Practical Computer Science
Projects


SeASiTe – Self-Adaptation of Time-step-based Simulation Techniques on Heterogeneous HPC Systems

The research project SeASiTe (official project page) has the purpose to thoroughly investigate self-adaptation of time-step-based simulation codes on heterogeneous HPC systems. The goal is the design and provision of a software toolset with which the application programmer can enrich a time-step-based simulation code with self-adaptation techniques. The approach comprises self-adaptation with respect to relevant system and program parameters as well as possible program transformations which may improve the performance of program execution. The optimization of the program execution for more than one non-functional objective (e.g. execution time and energy consumption) is based on a performance model which helps to reduce the search space for a more efficient program version. Application independent methods and strategies for self-adaptation are planned to be encapsulated in a software component called Autotuning Navigator.

Project partners

Projekt information

The joint project "SeASiTe" is a research project in the area of "Grundlagenorientierte Forschung für HPC-Software im Hoch- und Höchstleistungsrechnen" and is funded within the program "IKT 2020 – Forschung für Innovationen" by the Federal Ministry of Education and Research (BMBF).
Duration: 01.01.2017 – 30.06.2020
Gefördert vom BMBF

Contact

Publications

  • Dietze, R.; Kränert, M.: Parallel Ant Colony Optimization for Scheduling Independent Tasks. In: Lecture Notes in Networks and Systems: Innovations in Bio-Inspired Computing and Applications (IBICA 2022).: pp. 363-372. Springer Nature Switzerland  –  ISBN 978-3-031-27499-2. Online, March 2023. DOI: 10.1007/978-3-031-27499-2_34 Online resource available
  • Hofmann, M.; Kiesel, R.; Kramer, R.; Rünger, G.; Schaller, T.: Performance Comparison of Parallel Sorting Algorithms for Data-intensive Particle Simulations using OpenCL. To appear in: International Conference on High Performance Computing & Simulation (HPCS 2020): pp. . IEEE  –  ISSN . Barcelona, Spain, 2021.
  • Kramer, R.; Rünger, G.: A Workflow-based Support for the Automatic Creation and Selection of Energy-efficient Task-Schedules on DVFS Processors. In: Proceedings of Sixth International Congress on Information and Communication Technology (vol. 236): pp. 44-61. Springer Singapore  –  ISBN 978-981-16-2380-6, 2021. DOI: 10.1007/978-981-16-2380-6_23 Online resource available
  • Rauber, T.; Rünger, G.: Modeling the effect of application-specific program transformations on energy and performance improvements of parallel ODE solvers. In: Journal of Computational Science, vol. 51. Elsevier  –  ISSN 1877-7503, 2021. DOI: 10.1016/j.jocs.2021.101356 Online resource available
  • Dietze, R.; Rünger, G.: The Search-based Scheduling Algorithm HP* for Parallel Tasks on Heterogeneous Platforms. In: Concurrency and Computation: Practice and Experience. Wiley, 2020. DOI: 10.1002/cpe.5898 Online resource available
  • Kalinnik, N.; Kiesel, R.; Rauber, T.; Richter, M.; Rünger, G.: A performance- and energy-oriented extended tuning process for time-step-based scientific applications. In: The Journal of Supercomputing, vol. 76. Springer, August 2020. DOI: 10.1007/s11227-020-03402-y Online resource available
  • Kramer, R.; Rünger, G.: Performance and efficiency investigations of SIMD programs of Coulomb solvers on multi- and many-core systems with vector units. In: 2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing -- PDP 2020. IEEE Computer Society Conference Publishing Services (CPS)  –  ISBN 978-1-7281-6582-0, 2020. DOI: 10.1109/PDP50117.2020.00044 Online resource available
  • Rauber, T.; Rünger, G.: A Parameter Selection Process by Data Analysis for Tuning Multi-threaded Time-Stepping Algorithms. In: 2020 Seventh International Conference on Software Defined Systems (SDS): pp. 43--50. IEEE. Paris, Frankreich, 2020. DOI: 10.1109/SDS49854.2020.9143911 Online resource available
  • Dietze, R.; Rünger, G.: Search-based Scheduling for Parallel Tasks on Heterogenous Platforms. In: Euro-Par 2019: Parallel Processing Workshops: pp. 333-344. Springer  –  ISBN 978-3-030-48340-1. Göttingen, Germany, August 2019. DOI: 10.1007/978-3-030-48340-1_26 Online resource available
  • Jakobs, T.; Naumann, B.; Rünger, G.: Performance and energy consumption of the SIMD Gram–Schmidt process for vector orthogonalization. In: The Journal of Supercomputing. Springer  –  ISSN 1573-0484, 2019. DOI: 10.1007/s11227-019-02839-0 Online resource available
  • Kiesel, R.; Rünger, G.: Performance and Energy Evaluation of Parallel Particle Simulation Algorithms for Different Input Particle Data. In: Position Papers of the 2019 Federated Conference on Computer Science and Information Systems (FedCSIS 2019), 12th Workshop on Computer Aspects of Numerical Algorithms (CANA'19) (vol. 19): pp. 31-37. Leipzig, Germany, September 2019. DOI: 10.15439/2019F344 Online resource available
  • Rauber, T.; Rünger, G.: Multiprocessor Task Programming and Flexible Load Balancing for Time-stepping Methods on Heterogeneous Cloud Infrastructures. In: 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) : pp. 1537-1544. IEEE  –  ISBN 978-1-7281-4034-6. Leicester, UK, August 2019. DOI: 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00277 Online resource available
  • Rauber, T.; Rünger, G.: On the Energy Consumption and Accuracy of Multithreaded Embedded Runge-Kutta Methods. In: Proceedings of the The International Conference on High Performance Computing & Simulation (HPCS 2019) (vol. 15): pp. 382-389. IEEE  –  ISBN 978-1-7281-4485-6. Dublin, Ireland, July 2019. DOI: 10.1109/HPCS48598.2019.9188214 Online resource available
  • Rauber, T.; Rünger, G.: Enabling Scalability, Adaptivity, and Resilience in Cloud Applications by Software-defined M-Task-based Programming. In: Proceedings of the 6th International Conference on Software Defined Systems (SDS 2019): pp. 88-95. IEEE  –  ISBN 978-1-7281-0722-6. Rome, Italy, June 2019. DOI: 10.1109/sds.2019.8768599 Online resource available
  • Rauber, T.; Rünger, G.: DVFS RK: Performance and Energy Modeling of Frequency-Scaled Multithreaded Runge-Kutta Methods. In: Proceedings of the 27th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP 2019): pp. 392-399. IEEE  –  ISBN 978-1-7281-1644-0. Pavia, Italy, February 2019. DOI: 10.1109/empdp.2019.8671593 Online resource available
  • Rauber, T.; Rünger, G.: A Scheduling Selection Process for Energy-efficient Task Execution on DVFS Processors. In: Concurrency and Computation: Practice and Experience, vol. 31. Wiley  –  ISSN 1532-0626, Juni 2019. DOI: 10.1002/cpe.5043 Online resource available
  • Rauber, T.; Rünger, G.; Stachowski, M.: Model-based optimization of the energy efficiency of multi-threaded applications. In: Sustainable Computing: Informatics and Systems, vol. 22: pp. 44-61. Elsevier  –  ISSN 2210-5379, 2019. DOI: 10.1016/j.suscom.2019.01.022 Online resource available
  • Hofmann, M.; Kiesel, R.; Leichsenring, D.; Rünger, G.: A Hybrid CPU/GPU Implementation of Computationally Intensive Particle Simulations Using OpenCL. In: Proceedings of the 17th IEEE International Symposium On Parallel And Distributed Computing (ISPDC 2018): pp. 9-16. IEEE  –  ISBN 978-1-5386-5330-2. Geneva, Switzerland, June 2018. DOI: 10.1109/ISPDC2018.2018.00011 Online resource available
  • Hofmann, M.; Kiesel, R.; Rünger, G.: Energy and Performance Analysis of Parallel Particle Solvers from the ScaFaCoS Library. In: Proceedings of the 2018 ACM/SPEC International Conference on Performance Engineering (ICPE 2018): pp. 88-95. ACM  –  ISBN 978-1-4503-5095-2. Berlin, Germany, April 2018. DOI: 10.1145/3184407.3184409 Online resource available
  • Kalinnik, N.; Kiesel, R.; Rauber, T.; Richter, M.; Rünger, G.: Exploring Self-Adaptivity towards Performance and Energy for Time-stepping Methods. In: Proceedings of the 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2018): pp. 115-123. IEEE  –  ISSN 1550-6533. Lyon, France, September 2018. DOI: 10.1109/CAHPC.2018.8645887 Online resource available
  • Kalinnik, N.; Kiesel, R.; Rauber, T.; Richter, M.; Rünger, G.: On the Autotuning Potential of Time-stepping methods from Scientific Computing. In: Proceedings of the 2018 Federated Conference on Computer Science and Information Systems (FedCSIS 2018), 11th Workshop on Computer Aspects of Numerical Algorithms (CANA'18) (vol. 15): pp. 329-338. ACSIS  –  ISSN 2300-596. Poznań, Poland, September 2018. DOI: 10.15439/2018F169 Online resource available
  • Rauber, T.; Rünger, G.: Energy and Performance Improvement of Parallel ODE Solvers by Application-specific Program Transformations. In: Proceedings of the 19th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC-18), IEEE International Parallel and Distributed Processing Symposium Workshops: pp. 967-976. IEEE  –  ISBN 978-1-5386-5555-9. Vancouver, Canada, May 2018. DOI: 10.1109/IPDPSW.2018.00151 Online resource available
  • Rauber, T.; Rünger, G.: How do loop transformations affect the energy consumption of Runge-Kutta methods?. In: Proceedings of the 26th Euromicro International Conference on Parallel, Distributed, and Network-based Processing (PDP 2018): pp. 499-507. IEEE  –  ISBN 978-1-5386-4975-6. Cambridge, United Kingdom, March 2018. DOI: 10.1109/PDP2018.2018.00085 Online resource available
  • Richter, M.; Rünger, G.: Symbolic matrix multiplication for multi-threaded sparse GEMM utilizing sparse matrix formats. In: International Conference on High Performance Computing & Simulation (HPCS 2018): pp. 523-530. IEEE  –  ISBN 978-1-5386-7879-4. Orléans, France, July 2018. DOI: 10.1109/HPCS.2018.00088 Online resource available
  • Rauber, T.; Rünger, G.: Comparison of Time and Energy Oriented Scheduling for Task-based programs. In: Proceedings of the 12th International Conference on Parallel Processing and Applied Mathematics (PPAM 2017) (Lecture Notes in Computer Science, vol. 10777): pp. 185-196. Springer  –  ISBN 978-3-319-78024-5. Lublin, Poland, September 2017 (published March 2018). DOI: 10.1007/978-3-319-78024-5_17 Online resource available
  • Rauber, T.; Rünger, G.: Tuning Energy Effort and Execution Time of Application Software. In: Proceedings of the 38th International Conference on Information Systems Architecture and Technology (ISAT 2017) (Advances in Intelligent Systems and Computing, vol. 656): pp. 239-251. Springer  –  ISBN 978-3-319-67228-1. Szklarska Poręba, Poland, September 2017. DOI: 10.1007/978-3-319-67229-8_22 Online resource available
  • Rauber, T.; Rünger, G.; Stachowski, M.: Performance and Energy Metrics for Multi-threaded Applications on DVFS Processors. In: Sustainable Computing: Informatics and Systems, vol. 17: pp. 55-68. Elsevier  –  ISSN 2210-5379, 2017 (published March 2018). DOI: 10.1016/j.suscom.2017.10.015 Online resource available
  • Rauber, T.; Rünger, G.; Stachowski, M.: Model-based Optimization of the Energy Efficiency of Multi-threaded Applications. In: Proceedings of the 8th International Green and Sustainable Computing Conference (IGSC 2017): pp. 1-6. IEEE  –  ISBN 978-1-5386-3470-7. Orlando, USA, October 2017 (published 2018). DOI: 10.1109/IGCC.2017.8323578 Online resource available
  • Rauber, T.; Rünger, G.; Stachowski, M.: Towards New Metrics for Appraising Performance and Energy Efficiency of Parallel Scientific Programs. In: Proceedings of the 13th IEEE International Conference on Green Computing and Communication (GreenCom-2017): pp. 466-474. IEEE  –  ISBN 978-1-5386-3066-2. Exeter, United Kingdom, June 2017 (published 2018). DOI: 10.1109/iThings-GreenCom-CPSCom-SmartData.2017.75 Online resource available