Combining simulations of different scale in one application is non-trivial issue. this paper proposes solution that supports complex time interactions that can appear between elements of such applications. We show tha...
详细信息
ISBN:
(纸本)9783540681052
Combining simulations of different scale in one application is non-trivial issue. this paper proposes solution that supports complex time interactions that can appear between elements of such applications. We show that High Level Architecture, especially its time management service can be efficiently used to distribute and communicate multiscale components. Grid HLA Management System (which was presented in our previous work [10]) is used to run HLA-based distributed simulation system on the Grid. the example application is build from simulation modules taken from Multiscale Multiphysics Scientific Environment (MUSE)[8], which is sequential simulation system designed for calculating behaviour of dense stellar systems like globular clusters and galactic nuclei.
this paper develops a plug-and-play reusable LogGP model that can be used to predict the runtime and scaling behavior of different MPI-based pipelined wavefront applications running on modern parallel platforms with m...
详细信息
ISBN:
(纸本)9781424416936
this paper develops a plug-and-play reusable LogGP model that can be used to predict the runtime and scaling behavior of different MPI-based pipelined wavefront applications running on modern parallel platforms with multicore nodes. A key new feature of the model is that it requires only a few simple input parameters to project performance for wavefront codes with different structure to the sweeps in each iteration as well as different behavior during each wavefront computation and/or between iterations. We apply the model to three key benchmark applications that are used in high performance computing procurement, illustrating that the model parameters yield insight into the key differences among the codes. We also develop new, simple and highly accurate models of MPI send, receive, and group communication primitives on the dual-core Cray XT system. We validate the reusable model applied to each benchmark on up to 8192 processors on the XT3/XT4. Results show excellent accuracy for all high performance application and platform configurations that we were able to measure. Finally we use the model to assess application and hardware configurations, develop new metrics for procurement and configuration, identify bottlenecks, and assess new application design modifications that, to our knowledge, have not previously been explored.
this anomalies detection approach seeks the directions that maximize the projection index, so as to gain the anomalies structure information. Using genetic algorithm in this approach can search accurate optimal projec...
详细信息
ISBN:
(纸本)9780819473639
this anomalies detection approach seeks the directions that maximize the projection index, so as to gain the anomalies structure information. Using genetic algorithm in this approach can search accurate optimal projection directions, but it's a computation-intensive task. So, a parallel algorithm under distributed memory system was presented. the projection directions were searched efficiently by parallel genetic algorithm model, and the projection directions' precision was guaranteed by using a strengthened terminal qualification. then, the detected anomaly components were wiped off by projecting the data onto the subspace orthogonal to the previous projection directions, and the other anomalies were searched in the residual space. the final task of projection and objects segmentation was also completed in parallel. Using an OMIS hyperspectral data to test the parallel algorithm's performance under an eight-node cluster, the process time reduced from 15 minutes to 2.8 minutes. the results show the validity and comparative good parallel efficiency.
Even though Object Orientation has been proven to be an effective programming paradigm for software development, it has not been shown to be an ideal solution for the development of large scale parallel and distribute...
详细信息
ISBN:
(纸本)9783540681052
Even though Object Orientation has been proven to be an effective programming paradigm for software development, it has not been shown to be an ideal solution for the development of large scale parallel and distributed systems. there are a number of reasons for this: the parallelism and synchronisation in these systems has to be explicitly managed by the programmer;few Object Oriented languages have implicit support for Garbage Collection in parallel applications;and the state of a systems of concurrent objects is difficult to determine. In contrast, the Condensed Graph model provides a way of explicitly expressing parallelism but with implicit synchronisation;its implementation in the Web-Com system provides for automatic garbage collection and the dynamic state of the application is embodied in the topology of the Condensed Graph. these characteristics free programmers from the difficult and error prone process of explicitly managing parallelism and thus allows them to concentrate on expressing a solution to the problem rather than on its low level implementation. Object Oriented Condensed Graphs are a computational paradigm which combines Condensed Graphs with object orientation and this unified model leverages the advantages of both paradigms. this paper illustrates the Garbage Collection mechanism of Object Oriented Condensed Graphs as well as its basic concepts.
Conference proceedings front matter may contain various advertisements, welcome messages, committee or program information, and other miscellaneous conference information. this may in some cases also include the cover...
Conference proceedings front matter may contain various advertisements, welcome messages, committee or program information, and other miscellaneous conference information. this may in some cases also include the cover art, table of contents, copyright statements, title-page or half title-pages, blank pages, venue maps or other general information relating to the conference that was part of the original conference proceedings.
the proceedings contain 26 papers. the topics discussed include: reducing splaying by taking advantage of working sets;engineering burstsort: towards fast in-place string sorting;comparing integer data structures for ...
详细信息
ISBN:
(纸本)3540685480
the proceedings contain 26 papers. the topics discussed include: reducing splaying by taking advantage of working sets;engineering burstsort: towards fast in-place string sorting;comparing integer data structures for 32 and 64 bit keys;a new graph-theoretical model for k-dimensional guillotine-cutting problems;on the efficiency of a local iterative algorithm to compute Delaunay realizations;computing branch decomposition of large planar graphs;experimental evaluation of an exact algorithm for the orthogonal art gallery problem;engineering parallel in-place random generation of integer permutations;broadword implementation of rank/select queries;efficient implementations of heuristics for routing and wavelength assignment;myopic distributed protocols for singleton and independent-resource congestion games;when to reap and when to sow - lowering peak usage with realistic batteries;and fast local search for the maximum independent set problem.
the rising complexity of data processing algorithms in sensor networks combined withtheir severely limited computing power necessitates a in-depth understanding of their temporal behavior However today only cycle acc...
详细信息
ISBN:
(纸本)9780769531571
the rising complexity of data processing algorithms in sensor networks combined withtheir severely limited computing power necessitates a in-depth understanding of their temporal behavior However today only cycle accurate emulation and test-beds provide a detailed and accurate insight into the temporal behavior of sensor networks. In this paper we introduce fine grained, automated instrumentation of simulation models with cycle counts derived from sensor nodes and application binaries to provide detailed timing information. the presented approach bridges the gap between scalable but abstracting simulation and cycle accurate emulation for sensor network evaluation. By mapping device-specific code with simulation models, we can derive the time and duration a certain code line takes to get executed on a sensor node. Hence, eliminating the need to use expensive instruction-level emulators with limited speed and restricted scalability. Further-more, the proposed design is not bound to a specific hardware platform, a major advantage compared to existing emulators. Our evaluation shows that the proposed technique achieves a timing accuracy of 99% compared to emulation while adding only a small overhead. Concluding, it combines essential properties like accuracy, speed and scalability on a single simulation platform.
DAPSYS (international Conference on distributed and parallel Systems) is an international biannual conference series dedicated to all aspects of distributed and parallelcomputing. DAPSYS 2008, the 7thinternational C...
ISBN:
(数字)9780387794488
ISBN:
(纸本)9780387794471
DAPSYS (international Conference on distributed and parallel Systems) is an international biannual conference series dedicated to all aspects of distributed and parallelcomputing. DAPSYS 2008, the 7thinternational Conference on distributed and parallel Systems was held in September 2008in Hungary. distributed and parallel Systems: Desktop Grid computing, based on DAPSYS 2008, presents original research, novel concepts and methods, and outstanding results. Contributors investigate parallel and distributed techniques, algorithms, models and applications; present innovative software tools, environments and middleware; focus on various aspects of grid computing; and introduce novel methods for development, deployment, testing and evaluation. this volume features a special focus on desktop grid computing as well. Designed for a professional audience composed of practitioners and researchers in industry,this book is also suitable for advanced-level students in computer science.
Conference proceedings front matter may contain various advertisements, welcome messages, committee or program information, and other miscellaneous conference information. this may in some cases also include the cover...
Conference proceedings front matter may contain various advertisements, welcome messages, committee or program information, and other miscellaneous conference information. this may in some cases also include the cover art, table of contents, copyright statements, title-page or half title-pages, blank pages, venue maps or other general information relating to the conference that was part of the original conference proceedings.
this paper presents the Locusts Cyber foraging framework. Cyber foraging is the opportunistic use of computing resources available in the nearby environment, and using such resources thus fall into the category of dis...
详细信息
this paper presents the Locusts Cyber foraging framework. Cyber foraging is the opportunistic use of computing resources available in the nearby environment, and using such resources thus fall into the category of distributedcomputing. Furthermore, for the resources to be used efficiently, parallelcomputing techniques must also be employed. distributed and parallelcomputing are two concepts that are both notoriously known for being very hard for developers to grasp. Because of this one might think that techniques such as Cyber foraging would have a hard time surviving outside of research environments. In this paper a framework is presented that has special focus on making Cyber foraging accessible for all developers.
暂无评论