Sascha Hunold
Associate Prof. Dipl.-Inform. Dr.rer.nat.
Research Focus
- Computer Engineering: 100%
Roles
-
Associate Professor
Parallel Computing, E191-04 -
Faculty Council
Principal Member
Courses
2022W
- Bachelor Thesis for Informatics and Business Informatics / 184.716 / PR
- Parallel Algorithms / 184.727 / VU
- Project in Computer Science 1 / 191.120 / PR
- Project in Computer Science 2 / 191.121 / PR
- Scientific Programming with Python / 191.125 / VU
- Scientific Research and Writing / 193.052 / SE
- Seminar for Master Students in Computer Engineering / 180.778 / SE
- Seminar for PhD Students / 184.739 / SE
2023S
- Bachelor Thesis for Informatics and Business Informatics / 184.716 / PR
- Basics of Parallel Computing / 191.114 / VU
- Competitive Programming for Programming Contests / 191.126 / VU
- Interdisciplinary Project in Data Science / 194.060 / PR
- Parallel Computing / 184.710 / VU
- Project in Computer Science 1 / 191.120 / PR
- Project in Computer Science 2 / 191.121 / PR
- Scientific Research and Writing / 193.052 / SE
Projects
-
High Performance Molecular Screening at Massive Scale
2022 – 2023 / Austrian Research Promotion Agency (FFG)
Publications
Note: Due to the rollout of TU Wien’s new publication database, the list below may be slightly outdated. Once APIs for the new database have been released, everything will be up to date again.
2022
- MPI Performance Tools under the Microscope: A Thorough Overhead Analysis / J. Ajanohoun, I. Vardas, J. Träff, S. Hunold / Talk: Austrian-Slovenian HPC Meeting 2022 - ASHPC22, Grundlsee, Austria; 2022-05-31 - 2022-06-02; in: "Austrian-Slovenian HPC Meeting 2022 - ASHPC22", E. Reiter (ed.); EuroCC Austria, (2022), ISBN: 978-3-200-08499-5; 16
- mpisee: MPI Profiling for Communication and Communicator Structure / I. Vardas, S. Hunold, J. Ajanohoun, J. Träff / Talk: Austrian-Slovenian HPC Meeting 2022 - ASHPC22, Grundlsee, Austria; 2022-05-31 - 2022-06-02; in: "Austrian-Slovenian HPC Meeting 2022 - ASHPC22", E. Reiter (ed.); EuroCC Austria, (2022), ISBN: 978-3-200-08499-5; 15
2021
- MicroBench Maker: Reproduce, Reuse, Improve / S. Hunold, J. Ajanohoun, A. Carpen-Amarie / Talk: 12th IEEE International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2021) in conjunction with SC 2021 - Hybrid Conference, St. Louis, Missouri, USA; 2021-11-14 - 2021-11-19; in: "Proceedings of the International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2021)", IEEE, (2021), ISBN: 978-1-6654-1119-6; 69 - 74
- Teaching Complex Scheduling Algorithms / S. Hunold, B. Przybylski / Talk: 11th NSF/TCPP Workshop on Parallel and Distributed Computing Education (EduPar 2021) in conjunction with 35th IEEE IPDPS 2021 - Online Conference, Portland, Oregon, USA; 2021-05-17 - 2021-05-21; in: "IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPS Workshops 2021", IEEE, (2021), ISBN: 978-1-6654-1192-9; 321 - 327
- MPI collective communication through a single set of interfaces: A case for orthogonality / J. Träff, S. Hunold, G. Mercier, D. Holmes / Parallel Computing, Volume 107 (2021), 102826:1 - 102826:11
2020
- Collectives and Communicators: A Case for Orthogonality: (Or: How to get rid of MPI neighbor and enhance Cartesian collectives) / J. Träff, S. Hunold, G. Mercier, D. Holmes / Talk: 27th European MPI Users' Group Meeting (EuroMPI/USA 2020) - Online Conference, Austin, Texas, USA; 2020-09-21 - 2020-09-24; in: "Proceedings of the 27th European MPI Users' Group Meeting (EuroMPI/USA 2020)", IEEE, (2020), ISBN: 978-1-4503-8880-1; 31 - 38
- Decomposing MPI Collectives for Exploiting Multi-lane Communication / J. Träff, S. Hunold / Talk: IEEE International Conference on Cluster Computing (IEEE Cluster 2020) - Online Conference, Kobe, Japan; 2020-09-14 - 2020-09-17; in: "Proceedings of the IEEE International Conference on Cluster Computing (IEEE Cluster 2020)", IEEE, (2020), ISBN: 978-1-7281-6678-0; 270 - 280
- Predicting MPI Collective Communication Performance Using Machine Learning / S. Hunold, A. Bhatele, G. Bosilca, P. Knees / Talk: IEEE International Conference on Cluster Computing (IEEE Cluster 2020) - Online Conference, Kobe, Japan; 2020-09-14 - 2020-09-17; in: "Proceedings of the IEEE International Conference on Cluster Computing (IEEE Cluster 2020)", IEEE, (2020), ISBN: 978-1-7281-6678-0; 259 - 269
- Efficient Process-to-Node Mapping Algorithms for Stencil Computations (Best Paper Award) / K. von Kirchbach, M. Lehr, S. Hunold, C. Schulz, J. Träff / Talk: IEEE International Conference on Cluster Computing (IEEE Cluster 2020) - Online Conference, Kobe, Japan; 2020-09-14 - 2020-09-17; in: "Proceedings of the IEEE International Conference on Cluster Computing (IEEE Cluster 2020)", IEEE, (2020), ISBN: 978-1-7281-6678-0; 1 - 11
- Efficient Process-to-Node Mapping Algorithms for Stencil Computations / S. Hunold, K. von Kirchbach, M. Lehr, C. Schulz, J. Träff / Report for CoRR - Computing Research Repository; Report No. arXiv:2005.09521, 2020; 18 pages
- Scheduling.jl - Collaborative and Reproducible Scheduling Research with Julia / S. Hunold, B. Przybylski / Report for CoRR - Computing Research Repository; Report No. arXiv:2003.05217, 2020; 5 pages
2019
- Cartesian Collective Communication / J. Träff, S. Hunold / Talk: 48th International Conference on Parallel Processing (ICPP 2019), Kyoto, Japan; 2019-08-05 - 2019-08-08; in: "Proceedings of the 48th International Conference on Parallel Processing (ICPP 2019)", ACM, (2019), ISBN: 978-1-4503-6295-5; 48:1 - 48:11
- On the Importance of Data Quality when Tuning MPI Libraries / S. Hunold, A. Carpen-Amarie / Talk: Austrian HPC Meeting 2019 - AHPC19, Grundlsee, Austria; 2019-02-25 - 2019-02-27; in: "Austrian HPC Meeting 2019 - AHPC19 (AHPC19 booklet of abstracts)", G. Haase (ed.); Institut für Mathematik und wissenschaftliches Rechnen der Universität Graz, (2019), 15
- LigandScout Remote: A New User-Friendly Interface for HPC and Cloud Resources / T. Kainrad, S. Hunold, T. Seidel, T. Langer / Journal of Chemical Information and Modeling, Volume 59 (2019), Issue 1; 31 - 37
2018
- Algorithm Selection of MPI Collectives using Machine Learning Techniques / S. Hunold, A. Carpen-Amarie / Talk: 9th IEEE International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2018) in conjunction with SC 2018, Dallas, Texas, USA; 2018-11-11 - 2018-11-16; in: "Proceedings of the 2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2018)", IEEE, (2018), ISBN: 978-1-7281-0182-8; 45 - 50
- Hierarchical Clock Synchronization in MPI / S. Hunold, A. Carpen-Amarie / Talk: IEEE International Conference on Cluster Computing, CLUSTER 2018, Belfast, United Kingdom; 2018-09-10 - 2018-09-13; in: "Proceedings of the IEEE International Conference on Cluster Computing, CLUSTER 2018", IEEE, (2018), ISBN: 978-1-5386-8319-4; 325 - 336
- Autotuning MPI Collectives using Performance Guidelines / S. Hunold, A. Carpen-Amarie / Talk: International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia 2018), Tokyo, Japan; 2018-01-28 - 2018-01-31; in: "Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia 2018)", ACM, (2018), ISBN: 978-1-4503-5372-4; 64 - 74
2017
- Autotuning MPI Collectives using Performance Guidelines / S. Hunold, A. Carpen-Amarie / Talk: LIG - Bâtiment IMAG, St Martin d'Hères, France (invited); 2017-12-18
- Predicting the Energy-Consumption of MPI Applications at Scale Using a Single Node / F. Heinrich, T. Cornebize, A. Degomme, A. Legrand, A. Carpen-Amarie, S. Hunold, A. Orgerie, M. Quinson / Talk: IEEE International Conference on Cluster Computing (CLUSTER 2017), Honolulu, Hawaii, USA; 2017-09-05 - 2017-09-08; in: "Proceedings of the IEEE International Conference on Cluster Computing (CLUSTER 2017)", IEEE, (2017), ISBN: 978-1-5386-2326-8; 92 - 102
- Euro-Par 2016: Parallel Processing Workshops - Euro-Par 2016 International Workshops, Revised Selected Papers, LNCS 10104 / F. Desprez, P. Dutot, C. Kaklamanis, L. Marchal, K. Molitorisz, L. Ricci, V. Scarano, M. Vega-Rodriguez, A. Varbanescu, S. Hunold, S. Scott, S. Lankes, J. Weidendorfer / Springer Nature Switzerland AG 2021, 2017, ISBN: 978-3-319-58942-8; 850 pages
- On expected and observed communication performance with MPI derived datatypes / A. Carpen-Amarie, S. Hunold, J. Träff / Parallel Computing, Volume 69 (2017), Issue November; 98 - 117
- Scheduling Independent Moldable Tasks on Multi-Cores with GPUs / R. Bleuse, S. Hunold, S. Kedad-Sidhoum, F. Monna, G. Mounie, D. Trystram / IEEE Transactions on Parallel and Distributed Systems, Volume 28 (2017), Issue 9; 2689 - 2702
- Introduction to REPPAR Workshop / S. Hunold, A. Legrand, L. Nussbaum / in: "Proceedings of the IEEE 31st International Parallel and Distributed Processing Symposium (IPDPS 2017) Workshops", IEEE, 2017, ISBN: 978-1-5386-3408-0, 1559
- Tuning MPI Collectives by Verifying Performance Guidelines / S. Hunold, A. Carpen-Amarie / Report for CoRR - Computing Research Repository; Report No. arXiv:1707.09965, 2017; 16 pages
2016
- On the Expected and Observed Communication Performance with MPI Derived Datatypes / A. Carpen-Amarie, S. Hunold, J. Träff / Talk: 23rd European MPI Users' Group Meeting, EuroMPI 2016, Edinburgh, United Kingdom; 2016-09-25 - 2016-09-28; in: "Proceedings of the 23rd European MPI Users' Group Meeting, EuroMPI 2016", D. Holmes, C. Collis, J. Träff, L. Smith (ed.); ACM, (2016), ISBN: 978-1-4503-4234-6; 108 - 120
- The Art of MPI Benchmarking / S. Hunold / Talk: 45th SPEEDUP Workshop on High-Performance Computing, Basel, Switzerland (invited); 2016-09-15 - 2016-09-16
- Automatic Verification of Self-consistent MPI Performance Guidelines / S. Hunold, A. Carpen-Amarie, F. Lübbe, J. Träff / Talk: 22nd International European Conference on Parallel and Distributed Computing (Euro-Par 2016), Grenoble, France; 2016-08-22 - 2016-08-26; in: "Euro-Par 2016: Parallel Processing, 22nd International Conference on Parallel and Distributed Computing, Proceedings", P. Dutot, D. Trystram (ed.); Springer International Publishing, LNCS 9833 (2016), ISBN: 978-3-319-43658-6; 433 - 446
- The Art of MPI Benchmarking / S. Hunold / Talk: Lunchtime Seminar, Department of Computer Science, University of Innsbruck, Innsbruck, Austria (invited); 2016-06-09
- The art of benchmarking MPI libraries / S. Hunold / Talk: Austrian HPC Meeting 2016 - AHPC16, Grundlsee, Austria (invited); 2016-02-22 - 2016-02-24
- Clock Synchronization Algorithms and SimGrid / S. Hunold / Talk: SimGrid User Days, CNRS center Villa Clythia, Fréjus, France (invited); 2016-01-18 - 2016-01-21
- The art of benchmarking MPI libraries / S. Hunold, A. Carpen-Amarie, J. Träff / in: "Austrian HPC Meeting 2016 - AHPC 2016", I. Reichl, C. Blaas-Schenner, J. Zabloudil (ed.); Vienna Scientific Cluster (VSC), 2016, 45
- MPI Derived Datatypes: Performance Expectations and Status Quo / A. Carpen-Amarie, S. Hunold, J. Träff / Report for CoRR - Computing Research Repository; Report No. arXiv:1607.00178, 2016; 46 pages
- Message-Combining Algorithms for Isomorphic, Sparse Collective Communication / J. Träff, A. Carpen-Amarie, S. Hunold, A. Rougier / Report for CoRR - Computing Research Repository; Report No. arXiv:1606.07676, 2016; 12 pages
- PGMPI: Automatically Verifying Self-Consistent MPI Performance Guidelines / S. Hunold, A. Carpen-Amarie, F. Lübbe, J. Träff / Report for CoRR - Computing Research Repository; Report No. arXiv:1606.00215, 2016; 13 pages
2015
- Reproducibility in Parallel Computing / S. Hunold / Talk: Session: Performance Reproducibility in HPC - Challenges and State-of-the-Art at the 27th International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2015), Austin, Texas (invited); 2015-11-15 - 2015-11-20
- On the Impact of Synchronizing Clocks and Processes on Benchmarking MPI Collectives / S. Hunold, A. Carpen-Amarie / Talk: 22nd European MPI Users' Group Meeting, EuroMPI 2015, Bordeaux, France; 2015-09-21 - 2015-09-23; in: "Proceedings of the 22nd European MPI Users' Group Meeting, EuroMPI 2015", J. Dongarra, A. Denis, B. Goglin, E. Jeannot, G. Mercier (ed.); ACM, (2015), ISBN: 978-1-4503-3795-3; Paper ID 8, 10 pages
- Isomorphic, Sparse MPI-like Collective Communication Operations for Parallel Stencil Computations / J. Träff, F. Lübbe, A. Rougier, S. Hunold / Talk: 22nd European MPI Users' Group Meeting, EuroMPI 2015, Bordeaux, France; 2015-09-21 - 2015-09-23; in: "Proceedings of the 22nd European MPI Users' Group Meeting, EuroMPI 2015", J. Dongarra, A. Denis, B. Goglin, E. Jeannot, G. Mercier (ed.); ACM, (2015), ISBN: 978-1-4503-3795-3; Paper ID 10, 10 pages
- Accurately Measuring MPI Collectives with Synchronized Clocks / S. Hunold / Talk: Dagstuhl Seminar 15281: Algorithms and Scheduling Techniques to Manage Resilience and Power Consumption in Distributed Systems, Schloss Dagstuhl, Wadern, Germany (invited); 2015-07-05 - 2015-07-10
- One Step towards Bridging the Gap between Theory and Practice in Moldable Task Scheduling with Precedence Constraints / S. Hunold / Talk: Wirtschaftswissenschaftliche Fakultät, Universität Augsburg, Augsburg, Deutschland (invited); 2015-05-12
- Euro-Par 2015: Parallel Processing Workshops, Euro-Par 2015 International Workshops, Vienna, Austria, August 24-25, 2015, Revised Selected Papers, LNCS 9523 / S. Hunold, A. Costan, D. Gimenez, A. Iosup, L. Ricci, G. Gomez Requena, V. Scarano, A. Varbanescu, S. Scott, S. Lankes, J. Weidendorfer, M. Alexander / Springer International Publishing, 2015, ISBN: 978-3-319-27307-5; 880 pages
- Euro-Par 2015: Parallel Processing, 21st International Conference on Parallel and Distributed Computing, Vienna, Austria, August 24-28, 2015, Proceedings, LNCS 9233 / J. Träff, S. Hunold, F. Versaci / Springer-Verlag Berlin Heidelberg, 2015, ISBN: 978-3-662-48095-3; 732 pages
- One Step towards Bridging the Gap between Theory and Practice in Moldable Task Scheduling with Precedence Constraints / S. Hunold / Concurrency and Computation: Practice and Experience, Volume 27 (2015), Issue 4; 1010 - 1026
- A Survey on Reproducibility in Parallel Computing / S. Hunold / Report for CoRR - Computing Research Repository; Report No. arXiv:1511.04217, 2015; 15 pages
- MPI Benchmarking Revisited: Experimental Design and Reproducibility / S. Hunold, A. Carpen-Amarie / Report for CoRR - Computing Research Repository; Report No. arXiv:1505.07734, 2015; 40 pages
2014
- Reproducible MPI Micro-Benchmarking Isn´t As Easy As You Think / S. Hunold, A. Carpen-Amarie, J. Träff / Talk: Research Group Theory and Applications of Algorithms, University of Vienna, Vienna, Austria (invited); 2014-12-02
- One Step towards Bridging the Gap between Theory and Practice in Moldable Task Scheduling with Precedence Constraints / S. Hunold / Talk: AIT Austrian Institute of Technology, Seibersdorf, Austria (invited); 2014-11-25
- Reproducible MPI Micro-Benchmarking Isn´t As Easy As You Think (Best Paper Award) / S. Hunold, A. Carpen-Amarie, J. Träff / Talk: 21st European MPI Users' Group Meeting, EuroMPI/ASIA 2014, Kyoto, Japan; 2014-09-09 - 2014-09-12; in: "Proceedings of the 21st European MPI Users' Group Meeting", J. Dongarra, Y. Ishikawa, A. Hori (ed.); ACM, New York, NY, USA (2014), ISBN: 978-1-4503-2875-3; 69 - 76
- One Step towards Bridging the Gap between Theory and Practice in Moldable Task Scheduling with Precedence Constraints / S. Hunold / Talk: 9th Scheduling for Large Scale Systems Workshop, Lyon, France (invited); 2014-07-01 - 2014-07-04
- Implementing a Classic: Zero-copy All-to-all Communication with MPI Datatypes / J. Träff, A. Rougier, S. Hunold / Talk: 28th ACM International Conference on Supercomputing, ICS 2014, Munich, Germany; 2014-06-10 - 2014-06-13; in: "Proceedings of the 28th ACM International Conference on Supercomputing, ICS 2014", M. Gerndt, P. Stenström, L. Rauchwerger, B. Miller, M. Schulz (ed.); ACM, (2014), ISBN: 978-1-4503-2642-1; 135 - 144
- Moldable Task Scheduling: Theory and Practice / S. Hunold / Talk: Workshop on New Challenges in Scheduling Theory, Aussois, France (invited); 2014-03-31 - 2014-04-04
- Reproducibility of Experiments: It´s about the WHO and less the HOW / S. Hunold / Talk: Panel on reproducible research methodologies and new publication models, 4th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT 2014) co-located with HiPEAC 2014, Vienna, Austria (invited); 2014-01-20 - 2014-01-22
- Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International Workshops, Revised Selected Papers, Part II, LNCS 8806 / L. Lopes, J. Zilinskas, A. Costan, R. Cascella, G. Kecskemeti, E. Jeannot, M. Cannataro, L. Ricci, S. Benkner, S. Petit, V. Scarano, J. Gracia, S. Hunold, S. Scott, S. Lankes, C. Lengauer, J. Carretero, J. Breitbart, M. Alexander / Springer, 2014, ISBN: 978-3-319-14312-5; 590 pages
- Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International Workshops, Revised Selected Papers, Part I, LNCS 8805 / L. Lopes, J. Zilinskas, A. Costan, R. Cascella, G. Kecskemeti, E. Jeannot, M. Cannataro, L. Ricci, S. Benkner, S. Petit, V. Scarano, J. Gracia, S. Hunold, S. Scott, S. Lankes, C. Lengauer, J. Carretero, J. Breitbart, M. Alexander / Springer, 2014, ISBN: 978-3-319-14324-8; 620 pages
2013
- Can I repeat your parallel computing experiment? Yes, you can´t / S. Hunold / Talk: Technische Universität Dresden, Zentrale für Informationsdienste und Hochleistungsrechnen (ZIH), Dresden, Deutschland (invited); 2013-11-07
- On the Scalability of Moldable Task Scheduling Algorithms / S. Hunold / Talk: Dagstuhl Seminar 13381: Algorithms and Scheduling Techniques for Exascale Systems, Schloss Dagstuhl, Wadern, Germany (invited); 2013-09-15 - 2013-09-20
- Scheduling Moldable Tasks with Precedence Constraints and Arbitrary Speedup Functions on Multiprocessors / S. Hunold / Talk: Workshop on Scheduling for Parallel Computing (SPC 2013) in conjunction with the 10th International Conference on Parallel Processing and Applied Mathematics, PPAM 2013, Warsaw, Poland; 2013-09-08 - 2013-09-11; in: "Parallel Processing and Applied Mathematics, 10th International Conference, PPAM 2013, Revised Selected Papers, Part II", R. Wyrzykowski, J. Dongarra, K. Karczewski, J. Wasniewski (ed.); Springer, LNCS 8385 (2014), ISBN: 978-3-642-55194-9; 13 - 25
- Fair scheduling of bag-of-tasks applications using distributed Lagrangian optimization / R. Bertin, S. Hunold, A. Legrand, C. Touati / Journal of Parallel and Distributed Computing, Available online 23 August 2013 (2013), 1 - 16
- On the State and Importance of Reproducible Experimental Research in Parallel Computing / S. Hunold, J. Träff / Report for CoRR - Computing Research Repository; Report No. arXiv:1308.3648, 2013; 15 pages
2012
- Evolutionary Scheduling of Parallel Tasks Graphs onto Homogeneous Clusters / S. Hunold, J. Lepping / Talk: New Challenges in Scheduling Theory, Centre CNRS, Frejus, France (invited); 2012-10-21 - 2012-10-27
- Reproducibility and Data Provenance with VisTrails / S. Hunold / Talk: WP8 meeting, ANR SONGS project, INRIA, Paris, France (invited); 2012-10-04
Supervisions
Note: Due to the rollout of TU Wien’s new publication database, the list below may be slightly outdated. Once APIs for the new database have been released, everything will be up to date again.
- To Co-Schedule or Not To Co-Schedule? Efficiently Utilizing Large Multicore Machines / Master Thesis by B. Sarközi / Supervisor: S. Hunold; Institute of Computer Engineering, Research Unit Parallel Computing, 2021; final examination: 2021-11-05
- The Causes of Run Time Variability in HPC, How to Pin Them down, and How to Handle Them / Master Thesis by N. Roth / Supervisor: S. Hunold; Institute of Computer Engineering, Research Division of Parallel Computing, 2021; final examination: 2021-03-10
- Providing Transparent Remote Access to HPC Resources for Graphical Desktop Applications / Master Thesis by T. Kainrad / Supervisor: S. Hunold; Institute of Computer Engineering, Research Division of Parallel Computing, 2018; final examination: 2018-06-12
Awards
-
Best Short Paper / PMBS@Supercomputing
2022 / USA -
Best Paper Award IEEE CLUSTER 2020
2020 / Japan -
Best Paper Award EuroMPI/Asia
2014 / Japan
And more…
Soon, this page will include additional information such as reference projects, activities as journal reviewer and editor, memberships in councils and committees, and other research activities.
Until then, please visit Sascha Hunold’s research profile in TISS .