISSN 0377-0427
DOI: https://doi.org/10.1016/j.cam.2011.07.015

Korch, Matthias ; Rauber, Thomas:
Parallel Low-Storage Runge-Kutta Solvers for ODE Systems with Limited Access Distance.
In: The International Journal of High Performance Computing Applications. Bd. 25 (2011) Heft 2 . - S. 236-255.
ISSN 1741-2846
DOI: https://doi.org/10.1177/1094342010384418

Korch, Matthias ; Rauber, Thomas ; Scholtes, Carsten:
Scalability and locality of extrapolation methods on large parallel systems.
In: Concurrency and Computation. Bd. 23 (2011) Heft 15 . - S. 1789-1815.
ISSN 1532-0634
DOI: https://doi.org/10.1002/cpe.1765

2010

Kalinnik, Natalia ; Korch, Matthias ; Rauber, Thomas:
Applicability of Dynamic Selection of Implementation Variants of Sequential Iterated Runge-Kutta Methods.
In: 2010 IEEE International Conference on Cluster Computing workshops and posters (CLUSTER WORKSHOPS). - Piscataway, NJ : IEEE , 2010
ISBN 978-1-4244-8396-9
DOI: https://doi.org/10.1109/CLUSTERWKSP.2010.5613097

Korch, Matthias ; Rauber, Thomas ; Scholtes, Carsten:
Mixed-Parallel Implementations of Extrapolation Methods with Reduced Synchronization Overhead for Large Shared-Memory Computers.
In: IEEE 16th International Conference on Parallel and Distributed Systems (ICPADS) : Proceedings. - Los Alamitos, Calif. : IEEE , 2010 . - S. 131-138
ISBN 978-0-7695-4307-9
DOI: https://doi.org/10.1109/ICPADS.2010.12

Korch, Matthias ; Rauber, Thomas:
Parallel Low-Storage Runge-Kutta Solvers for ODE Systems with Limited Access Distance.
Bayreuth , 2010

Korch, Matthias ; Rauber, Thomas ; Scholtes, Carsten:
Scalability and Locality of Extrapolation Methods for Distributed-Memory Architectures.
In: D'Ambra, Pasqua ; Guarracino, Mario ; Talia, Domenico (Hrsg.): Euro-Par 2010 - Parallel Processing : Proceedings. Part II. - Berlin : Springer , 2010 . - S. 65-76 . - (Lecture Notes in Computer Science ; 6272 )
ISBN 978-3-642-15291-7
DOI: https://doi.org/10.1007/978-3-642-15291-7_8

Korch, Matthias ; Rauber, Thomas:
Storage Space Reduction for the Solution of Systems of Ordinary Differential Equations by Pipelining and Overlapping of Vectors.
In: IEEE International Symposium on Parallel & Distributed Processing workshops and Phd forum (IPDPSW). - Piscataway, NJ : IEEE , 2010
ISBN 978-1-4244-6533-0
DOI: https://doi.org/10.1109/IPDPSW.2010.5470768

2009

Korch, Matthias ; Rauber, Thomas:
Parallel Implementation of Runge-Kutta Integrators with Low Storage Requirements.
In: Sips, Henk ; Epema, Dick ; Lin, Hai-Xiang (Hrsg.): Euro-Par 2009 Parallel Processing : Proceedings. - Berlin : Springer , 2009 . - S. 785-796 . - (Lecture Notes in Computer Science ; 5704 )
ISBN 978-3-642-03869-3
DOI: https://doi.org/10.1007/978-3-642-03869-3_73

Korch, Matthias ; Rauber, Thomas:
Scalability of Time- and Space-Efficient Embedded Runge-Kutta Solvers for Distributed Address Space.
In: Proceedings of the 38th International Conference on Parallel Processing. - Los Alamitos, Calif. : IEEE , 2009 . - S. 404-411
ISBN 978-0-7695-3802-0
DOI: https://doi.org/10.1109/ICPP.2009.14

Hoffmann, Ralf ; Hunold, Sascha ; Korch, Matthias ; Rauber, Thomas:
Towards Scalable Parallel Numerical Algorithms and Dynamic Load Balancing Strategies.
In: Wagner, Siegfried ; Steinmetz, Matthias ; Bode, Arndt ; Brehm, Matthias (Hrsg.): High Performance Computing in Science and Engineering, Garching/Munich 2007 : Transactions. - Berlin : Springer , 2009 . - S. 503-516
ISBN 978-3-540-69182-2
DOI: https://doi.org/10.1007/978-3-540-69182-2_40

2008

Korch, Matthias:
Eingebettete Runge-Kutta-Verfahren für parallele Rechnersysteme : Effiziente Implementierung durch Ausnutzung der Speicherzugriffslokalität.
Saarbrücken : VDM Verlag Dr. Müller , 2008 . - XVI, 272 S.
ISBN 978-3-8364-9140-2

Hunold, Sascha ; Korch, Matthias ; Krellner, Björn ; Rauber, Thomas ; Reichel, Thomas ; Rünger, Gudula:
Inkrementelle Transformation einer monolithischen Geschäftssoftware.
In: Software Engineering 2008 - Workshopband. - Bonn : Ges. für Informatik , 2008 . - S. 226-231
ISBN 978-3-88579-216-1

Hunold, Sascha ; Korch, Matthias ; Krellner, Björn ; Rauber, Thomas ; Reichel, Thomas ; Rünger, Gudula:
Transformation of Legacy Software into Client/Server Applications through Pattern-based Rearchitecturing.
In: 32nd Annual IEEE International Computer Software and Applications Conference, 2008. - Piscataway, NJ : IEEE , 2008 . - S. 303-310
ISBN 978-0-7695-3262-2
DOI: https://doi.org/10.1109/COMPSAC.2008.158

2007

Korch, Matthias ; Rauber, Thomas:
Locality Optimized Shared-Memory Implementations of Iterated Runge-Kutta Methods.
In: Kermarrec, Anne-Marie ; Bougé, Luc ; Priol, Thierry (Hrsg.): Euro-Par 2007 Parallel Processing : Proceedings. - Berlin : Springer , 2007 . - S. 737-747 . - (Lecture Notes in Computer Science ; 4641 )
ISBN 978-3-540-74466-5
DOI: https://doi.org/10.1007/978-3-540-74466-5_78

2006

Korch, Matthias ; Rauber, Thomas:
Applicability of Load Balancing Strategies to Data-Parallel Embedded Runge-Kutta Integrators.
In: Euro-Par 2006 Parallel Processing : Proceedings. - Berlin : Springer , 2006 . - S. 720-729 . - (Lecture Notes in Computer Science ; 4128 )
ISBN 978-3-540-37784-9
DOI: https://doi.org/10.1007/11823285_75

Korch, Matthias:
Effiziente Implementierung eingebetteter Runge-Kutta-Verfahren durch Ausnutzung der Speicherzugriffslokalität.
Bayreuth , 2006
( Dissertation, 2006 , Universität Bayreuth, Fakultät für Mathematik, Physik und Informatik)

Korch, Matthias ; Rauber, Thomas:
Optimizing Locality and Scalability of Embedded Runge-Kutta Solvers Using Block-Based Pipelining.
In: Journal of Parallel and Distributed Computing. Bd. 66 (2006) Heft 3 . - S. 444-468.
ISSN 0743-7315
DOI: https://doi.org/10.1016/j.jpdc.2005.09.003

Korch, Matthias ; Rauber, Thomas:
Simulation-based analysis of parallel Runge-Kutta solvers.
In: Applied Parallel Computing : State of the Art in Scientific Computing ; Revised Selected Papers. - Berlin : Springer , 2006 . - S. 1105-1114 . - (Lecture Notes in Computer Science ; 3732 )
ISBN 978-3-540-33498-9
DOI: https://doi.org/10.1007/11558958_133

2004

Korch, Matthias ; Rauber, Thomas:
Comparison of Parallel Implementations of Runge-Kutta Solvers : Message Passing vs. Threads.
In: Parallel Computing : Software Technology, Algorithms, Architectures Applications ; Proceedings. - Amsterdam : Elsevier , 2004 . - S. 209-216
ISBN 978-0-444-51689-3
DOI: https://doi.org/10.1016/S0927-5452(04)80029-7

Korch, Matthias ; Rauber, Thomas:
A comparison of task pools for dynamic load balancing of irregular algorithms.
In: Concurrency and Computation. Bd. 16 (2004) Heft 1 . - S. 1-47.
ISSN 1532-0634
DOI: https://doi.org/10.1002/cpe.745

Hoffmann, Ralf ; Korch, Matthias ; Rauber, Thomas:
Performance Evaluation of Task Pools Based on Hardware Synchronization.
In: SC2004 : Briding Communities ; Proceedings. - Piscataway, NJ : IEEE , 2004
ISBN 0-7695-2153-3
DOI: https://doi.org/10.1109/SC.2004.38

Korch, Matthias ; Rauber, Thomas ; Rünger, Gudula:
Performance Optimization of RK Methods Using Block-based Pipelining.
In: Getov, Vladimir ; Gerndt, Michael ; Hoisie, Adolfy ; Malony, Allen ; Miller, Barton (Hrsg.): Performance Analysis and Grid Computing : Selected Articles. - Boston, MA : Springer , 2004 . - S. 41-56
ISBN 978-1-4615-0361-3
DOI: https://doi.org/10.1007/978-1-4615-0361-3_3

Hoffmann, Ralf ; Korch, Matthias ; Rauber, Thomas:
Using Hardware Operations to Reduce the Synchronization Overhead of Task Pools.
In: Proceedings 2004 International Conference on Parallel Processing ICPP. - Los Alamitos, Calif. : IEEE , 2004 . - S. 241-249
ISBN 0-7695-2197-5
DOI: https://doi.org/10.1109/ICPP.2004.1327927

2003

Korch, Matthias ; Rauber, Thomas:
Scalable Parallel RK Solvers for ODEs Derived by the Method of Lines.
In: Euro-Par 2003 Parallel Processing : Proceedings. - Berlin : Springer , 2003 . - S. 830-839 . - (Lecture Notes in Computer Science ; 2790 )
ISBN 978-3-540-45209-6
DOI: https://doi.org/10.1007/978-3-540-45209-6_113

2002

Korch, Matthias ; Rauber, Thomas:
Evaluation of Task Pools for the Implementation of Parallel Irregular Algorithms.
In: Proceedings International Conference on Parallel Processing Workshops. - Los Alamitos, Calif. : IEEE , 2002 . - S. 597-604
ISBN 0-7695-1680-7
DOI: https://doi.org/10.1109/ICPPW.2002.1039782

Korch, Matthias ; Rauber, Thomas ; Rünger, Gudula:
Pipelining for Locality Improvement in RK Methods.
In: Monien, Burkhard ; Feldmann, Rainer (Hrsg.): Euro-Par 2002 Parallel Processing : Proceedings. - Berlin : Springer , 2002 . - S. 724-733 . - (Lecture Notes in Computer Science ; 2400 )
ISBN 978-3-540-45706-0
DOI: https://doi.org/10.1007/3-540-45706-2_100

2001

Korch, Matthias:
Einsatz von Taskpools in Pthreads und Java zur parallelen Implementierung irregulärer Algorithmen.
Halle , 2001
(Masterarbeit, 2001, Martin-Luther-Universität Halle-Wittenberg)