@misc{Kruber2009, type = {Master Thesis}, author = {Kruber, Nico}, title = {DHT Load Balancing with Estimated Global Information}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11514}, school = {Zuse Institute Berlin (ZIB)}, year = {2009}, abstract = {One of the biggest impacts on the performance of a Distributed Hash Table (DHT), once established, is its ability to balance load among its nodes. DHTs supporting range queries for example suffer from a potentially huge skew in the distribution of their items since techniques such as consistent hashing can not be applied. Thus explicit load balancing schemes need to be deployed. Several such schemes have been developed and are part of recent research, most of them using only information locally available in order to scale to arbitrary systems. Gossiping techniques however allow the retrieval of fairly good estimates of global information with low overhead. Such information can then be added to existing load balancing algorithms that can use the additional knowledge to improve their performance. Within this thesis several schemes are developed that use global information like the average load and the standard deviation of the load among the nodes to primarily reduce the number of items an algorithm moves to achieve a certain balance. Two novel load balancing algorithms have then been equipped with implementations of those schemes and have been simulated on several scenarios. Most of these variants show better balance results and move far less items than the algorithms they are based on. The best of the developed algorithms achieves a 15-30\% better balance and moves only about 50-70\% of the number of items its underlying algorithm moves. This variation is also very robust to erroneous estimates and scales linearly with the system size and system load. Further experiments with self-tuning algorithms that set an algorithm's parameter according to the system's state show that even more improvements can be gained if additionally applied. Such a variant based on the algorithm described by Karger and Ruhl shows the same balance improvements of 15-30\% as the variant above but reduces the number of item movements further to 40-65\%.}, language = {en} } @misc{MoserHaridiShafaatetal.2009, author = {Moser, Monika and Haridi, Seif and Shafaat, Tallat and Sch{\"u}tt, Thorsten and H{\"o}gqvist, Mikael and Reinefeld, Alexander}, title = {Transactional DHT Algorithms}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11532}, number = {09-34}, year = {2009}, abstract = {We present a framework for transactional data access on data stored in a DHT. It allows to atomically read and write items and to run distributed transactions consisting of a sequence of read and write operations on the items. Items are symmetrically replicated in order to achieve durability of data stored in the SON. To provide availability of items despite the unavailability of some replicas, operations on items are quorum-based. They make progress as long as a majority of replicas can be accessed. Our framework processes transactions optimistically with an atomic commit protocol that is based on Paxos atomic commit. We present algorithms for the whole framework with an event based notation. Additionally we discuss the problem of lookup inconsistencies and its implications on the one-copy serializability property of the transaction processing in our framework.}, language = {en} } @misc{Mauter2009, type = {Master Thesis}, author = {Mauter, Daniel}, title = {Ein eingebettetes Hauptspeicher-Datenbanksystem mit Snapshot-Reads}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11552}, school = {Zuse Institute Berlin (ZIB)}, year = {2009}, abstract = {Entwurf und Entwicklung eines eingebetteten Hauptspeicher-Datenbanksystems mit Snapshot-Reads.}, language = {de} } @misc{SchintkeReinefeldHaridietal.2009, 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}, year = {2009}, 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{Tuschl2009, type = {Master Thesis}, author = {Tuschl, Roland}, title = {Ein Userspace-Dateisystem zur Verwaltung von Grid-Daten}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11483}, school = {Zuse Institute Berlin (ZIB)}, year = {2009}, abstract = {Das Ziel dieser Arbeit ist die Schaffung einer Zugriffs-Komponente f{\"u}r das Grid-Datenmanagement-System ZIB-DMS, das dessen transparente Einbindung in den Verzeichnisbaum eines Linux-Systems erlaubt. Dazu wird unter Verwendung des FUSE-Rahmenwerkes ein Userspace-Dateisystem mit Anbindung an das ZIB-DMS konzipiert und implementiert. Im Fokus stehen dabei die Abbildung der erweiterten Verwaltungsmechanismen des Systems auf die limitierte Schnittstelle hierarchischer Dateisysteme und die dazu notwendigen {\"A}nderungen am ZIB-DMS.}, language = {de} } @misc{Prollius2009, type = {Master Thesis}, author = {Prollius, Christian von}, title = {Ein Peer-to-Peer System mit Bereichsabfragen in PlanetLab}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11492}, school = {Zuse Institute Berlin (ZIB)}, year = {2009}, abstract = {Aktuelle Entwicklungen zeigen, dass Peer-to-Peer (P2P) Anwendungen wie Skype oder Bittorrent im Internet immer mehr an Bedeutung gewinnen. In den letzten Jahren hat es einen explosionsartigen Anstieg an Nutzern und Daten in solchen Netzen gegeben. Dabei stellt der eigentliche Dateitransfer zwischen zwei Rechnern kein großes Problem mehr dar und auch der Speicherbedarf f{\"u}r die große Menge an Daten kann durch die Weiterentwicklung der Hardware gut gedeckt werden. Das eigentliche Problem liegt vielmehr darin, den Rechner zu finden, der die gew{\"u}nschten Daten hat. Client-Server Architekturen, wie zum Beispiel Napster, haben sich als ung{\"u}nstig herausgestellt. Wenige Server, die eine große Anzahl an Clients bedienen m{\"u}ssen, sind einerseits sehr anf{\"a}llig gegen{\"u}ber Angriffen und Ausf{\"a}llen (Single Point of Failure)und kommen auch nicht mit der st{\"a}ndig wachsenden Anzahl an Nutzern zurecht. Verteilte Hashtabellen (DHT) bieten hier einen guten L{\"o}sungsansatz, der mit einer großen Anzahl an Nutzern skaliert und ausfallsicher ist. Andere dezentrale L{\"o}sungen, wie zum Beispiel das P2P Netzwerk Gnutella haben zwar das Problem des Single Point of Failure gel{\"o}st, jedoch haben sie starke Nachteile bei der Suche nach Keys. Bei einer Suche wird ein Broadcast verwendet (jeder schickt die Anfrage an jeden weiter) und damit ein enormer Netzwerkverkehr erzeugt. In "Why Gnutella Can't Scale. No, Really" wird erkl{\"a}rt, dass eine Suchanfrage bei Standardeinstellungen in der Clientsoftware einen Netzwerkverkehr von 17MB erzeugt. Deswegen wird zus{\"a}tzlich eine L{\"o}sung ben{\"o}tigt, die Keys und Values geordnet verteilt, damit sie gezielt gesucht werden k{\"o}nnen. Aus diesem Grund besch{\"a}ftigt sich die folgende Arbeit mit einer v{\"o}llig dezentralen Architektur, die außerdem eine sinnvolle Platzierung der Keys vornimmt. Die dezentrale Architektur hat den Vorteil, dass die Endger{\"a}te den Hauptteil des Dienstes selbst erbringen und damit jeder zus{\"a}tzliche Teilnehmer seine eigenen Ressourcen beisteuert. Diese Arbeit pr{\"a}sentiert Chord\#, eine dezentrale, skalierbare und selbstorganisierende verteilte Hashtabelle. Chord\# wurde ausgew{\"a}hlt, da in dieser Arbeit auch Wert auf Bereichsabfragen gelegt wurde. Diese sind zum Beispiel bei dem Chord Algorithmus nicht m{\"o}glich, da dieser eine Hashfunktion f{\"u}r die Keys verwendet und somit die Daten zwar gleichm{\"a}ßig aber unsortiert auf die Teilnehmer verteilt. Es wird in dieser Arbeit gezeigt, dass mit Hilfe von Chord\# auch ohne die Hashfunktion gute Ergebnisse erzielt werden. Außerdem k{\"o}nnen durch den Verzicht auf die Hashfunktion Bereichsabfragen erm{\"o}glicht werden. Daf{\"u}r wird der Chord\# Algorithmus in Java implementiert (ca. 1500 Zeilen Code) und in dem Forschungsnetz PlanetLab ausf{\"u}hrlich auf Laufzeiten, Instandhaltungskosten und Skalierung getestet.}, language = {de} } @misc{AllalenBrehmStueben2008, author = {Allalen, Mohammed and Brehm, Matthias and St{\"u}ben, Hinnerk}, title = {Performance of Quantum Chromodynamics (QCD) Simulations on the SGI Altix}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11086}, number = {08-54}, year = {2008}, abstract = {We study performance and scaling of the Berlin Quantum Chromodynamics Program (BQCD) on the SGI Altix 4700 at Leibniz Supercomputing Centre (LRZ). We employ different communication methods (MPI, MPI with two OpenMP threads per process, as well as the shmem library) and run the MPI version on the two types of nodes of that machine. For comparison with other machines we made performance measurements on an IBM p690 cluster and a Cray XT4.}, language = {en} } @misc{StreuerStueben2008, author = {Streuer, Thomas and St{\"u}ben, Hinnerk}, title = {Simulations of QCD in the Era of Sustained Tflop/s Computing}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-10623}, number = {07-48}, year = {2008}, abstract = {The latest machine generation installed at supercomputer centres in Germany offers a peak performance in the tens of Tflop/s range. We study performance and scaling of our quantum chromodynamics simulation programme BQCD that we obtained on two of these machines, an IBM Blue Gene/L and an SGI Altix 4700. We compare the performance of Fortran/MPI code with assembler code. The latter allows to exploit concurrency at more levels, in particular in overlapping communication and computation as well as prefetching data from main memory.}, language = {en} } @phdthesis{Roeblitz2009, author = {R{\"o}blitz, Thomas}, title = {Co-Reservation of Resources in the Grid}, isbn = {978-3-86853-137-4}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11626}, year = {2009}, abstract = {Executing applications in the Grid often requires access to multiple geographically distributed resources. In a Grid environment, these resources belong to different administrative domains, each employing its own scheduling policy. That is, at which time an activity (e.g., compute job, data transfer) is started, is decided by the resource's local management system. In such an environment, the coordinated execution of distributed applications requires guarantees on the quality of service (QoS) of the needed resources. Reserving resources in advance is an accepted means to obtain QoS guarantees from a single provider. The challenge, however, is to coordinate advance reservations of multiple resources. This work presents a system architecture and mechanisms to coordinate multiple advance reservations -- called co-reservations -- for delivering QoS guarantees to complex applications. We formally define the co-reservation problem as an optimization problem. The presented model supports three dimensions of freedom: the start time, the duration and the service level of a reservation. Requests and resources are described in a simple language. After matching the static properties and requirements of either side in a mapping, the reservation mechanism probes information about the future status of the resources. The versatile design of the probing step allows the efficient processing of requests, but also lets the resources express their preferences among the myriads of reservation candidates. Next, the best mapping is found through an implementation of the formal co-reservation model. Then, the mapping has to be secured, i.e., resources need to be allocated to a co-reservation candidate with all-or-nothing semantics. We study several goal-driven sequential and concurrent allocation mechanisms and define schemes for handling allocation failures. Finally, we introduce the concept of virtual resources for seamlessly embedding co-reservations into Grid resource management.}, language = {en} } @misc{KolbeckHoegqvistStenderetal.2010, author = {Kolbeck, Bj{\"o}rn and H{\"o}gqvist, Mikael and Stender, Jan and Hupfeld, Felix}, title = {Fault-Tolerant and Decentralized Lease Coordination in Distributed Systems}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11658}, number = {10-02}, year = {2010}, abstract = {Applications which need exclusive access to a shared resource in distributed systems require a fault-tolerant and scalable mechanism to coordinate this exclusive access. Examples of such applications include distributed file systems and master/slave data replication. We present Flease, an algorithm for decentralized and fault-tolerant lease coordination in distributed systems. Our algorithm allows the processes competing for a resource to coordinate exclusive access through leases among themselves without a central component. The resulting system easily scales with an increasing number of nodes and resources. We prove that Flease ensures exclusive access, i.e. guarantees that there is at most one valid lease at any time.}, language = {en} } @misc{Plantikow2007, type = {Master Thesis}, author = {Plantikow, Stefan}, title = {Transaktionen f{\"u}r verteilte Wikis auf strukturierten Overlay Netzwerken}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-10176}, school = {Zuse Institute Berlin (ZIB)}, year = {2007}, abstract = {Die Diplomarbeit pr{\"a}sentiert ein Transaktionsverfahren f{\"u}r strukturierte Overlay-Netzwerke, das an die Erfordernisse verteilter Informationssysteme mit relationalem Datenmodell angepasst ist. Insbesondere wird der Einsatz von Transaktionen f{\"u}r verteilte Wikis betrachtet, die moderne Funktionalit{\"a}ten, wie Metadaten und zus{\"a}tzliche Indexe f{\"u}r die Navigation, unterst{\"u}tzen. Konsistenz und Dauerhaftigkeit der gespeicherten Daten erfordert die Behandlung von Knotenausf{\"a}llen. Die Arbeit schl{\"a}gt daf{\"u}r das Zellenmodell vor: Das Overlay wird aus replizierten Zustandsmaschinen gebildet, um Verf{\"u}gbarkeit zu gew{\"a}hrleisten. Das Transaktionsverfahren baut darauf auf und verwendet Two-Phase-Commit mit Fehlererkennung und Widerherstellung von ausgefallenen Transaktionsmanagern. Anwendungen wird eine Auswahl an pessimistischen und hybrid-optimistischen Nebenl{\"a}ufigkeitskontrollverfahren geboten, die die Minimierung von Latenzeffekten und die schnelle Ausf{\"u}hrung von Nur-Lese-Transaktionen erm{\"o}glichen. F{\"u}r die Beispielanwendung Wiki wird der erforderliche Pseudocode angegeben und die verschiedenen Nebenl{\"a}ufigkeitskontrollverfahren hinsichtlich ihrer Nachrichtenkomplexit{\"a}t verglichen.}, language = {de} } @misc{MayBauerKoeberleetal.2006, author = {May, Patrick and Bauer, Markus and K{\"o}berle, Christian and Klau, Gunnar}, title = {A computational approach to microRNA detection}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-9383}, number = {06-44}, year = {2006}, abstract = {During the last few years more and more functionalities of RNA have been discovered that were previously thought of being carried out by proteins alone. One of the most striking discoveries was the de tection of microRNAs, a class of noncoding RNAs that play an important role in post-transcriptional gene regulation. Large-scale analyses are needed for the still increasingly growing amount of sequen ce data derived from new experimental technologies. In this paper we present a framework for the detection of the distinctive precursor structure of microRNAS that is based on the well-known Smith-Wat erman algorithm and various filtering steps. We conducted experiments on real genomic data and we found several new putative hits for microRNA precursor structures.}, language = {en} } @misc{MaySteinke2006, author = {May, Patrick and Steinke, Thomas}, title = {THESEUS - Protein Structure Prediction at ZIB}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-9184}, number = {06-24}, year = {2006}, abstract = {THESEUS, the ZIB threading environment, is a parallel implementation of a protein threading based on a multi-queued branch-and-bound optimal search algorithm to find the best sequence-to-structure alignment through a library of template structures. THESEUS uses a template core model based on secondary structure definition and a scoring function based on knowledge-based potentials reflecting pairwise interactions and the chemical environment, as well as pseudo energies for homology detection, loop alignment, and secondary structure matching. The threading core is implemented in C++ as a SPMD parallization architecture using MPI for communication. The environment is designed for generic testing of different scoring functions, e.g. different secondary structure prediction terms, different scoring matrices and information derived from multiple sequence alignments. A validaton of the structure prediction results has been done on the basis of standard threading benchmark sets. THESEUS successfully participated in the 6th Critical Assessment of Techniques for Protein Structure Prediction (CASP) 2004.}, language = {en} } @misc{Golas2012, author = {Golas, Ulrike}, title = {A General Attribution Concept for Models in M- adhesive Transformation Systems: Long Version}, issn = {1438-0064}, doi = {10.1007/978-3-642-33654-6_13}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-15547}, year = {2012}, abstract = {Attributes are an important concept for modeling data in practical applications. Up to now there is no adequate way to define attributes for different kinds of models used in M-adhesive transformation systems, which are a special kind of graph transformation systems based on M-adhesive categories. Especially a proper representation and definition of attributes and their values as well as a suitable handling of the data does not fit well with other graph transformation formalisms. In this paper, we propose a new method to define attributes in a natural, but still formally precise and widely applicable way. We define a new kind of adhesive category, called W-adhesive, that can be used for transformations of attributes, while the underlying models are still M-adhesive ones. As a result, attributed models can be used as they are intended to be, but with a formal background and proven well-behavior.}, language = {en} } @misc{DresslerSteinke2012, author = {Dreßler, Sebastian and Steinke, Thomas}, title = {A Novel Hybrid Approach to Automatically Determine Kernel Interface Data Volumes}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-15569}, year = {2012}, abstract = {Scheduling algorithms for heterogeneous platforms make scheduling decisions based on several metrics. One of these metrics is the amount of data to be transferred from and to the accelerator. However, the automated determination of this metric is not a simple task. A few schedulers and runtime systems solve this problem by using regression models, which are imprecise though. Our novel approach for the determination of data volumes removes this limitation and thus provides a solution to obtain exact information.}, language = {en} } @misc{Wende2010, type = {Master Thesis}, author = {Wende, Florian}, title = {Simulation of Spin Models on Nvidia Graphics Cards using CUDA}, school = {Humboldt-Universit{\"a}t zu Berlin}, pages = {149}, year = {2010}, abstract = {This thesis reports on simulating spin models on Nvidia graphics cards using the CUDA programming model; a particular approach for making GPGPU (General Purpose Computation on Graphics Processing Units) available for a wide range of software developers not necessarily acquainted with (massively) parallel programming. By comparing program execution times for simulations of the Ising model and the Ising spin glass by means of the Metropolis algorithm on Nvidia Tesla C1060 graphics cards and an Intel Core i7-920 quad-core x86 CPU (we used OpenMP to make our simulations run on all 4 execution units of the CPU), we noticed that the Tesla C1060 performed about a factor 5-10 faster than the Core i7-920, depending on the particular model and the accuracy of the calculations (32-bit or 64-bit). We also investigated the reliability of GPGPU computations, especially with respect to the occurrence of soft-errors as suggested in [23]. We noticed faulty program outputs during long-time simulations of the Ising model on ''large'' lattices. We were able to link these problems to overheating of the corresponding graphics cards. Doing Monte Carlo simulations on parallel computer architectures, as was the case in this thesis, suggests to also generate random numbers in a parallel manner. We present implementations of the random number generators Ranlux and Mersenne Twister. In addition, we give an alternative and very efficient approach for producing parallel random numbers on Nvidia graphics cards. We successfully tested all random number generators used in this thesis for their quality by comparing Monte Carlo estimates against exact calculations.}, language = {en} } @masterthesis{Wende2013, type = {Bachelor Thesis}, author = {Wende, Florian}, title = {Dynamic Load Balancing on Massively Parallel Computer Architectures}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42166}, school = {Zuse Institute Berlin (ZIB)}, pages = {100}, year = {2013}, abstract = {This thesis reports on using dynamic load balancing methods on massively parallel computers in the context of multithreaded computations. In particular we investigate the applicability of a randomized work stealing algorithm to ray tracing and breadth-first search as representatives of real-world applications with dynamic work creation. For our considerations we made use of current massively parallel hardware accelerators: Nvidia Tesla M2090, and Intel Xeon Phi. For both of the two we demonstrate the suitability of the work stealing scheme for the said real-world applications. Also the necessity of dynamic load balancing for irregular computations on such hardware is illustrated.}, language = {en} } @misc{WendeSteinke2013, author = {Wende, Florian and Steinke, Thomas}, title = {Swendsen-Wang Multi-Cluster Algorithm for the 2D/3D Ising Model on Xeon Phi and GPU}, issn = {1438-0064}, doi = {10.1145/2503210.2503254}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42187}, year = {2013}, abstract = {Simulations of the critical Ising model by means of local update algorithms suffer from critical slowing down. One way to partially compensate for the influence of this phenomenon on the runtime of simulations is using increasingly faster and parallel computer hardware. Another approach is using algorithms that do not suffer from critical slowing down, such as cluster algorithms. This paper reports on the Swendsen-Wang multi-cluster algorithm on Intel Xeon Phi coprocessor 5110P, Nvidia Tesla M2090 GPU, and x86 multi-core CPU. We present shared memory versions of the said algorithm for the simulation of the two- and three-dimensional Ising model. We use a combination of local cluster search and global label reduction by means of atomic hardware primitives. Further, we describe an MPI version of the algorithm on Xeon Phi and CPU, respectively. Significant performance improvements over known im plementations of the Swendsen-Wang algorithm are demonstrated.}, language = {en} } @misc{DresslerSteinke2013, author = {Dreßler, Sebastian and Steinke, Thomas}, title = {An Automated Approach for Estimating the Memory Footprint of Non-Linear Data Objects}, issn = {1438-0064}, doi = {10.1007/978-3-642-54420-0_25}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42224}, year = {2013}, abstract = {Current programming models for heterogeneous devices with disjoint physical memory spaces require explicit allocation of device memory and explicit data transfers. While it is quite easy to manually implement these operations for linear data objects like arrays, this task becomes more difficult for non-linear objects, e.g. linked lists or multiple inherited classes. The difficulties arise due to dynamic memory requirements at run-time and the dependencies between data structures. In this paper we present a novel method to build a graph-based static data type description which is used to create code for injectable functions that automatically determine the memory footprint of data objects at run-time. Our approach is extensible to implement automatically generated optimized data transfers across physical memory spaces.}, language = {en} } @misc{Maier2011, type = {Master Thesis}, author = {Maier, Robert}, title = {Massiv-parallele Suche und effiziente Heuristiken}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42448}, school = {Humboldt-Universit{\"a}t zu Berlin}, pages = {81}, year = {2011}, abstract = {Pattern Datenbanken (PDBs) werden in der heuristischen Suche eingesetzt, um irrelevante Pfade in der Suche auszuschließen. Da die Leistung einer PDB mit ihrer Gr{\"o}ße steigt und f{\"u}r die effektive heuristische Suche in großen Zustandsr{\"a}umen große PDBs n{\"o}tig sind, ist ein paralleler Ansatz notwendig, um sehr große PDBs zu erzeugen. Diese Arbeit erweitert einen, auf MapReduce basierenden, Algorithmus von Reinefeld und Sch{\"u}tt (2009) zur massiv-parallelen Breitensuche so, dass damit sehr große PDBs erzeugt werden k{\"o}nnen. So entsteht die erste vollst{\"a}ndige 8+8+8 PDB f{\"u}r das 24er-Puzzle. Reinefeld und Sch{\"u}tt implementieren ebenfalls das heuristische Suchverfahren BFIDA* f{\"u}r MapReduce. In dieser Arbeit wird dieser Implementation ein Speedup von 857 bei 2039 Kernen nachgewiesen. Weiterhin f{\"u}hrt diese Arbeit ein Schema ein, mit dem PDBs bei der Suche direkt von der Festplatte gelesen werden k{\"o}nnen. Des Weiteren wird der Nutzen von großen PDBs in einer Gruppe von PDBs untersucht, deren Heuristikwerte maximiert werden. Dazu wird analysiert, wie sich Gruppen von PDBs mit unterschiedlicher Gr{\"o}ße verhalten und welche Faktoren bei solchen Konstellationen zum Erfolg der Gruppe beitragen. Es wird gezeigt, dass der Einsatz von großen PDBs effizient ist, wenn der zur Verf{\"u}gung stehende Hauptspeicher ausreicht, eine Gruppe zusammen mit einigen kleineren PDBs zu bilden.}, language = {de} }