@misc{SchintkeReinefeldHaridietal., author = {Schintke, Florian and Reinefeld, Alexander and Haridi, Seif and Sch{\"u}tt, Thorsten}, title = {Enhanced Paxos Commit for Transactions on DHTs}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11448}, number = {09-28}, abstract = {Key/value stores which are built on structured overlay networks often lack support for atomic transactions and strong data consistency among replicas. This is unfortunate, because consistency guarantees and transactions would allow a wide range of additional application domains to benefit from the inherent scalability and fault-tolerance of DHTs. The Scalaris key/value store supports strong data consistency and atomic transactions. It uses an enhanced Paxos Commit protocol with only four communication steps rather than six. This improvement was possible by exploiting information from the replica distribution in the DHT. Scalaris enables implementation of more reliable and scalable infrastructure for collaborative Web services that require strong consistency and atomic changes across multiple items.}, language = {en} } @misc{Schintke, type = {Master Thesis}, author = {Schintke, Florian}, title = {Ermittlung von Programmlaufzeiten anhand von Speicherzugriffen, Microbenchmarks und Simulation von Speicherhierarchien}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-10063}, school = {Zuse Institute Berlin (ZIB)}, abstract = {Kostenmodelle dienen der Ermittlung von Programmlaufzeiten, zum Vergleich der Effizienz von Algorithmen und zur Analyse des Verhaltens von Speicherhierarchien. Ein neuartiges Kostenmodell ist das Latency-of-Data-Access (LDA) Modell, das mehrere hierarchische Speicherebenen mit unterschiedlichen Latenzzeiten ber{\"u}cksichtigt. In dieser Diplomarbeit wird ein Simulator f{\"u}r Speicherhierarchien pr{\"a}sentiert, der die Berechnung von Programmausf{\"u}hrungszeiten nach dem LDA-Modell erlaubt. Mit Hilfe des Simulators wird die These gepr{\"u}ft, daß mit diesem Modell die Ausf{\"u}hrungszeit eines Programms ad{\"a}quat abgesch{\"a}tzt werden kann. Mit dem Simulator ist es erstmals praktikabel m{\"o}glich, Programmausf{\"u}hrungszeiten nach dem LDA-Modell zu bestimmen. Der Simulator kann f{\"u}r Systeme mit unterschiedlichen Speicherarchitekturen konfiguriert werden und unterst{\"u}tzt Mehrprozessorsysteme mit gemeinsamem Speicher (SMP-Systeme) mit verschiedenen Koh{\"a}renzprotokollen. Der Simulator kann mit den Ergebnissen von Microbenchmarks konfiguriert werden, die die Architekturparameter einer Speicherhierarchie messen. Die Ergebnisse best{\"a}tigen die These nicht nur f{\"u}r Einzelprozessorsysteme, sondern auch f{\"u}r SMP-Systeme, wo gleichzeitig interagierende Prozessoren gegenseitig ihre Zugriffsse-quenz auf Zwischenspeicher beeinflussen. Zus{\"a}tzlich wurde eine neue Einsatzm{\"o}glichkeit des LDA-Modells entwickelt, um die Ausf{\"u}hrungszeit von Programmteilen zu bestimmen. Einzelne Zugriffskosten k{\"o}nnen einem mehrerer parallel laufender Modelle zugeordnet werden. Dadurch k{\"o}nnen Kosten, die Zugriffe auf einzelne Speicherbereiche verursachen, separat bestimmt werden. Diese Profiling-Technik erlaubt Optimierungen an Datenstrukturen und Speicherzugriffsmustern durch pr{\"a}zise und gezielte Informationsproduktion.}, language = {de} } @phdthesis{Schintke2010, author = {Schintke, Florian}, title = {Management verteilter Daten in Grid- und Peer-to-Peer-Systemen}, year = {2010}, language = {en} } @inproceedings{KindermannSchintkeFritzsch2012, author = {Kindermann, S. and Schintke, Florian and Fritzsch, B.}, title = {A Collaborative Data Management Infrastructure for Climate Data Analysis}, series = {Geophysical Research Abstracts}, volume = {14, EGU2012-10569}, booktitle = {Geophysical Research Abstracts}, doi = {10013/epic.39635.d001}, year = {2012}, language = {en} } @inproceedings{SchintkeReinefeldHaridietal.2010, author = {Schintke, Florian and Reinefeld, Alexander and Haridi, Seif and Sch{\"u}tt, Thorsten}, title = {Enhanced Paxos Commit for Transactions on DHTs}, series = {CCGRID}, booktitle = {CCGRID}, publisher = {IEEE}, doi = {10.1109/CCGRID.2010.41}, pages = {448 -- 454}, year = {2010}, language = {en} } @inproceedings{SchuettReinefeldSchintkeetal.2009, author = {Sch{\"u}tt, Thorsten and Reinefeld, Alexander and Schintke, Florian and Hennig, C.}, title = {Self-Adaptation in Large-Scale Systems: A Study on Structured Overlays Across Multiple Datacenters}, series = {Architectures and Languages for Self-Managing Distributed Systems (SelfMan@SASO)}, booktitle = {Architectures and Languages for Self-Managing Distributed Systems (SelfMan@SASO)}, doi = {10.1109/SASOW.2010.65}, year = {2009}, language = {en} } @inproceedings{SchuettMoserPlantikowetal.2008, author = {Sch{\"u}tt, Thorsten and Moser, Monika and Plantikow, Stefan and Schintke, Florian and Reinefeld, Alexander}, title = {A Transactional Scalable Distributed Data Store}, series = {1st IEEE International Scalable Computing Challenge, co-located with CCGrid'08}, booktitle = {1st IEEE International Scalable Computing Challenge, co-located with CCGrid'08}, year = {2008}, language = {en} } @inproceedings{SchuettReinefeldSchintkeetal.2009, author = {Sch{\"u}tt, Thorsten and Reinefeld, Alexander and Schintke, Florian and Hoffmann, Marie}, title = {Gossip-based Topology Inference for Efficient Overlay Mapping on Data Centers}, series = {Peer-to-Peer Computing}, booktitle = {Peer-to-Peer Computing}, doi = {10.1109/P2P.2009.5284553}, pages = {147 -- 150}, year = {2009}, language = {en} } @incollection{ReinefeldSchintkeSchuettetal.2009, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten and Haridi, Seif}, title = {A Scalable, Transactional Data Store for Future Internet Services}, series = {Towards the Future Internet - A European Research Perspective}, booktitle = {Towards the Future Internet - A European Research Perspective}, editor = {Tselentis, G. and Domingue, J. and Galis, A. and Gavras, A. and Hausheer, D. and Krco, S. and Lotz, V. and Zahariadis, T.}, publisher = {IOS Press}, doi = {10.3233/978-1-60750-007-0-148}, pages = {148 -- 159}, year = {2009}, language = {en} } @inproceedings{PlantikowReinefeldSchintke2008, author = {Plantikow, Stefan and Reinefeld, Alexander and Schintke, Florian}, title = {Transactions and Concurrency Control for Peer-to-Peer-Wikis: An Evaluation}, series = {Making Grids Work}, booktitle = {Making Grids Work}, editor = {Danelutto, Marco and Fragopoulou, Paraskevi and Getov, Vladimir}, doi = {10.1007/978-0-387-78448-9_27}, pages = {337 -- 349}, year = {2008}, language = {en} } @misc{AndrzejakReinefeldSchintkeetal.2008, author = {Andrzejak, Artur and Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten and Mastroianni, Carlo and Fragopoulou, Paraskevi and Kondo, Derrick and Malecot, Paul and Cosmin Silaghi, Gheorghe and Moura Silva, Luis and Trunfio, Paolo and Zeinalipour-Yazti, Demetris and Zimeo, Eugenio}, title = {Grid Architectural Issues: State-of-the-art and Future Trends}, number = {WHP-0004}, publisher = {Institute on Architectural Issues: Scalability, Dependability, Adaptability, CoreGRID - Network of Excellence}, year = {2008}, language = {en} } @article{SchuettSchintkeReinefeld2008, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Range Queries on structured overlay networks}, series = {Computer Communications}, volume = {31}, journal = {Computer Communications}, number = {2}, publisher = {Elsevier}, doi = {10.1016/j.comcom.2007.08.027}, pages = {280 -- 291}, year = {2008}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2008, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Scalaris: Reliable Transactional P2P Key/Value}, series = {ERLANG '08: Proceedings of the 7th ACM SIGPLAN workshop on ERLANG}, booktitle = {ERLANG '08: Proceedings of the 7th ACM SIGPLAN workshop on ERLANG}, doi = {10.1145/1411273.1411280}, pages = {41 -- 47}, year = {2008}, language = {en} } @article{EnkePartlReinefeldetal.2012, author = {Enke, Harry and Partl, Adrian and Reinefeld, Alexander and Schintke, Florian}, title = {Handling Big Data in Astronomy and Astrophysics}, series = {Datenbank-Spektrum}, volume = {12}, journal = {Datenbank-Spektrum}, number = {3}, publisher = {Springer-Verlag}, doi = {10.1007/s13222-012-0099-1}, pages = {173 -- 181}, year = {2012}, language = {en} } @article{Schintke2013, author = {Schintke, Florian}, title = {XtreemFS \& Scalaris}, series = {Science \& Technology}, journal = {Science \& Technology}, number = {6}, publisher = {Pan European Networks}, pages = {54 -- 55}, year = {2013}, language = {en} } @incollection{EnkeFiedlerFischeretal.2013, author = {Enke, Harry and Fiedler, Norman and Fischer, Thomas and Gnadt, Timo and Ketzan, Erik and Ludwig, Jens and Rathmann, Torsten and St{\"o}ckle, Gabriel and Schintke, Florian}, title = {Leitfaden zum Forschungsdaten-Management}, series = {Leitfaden zum Forschungsdaten-Management}, booktitle = {Leitfaden zum Forschungsdaten-Management}, editor = {Enke, Harry and Ludwig, Jens}, publisher = {Verlag Werner H{\"u}lsbusch, Gl{\"u}ckstadt}, year = {2013}, language = {en} } @article{ReinefeldStuebenSchintkeetal.2002, author = {Reinefeld, Alexander and St{\"u}ben, Hinnerk and Schintke, Florian and Din, George}, title = {GuiGen: a toolset for creating customized interfaces for Grid user communities}, series = {Future Generation Comp. Syst.}, volume = {18}, journal = {Future Generation Comp. Syst.}, number = {8}, doi = {10.1016/S0167-739X(02)00086-9}, pages = {1075 -- 1084}, year = {2002}, language = {en} } @inproceedings{FajerskiNoackReinefeldetal., author = {Fajerski, J. and Noack, Matthias and Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten and Steinke, Thomas}, title = {Fast In-Memory Checkpointing with POSIX API for Legacy Exascale-Applications}, series = {SPPEXA Symposium 2016}, booktitle = {SPPEXA Symposium 2016}, doi = {10.1007/978-3-319-40528-5_19}, language = {en} } @article{AblyazimovAbuhozaAdaketal., author = {Ablyazimov, T. and Abuhoza, A. and Adak, R. P. and Reinefeld, Alexander and Schintke, Florian and et al.,}, title = {Challenges in QCD matter physics - The scientific programme of the Compressed Baryonic Matter experiment at FAIR}, series = {The European Physical Journal A}, journal = {The European Physical Journal A}, doi = {10.1140/epja/i2017-12248-y}, language = {en} } @article{AllenDavisGoodaleetal.2005, author = {Allen, Gabrielle and Davis, K. and Goodale, Tom and Hutanu, Andrei and Kaiser, Hartmut and Kielmann, Thilo and Merzky, Andre and Nieuwpoort, R. and Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten and Seidel, Edward and Ullmer, Brygg}, title = {The Grid Application Toolkit: Toward Generic and Easy Appliction Programming Interfaces for the Grid}, series = {Procceedings of the IEEE}, volume = {93}, journal = {Procceedings of the IEEE}, number = {3}, publisher = {IEEE Computer Society Press}, doi = {10.1109/JPROC.2004.842755}, pages = {534 -- 550}, year = {2005}, language = {en} } @inproceedings{Schintke2005, author = {Schintke, Florian}, title = {The ZIB distributed data management system}, series = {Future Generation Grids}, booktitle = {Future Generation Grids}, number = {04451}, editor = {Cosnard, Michel and Getov, Vladimir and Laforenza, Domenico and Reinefeld, Alexander}, publisher = {Internationales Begegnungs- und Forschungszentrum f{\"u}r Informatik (IBFI), Schloss Dagstuhl, Germany}, address = {Dagstuhl, Germany}, pages = {20}, year = {2005}, language = {en} } @article{RoeblitzSchintkeReinefeldetal.2004, author = {R{\"o}blitz, Thomas and Schintke, Florian and Reinefeld, Alexander and B{\"a}rring, Olof and Lopez, Maite Barroso and Cancio, German and Chapeland, Sylvain and Chouikh, Karim and Cons, Lionel and Poznanski, Piotr and Defert, Philippe and Iven, Jan and Kleinwort, Thorsten and Panzer-Steindel, Bernd and Polok, Jaroslaw and Rafflin, Catherine and Silverman, Alan and Smith, Tim and van Eldik, Jan and Front, David and Biasotto, Massimo and Aiftimiei, Cristina and Ferro, Enrico and Maron, Gaetano and Chierici, Andrea and dell'Agnello, Luca and Serra, Marco and Michelotto, Michele and Hess, Lord and Lindenstruth, Volker and Pister, Frank and Steinbeck, Timm and Groep, David and Steenbakkers, Martijn and Koeroo, Oscar and de Cerff, Wim and Venekamp, Gerben and Anderson, Paul and Colles, Tim and Holt, Alexander and Scobie, Alastair and George, Michael and Washbrook, Andrew and Leiva, Rafael}, title = {Autonomic Management of Large Clusters and Their Integration into the Grid}, series = {J. Grid Comput.}, volume = {2}, journal = {J. Grid Comput.}, number = {3}, doi = {10.1007/s10723-004-7647-3}, pages = {247 -- 260}, year = {2004}, language = {en} } @inproceedings{ReinefeldSchintke2004, author = {Reinefeld, Alexander and Schintke, Florian}, title = {Dienste und Standards f{\"u}r das Grid Computing}, series = {E-Science and Grid - Ad-hoc-Netze - Medienintegration, 18. DFN-Arbeitstagung {\"u}ber Kommunikationsnetze, D{\"u}sseldorf, 2004}, volume = {P-55}, booktitle = {E-Science and Grid - Ad-hoc-Netze - Medienintegration, 18. DFN-Arbeitstagung {\"u}ber Kommunikationsnetze, D{\"u}sseldorf, 2004}, editor = {von Knop, Jan and Haverkamp, Wilhelm and Jessen, Eike}, publisher = {GI}, pages = {293 -- 304}, year = {2004}, language = {en} } @inproceedings{RoeblitzSchintkeWendler2004, author = {R{\"o}blitz, Thomas and Schintke, Florian and Wendler, Jan}, title = {Elastic Grid Reservations with User-Defined Optimization Policies}, series = {Proceedings of the 2nd Workshop on Adaptive Grid Middleware (AGridM'04), in conjunction with PACT 2004, Antibes Juan-les-Pins, France}, booktitle = {Proceedings of the 2nd Workshop on Adaptive Grid Middleware (AGridM'04), in conjunction with PACT 2004, Antibes Juan-les-Pins, France}, year = {2004}, language = {en} } @article{ReinefeldSchintke2004, author = {Reinefeld, Alexander and Schintke, Florian}, title = {Grid Services: Web Services zur Nutzung verteilter Ressourcen}, series = {Informatik Spektrum}, volume = {27}, journal = {Informatik Spektrum}, number = {2}, doi = {10.1007/s00287-004-0379-8}, pages = {129 -- 135}, year = {2004}, language = {en} } @inproceedings{WendlerSchintke2004, author = {Wendler, Jan and Schintke, Florian}, title = {Grid-Enabled Computational Fluid Dynamics using FlowGrid}, series = {Cracow Grid Workshop '03 Proceedings}, booktitle = {Cracow Grid Workshop '03 Proceedings}, publisher = {Academic Computer Centre CYFRONET AGH}, address = {ul. Nawojki 11, 30-950 Krakow 61, P.O.Box 386, Poland}, pages = {59 -- 66}, year = {2004}, language = {en} } @inproceedings{SchuettMerzkyHutanuetal.2004, author = {Sch{\"u}tt, Thorsten and Merzky, Andr{\´e} and Hutanu, Andrei and Schintke, Florian}, title = {Remote partial file access using compact pattern descriptions}, series = {4th IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGrid 2004), April 19-22, 2004, Chicago, Illinois, USA}, booktitle = {4th IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGrid 2004), April 19-22, 2004, Chicago, Illinois, USA}, publisher = {IEEE Computer Society}, doi = {10.1109/CCGrid.2004.1336604}, pages = {482 -- 489}, year = {2004}, language = {en} } @incollection{ReinefeldSchintkeSchuett2004, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Scalable and Self-Optimizing Data Grids}, series = {Annual Review of Scalable Computing}, volume = {6}, booktitle = {Annual Review of Scalable Computing}, number = {chapter 2}, publisher = {World Scientific}, doi = {10.1142/9789812794727_0002}, pages = {30 -- 60}, year = {2004}, language = {en} } @article{WendlerSchintke2005, author = {Wendler, Jan and Schintke, Florian}, title = {Executing and observing CFD applications on the Grid}, series = {Future Generation Computer Systems the International Journal of Grid Computing: Theory, Methods and Applications}, volume = {21}, journal = {Future Generation Computer Systems the International Journal of Grid Computing: Theory, Methods and Applications}, number = {1}, publisher = {Elsevier Science Publishers}, doi = {10.1016/j.future.2004.09.026}, pages = {11 -- 18}, year = {2005}, language = {en} } @misc{ReinefeldSchintkeSchuett2007, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Vorrichtung und Verfahren zum Abrufen / Speichern von elektronischen Daten in einem System mit mehreren Datenverarbeitungseinheiten}, publisher = {Europ{\"a}isches Patent EP 1 744 257 A1}, year = {2007}, language = {en} } @misc{ReinefeldSchintkeSchuett2007, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Vorrichtung und Verfahren zum Speichern / Abrufen von Objekten mit mehrdimensional adressierten, elektronischen Daten}, publisher = {Europ{\"a}ische Patentanmeldung Nr. 06012030.0 vom 12.06.2006, Patent Nr: 1868114}, year = {2007}, language = {en} } @inproceedings{GrimmeLanghammerPapaspyrouetal.2007, author = {Grimme, Christian and Langhammer, Tobias and Papaspyrou, Alexander and Schintke, Florian}, title = {Negotiation-based Choreography of Data-intensive Applications in the C3Grid Project}, series = {German E-Science Conference}, booktitle = {German E-Science Conference}, publisher = {Max Planck Digital Library}, address = {Baden-Baden}, year = {2007}, language = {en} } @inproceedings{PlantikowReinefeldSchintke2007, author = {Plantikow, Stefan and Reinefeld, Alexander and Schintke, Florian}, title = {Transactions for Distributed Wikis on Structured Overlays}, series = {DSOM}, volume = {4785}, booktitle = {DSOM}, editor = {Clemm, Alexander and Granville, Lisandro and Stadler, Rolf}, publisher = {Springer}, address = {Silicon Valley, CA, USA}, doi = {10.1007/978-3-540-75694-1_25}, pages = {256 -- 267}, year = {2007}, language = {en} } @inproceedings{SchintkeSchuettReinefeld2003, author = {Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {A Framework for Self-Optimizing Grids Using P2P Components}, series = {14th International Workshop on Database and Expert Systems Applications (DEXA'03), September 1-5, 2003, Prague, Czech Republic}, booktitle = {14th International Workshop on Database and Expert Systems Applications (DEXA'03), September 1-5, 2003, Prague, Czech Republic}, publisher = {IEEE Computer Society}, doi = {10.1109/DEXA.2003.1232101}, pages = {689 -- 693}, year = {2003}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2003, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Efficient Synchronization of Replicated Data in Distributed Systems}, series = {Computational Science - ICCS 2003, International Conference, Melbourne, Australia and St. Petersburg, Russia, June 2-4, 2003. Proceedings, Part I}, volume = {2657}, booktitle = {Computational Science - ICCS 2003, International Conference, Melbourne, Australia and St. Petersburg, Russia, June 2-4, 2003. Proceedings, Part I}, editor = {Sloot, Peter and Abramson, David and Bogdanov, Alexander and Dongarra, Jack and Zomaya, Albert and Gorbachev, Yuri}, publisher = {Springer}, doi = {10.1007/3-540-44860-8_28}, pages = {274 -- 283}, year = {2003}, language = {en} } @inproceedings{RoeblitzSchintkeReinefeld2003, author = {R{\"o}blitz, Thomas and Schintke, Florian and Reinefeld, Alexander}, title = {From Clusters to the Fabric: The Job Management Perspective}, series = {2003 IEEE International Conference on Cluster Computing (CLUSTER 2003), 1-4 December 2003, Kowloon, Hong Kong, China}, booktitle = {2003 IEEE International Conference on Cluster Computing (CLUSTER 2003), 1-4 December 2003, Kowloon, Hong Kong, China}, publisher = {IEEE Computer Society}, doi = {10.1109/CLUSTR.2003.1253351}, pages = {468 -- 473}, year = {2003}, language = {en} } @article{ReinefeldSchintke2003, author = {Reinefeld, Alexander and Schintke, Florian}, title = {Grid Computing in Deutschland}, series = {Spektrum der Wissenschaft}, journal = {Spektrum der Wissenschaft}, publisher = {Spektrum der Wissenschaft Verlagsgesellschaft, Heidelberg}, pages = {72 -- 73}, year = {2003}, language = {en} } @inproceedings{AndrzejakReinefeldSchintkeetal.2006, author = {Andrzejak, Artur and Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {On Adaptability in Grid Systems}, series = {Future Generation Grids: Proceedings of the Workshop on Future Generation Grids, November 1-5, 2004, Dagstuhl, Germany}, booktitle = {Future Generation Grids: Proceedings of the Workshop on Future Generation Grids, November 1-5, 2004, Dagstuhl, Germany}, editor = {Getov, Vladimir and Laforenza, Domenico and Reinefeld, Alexander}, publisher = {Springer}, doi = {10.1007/978-0-387-29445-2_2}, pages = {29 -- 46}, year = {2006}, language = {en} } @article{RoeblitzSchintkeReinefeld2006, author = {R{\"o}blitz, Thomas and Schintke, Florian and Reinefeld, Alexander}, title = {Resource reservations with fuzzy requests}, series = {Concurrency and Computation: Practice and Experience}, volume = {18}, journal = {Concurrency and Computation: Practice and Experience}, number = {13}, doi = {10.1002/cpe.1023}, pages = {1681 -- 1703}, year = {2006}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2006, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Structured Overlay without Consistent Hashing: Empirical Results}, series = {Sixth Workshop on Global and Peer-to-Peer Computing (GP2PC'06) at Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2006), 16-19 May 2006, Singapore}, booktitle = {Sixth Workshop on Global and Peer-to-Peer Computing (GP2PC'06) at Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2006), 16-19 May 2006, Singapore}, publisher = {IEEE Computer Society}, doi = {10.1109/CCGRID.2006.175}, pages = {8}, year = {2006}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2007, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {A Structured Overlay for Multi-dimensional Range Queries}, series = {Euro-Par Conference}, volume = {4641}, booktitle = {Euro-Par Conference}, editor = {Kermarrec, Anne-Marie}, publisher = {Springer}, doi = {10.1007/978-3-540-74466-5_54}, pages = {503 -- 513}, year = {2007}, language = {en} } @misc{ReinefeldSchintkeSchuett2007, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Device and method for retrieving / storing electronic data in a system with a plurality of data processing units}, publisher = {United States Patent Application Publication No. US 2007/0165619 A1}, year = {2007}, language = {en} } @inproceedings{PlantikowReinefeldSchintke2007, author = {Plantikow, Stefan and Reinefeld, Alexander and Schintke, Florian}, title = {Distributed Wikis on Structured Overlays}, series = {CoreGrid Workshop on Grid Programming Models, Grid and P2P System Architecture, Grid Systems, Tools and Environments}, booktitle = {CoreGrid Workshop on Grid Programming Models, Grid and P2P System Architecture, Grid Systems, Tools and Environments}, year = {2007}, language = {en} } @inproceedings{KruberLangeSchintke, author = {Kruber, Nico and Lange, Maik and Schintke, Florian}, title = {Approximate Hash-Based Set Reconciliation for Distributed Replica Repair}, series = {2015 IEEE 34th International Symposium on Reliable Distributed Systems (SRDS)}, booktitle = {2015 IEEE 34th International Symposium on Reliable Distributed Systems (SRDS)}, publisher = {IEEE}, doi = {10.1109/SRDS.2015.30}, pages = {166 -- 175}, language = {en} } @article{SchintkeReinefeld2003, author = {Schintke, Florian and Reinefeld, Alexander}, title = {Modeling Replica Availability in Large Data Grids}, series = {J. Grid Computing}, volume = {1}, journal = {J. Grid Computing}, number = {2}, doi = {10.1023/B:GRID.0000024086.50333.0d}, pages = {219 -- 227}, year = {2003}, language = {en} } @inproceedings{ReinefeldSchintke2002, author = {Reinefeld, Alexander and Schintke, Florian}, title = {Concepts and Technologies for a Worldwide Grid Infrastructure}, series = {Euro-Par 2002, Parallel Processing, 8th International Euro-Par Conference Paderborn, Germany, August 27-30, 2002, Proceedings}, volume = {2400}, booktitle = {Euro-Par 2002, Parallel Processing, 8th International Euro-Par Conference Paderborn, Germany, August 27-30, 2002, Proceedings}, editor = {Monien, Burkhard and Feldmann, Rainer}, publisher = {Springer}, doi = {10.1007/3-540-45706-2_6}, pages = {62 -- 72}, year = {2002}, language = {en} } @inproceedings{KruberSchintkeBerlin, author = {Kruber, Nico and Schintke, Florian and Berlin, Michael}, title = {A Relational Database Schema on the Transactional Key-Value Store Scalaris}, series = {Proceedings of 2nd Workshop on Scalable Cloud Data Management}, booktitle = {Proceedings of 2nd Workshop on Scalable Cloud Data Management}, doi = {10.1109/BigData.2014.7004441}, language = {en} } @inproceedings{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Linearizable State Machine Replication of State-Based CRDTs without Logs}, series = {Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing, PODC 2019}, booktitle = {Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing, PODC 2019}, doi = {10.1145/3293611.3331568}, pages = {455 -- 457}, abstract = {General solutions of state machine replication have to ensure that all replicas apply the same commands in the same order, even in the presence of failures. Such strict ordering incurs high synchronization costs due to the use of distributed consensus or a leader. This paper presents a protocol for linearizable state machine replication of conflict-free replicated data types (CRDTs) that neither requires consensus nor a leader. By leveraging the properties of state-based CRDTs—in particular the monotonic growth of a join semilattice—synchronization overhead is greatly reduced. In addition, updates just need a single round trip and modify the state 'in-place' without the need for a log. Furthermore, the message size overhead for coordination consists of a single counter per message. While reads in the presence of concurrent updates are not wait-free without a coordinator, we show that more than 97 \% of reads can be handled in one or two round trips under highly concurrent accesses. Our protocol achieves high throughput without auxiliary processes such as command log management or leader election. It is well suited for all practical scenarios that need linearizable access on CRDT data on a fine-granular scale.}, language = {en} } @inproceedings{HartungSchintke, author = {Hartung, Marc and Schintke, Florian}, title = {Learned Clause Minimization in Parallel SAT Solvers}, series = {Pragmatics of SAT 2019}, booktitle = {Pragmatics of SAT 2019}, pages = {1 -- 11}, abstract = {Learned clauses minimization (LCM) let to performance improvements of modern SAT solvers especially in solving hard SAT instances. Despite the success of LCM approaches in sequential solvers, they are not widely incorporated in parallel SAT solvers. In this paper we explore the potential of LCM for parallel SAT solvers by defining multiple LCM approaches based on clause vivification, comparing their runtime in different SAT solvers and discussing reasons for performance gains and losses. Results show that LCM only boosts performance of parallel SAT solvers on a fraction of SAT instances. More commonly applying LCM decreases performance. Only certain LCM approaches are able to improve the overall performance of parallel SAT solvers.}, language = {en} } @inproceedings{AllenDramlitschGoodaleetal., author = {Allen, Gabrielle and Dramlitsch, Thomas and Goodale, Tom and Lanfermann, Gerd and Radke, Thomas and Seidel, Edward and Kielmann, Thilo and Verstoep, Kees and Balaton, Zolt{\´a}n and Kacsuk, P{\´e}ter and Szalai, Ferenc and Gehring, J{\"o}rn and Keller, Axel and Streit, Achim and Matyska, Ludek and Ruda, Miroslav and Krenek, Ales and Knipp, Harald and Merzky, Andr{\´e} and Reinefeld, Alexander and Schintke, Florian and Ludwiczak, Bogdan and Nabrzyski, Jarek and Pukacki, Juliusz and Kersken, Hans-Peter and Aloisio, Giovanni and Cafaro, Massimo and Ziegler, Wolfgang and Russell, Michael}, title = {Early experiences with the EGrid testbed}, series = {Proceedings First IEEE/ACM International Symposium on Cluster Computing and the Grid}, booktitle = {Proceedings First IEEE/ACM International Symposium on Cluster Computing and the Grid}, doi = {10.1109/CCGRID.2001.923185}, pages = {130 -- 137}, language = {en} } @inproceedings{MillerLabartaSchintkeetal., author = {Miller, Barton P. and Labarta, Jes{\´u}s and Schintke, Florian and Simon, Jens}, title = {Performance Evaluation, Analysis and Optimization}, series = {Euro-Par 2002 Parallel Processing}, volume = {2400}, booktitle = {Euro-Par 2002 Parallel Processing}, doi = {10.1007/3-540-45706-2_15}, pages = {131 -- 131}, language = {en} } @inproceedings{IamnitchiTrunfioLedlieetal., author = {Iamnitchi, Adriana and Trunfio, Paolo and Ledlie, Jonathan and Schintke, Florian}, title = {Peer-to-Peer Computing}, series = {Euro-Par 2010 - Parallel Processing}, volume = {6271}, booktitle = {Euro-Par 2010 - Parallel Processing}, doi = {10.1007/978-3-642-15277-1_42}, pages = {444 -- 445}, language = {en} } @inproceedings{BaerringLopezCancioetal., author = {B{\"a}rring, Olof and Lopez, Maite Barroso and Cancio, German and R{\"o}blitz, Thomas and Schintke, Florian and et al.,}, title = {Towards automation of computing fabrics using tools from the fabric management workpackage of the EU DataGrid project}, series = {Computing in High Energy and Nuclear Physics (CHEP03)}, booktitle = {Computing in High Energy and Nuclear Physics (CHEP03)}, pages = {1 -- 8}, language = {en} } @article{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {RMWPaxos: Fault-Tolerant In-Place Consensus Sequences}, series = {IEEE Transactions on Parallel and Distributed Systems}, volume = {31}, journal = {IEEE Transactions on Parallel and Distributed Systems}, number = {10}, issn = {1045-9219}, doi = {10.1109/TPDS.2020.2981891}, pages = {2392 -- 2405}, language = {en} } @inproceedings{SchintkeSimonReinefeld, author = {Schintke, Florian and Simon, Jens and Reinefeld, Alexander}, title = {A Cache Simulator for Shared Memory Systems}, series = {Computational Science - ICCS 2001}, volume = {2074}, booktitle = {Computational Science - ICCS 2001}, doi = {10.1007/3-540-45718-6_62}, pages = {569 -- 578}, language = {en} } @inproceedings{HartungSchintkeSchuett, author = {Hartung, Marc and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Pinpoint Data Races via Testing and Classification}, series = {2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW); 3rd International Workshop on Software Faults (IWSF 2019)}, booktitle = {2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW); 3rd International Workshop on Software Faults (IWSF 2019)}, doi = {10.1109/ISSREW.2019.00100}, pages = {386 -- 393}, language = {en} } @article{SkrzypczakSchintke, author = {Skrzypczak, Jan and Schintke, Florian}, title = {Towards Log-Less, Fine-Granular State Machine Replication}, series = {Datenbank Spektrum}, volume = {20}, journal = {Datenbank Spektrum}, number = {3}, doi = {10.1007/s13222-020-00358-4}, pages = {231 -- 241}, language = {en} } @misc{SchefflerSipsBehlingetal., author = {Scheffler, Daniel and Sips, Mike and Behling, Robert and Dransch, Doris and Eggert, Daniel and Fajerski, Jan and Freytag, Johann-Christoph and Griffiths, Patrick and Hollstein, Andr{\´e} and Hostert, Patrick and K{\"o}thur, Patrick and Peters, Mathias and Pflugmacher, Dirk and Rabe, Andreas and Reinefeld, Alexander and Schintke, Florian and Segel, Karl}, title = {GeoMultiSens - Scalable Multisensoral Analysis of Satellite Remote Sensing Data}, series = {ESA Living Planet Symposium, EO Open Science Posters}, journal = {ESA Living Planet Symposium, EO Open Science Posters}, language = {en} } @inproceedings{SchefflerSipsBehlingetal., author = {Scheffler, Daniel and Sips, Mike and Behling, Robert and Dransch, Doris and Eggert, Daniel and Fajerski, Jan and Freytag, Johann-Christoph and Griffiths, Patrick and Hollstein, Andr{\´e} and Hostert, Patrick and K{\"o}thur, Patrick and Peters, Mathias and Pflugmacher, Dirk and Rabe, Andreas and Reinefeld, Alexander and Schintke, Florian and Segel, Karl}, title = {Geomultisens - a common automatic processing and analysis system for multi-sensor satellite data}, series = {Advancing Horizons for Land Cover Services Entering the Big Data Era, Second joint Workshop of the EARSeL Special Interest Group on Land Use \& Land Cover and the NASA LCLUC Program}, booktitle = {Advancing Horizons for Land Cover Services Entering the Big Data Era, Second joint Workshop of the EARSeL Special Interest Group on Land Use \& Land Cover and the NASA LCLUC Program}, pages = {18 -- 19}, language = {en} } @article{SeibertPetersSchintke, author = {Seibert, Felix and Peters, Mathias and Schintke, Florian}, title = {Improving I/O Performance Through Colocating Interrelated Input Data and Near-Optimal Load Balancing}, series = {Proceedings of the IPDPSW; Fourth IEEE International Workshop on High-Performance Big Data, Deep Learning, and Cloud Computing (HPBDC)}, volume = {2018}, journal = {Proceedings of the IPDPSW; Fourth IEEE International Workshop on High-Performance Big Data, Deep Learning, and Cloud Computing (HPBDC)}, doi = {10.1109/IPDPSW.2018.00081}, pages = {448 -- 457}, abstract = {Most distributed file systems assign new files to storage servers randomly. While working well in some situations, this does not help to optimize the input performance for most MapReduce computations' data access patterns. In this work, we consider an access pattern where input files are partitioned into groups of heterogeneous size. Each group is accessed by exactly one process. We design and implement a data placement strategy that places these file groups together on the same storage server. This colocation approach is combined with near-optimal storage load balancing. To do so, we use a classical scheduling approximation algorithm to solve the NP hard group assignment problem. We argue that local processing is not only beneficial because of reduced network traffic, but especially because it imposes an even resource schedule. Our experiments, based on the parallel processing of remote sensing images, reveal an enormous reduction of network traffic and up to 39 \% faster input read times. Further, simulations show that our approximate assignments limit storage server imbalances to less than 5 \% above the theoretical minimum, in contrast to more than 85 \% with random assignment.}, language = {en} } @inproceedings{SchmidtkeSchintkeSchuett, author = {Schmidtke, Robert and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {From Application to Disk: Tracing I/O Through the Big Data Stack}, series = {High Performance Computing ISC High Performance 2018 International Workshops, Frankfurt/Main, Germany, June 24 - 28, 2018, Revised Selected Papers, Workshop on Performance and Scalability of Storage Systems (WOPSSS)}, booktitle = {High Performance Computing ISC High Performance 2018 International Workshops, Frankfurt/Main, Germany, June 24 - 28, 2018, Revised Selected Papers, Workshop on Performance and Scalability of Storage Systems (WOPSSS)}, doi = {10.1007/978-3-030-02465-9_6}, pages = {89 -- 102}, abstract = {Typical applications in data science consume, process and produce large amounts of data, making disk I/O one of the dominating — and thus worthwhile optimizing — factors of their overall performance. Distributed processing frameworks, such as Hadoop, Flink and Spark, hide a lot of complexity from the programmer when they parallelize these applications across a compute cluster. This exacerbates reasoning about I/O of both the application and the framework, through the distributed file system, such as HDFS, down to the local file systems. We present SFS (Statistics File System), a modular framework to trace each I/O request issued by the application and any JVM-based big data framework involved, mapping these requests to actual disk I/O. This allows detection of inefficient I/O patterns, both by the applications and the underlying frameworks, and builds the basis for improving I/O scheduling in the big data software stack.}, language = {en} } @inproceedings{ClauseckerSchintke, author = {Clausecker, Robert and Schintke, Florian}, title = {A Measure of Quality for IDA* Heuristics}, series = {Proceedings of the Fourteenth International Symposium on Combinatorial Search (SoCS 2021)}, booktitle = {Proceedings of the Fourteenth International Symposium on Combinatorial Search (SoCS 2021)}, pages = {55 -- 63}, language = {en} } @article{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Linearizable State Machine Replication of State-Based CRDTs without Logs}, series = {arXiv}, journal = {arXiv}, abstract = {General solutions of state machine replication have to ensure that all replicas apply the same commands in the same order, even in the presence of failures. Such strict ordering incurs high synchronization costs caused by distributed consensus or by the use of a leader. This paper presents a protocol for linearizable state machine replication of conflict-free replicated data types (CRDTs) that neither requires consensus nor a leader. By leveraging the properties of state-based CRDTs - in particular the monotonic growth of a join semilattice - synchronization overhead is greatly reduced. In addition, updates just need a single round trip and modify the state `in-place' without the need for a log. Furthermore, the message size overhead for coordination consists of a single counter per message. While reads in the presence of concurrent updates are not wait-free without a coordinator, we show that more than 97\% of reads can be handled in one or two round trips under highly concurrent accesses. Our protocol achieves high throughput without auxiliary processes like command log management or leader election. It is well suited for all practical scenarios that need linearizable access on CRDT data on a fine-granular scale.}, language = {en} } @article{SchuettSchintkeSkrzypczak, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Skrzypczak, Jan}, title = {Transactions on Red-black and AVL trees in NVRAM}, series = {arXiv}, journal = {arXiv}, language = {en} } @misc{ReinefeldSchintkeSchuett, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {P2P Routing of Range Queries in Skewed Multidimensional Data Sets}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-9671}, number = {07-23}, abstract = {We present a middleware to store multidimensional data sets on Internet-scale distributed systems and to efficiently perform range queries on them. Our structured overlay network \emph{SONAR (Structured Overlay Network with Arbitrary Range queries)} puts keys which are adjacent in the key space on logically adjacent nodes in the overlay and is thereby able to process multidimensional range queries with a single logarithmic data lookup and local forwarding. The specified ranges may have arbitrary shapes like rectangles, circles, spheres or polygons. Empirical results demonstrate the routing performance of SONAR on several data sets, ranging from real-world data to artificially constructed worst case distributions. We study the quality of SONAR's routing information which is based on local knowledge only and measure the indegree of the overlay nodes to find potential hot spots in the routing process. We show that SONAR's routing table is self-adjusting, even under extreme situations, keeping always a maximum of \$\lceil \log N \rceil\$ routing entries.}, language = {en} } @misc{SchuettSchintkeReinefeld, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Chord\#: Structured Overlay Network for Non-Uniform Load-Distribution}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-8736}, number = {05-40}, abstract = {\newcommand{\chordsharp}{Chord\$^\\#\#\$} Data lookup is a fundamental problem in peer-to-peer systems: Given a key, find the node that stores the associated object. Chord and other P2P algorithms use distributed hash tables (DHTs) to distribute the keys and nodes evenly across a logical ring. Using an efficient routing strategy, DHTs provide a routing performance of \$O (\log N)\$ in networks of \$N\$ nodes. While the routing performance has been shown to be optimal, the uniform key distribution makes it impossible for DHTs to support range queries. For range queries, consecutive keys must be stored on lo gically neighboring nodes. In this paper, we present an enhancement of Chord that eliminates the hash function while keeping the same routing performance. The resulting algorithm, named \chordsharp{}, provides a richer function ality while maintaining the same complexity. In addition to Chord, \chordsharp{} adapts to load imbalance.}, language = {en} } @misc{ReinefeldStuebenSchintkeetal., author = {Reinefeld, Alexander and St{\"u}ben, Hinnerk and Schintke, Florian and Din, George}, title = {GuiGen: A Toolset for Creating Customized Interfaces for Grid User Communities}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-6737}, number = {02-06}, abstract = {\textsf{\itshape{GuiGen}} is a comprehensive set of tools for creating customized graphical user interfaces (GUIs). It draws from the concept of computing portals, which are here seen as interfaces to application-specific computing services for user communities. While \textsf{\itshape{GuiGen}} was originally designed for the use in computational grids, it can be used in client/server environments as well. Compared to other GUI generators, \textsf{\itshape{GuiGen}} is more versatile and more portable. It can be employed in many different application domains and on different target platforms. With \textsf{\itshape{GuiGen}}, application experts (rather than computer scientists) are able to create their own individually tailored GUIs.}, language = {en} } @misc{SchintkeReinefeld, author = {Schintke, Florian and Reinefeld, Alexander}, title = {On the Cost of Reliability in Large Data Grids}, doi = {10.1023/B:GRID.0000024086.50333.0d}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-7195}, number = {02-52}, abstract = {Global grid environments do not only provide massive aggregated computing power but also an unprecedented amount of distributed storage space. Unfortunately, dynamic changes caused by component failures, local decisions, and irregular data updates make it difficult to efficiently use this capacity. In this paper, we address the problem of improving data availability in the presence of unreliable components. We present an analytical model for determining an optimal combination of distributed replica catalogs, catalog sizes, and replica servers. Empirical simulation results confirm the accuracy of our theoretical analysis. Our model captures the characteristics of highly dynamic environments like peer-to-peer networks, but it can also be applied to more centralized, less dynamic grid environments like the European {\em DataGrid}.}, language = {en} } @inproceedings{SalemSchuettSchintkeetal., author = {Salem, Farouk and Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Scheduling Data Streams for Low Latency and High Throughput on a Cray XC40 Using Libfabric}, series = {CUG Conference Proceedings}, booktitle = {CUG Conference Proceedings}, abstract = {Achieving efficient many-to-many communication on a given network topology is a challenging task when many data streams from different sources have to be scattered concurrently to many destinations with low variance in arrival times. In such scenarios, it is critical to saturate but not to congest the bisectional bandwidth of the network topology in order to achieve a good aggregate throughput. When there are many concurrent point-to-point connections, the communication pattern needs to be dynamically scheduled in a fine-grained manner to avoid network congestion (links, switches), overload in the node's incoming links, and receive buffer overflow. Motivated by the use case of the Compressed Baryonic Matter experiment (CBM), we study the performance and variance of such communication patterns on a Cray XC40 with different routing schemes and scheduling approaches. We present a distributed Data Flow Scheduler (DFS) that reduces the variance of arrival times from all sources at least 30 times and increases the achieved aggregate bandwidth by up to 50\%.}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Scheduling data streams for low latency and high throughput on a Cray XC40 using Libfabric}, series = {Concurrency and Computation Practice and Experience}, volume = {32}, journal = {Concurrency and Computation Practice and Experience}, number = {20}, doi = {10.1002/cpe.5563}, pages = {1 -- 14}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Improving the throughput of a scalable FLESnet using the Data-Flow Scheduler}, series = {CBM Progress Report 2018}, journal = {CBM Progress Report 2018}, isbn = {978-3-9815227-6-1}, doi = {10.15120/GSI-2019-01018}, pages = {149 -- 150}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Supporting various interconnects in FLESnet using Libfabric}, series = {CBM Progress Report 2016}, journal = {CBM Progress Report 2016}, isbn = {978-3-9815227-4-7}, pages = {159 -- 160}, language = {en} } @article{SalemSchintkeReinefeld, author = {Salem, Farouk and Schintke, Florian and Reinefeld, Alexander}, title = {Handling Compute-Node Failures in FLESnet}, series = {CBM Progress Report 2019}, journal = {CBM Progress Report 2019}, isbn = {978-3-9815227-8-5}, doi = {10.15120/GSI-2020-00904}, pages = {167 -- 168}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Data-flow scheduling for a scalable FLESnet}, series = {CBM Progress Report 2017}, journal = {CBM Progress Report 2017}, isbn = {978-3-9815227-5-4}, doi = {10.15120/GSI-2018-00485}, pages = {130 -- 131}, language = {en} } @article{SalemSchintke, author = {Salem, Farouk and Schintke, Florian}, title = {Load balancing mechanism for FLESnet}, series = {CBM Progress Report 2020}, journal = {CBM Progress Report 2020}, doi = {10.15120/GSI-2021-00421}, pages = {156 -- 157}, language = {en} } @misc{Schintke, author = {Schintke, Florian}, title = {Ermittlung von Programmlaufzeiten anhand von Speicherzugriffen, Microbenchmarks und Simulation vonSpeicherhierarchien}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-6018}, number = {00-33}, abstract = {\\{\bf Zusammenfassung:} Kostenmodelle dienen der Ermittlung von Programmlaufzeiten, zum Vergleich der Effizienz von Algorithmen und zur Analyse des Verhaltens von Speicherhierarchien. Ein neuartiges Kostenmodell ist das Latency-of-Data-Access (LDA) Modell, das mehrere hierarchische Speicherebenen mit unterschiedlichen Latenzzeiten ber{\"u}{}cksichtigt. In dieser Diplomarbeit wird ein Simulator f{\"u}{}r Speicherhierarchien pr{\"a}{}sentiert, der die Berechnung von Programmausf{\"u}{}hrungszeiten nach dem LDA-Modell erlaubt. Mit Hilfe des Simulators wird die These gepr{\"u}{}ft, da\ss{} mit diesem Modell die Ausf{\"u}{}hrungszeit eines Programms ad{\"a}{}quat abgesch{\"a}{}tzt werden kann. Mit dem Simulator ist es erstmals praktikabel m{\"o}{}glich, Programmausf{\"u}{}hrungszeiten nach dem LDA-Modell zu bestimmen. Der Simulator kann f{\"u}{}r Systeme mit unterschiedlichen Speicherarchitekturen konfiguriert werden und unterst{\"u}{}tzt Mehrprozessorsysteme mit gemeinsamem Speicher (SMP-Systeme) mit verschiedenen Koh{\"a}{}renzprotokollen. Der Simulator kann mit den Ergebnissen von Microbenchmarks konfiguriert werden, die die Architekturparameter einer Speicherhierarchie messen. Die Ergebnisse best{\"a}{}tigen die These nicht nur f{\"u}{}r Einzelprozessorsysteme, sondern auch f{\"u}{}r SMP-Systeme, wo gleichzeitig interagierende Prozessoren gegenseitig ihre Zugriffssequenz auf Zwischenspeicher beeinflussen. Zus{\"a}{}tzlich wurde eine neue Einsatzm{\"o}{}glichkeit des LDA-Modells entwickelt, um die Ausf{\"u}{}hrungszeit von Programmteilen zu bestimmen. Einzelne Zugriffskosten k{\"o}{}nnen einem mehrerer parallel laufender Modelle zugeordnet werden. Dadurch k{\"o}{}nnen Kosten, die Zugriffe auf einzelne Speicherbereiche verursachen, separat bestimmt werden. Diese Profiling-Technik erlaubt Optimierungen an Datenstrukturen und Speicherzugriffsmustern durch pr{\"a}{}zise und gezielte Informationsproduktion.Cost models are used to determine the execution time of programs, to compare the efficiency of algorithms, and to analyse the behaviour of memory hierarchies. The Latency-of-Data-Access (LDA) model that takes into account multiple hierarchical memory levels with different latencies, is a newly proposed, innovative cost model. In this diploma-thesis, a simulator for memory hierarchies is presented that allows the calculation of execution times using the LDA-model. The simulator is used to prove the claim that the execution time of a program can be accurately estimated with the LDA-model. With the simulator, it is for the first time possible to determine the execution time of programs with this model in a practical way. The simulator can be configured for systems with various cache architectures and supports shared memory (SMP) multiprocessor systems with different cache coherence protocols. The simulator can be configured with the results from microbenchmarks which measure the architectural properties of a memory hierarchy. The results confirm the claim not only for single processor systems, but also for SMP systems, where concurrently interacting processors influence each others cache access sequence. Additionally, a new field of usage of the LDA-model was developed to determine execution times of program parts. Single access costs can be assigned to one of several parallel running models. As an example the costs of accesses to different memory areas can be split and determined separately. This profiling technique allows to optimise data structures and memory access patterns of sequential and parallel SMP programs by precise production of information.}, language = {de} } @article{LoesserWitzkeSchintkeetal., author = {L{\"o}ßer, Angar and Witzke, Joel and Schintke, Florian and Scheuermann, Bj{\"o}rn}, title = {BottleMod: Modeling Data Flows and Tasks for Fast Bottleneck Analysis}, series = {arXiv}, journal = {arXiv}, doi = {10.48550/arXiv.2209.05358}, pages = {1 -- 20}, language = {en} } @article{LeserHilbrichDraxletal., author = {Leser, Ulf and Hilbrich, Marcus and Draxl, Claudia and Eisert, Peter and Grunske, Lars and Hostert, Patrick and Kainm{\"u}ller, Dagmar and Kao, Odej and Kehr, Birte and Kehrer, Timo and Koch, Christoph and Markl, Volker and Meyerhenke, Henning and Rabl, Tilmann and Reinefeld, Alexander and Reinert, Knut and Ritter, Kerstin and Scheuermann, Bj{\"o}rn and Schintke, Florian and Schweikardt, Nicole and Weidlich, Matthias}, title = {The Collaborative Research Center FONDA}, series = {Datenbank-Spektrum}, volume = {21}, journal = {Datenbank-Spektrum}, number = {3}, doi = {10.1007/s13222-021-00397-5}, pages = {255 -- 260}, language = {en} } @inproceedings{LoesserWitzkeSchintkeetal., author = {L{\"o}ßer, Angar and Witzke, Joel and Schintke, Florian and Scheuermann, Bj{\"o}rn}, title = {BottleMod: Modeling Data Flows and Tasks for Fast Bottleneck Analysis}, series = {2022 IEEE International Conference on Big Data, Posters}, booktitle = {2022 IEEE International Conference on Big Data, Posters}, language = {en} } @article{SalemSchintke, author = {Salem, Farouk and Schintke, Florian}, title = {Large-Scale Performance of the Data-Flow Scheduler (DFS) and FLESnet}, series = {CBM Progress Report 2021}, journal = {CBM Progress Report 2021}, doi = {10.15120/GSI-2022-00599}, pages = {170 -- 171}, language = {en} } @inproceedings{WitzkeSchintkeLoesseretal., author = {Witzke, Joel and Schintke, Florian and L{\"o}ßer, Ansgar and Scheuermann, Bj{\"o}rn}, title = {Proactive Resource Management to Optimize Distributed Workflow Executions}, series = {IEEE International Conference on Big Data, BigData 2023, Sorrento, Italy, December 15-18, 2023}, booktitle = {IEEE International Conference on Big Data, BigData 2023, Sorrento, Italy, December 15-18, 2023}, publisher = {IEEE}, doi = {10.1109/BigData59044.2023.10386493}, pages = {6305 -- 6307}, language = {en} } @article{SchintkeDeMecquenemGuarinoetal., author = {Schintke, Florian and De Mecquenem, Ninon and Guarino, Vanessa Emanuela and Hilbrich, Marcus and Lehmann, Fabian and Sattler, Rebecca and Sparka, Jan Arne and Speckhard, Daniel and Stolte, Hermann and Vu, Anh Duc and Leser, Ulf}, title = {Validity Constraints for Data Analysis Workflows}, series = {arXiv}, journal = {arXiv}, doi = {10.48550/arXiv.2305.08409}, pages = {1 -- 28}, language = {en} } @article{SchintkeBelhajjameDeMecquenemetal., author = {Schintke, Florian and Belhajjame, Khalid and De Mecquenem, Ninon and Frantz, David and Guarino, Vanessa Emanuela and Hilbrich, Marcus and Lehmann, Fabian and Missier, Paolo and Sattler, Rebecca and Sparka, Jan Arne and Speckhard, Daniel T. and Stolte, Hermann and Vu, Anh Duc and Leser, Ulf}, title = {Validity constraints for data analysis workflows}, series = {Future Generation Computer Systems}, volume = {157}, journal = {Future Generation Computer Systems}, doi = {10.1016/j.future.2024.03.037}, pages = {82 -- 97}, language = {en} } @inproceedings{GholamiSchintkeSchuett, author = {Gholami, Masoud and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Checkpoint Scheduling for Shared Usage of Burst-Buffers in Supercomputers}, series = {Proceedings of the 47th International Conference on Parallel Processing Companion; SRMPDS 2018: The 14th International Workshop on Scheduling and Resource Management for Parallel and Distributed Systems}, booktitle = {Proceedings of the 47th International Conference on Parallel Processing Companion; SRMPDS 2018: The 14th International Workshop on Scheduling and Resource Management for Parallel and Distributed Systems}, doi = {10.1145/3229710.3229755}, pages = {44:1 -- 44:10}, abstract = {User-defined and system-level checkpointing have contrary properties. While user-defined checkpoints are smaller and simpler to recover, system-level checkpointing better knows the global system's state and parameters like the expected mean time to failure (MTTF) per node. Both approaches lead to non-optimal checkpoint time, intervals, sizes, or I/O bandwidth when concurrent checkpoints conflict and compete for it. We combine user-defined and system-level checkpointing to exploit the benefits and avoid the drawbacks of each other. Thus, applications frequently offer to create checkpoints. The system accepts such offers according to the current status and implied costs to recalculate from the last checkpoint or denies them, i.e., immediately lets continue the application without checkpoint creation. To support this approach, we develop economic models for multi-application checkpointing on shared I/O resources that are dedicated for checkpointing (e.g. burst-buffers) by defining an appropriate goal function and solving a global optimization problem. Using our models, the checkpoints of applications on a supercomputer are scheduled to effectively use the available I/O bandwidth and minimize the failure overhead (checkpoint creations plus recalculations). Our simulations show an overall reduction in failure overhead of all nodes of up to 30\% for a typical supercomputer workload (HLRN). We can also derive the most cost effective burst-buffer bandwidth for a given node's MTTF and application workload.}, language = {en} } @inproceedings{WeinholdLackorzynskiBierbaumetal., author = {Weinhold, Carsten and Lackorzynski, Adam and Bierbaum, Jan and K{\"u}ttler, Martin and Planeta, Maksym and Weisbach, Hannes and Hille, Matthias and H{\"a}rtig, Hermann and Margolin, Alexander and Sharf, Dror and Levy, Ely and Gak, Pavel and Barak, Amnon and Gholami, Masoud and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander and Lieber, Matthias and Nagel, Wolfgang}, title = {FFMK: A Fast and Fault-Tolerant Microkernel-Based System for Exascale Computing}, series = {Software for Exascale Computing - SPPEXA 2016-2019}, booktitle = {Software for Exascale Computing - SPPEXA 2016-2019}, publisher = {Springer}, doi = {10.1007/978-3-030-47956-5_16}, pages = {483 -- 516}, language = {en} } @article{GholamiSchintke, author = {Gholami, Masoud and Schintke, Florian}, title = {IOSIG: Declarative I/O-Stream Properties Using Pragmas}, series = {Datenbank-Spektrum}, volume = {22}, journal = {Datenbank-Spektrum}, number = {2}, publisher = {Springer Berlin Heidelberg}, doi = {10.1007/s13222-022-00419-w}, pages = {109 -- 119}, language = {en} } @inproceedings{GholamiSchintke, author = {Gholami, Masoud and Schintke, Florian}, title = {Combining XOR and Partner Checkpointing for Resilient Multilevel Checkpoint/Restart}, series = {2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, booktitle = {2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, doi = {10.1109/IPDPS49936.2021.00036}, pages = {277 -- 288}, language = {en} } @inproceedings{GholamiSchintke, author = {Gholami, Masoud and Schintke, Florian}, title = {Multilevel Checkpoint/Restart for Large Computational Jobs on Distributed Computing Resources}, series = {2019 IEEE 38th Symposium on Reliable Distributed Systems (SRDS)}, booktitle = {2019 IEEE 38th Symposium on Reliable Distributed Systems (SRDS)}, doi = {10.1109/SRDS47363.2019.00025}, pages = {143 -- 152}, language = {en} } @article{GholamiSchintke, author = {Gholami, Masoud and Schintke, Florian}, title = {CAWL: A Cache-aware Write Performance Model of Linux Systems}, series = {arXiv}, journal = {arXiv}, doi = {10.48550/arXiv.2306.05701}, pages = {1 -- 22}, language = {en} } @misc{GholamiSchintkeSchuettetal., author = {Gholami, Masoud and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Modeling Checkpoint Schedules for Concurrent HPC Applications}, series = {CoSaS 2018 International Symposium on Computational Science at Scale}, journal = {CoSaS 2018 International Symposium on Computational Science at Scale}, language = {en} }