@inproceedings{KruberSchintkeBerlin2014, author = {Kruber, Nico and Schintke, Florian and Berlin, Michael}, title = {A Relational Database Schema on the Transactional Key-Value Store Scalaris}, booktitle = {Proceedings of 2nd Workshop on Scalable Cloud Data Management}, doi = {10.1109/BigData.2014.7004441}, year = {2014}, language = {en} } @article{KramerLaeuterRubinetal.2017, author = {Kramer, Tobias and L{\"a}uter, Matthias and Rubin, Martin and Altwegg, Kathrin}, title = {Seasonal changes of the volatile density in the coma and on the surface of comet 67P/Churyumov-Gerasimenko}, volume = {469}, journal = {Monthly Notices of the Royal Astronomical Society}, arxiv = {http://arxiv.org/abs/1704.03874}, doi = {10.1093/mnras/stx866}, pages = {S20 -- S28}, year = {2017}, abstract = {Starting from several monthly data sets of Rosetta's COmetary Pressure Sensor we reconstruct the gas density in the coma around comet 67P/Churyumov-Gerasimenko. The underlying inverse gas model is constructed by fitting ten thousands of measurements to thousands of potential gas sources distributed across the entire nucleus surface. The ensuing self-consistent solution for the entire coma density and surface activity reproduces the temporal and spatial variations seen in the data for monthly periods with Pearson correlation coefficients of 0.93 and higher. For different seasonal illumination conditions before and after perihelion we observe a systematic shift of gas sources on the nucleus.}, language = {en} } @article{ZanderDreischarfTimmetal.2016, author = {Zander, Thomas and Dreischarf, Marcel and Timm, Anne-Katrin and Baumann, Wolfgang and Schmidt, Hendrik}, title = {Impact of material and morphological parameters on the mechanical response of the lumbar spine - A finite element sensitivity study}, volume = {53}, journal = {Journal of Biomechanics}, doi = {10.1016/j.jbiomech.2016.12.014}, pages = {185 -- 190}, year = {2016}, language = {en} } @article{RitterBelavyBaumannetal.2017, author = {Ritter, Zully and Belavy, Daniel and Baumann, Wolfgang and Felsenberg, Dieter}, title = {In vivo bone remodeling rates determination and compressive stiffness variations before, during 60 days bed rest and two years follow up: a micro-FE-analysis from HR-pQCT measurements of the Berlin bed rest study-2}, volume = {132}, journal = {Acta Astronautica}, doi = {10.1016/j.actaastro.2016.12.002}, pages = {67 -- 77}, year = {2017}, language = {en} } @article{KramerRodriguez2017, author = {Kramer, Tobias and Rodriguez, Mirta}, title = {Two-dimensional electronic spectra of the photosynthetic apparatus of green sulfur bacteria}, volume = {7}, journal = {Scientific Reports}, doi = {10.1038/srep45245}, pages = {45245}, year = {2017}, abstract = {Advances in time resolved spectroscopy have provided new insight into the energy transmission in natural photosynthetic complexes. Novel theoretical tools and models are being developed in order to explain the experimental results. We provide a model calculation for the two-dimensional electronic spectra of Cholorobaculum tepidum which correctly describes the main features and transfer time scales found in recent experiments. From our calculation one can infer the coupling of the antenna chlorosome with the environment and the coupling between the chlorosome and the Fenna-Matthews-Olson complex. We show that environment assisted transport between the subunits is the required mechanism to reproduce the experimental two-dimensional electronic spectra.}, language = {en} } @article{AblyazimovAbuhozaAdaketal.2017, 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}, journal = {The European Physical Journal A}, doi = {10.1140/epja/i2017-12248-y}, year = {2017}, language = {en} } @article{SalemSchintkeSchuettetal.2017, author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Supporting various interconnects in FLESnet using Libfabric}, journal = {CBM Progress Report 2016}, isbn = {978-3-9815227-4-7}, pages = {159 -- 160}, year = {2017}, language = {en} } @article{OrgisLaeuterHandorfetal.2017, author = {Orgis, Thomas and L{\"a}uter, Matthias and Handorf, D{\"o}rthe and Dethloff, Klaus}, title = {Baroclinic waves on the β plane using low-order Discontinuous Galerkin discretisation}, volume = {339}, journal = {Journal of Computational Physics}, doi = {10.1016/j.jcp.2017.03.029}, pages = {461 -- 481}, year = {2017}, abstract = {A classic Discontinuous Galerkin Method with low-order polynomials and explicit as well as semi-implicit time-stepping is applied to an atmospheric model employing the Euler equations on the β plane. The method, which was initially proposed without regard for the source terms and their balance with the pressure gradient that dominates atmospheric dynamics, needs to be adapted to be able to keep the combined geostrophic and hydrostatic balance in three spatial dimensions. This is achieved inside the discretisation through a polynomial mapping of both source and flux terms without imposing filters between time steps. After introduction and verification of this balancing, the realistic development of barotropic and baroclinic waves in the model is demonstrated, including the formation of a retrograde Rossby wave pattern. A prerequesite is the numerical solution of the thermal wind equation to construct geostrophically balanced initial states in z coordinates with arbitrary prescribed zonal wind profile, offering a new set of test cases for atmospheric models employing z coordinates. The resulting simulations demonstrate that the balanced low-order Discontinous Galerkin discretisation with polynomial degrees down to k=1 can be a viable option for atmospheric modelling.}, language = {en} } @incollection{CoutinhoStillwellArgyrakietal.2017, author = {Coutinho, Jose and Stillwell, Mark and Argyraki, Katerina and Ioannidis, George and Iordache, Anca and Kleineweber, Christoph and Koliousis, Alexandros and McGlone, John and Pierre, Guillaume and Ragusa, Carmelo and Sanders, Peter and Sch{\"u}tt, Thorsten and Yu, Teng and Wolf, Alexander}, title = {The HARNESS Platform: A Hardware- and Network-Enhanced Software System for Cloud Computing}, booktitle = {Software Architecture for Big Data and the Cloud}, publisher = {Morgan Kaufmann}, isbn = {9780128054673}, pages = {323 -- 351}, year = {2017}, language = {en} } @misc{WendeLaubenderSteinke2014, author = {Wende, Florian and Laubender, Guido and Steinke, Thomas}, title = {Integration of Intel Xeon Phi Servers into the HLRN-III Complex: Experiences, Performance and Lessons Learned}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-49990}, year = {2014}, abstract = {The third generation of the North German Supercomputing Alliance (HLRN) compute and storage facilities comprises a Cray XC30 architecture with exclusively Intel Ivy Bridge compute nodes. In the second phase, scheduled for November 2014, the HLRN-III configuration will undergo a substantial upgrade together with the option of integrating accelerator nodes into the system. To support the decision-making process, a four-node Intel Xeon Phi cluster is integrated into the present HLRN-III infrastructure at ZIB. This integration includes user/project management, file system access and job management via the HLRN-III batch system. For selected workloads, in-depth analysis, migration and optimization work on Xeon Phi is in progress. We will report our experiences and lessons learned within the Xeon Phi installation and integration process. For selected examples, initial results of the application evaluation on the Xeon Phi cluster platform will be discussed.}, language = {en} } @article{HermannEhrigGolasetal.2014, author = {Hermann, Frank and Ehrig, Hartmut and Golas, Ulrike and Orejas, Fernando}, title = {Formal Analysis of Model Transformations Based on Triple Graph Grammars}, volume = {24}, journal = {Mathematical Structures in Computer Science}, number = {4}, doi = {10.1017/S0960129512000370}, pages = {1 -- 57}, year = {2014}, language = {en} } @article{EhrigGolasHabeletal.2014, author = {Ehrig, Hartmut and Golas, Ulrike and Habel, A. and Lambers, L. and Orejas, Fernando}, title = {M-Adhesive Transformation Systems with Nested Application Conditions. Part 1: Parallelism, Concurreny and Amalgamation}, volume = {24}, journal = {Mathematical Structures in Computer Science}, number = {4}, doi = {10.1017/S0960129512000357}, pages = {1 -- 48}, year = {2014}, language = {en} } @article{GabrielBraatzEhrigetal.2014, author = {Gabriel, Karsten and Braatz, Benjamin and Ehrig, Hartmut and Golas, Ulrike}, title = {Finitary M-Adhesive Categories}, volume = {24}, journal = {Mathematical Structures in Computer Science}, number = {4}, doi = {10.1017/S0960129512000321}, pages = {1 -- 40}, year = {2014}, language = {en} } @inproceedings{KleineweberReinefeldSchuett2014, author = {Kleineweber, Christoph and Reinefeld, Alexander and Sch{\"u}tt, Thorsten}, title = {QoS-aware Storage Virtualization for Cloud File Systems}, booktitle = {Proceedings of the 1st ACM International Workshop on Programmable File Systems}, doi = {10.1145/2603941.2603944}, pages = {19 -- 26}, year = {2014}, language = {en} } @inproceedings{DresslerSteinke2014, author = {Dreßler, Sebastian and Steinke, Thomas}, title = {An Automated Approach for Estimating the Memory Footprint of Non-linear Data Objects}, volume = {8374}, booktitle = {Euro-Par 2013: Parallel Processing Workshops}, doi = {10.1007/978-3-642-54420-0_25}, pages = {249 -- 258}, year = {2014}, language = {en} } @masterthesis{Fischer2014, type = {Bachelor Thesis}, author = {Fischer, Jens V.}, title = {A Gossiping Framework for Scalaris}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-50685}, year = {2014}, language = {en} } @article{GolasHabelEhrig2014, author = {Golas, Ulrike and Habel, A. and Ehrig, Hartmut}, title = {Multi-Amalgamation of Rules with Application Conditions in M-Adhesive Categories}, volume = {24}, journal = {Mathematical Structures in Computer Science}, number = {4}, doi = {10.1017/S0960129512000345}, pages = {1 -- 68}, year = {2014}, language = {en} } @misc{WendeSteinkeCordes2014, author = {Wende, Florian and Steinke, Thomas and Cordes, Frank}, title = {Multi-threaded Kernel Offloading to GPGPU Using Hyper-Q on Kepler Architecture}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-50362}, year = {2014}, abstract = {Small-scale computations usually cannot fully utilize the compute capabilities of modern GPGPUs. With the Fermi GPU architecture Nvidia introduced the concurrent kernel execution feature allowing up to 16 GPU kernels to execute simultaneously on a shared GPU device for a better utilization of the respective resources. Insufficient scheduling capabilities in this respect, however, can significantly reduce the theoretical concurrency level. With the Kepler GPU architecture Nvidia addresses this issue by introducing the Hyper-Q feature with 32 hardware managed work queues for concurrent kernel execution. We investigate the Hyper-Q feature within heterogeneous workloads with multiple concurrent host threads or processes offloading computations to the GPU each. By means of a synthetic benchmark kernel and a hybrid parallel CPU-GPU real-world application, we evaluate the performance obtained with Hyper-Q on GPU and compare it against a kernel reordering mechanism introduced by the authors for the Fermi architecture.}, language = {en} } @misc{Noack2014, author = {Noack, Matthias}, title = {HAM - Heterogenous Active Messages for Efficient Offloading on the Intel Xeon Phi}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-50610}, year = {2014}, abstract = {The applicability of accelerators is limited by the attainable speed-up for the offloaded computations and by the offloading overheads. While GPU programming models like CUDA and OpenCL only allow to optimise the application code and its speed-up, the available low-level APIs for the Intel Xeon Phi provide opportunity to address the overheads, too. This work presents an Heterogeneous Active Message (HAM) layer that minimises software overheads for offloading on Intel's Xeon Phi. It provides the basis for an offload API with similar semantics as the Intel Language Extensions for Offload (LEO). In contrast to LEO, HAM works within the C++ language and needs no additional compiler support. We evaluated HAM on top of SCIF and MPI as communication backends. While the SCIF backend offers the best performance, the MPI backend allows for inter-node offloads which are not possible with other offload solutions. Benchmark results show that the cost for offloading a function call can be decreased by a factor up to 18 compared with LEO.}, language = {en} } @inproceedings{Schaefer2014, author = {Sch{\"a}fer, Patrick}, title = {Towards Time Series Classification without Human Preprocessing}, volume = {8556}, booktitle = {MLDM 2014}, doi = {10.1007/978-3-319-08979-9_18}, pages = {228 -- 242}, year = {2014}, language = {en} } @article{PotamitisSchaefer2014, author = {Potamitis, Ilyas and Sch{\"a}fer, Patrick}, title = {On Classifying Insects from their Wing-Beat: New Results}, journal = {Ecology and acoustics: emergent properties from community to landscape, Paris, France}, year = {2014}, language = {en} } @article{KruegerGrunzkeGesingetal.2014, author = {Kr{\"u}ger, Jens and Grunzke, Richard and Gesing, Sandra and Breuers, Sebastian and Brinkmann, Andr{\´e} and de la Garza, Luis and Kohlbacher, Oliver and Kruse, Martin and Nagel, Wolfgang and Packschies, Lars and M{\"u}ller-Pfefferkorn, Ralph and Sch{\"a}fer, Patrick and Sch{\"a}rfe, Charlotta and Steinke, Thomas and Schlemmer, Tobias and Warzecha, Klaus Dieter and Zink, Andreas and Herres-Pawlis, Sonja}, title = {The MoSGrid Science Gateway - A Complete Solution for Molecular Simulations}, volume = {10}, journal = {Journal of Chemical Theory and Computation}, number = {6}, doi = {10.1021/ct500159h}, pages = {2232 -- 2245}, year = {2014}, language = {en} } @misc{Lorenz2009, type = {Master Thesis}, author = {Lorenz, Christian}, title = {Leistungsverbesserung der Daten{\"u}bertragung bei der Replikation von nicht ver{\"a}nderlichen Dateien in einem verteilten Dateisystem}, year = {2009}, language = {de} } @masterthesis{Hoffmann2009, type = {Bachelor Thesis}, author = {Hoffmann, Marie}, title = {Ein agglomeratives, gossipbasiertes Clustering-Verfahren f{\"u}r verteilte Systeme implementiert in Scalaris}, year = {2009}, language = {de} } @misc{Muennich2011, type = {Master Thesis}, author = {M{\"u}nnich, Bert}, title = {K{\"u}rzeste-Wege-Suche mit Grafikkarten}, year = {2011}, language = {de} } @misc{Langner2012, type = {Master Thesis}, author = {Langner, Felix}, title = {{\"U}berlastungsschutz mit Anfragepriorisierung f{\"u}r das Internetdateisystem XtreemFS}, year = {2012}, language = {de} } @misc{Beick2010, type = {Master Thesis}, author = {Beick, Matthias}, title = {On-Line Processing of Streams and Time Series - An Evaluation}, year = {2010}, language = {en} } @misc{Borchert2011, type = {Master Thesis}, author = {Borchert, Sebastian}, title = {Generische Templates zur Kommunikation in heterogenen Manycore-Systemen}, year = {2011}, language = {de} } @misc{Merkulow2013, type = {Master Thesis}, author = {Merkulow, Igor}, title = {Parameter selection and evaluation for programming of heterogeneous architectures}, year = {2013}, language = {en} } @article{HaertigMatsuokaMuelleretal.2015, author = {H{\"a}rtig, Hermann and Matsuoka, Satoshi and Mueller, Frank and Reinefeld, Alexander}, title = {Resilience in Exascale Computing (Dagstuhl Seminar 14402)}, volume = {4}, journal = {Dagstuhl Reports}, number = {9}, doi = {10.4230/DagRep.4.9.124}, pages = {124 -- 139}, year = {2015}, language = {en} } @article{TumaSauer2015, author = {Tuma, Christian and Sauer, Joachim}, title = {Quantum chemical ab initio prediction of proton exchange barriers between CH4 and different H-zeolites}, volume = {143}, journal = {The Journal of Chemical Physics}, number = {10}, doi = {10.1063/1.4923086}, pages = {102810-1 -- 102810-13}, year = {2015}, language = {en} } @inproceedings{WendeSteinkeReinefeld2015, author = {Wende, Florian and Steinke, Thomas and Reinefeld, Alexander}, title = {The Impact of Process Placement and Oversubscription on Application Performance: A Case Study for Exascale Computing}, booktitle = {Proceedings of the 3rd International Conference on Exascale Applications and Software, EASC 2015}, editor = {Gray, A. and Smith, L. and Weiland, M.}, publisher = {The University of Edinburgh}, isbn = {978 -0-9 926615 -1-9}, pages = {13 -- 18}, year = {2015}, language = {en} } @incollection{NoackWendeOertel2015, author = {Noack, Matthias and Wende, Florian and Oertel, Klaus-Dieter}, title = {OpenCL: There and Back Again}, volume = {2}, booktitle = {High Performance Parallelism Pearls}, editor = {Reinders, James and Jeffers, Jim}, publisher = {Morgan Kaufman, Elsevier}, isbn = {978-0-12-803819-2}, pages = {355 -- 378}, year = {2015}, language = {en} } @article{KramerNoack2015, author = {Kramer, Tobias and Noack, Matthias}, title = {Prevailing Dust-transport Directions on Comet 67P/Churyumov-Gerasimenko}, volume = {813}, journal = {The Astrophysical Journal Letters}, number = {2}, doi = {10.1088/2041-8205/813/2/L33}, pages = {L33}, year = {2015}, abstract = {Dust transport and deposition behind larger boulders on the comet 67P/Churyumov-Gerasimenko (67P/C-G) have been observed by the Rosetta mission. We present a mechanism for dust-transport vectors based on a homogeneous surface activity model incorporating in detail the topography of 67P/C-G. The combination of gravitation, gas drag, and Coriolis force leads to specific dust transfer pathways, which for higher dust velocities fuel the near-nucleus coma. By distributing dust sources homogeneously across the whole cometary surface, we derive a global dust-transport map of 67P/C-G. The transport vectors are in agreement with the reported wind-tail directions in the Philae descent area.}, language = {en} } @article{Schaefer2015, author = {Sch{\"a}fer, Patrick}, title = {Scalable time series classification}, journal = {Data Mining and Knowledge Discovery}, doi = {10.1007/s10618-015-0441-y}, pages = {1 -- 26}, year = {2015}, abstract = {Time series classification tries to mimic the human understanding of similarity. When it comes to long or larger time series datasets, state-of-the-art classifiers reach their limits because of unreasonably high training or testing times. One representative example is the 1-nearest-neighbor dynamic time warping classifier (1-NN DTW) that is commonly used as the benchmark to compare to. It has several shortcomings: it has a quadratic time complexity in the time series length and its accuracy degenerates in the presence of noise. To reduce the computational complexity, early abandoning techniques, cascading lower bounds, or recently, a nearest centroid classifier have been introduced. Still, classification times on datasets of a few thousand time series are in the order of hours. We present our Bag-Of-SFA-Symbols in Vector Space classifier that is accurate, fast and robust to noise. We show that it is significantly more accurate than 1-NN DTW while being multiple orders of magnitude faster. Its low computational complexity combined with its good classification accuracy makes it relevant for use cases like long or large amounts of time series or real-time analytics.}, language = {en} } @inproceedings{KruberLangeSchintke2015, author = {Kruber, Nico and Lange, Maik and Schintke, Florian}, title = {Approximate Hash-Based Set Reconciliation for Distributed Replica Repair}, booktitle = {2015 IEEE 34th International Symposium on Reliable Distributed Systems (SRDS)}, publisher = {IEEE}, doi = {10.1109/SRDS.2015.30}, pages = {166 -- 175}, year = {2015}, language = {en} } @book{EhrigErmelGolasetal.2015, author = {Ehrig, Hartmut and Ermel, Claudia and Golas, Ulrike and Hermann, Frank}, title = {Graph and Model Transformation}, publisher = {Springer-Verlag Berlin Heidelberg}, isbn = {978-3-662-47979-7}, doi = {10.1007/978-3-662-47980-3}, year = {2015}, abstract = {This book is a comprehensive explanation of graph and model transformation. It contains a detailed introduction, including basic results and applications of the algebraic theory of graph transformations, and references to the historical context. Then in the main part the book contains detailed chapters on M-adhesive categories, M-adhesive transformation systems, and multi-amalgamated transformations, and model transformation based on triple graph grammars. In the final part of the book the authors examine application of the techniques in various domains, including chapters on case studies and tool support. The book will be of interest to researchers and practitioners in the areas of theoretical computer science, software engineering, concurrent and distributed systems, and visual modelling.}, language = {en} } @phdthesis{Schaefer2015, author = {Sch{\"a}fer, Patrick}, title = {Scalable Time Series Similarity Search for Data Analytics}, year = {2015}, language = {en} } @misc{Lange2012, type = {Master Thesis}, author = {Lange, Maik}, title = {Effiziente Reparatur von Repliken in Distributed Hash Tables}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42275}, school = {Zuse Institute Berlin (ZIB)}, year = {2012}, abstract = {Eine distributed hash Table (DHT) stellt eine {\"u}ber multiple Rechner strukturiert verteilte Tabelle von Schl{\"u}ssel-Wert-Paaren dar. Ein verteiltes System unterliegt zumeist einer Teilnehmerdynamik in Form von ausfallenden oder beitretenden Knoten, wodurch Daten verloren gehen k{\"o}nnen. Zur Sicherstellung der Verf{\"u}gbarkeit aller Schl{\"u}ssel-Wert-Paare ist Redundanz notwendig. Die Einf{\"u}hrung einer Redundanzschicht erh{\"o}ht die Verf{\"u}gbarkeit der Daten erheblich auf Kosten einer verringerten Leistungsf{\"a}higkeit. Der Fokus dieser Arbeit liegt im Erhalt der Redundanz, was die Regeneration verlorener Kopien sowie eine Aktualisierung veralteter Kopien umfasst. Die Regeneration verlorener Kopien ist notwendig um die Verf{\"u}gbarkeit langfristig zu sichern. Die Aktualisierung ist optional und verbessert die Leselatenz in geografisch weit verteilten Systemen. Die vorgestellte L{\"o}sung besteht aus drei Komponenten. Der Set Reconciliation Dienst erm{\"o}glicht den effizienten Vergleich zweier Knoten zur Identifikation verlorener und veralteter Kopien. Der Aktualisierungsdienst synchronisiert die verglichenen Knoten durch die {\"U}bertragung der Differenzen. Die dritte Komponente ist ein Anti-Entropie Protokoll, dass die Auswahl eines jeden Knotens als Synchronisationspartner sicherstellt. Das Ziel dieser Arbeit liegt in dem Vergleich dreier Set Reconciliation Algorithmen, deren Eignung und Leistungsf{\"a}higkeit f{\"u}r die Erkennung verlorener und veralteter Kopien evaluiert werden soll. Ausgew{\"a}hlt wurden der Bloom Filter, der Merkle-Tree sowie deren Kombination der Approximate Reconciliation Tree. Die Evaluation zeigte, dass der Merkle-Tree die h{\"o}chste Genauigkeit besitzt und sp{\"a}testens nach einer initiierten Synchronisation eines jeden Knotens zur vollst{\"a}ndigen Synchronit{\"a}t in der DHT f{\"u}hrt. Der Bloom Filter besitzt bei der Erkennung verlorener Repliken nur die halbe Genauigkeit gegen{\"u}ber veralteten Repliken, wodurch die Konvergenzgeschwindigkeit dementsprechend geringer ist gegen{\"u}ber dem Merkle-Tree. Daf{\"u}r sind die {\"U}bertragungskosten des Bloom Filter um bis zu 80\% geringer als beim Merkle-Tree und weisen kaum nennenswerte Spitzen auf. Die {\"U}bertragungskosten des Merkle-Tree sind abh{\"a}ngig von der Anzahl der Differenzen, sodass bei einer Differenz von Null nur eine Signatur mit weniger als einem kByte {\"u}bertragen werden muss. Ist die Differenz gr{\"o}ßer, steigen die Kosten je nach Bucket-Gr{\"o}ße an. Der Approximate Reconciliation Tree ist ein als Bloom Filter codierter Merkle-Tree, der je nach Parameterkonstellation die Eigenschaften einer der beiden Strukturen aufweist. Die Bloom Filter {\"a}hnlichen Konfigurationen bieten keinen Vorteil, wohingegen die Merkle-Tree {\"a}hnlichen nur zwei Mitteilungsrunden ben{\"o}tigen bei einer leichten Genauigkeitsverringerung gegen{\"u}ber dem Merkle-Tree.}, language = {de} } @misc{Keidel2013, type = {Master Thesis}, author = {Keidel, Stefan}, title = {Snapshots in Scalaris}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42282}, school = {Zuse Institute Berlin (ZIB)}, pages = {87}, year = {2013}, abstract = {Eines der gr{\"o}ßten Hindernisse beim praktischen Einsatz von Scalaris, einer skalierbaren Implementierung einer verteilten Hashtabelle mit Unterst{\"u}tzung f{\"u}r Transaktionen, ist das Fehlen eines Verfahrens zur Aufnahme eines konsistenten Zustandes des gesamten Systems. Wir stellen in dieser Arbeit ein einfaches Protokoll vor, dass diese Aufgabe erf{\"u}llt und sich, auf Grund der von uns gew{\"a}hlten Herangehensweise, leicht implementieren l{\"a}sst. Als Ausgangspunkt daf{\"u}r w{\"a}hlen wir aus einer Reihe von „klassischen" Snapshot-Algorithmen ein 1993 von Mattern entworfenes Verfahren, welches auf dem Algorithmus von Lai und Yang basiert, aus. Diese Entscheidung basiert auf einer gr{\"u}ndlichen Analyse der Protokolle unter Ber{\"u}cksichtigung der Architektur der existierenden Software. Im n{\"a}chsten Arbeitsschritt benutzen wir unser vollst{\"a}ndiges Wissen {\"u}ber die Interna des Transaktionssystems von Scalaris und vereinfachen damit das Verfahren hinsichtlich Benutzbarkeit und Implementierungskomplexit{\"a}t, ohne die Anforderungen an den aufgenommenen Zustand aufzuweichen. Statt einer losen Anh{\"a}ufung lokaler Zust{\"a}nde der einzelnen Teilnehmerknoten k{\"o}nnen wir am Ende eine große Schl{\"u}ssel-Wert-Tabelle als Ergebnis erzeugen, die konsistent ist, sich leicht weiterverarbeiten l{\"a}sst und die einem Zustand entspricht, in dem sich das System einmal befunden haben k{\"o}nnte. Nachdem wir das Verfahren dann in Software umgesetzt haben, werten wir die Ergebnisse hinsichtlich des Einflusses auf die Performanz des Gesamtsystems aus und diskutieren m{\"o}gliche Weiterentwicklungen.}, language = {de} } @phdthesis{Hupfeld2009, author = {Hupfeld, Felix}, title = {Causal weak-consistency replication - a systems approach}, url = {http://nbn-resolving.de/nbn:de:kobv:11-100100235}, year = {2009}, language = {en} } @misc{Hoffmann2013, type = {Master Thesis}, author = {Hoffmann, Marie}, title = {Approximate Algorithms for Distributed Systems}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42370}, school = {Zuse Institute Berlin (ZIB)}, pages = {75}, year = {2013}, abstract = {Peer-to-peer (P2P) systems form a special class of distributed systems. Typically, nodes in a P2P system are flat and share the same responsabilities. In this thesis we focus on three problems that occur in P2P systems: the storage of data replicates, quantile computation on distributed data streams, and churn rate estimation. Data replication is one of the oldest techniques to maintain stored data in a P2P system and to reply to read requests. Applications, which use data replication are distributed databases. They are part of an abstract overlay network and do not see the underlying network topology. The question is how to place a set of data replicates in a distributed system such that response times and failure probabilities become minimal without a priori knowledge of the topology of the underlying hardware nodes? We show how to utilize an agglomerative clustering procedure to reach this goal. State-of-the-art algorithms for aggregation of distributed data or data streams require at some point synchronization, or merge data aggregates hierarchically, which does not accompany the basic principle of P2P systems. We test whether randomized communication and merging of data aggregates are able to produce the same results. These data aggregates serve for quantile queries. Constituting and maintaining a P2P overlay network requires frequent message passing. It is a goal to minimize the number of maintenance messages since they consume bandwidth which might be missing for other applications. The lower bound of the frequency for mainte- nance messages is highly dependent on the churn rate of peers. We show how to estimate the mean lifetime of peers and to reduce the frequency for maintenance messages without destabilizing the infrastructure of the constituting overlay.}, language = {en} } @misc{Berlin2011, type = {Master Thesis}, author = {Berlin, Michael}, title = {Popularit{\"a}tsbasierte Anpassung des Replikationsfaktors in verteilten Dateisystemen}, school = {Humboldt-Universit{\"a}t zu Berlin}, year = {2011}, abstract = {Verteilte Dateisysteme erlauben es zus{\"a}tzliche Replikate von Dateien anzulegen, um Client-Zugriffe auf mehrere Server zu verteilen. Bei einer einheitlichen Festlegung des Replikationsfaktors f{\"u}r alle Dateien wird der beschr{\"a}nkte verf{\"u}gbare Speicherplatz jedoch nicht effizient genutzt, da es nur einen geringen Anteil von Dateien gibt, die h{\"a}ufig angefragt werden, w{\"a}hrend die restlichen Dateien unn{\"o}tig Speicherplatz belegen. Der erste Teil dieser Arbeit beschreibt daher ein Verfahren den Replikationsfaktor einer Datei in Abh{\"a}ngigkeit ihrer Popularit{\"a}t festzulegen. Im Kontext des verteilten Dateisystems XtreemFS wurde dazu ein zentraler Dienst f{\"u}r die dynamische Replikation implementiert und mit einem Trace simuliert. Die Auswertung zeigt, dass die popularit{\"a}tsbasierte Anpassung ein geeignetes Verfahren ist den Replikationsfaktor dynamisch festzulegen, da bei einer w{\"o}chentlichen Ermittlung der Popularit{\"a}t weniger als durchschnittlich 3,1\% zus{\"a}tzliche Replikate angelegt wurden. Da der Dienst selbst nicht mit einer beliebigen Anzahl von Dateien skaliert, muss er in mehrere Partitionen unterteilt und dezentral ausgef{\"u}hrt werden. Darum entwickelt der zweite Teil der Arbeit eine dezentrale Variante des Dienstes und zeigt, dass der Replikationsfaktor identisch zum zentralen Fall festgelegt werden kann. Nur im Fall eines Netzwerkausfalls oder nicht synchronisierter lokaler Uhren tritt eine Abweichung der Replikationsfaktoren auf, deren Ausmaß in der Simulation untersucht wurde.}, language = {de} } @article{GrunzkeBreuersGesingetal.2013, author = {Grunzke, Richard and Breuers, Sebastian and Gesing, Sandra and Herres-Pawlis, Sonja and Kruse, Martin and Blunk, Dirk and de la Garza, Luis and Packschies, Lars and Sch{\"a}fer, Patrick and Sch{\"a}rfe, Charlotta and Schlemmer, Tobias and Steinke, Thomas and Schuller, Bernd and M{\"u}ller-Pfefferkorn, Ralph and J{\"a}kel, Ren{\´e} and Nagel, Wolfgang and Atkinson, Malcolm and Kr{\"u}ger, Jens}, title = {Standards-based metadata management for molecular simulations}, journal = {Concurrency and Computation: Practice and Experience}, doi = {10.1002/cpe.3116}, year = {2013}, language = {en} } @inproceedings{WeinholdLackorzynskiBierbaumetal.2016, author = {Weinhold, Carsten and Lackorzynski, Adam and Bierbaum, Jan and K{\"u}ttler, Martin and Planeta, Maksym and H{\"a}rtig, Hermann and Shiloh, Amnon and Levy, Ely and Ben-Nun, Tal and Barak, Amnon and Steinke, Thomas and Sch{\"u}tt, Thorsten and Fajerski, Jan and Reinefeld, Alexander and Lieber, Matthias and Nagel, Wolfgang}, title = {FFMK: A Fast and Fault-tolerant Microkernel-based System for Exascale Computing}, booktitle = {SPPEXA Symposium 2016}, doi = {10.1007/978-3-319-40528-5_18}, year = {2016}, language = {en} } @inproceedings{FajerskiNoackReinefeldetal.2016, 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}, booktitle = {SPPEXA Symposium 2016}, doi = {10.1007/978-3-319-40528-5_19}, year = {2016}, language = {en} } @misc{Baerhold2016, type = {Master Thesis}, author = {B{\"a}rhold, Robert}, title = {Konzipierung und Implementierung eines Quota-Protokolls in objektbasierten Dateisystemen}, pages = {83}, year = {2016}, abstract = {Verteilte Dateisysteme, wie sie unter anderem in Cloud-Umgebungen eingesetzt werden, werden h{\"a}ufig von verschiedenen Anwendern und Anwendungen zeitgleich verwendet. Da diese Ressourcen in Cloud-Umgebungen gemietet sind, muss sichergestellt werden, dass ein Kunde nur die Ressourcen verwenden kann, f{\"u}r die er bezahlt hat. Andernfalls k{\"o}nnten andere Kunden beeintr{\"a}chtigt werden. Solch eine Obergrenze wird auch als Quota bezeichnet. Speziell f{\"u}r objektbasierte Dateisysteme, bei denen die Metadaten einer Datei von den Dateiinhalten getrennt gespeichert und verwaltet werden, erfordert die Forcierung einer Quota ein verteiltes Protokoll. Im Rahmen der vorliegenden Arbeit wurde ein Quota-Protokoll f{\"u}r objektbasierte Dateisysteme entwickelt und implementiert. Bei einer aktiven Quota wird zun{\"a}chst ein Teil des Speicherplatzes f{\"u}r eine bestimmte Datei blockiert, der als Voucher bezeichnet wird. Anschließend wird dem Client die maximale Dateigr{\"o}ße in signierter Form zugewiesen. Sie ergibt sich aus der Summe der bisherigen Dateigr{\"o}ße und allen erstellten Vouchers. Durch diesen Ansatz k{\"o}nnen die Speicherserver bei jedem Zugriff lokal pr{\"u}fen, ob der Schreibzugriff die maximale Dateigr{\"o}ße {\"u}berschreiten w{\"u}rde. Reicht diese nicht aus, muss ein zus{\"a}tzlicher Voucher erstellt werden, sofern noch Speicherplatz verf{\"u}gbar ist. Nicht verbrauchter Speicherplatz wird am Ende wieder freigegeben. Zus{\"a}tzlich unterst{\"u}tzt das Protokoll die Verteilung der Inhalte einer Datei auf mehrere Server (Striping) sowie Sparse-Dateien, bei denen beliebige Bereiche der Datei leer bleiben. Die Implementierung erfolgte im objektbasierten Dateisystem XtreemFS. Dabei wurden spezielle Funktionen von XtreemFS, wie die Dateireplikation, mit einbezogen. In einer abschließenden Evaluation wurde der Einfluss des implementierten Quota- Protokolls bez{\"u}glich der Performanz von XtreemFS untersucht. Dabei zeigte sich zun{\"a}chst, dass bei einer aktiven Quota die Performanz beim Schreiben großer Daten- mengen abh{\"a}ngig von der eingestellten Voucher-Gr{\"o}ße ist. Ist diese zu niedrig gew{\"a}hlt, so muss der Client seine maximale Dateigr{\"o}ße durch zus{\"a}tzliche Anfragen beim Metada- tenserver erh{\"o}hen, was die Performanz negativ beeintr{\"a}chtigt. Bei einer Voucher-Gr{\"o}ße von 100 MiB wurde beim Schreiben einer 10 GiB-Datei ein Performanzverlust von unter 2\% gemessen, verglichen mit dem Entwicklungsstand ohne implementiertes Quota- Protokoll. Bei der Erstellung mehrerer 64 KiB-Dateien wurde aufgrund zus{\"a}tzlicher Nachrichten ein Verlust von rund 8\% gemessen.}, language = {de} } @misc{Clausecker2017, author = {Clausecker, Robert}, title = {Notes on the Construction of Pattern Databases}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-65586}, year = {2017}, abstract = {This report aims to explain and extend pattern databases as a tool in finding optimal solutions to combination puzzles. Using sliding tile puzzles as an example, an overview over techniques to construct and use pattern databases is given, analysed, and extended. As novel results, zero aware additive pattern databases and PDB catalogues are introduced. This report originally appeared as a bachelor thesis at Humboldt University of Berlin under the title Notes on the Construction of Tablebases.}, language = {en} } @misc{Skrzypczak2017, author = {Skrzypczak, Jan}, title = {Weakening Paxos Consensus Sequences for Commutative Commands}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-65741}, year = {2017}, abstract = {Consensus (agreement on a value) is regarded as a fundamental primitive in the design of fault tolerant distributed systems. A well-known solution to the consensus problem is Paxos. Extensions of the Paxos algorithm make it possible to reach agreement on a sequence of commands which can then be applied on a replicated state. However, concurrently proposed commands can create conflicts that must be resolved by ordering them. This thesis delivers an in-depth description of a Paxos-based algorithm to establish such command sequences, called Paxos Round Based Register (PRBR). In contrast to conventional approaches like Multi-Paxos, PRBR can manage multiple command sequences independently. Furthermore, each sequence is established in-place, which eliminates the need for managing multiple Paxos instances. PRBR is extended as part of this thesis to exploit the commutativity of concurrently proposed commands. As a result, conflict potential can be greatly reduced which increases the number of commands that can be handled by PRBR. This is shown for a number of workloads in an experimental evaluation.}, language = {en} } @misc{Skrzypczak2017, type = {Master Thesis}, author = {Skrzypczak, Jan}, title = {Weakening Paxos Consensus Sequences for Commutative Commands}, year = {2017}, abstract = {Consensus (agreement on a value) is regarded as a fundamental primitive in the design of fault tolerant distributed systems. A well-known solution to the consensus problem is Paxos. Extensions of the Paxos algorithm make it possible to reach agreement on a sequence of commands which can then be applied on a replicated state. However, concurrently proposed commands can create conflicts that must be resolved by ordering them. This thesis delivers an in-depth description of a Paxos-based algorithm to establish such command sequences, called Paxos Round Based Register (PRBR). In contrast to conventional approaches like Multi-Paxos, PRBR can manage multiple command sequences independently. Furthermore, each sequence is established in-place, which eliminates the need for managing multiple Paxos instances. PRBR is extended as part of this thesis to exploit the commutativity of concurrently proposed commands. As a result, conflict potential can be greatly reduced which increases the number of commands that can be handled by PRBR. This is shown for a number of workloads in an experimental evaluation.}, language = {en} } @inproceedings{Noack2017, author = {Noack, Matthias}, title = {OpenCL in Scientific High Performance Computing: The Good, the Bad, and the Ugly}, booktitle = {Proceedings of the 5th International Workshop on OpenCL}, doi = {10.1145/3078155.3078170}, pages = {12:1 -- 12:3}, year = {2017}, abstract = {For writing a new scientific application, portability across existing and future hardware should be the major design goal, as there is a multitude of different compute devices, and programme codes typically outlive systems by far. Unlike other programming models that address parallelism or heterogeneity, OpenCL does provide practical portability across a wide range of HPC-relevant architectures. Other than that, it has a range of further advantages like being a library-only implementation, and using runtime kernel-compilation. We present experiences with utilising OpenCL alongside C++, MPI, and CMake in two real-world scientific codes. Our targets are a Cray XC40 supercomputer with multi- and many-core (Xeon Phi) CPUs, as well as multiple smaller systems with Nvidia and AMD GPUs. We shed light on practical issues arising in such a scenario, like the interaction between OpenCL and MPI, discuss solutions, and point out current limitations of OpenCL in the domain of scientific HPC from an application developer's and user's point of view.}, language = {en} }