A. Polze
Hasso Plattner Institute, Operating Systems and Middleware, Faculty Member
Research Interests:
GPU compute devices have become very popular for general purpose computations. However, the SIMD-like hardware of graphics processors is currently not well suited for irregular workloads, like searching unbalanced trees. In order to... more
GPU compute devices have become very popular for general purpose computations. However, the SIMD-like hardware of graphics processors is currently not well suited for irregular workloads, like searching unbalanced trees. In order to mitigate this drawback, NVIDIA introduced an extension to GPU programming models called dynamic parallelism. This extension enables GPU programs to spawn new units of work directly on the GPU, allowing the refinement of subsequent work items based on intermediate results without any involvement of the main CPU. This work investigates methods for employing dynamic parallelism with the goal of improved workload distribution for tree search algorithms on modern GPU hardware. For the evaluation of the proposed approaches, a case study is conducted on the n-queens problem. Extensive benchmarks indicate that the benefits of improved resource utilization fail to outweigh high management overhead and runtime limitations due to the very fine level of granularity of the investigated problem. However, novel memory management concepts for passing parameters to child grids are presented. These general concepts are applicable to other, more coarse-grained problems that benefit from the use of dynamic parallelism.
Research Interests:
Research Interests:
With memory-centric architectures appearing on the horizon as potential candidates for future computer architectures, we propose that the tuple space paradigm is well suited for the task of managing the large shared memory pools that are... more
With memory-centric architectures appearing on the horizon as potential candidates for future computer architectures, we propose that the tuple space paradigm is well suited for the task of managing the large shared memory pools that are a central concept of these new architectures. We support this hypothesis by presenting MemSpaces, an implementation of the tuple space paradigm based on POSIX shared memory objects. To demonstrate both efficacy and efficiency of the approach, we provide a performance evaluation that compares MemSpaces to message-based implementations of the tuple space paradigm. Due to the lack of commercial availability of adequate hardware, we perform the evaluation inside an emulated environment that mimics the general characteristics of memory-centric architectures. For many operations, MemSpaces performs an order of magnitude faster compared to state of the art implementations.
Research Interests:
Research Interests:
Ich erkläre mich damit einverstanden, daß die vorliegende Diplomarbeit in der
Contemporary distributed computing systems may provide high computing power combined with upcoming new networking technologies. However, until now network-based parallel systems which employ interconnected computers (PC's,... more
Contemporary distributed computing systems may provide high computing power combined with upcoming new networking technologies. However, until now network-based parallel systems which employ interconnected computers (PC's, workstations, mainframes) as processing ...
The Object Management Group's(OMG) Common Object Request Broker Architecture (CORBA) is an important and popular technology that supports the development of object-based, distributed applications. The benefits of abstraction promised... more
The Object Management Group's(OMG) Common Object Request Broker Architecture (CORBA) is an important and popular technology that supports the development of object-based, distributed applications. The benefits of abstraction promised by CORBA(location transparency, heterogeneity,dynamic configuration, etc.) are appealing in manyapplication domains, including those that satisfy real-time requirements --- such as manufacturing, process control, and transport systems. Furthermore, those attributes makeCORBAaninteresting candidate for responsive (fault-tolerant, real-time) cluster computing. However, the specification of timing behavior and quality-of-service parameters likecommunication latency and acceptable processor utilization is beyond the scope of today'sCORBA. Here, we present the "Composite Objects"approach for predictable integration of CORBA with real-time requirements. We discuss data replication and weak memory consistencyasthe key concepts for implementat...
Research Interests:
Research Interests:
Research Interests:
This paper introduces an artificial neural networks (ANN) based framework for joint demosaicing of color field array (CFA) raw image sequences. We propose an algorithm that offers superior resolution, signal to noise ratio and dynamic... more
This paper introduces an artificial neural networks (ANN) based framework for joint demosaicing of color field array (CFA) raw image sequences. We propose an algorithm that offers superior resolution, signal to noise ratio and dynamic range when compared to single-frame demosaicing. A rich set of both synthetic and real world experimental results illustrates its capabilities.
Research Interests:
Research Interests:
Research Interests: Computer Science, Object Oriented Programming, Software Architecture, User Interface, Mobile Computing, and 15 moreJava, Mobile Application, Protocols, Net, Mobile Device, Mobile Devices, Open Systems, Corba, Environmental Conditions, Communication protocols, Programming Paradigm, Transport Protocols, Dynamic Reconfiguration, Service Orientation, and Application Software
This paper reflects different understanding and positions on future trends of GRID-oriented technologies, applications, and networks, as perceived by representatives from industry and academia. There is no definitive answer on the topic... more
This paper reflects different understanding and positions on future trends of GRID-oriented technologies, applications, and networks, as perceived by representatives from industry and academia. There is no definitive answer on the topic that is raised in the title. Instead, the ...
Research Interests:
Research Interests:
Abstract: Die Anforderungen an Anwendungen für IT-gestütztes Management eines MANV sind vielfältig. Neben Aspekten der Ergonomie (Hardware, Benutzeroberflächen) müssen organisatorische Fragen berücksichtigt werden. Die Nutzer sind im MANV... more
Abstract: Die Anforderungen an Anwendungen für IT-gestütztes Management eines MANV sind vielfältig. Neben Aspekten der Ergonomie (Hardware, Benutzeroberflächen) müssen organisatorische Fragen berücksichtigt werden. Die Nutzer sind im MANV besonders stressreichen Situationen ausgesetzt, und die Einstellung zur Technik und der Umgang mit neuen Technologien können eine entscheidende Rolle spielen. Bei einem MANV muss zudem davon ausgegangen werden, dass Kommunikationsinfrastruktur gar nicht oder nur ...
Almost a year ago, Microsoft has introduced the .NET architecture as a new component-based programming environment, which allows for easy integration of classical distributed programming techniques with Web computing. .NETdefines a type... more
Almost a year ago, Microsoft has introduced the .NET architecture as a new component-based programming environment, which allows for easy integration of classical distributed programming techniques with Web computing. .NETdefines a type system and introduces notions such ...
Research Interests: Computer Architecture, Distributed Computing, Object Oriented Programming, Service Oriented Architecture, Reflection, and 12 moreFault Tolerance, Security Requirements, Computer Languages, Software Fault Tolerance, Aspect Oriented Programming, Distributed Applications, Type System, Object-oriented languages, Fault Tolerant, NET Framework, Programming language, and Distributed Programming
The tremendous advances in wireless networks, mobile computing, and sensor networks, along with the rapid growth of small, portable and powerful computing devices, offers more and more opportunities for pervasive computing and... more
The tremendous advances in wireless networks, mobile computing, and sensor networks, along with the rapid growth of small, portable and powerful computing devices, offers more and more opportunities for pervasive computing and communications. This topic deals with cutting-edge research in various aspects related to the theory and practice of mobile computing or wireless and mobile networking. These aspects include architectures, algorithms, networks, protocols, modeling and performance issues, data management, ...
Research Interests: Ubiquitous Computing, Data Management, Software Architecture, Semantic Web, Mobile IP, and 15 moreInformation Processing, Wireless Network, Radio Frequency Identification, Cellular Network, Mobile Device, Sensor Network, Smart Card, Secure Communication, Mobile Network, Optimal Control Problem, Fault Tolerant, Data Consistency, Wireless Ad Hoc Network, Mobile Computer, and Optimistic Replication
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Computer Architecture, Distributed Computing, Software Engineering, Software Components, Distributed System, and 13 moreFault Tolerance, Middleware, Real Time Systems, Real Time Control, Software Fault Tolerance, Real Time, Publish/subscribe, Fault Tolerant, RTAs, Software Engineering at Institute of management Sciences, Application Software, Human in the Loop, and Hard Real-Time
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Computer Science, Computer Architecture, Object Oriented Programming, Real Time Computing, Computer Aided Manufacturing, and 11 moreSystem Integration, Synchronization, Fault Tolerance, Distributed Processing, Quality of Service, Hardware, Real Time Systems, Real Time, Corba, Fault Tolerant, and Application Software
Research Interests: Genetics, Computer Architecture, Distributed Computing, Group communication, Fault Tolerance, and 11 moreProtocols, Graphic User Interface Design, Software Fault Tolerance, Aspect Oriented Programming, Encapsulation, Replication, Automatic code generation, Fault Tolerant, Graphical User Interface, Functional Properties, and Interface Definition Language
Research Interests:
Research Interests:
Research Interests:
ABSTRACT
Research Interests: Distributed Computing, Software Engineering, Computational Modeling, Computer Networks, Synchronization, and 14 moreDistributed Systems, Fault Tolerance, Programming, Faults, Real Time Systems, Local Area Networks, Software Fault Tolerance, Real Time, High performance, Reconfiguration, Fault Tolerant, Networked Systems, Application Software, and Synchronisation
Research Interests:
Research Interests:
Research Interests:
The Object Management Group's (OMG) Common Object Request Broker Architecture (CORBA) is an important and popular technology that supports the development of object based, distributed applications. The benefits promised by... more
The Object Management Group's (OMG) Common Object Request Broker Architecture (CORBA) is an important and popular technology that supports the development of object based, distributed applications. The benefits promised by CORBA (abstraction, heterogeneity, etc.) are appealing in many application domains, including those that satisfy real time requirements-such as manufacturing. Unfortunately, CORBA was not specified in light of real time requirements,
Research Interests: Computer Architecture, Object Oriented Programming, Technology Management, Control Systems, Distributed Processing, and 11 moreHardware, Real Time Systems, Real Time, Corba, NIST, Manufacturing System, Boolean Satisfiability, National Institute of Standards and Technology, Non Real time, Application Software, and Commercial Off-The-Shelf
ABSTRACT Desktop software developers' interest in graphics hardware is increasing as a result of modern graphics cards' capabilities to act as compute devices that augment the main processor. This capability means parallel... more
ABSTRACT Desktop software developers' interest in graphics hardware is increasing as a result of modern graphics cards' capabilities to act as compute devices that augment the main processor. This capability means parallel computing is no longer a dedicated task for the CPU. A trend toward heterogeneous computing combines the main processor and graphics processing unit (GPU). This overview of how to utilize GPU compute power in the best possible way includes explanations of the primary GPU hardware concepts and the corresponding programming principles. On this foundation, the authors discuss a collection of commonly agreed-upon critical performance optimization strategies that are the key factor for getting true scalability and performance improvements when moving parts of your application from a multithreaded to a GPU-enhanced version.