Bilinear interpolation algorithm is broadly applied in digital image processing but its calculation speed is very slow. In order to improve its performance in calculation, this paper proposes a graphic processing unit...
详细信息
ISBN:
(纸本)9781479966363
Bilinear interpolation algorithm is broadly applied in digital image processing but its calculation speed is very slow. In order to improve its performance in calculation, this paper proposes a graphic processing unit acceleration-based bilinear interpolation parallel It mainly utilizes Wallis transforming independence among various blocks in bilinear interpolation, which is adaptable to characteristics of GPU parallelprocessing structure. It maps traditional serial bilinear interpolation algorithm to CUDA parallel programming model and optimize thread allocation, memory usage, hardware resources division, etc, to make full use of huge calculation ability. the experiment results show bilinear interpolation parallel algorithm can greatly improve calculation speed with increasing image resolution.
Several parallel simulated annealing algorithms with different co-operation schemes are considered. the theoretical analysis of speedups of the algorithms is presented. the outcome of the theoretical analysis was veri...
详细信息
ISBN:
(纸本)9783540681052
Several parallel simulated annealing algorithms with different co-operation schemes are considered. the theoretical analysis of speedups of the algorithms is presented. the outcome of the theoretical analysis was verified by practical experiments whose aim was to investigate the influence of the co-operation of parallel simulated annealing processes on the quality of results. the experiments were performed assuming a constant cost of parallel computations, i.e., searching for solutions was conducted with a given number of processors for a specified period of time. For the experiments a suite of benchmarking tests for the vehicle routing problem with time windows was used.
Classification is one of the most widely used methods in data mining, with numerous applications in biomedicine. the scope and the resolution of data involved in many real life applications require very efficient impl...
详细信息
ISBN:
(纸本)9783540681052
Classification is one of the most widely used methods in data mining, with numerous applications in biomedicine. the scope and the resolution of data involved in many real life applications require very efficient implementations of classification methods, developed to run on parallel or distributed computational systems. In this study we describe SVD-ReGEC, a fully parallel implementation, for distributed memory multicomputers, of a classification algorithm with a feature reduction. the classification is based on Regularized Generalized Eigenvalue Classifier (ReGEC) and the preprocessing stage is a filter method algorithm based on Singular Value Decomposition (SVD), that reduces the dimension of the space in which classification is accomplished. the implementation is tested on random datasets and results are discussed using standard parameters.
the fixed-size processor array architecture, which is intended for realization of matrix LLT-decomposition based on Cholesky algorithm, is proposed. In order to implement this architecture in modern FPGA devices, the ...
详细信息
ISBN:
(纸本)9783540681052
the fixed-size processor array architecture, which is intended for realization of matrix LLT-decomposition based on Cholesky algorithm, is proposed. In order to implement this architecture in modern FPGA devices, the arithmetic unit (AU) operating in the rational fraction arithmetic is designed. the AU is intended for configuring in the Xilinx Virtex4 FPGAs, and its hardware complexity is much less than the complexity of similar AUs operating with floating-point numbers.
this paper presents and investigates for the first time a new trail for parallel solving of the Satisfiability problem based on a simple and efficient structural decomposition heuristic. A new Joining and model Checki...
详细信息
ISBN:
(纸本)9783540681052
this paper presents and investigates for the first time a new trail for parallel solving of the Satisfiability problem based on a simple and efficient structural decomposition heuristic. A new Joining and model Checking scheme (JaCk-SAT) is introduced. the main goal of this methodology is to recursively cut the variable-set in two subsets of about equal size. On the one hand, in contrast with recent propositions [12,16] for sequential resolution, we do not use sophisticated hypergraph decomposition techniques such as Tree Decomposition that are very likely infeasible. On the other hand, in contrast with all the actual propositions [27] for parallel resolution, we make use of a structural decomposition (of the problem) instead of a search space one. the very first preliminary results of this new approach are presented.
Data processing computer systems store and process large volumes of data. the volumes tend to grow very quickly, especially in data warehouse systems. A few years ago data warehouses were used only for supporting stri...
详细信息
ISBN:
(纸本)9783540681052
Data processing computer systems store and process large volumes of data. the volumes tend to grow very quickly, especially in data warehouse systems. A few years ago data warehouses were used only for supporting strictly business decisions but nowadays they find their application in many domains of everyday life. New and very demanding field is stream data warehousing. Car traffic monitoring, cell phones tracking or utilities meters integrated reading systems generate stream data. In a stream data warehouse the ETL process is a continuous one. Stream data processing poses many new challenges to memory management and data processing algorithms. the most important aspects concern efficiency and scalability of the designed solutions. In this paper we present an example of a stream data warehouse and then, basing on the presented example and our previous work results, we discuss a solution for stream data parallelprocessing. We also show, how to integrate the presented solution with a spatial aggregating index.
Multi-core processors represent an evolutionary change in conventional computing as well setting the new trend for high performance computing. the chip-level multiprocessing architectures with a large number of cores ...
详细信息
ISBN:
(纸本)9783540681052
Multi-core processors represent an evolutionary change in conventional computing as well setting the new trend for high performance computing. the chip-level multiprocessing architectures with a large number of cores continue to offer dramatically increased performance and power savings characteristics. Energy efficiency and scalability in performance have become more important to many enterprises and play important role in a cluster environment as well. this paper will describe how much we may expect from the cluster systems in terms of performance and power saving if we based the installation on the servers which are founded on the Intel Xeon Quad-Core and Intel Xeon Dual-Core processors family.
this special issue aims to present new developments and advances in techniques for assessment performance portability of high performance computing applications. It contains revised and extended versions of selected p...
详细信息
the Semantic Grid is a recent initiative to expose semantically rich information associated with Grid resources to build more intelligent Grid services [2]. Recently, several projects have embraced this vision and the...
详细信息
ISBN:
(纸本)9783540681052
the Semantic Grid is a recent initiative to expose semantically rich information associated with Grid resources to build more intelligent Grid services [2]. Recently, several projects have embraced this vision and there are several successful applications that combine the strengths of the Grid and of semantic technologies [5,11,4]. However, Semantic Grid still lacks a technology, which would provide the needed scalability and integration with existing infrastructure. In this paper we present our on-going work on a semantic grid repository, which is capable of addressing complex schemas and answer queries over ontologies with large number of instances. We present the details of our approach and describe the underlying architecture of the system. We conclude with a performance evaluation, which compares the current state-of-the-art reasoners with our system.
the three-dimensional variational assimilation (3D-Var) is the most commonly used technique currently to generate an analysis that provides better consistent initial conditions for numerical weather prediction (NWP). ...
详细信息
ISBN:
(纸本)9783540681052
the three-dimensional variational assimilation (3D-Var) is the most commonly used technique currently to generate an analysis that provides better consistent initial conditions for numerical weather prediction (NWP). the Global and Regional Assimilation Prediction System (GRAPES) is a new generation NWP system in China, in which 3D-Var is one of the main components and plays an important role in direct assimilation for non-conventional observations. In this study, the principal theory and serial implementation of GRAPES 3D-Var are introduced firstly, and the details of distributed parallel computing algorithm of GRAPES 3D-Var are discussed, including data partitioning strategies, data communication strategies and stagger parallelization strategies. At last, some parallel experimental results on 16-CPU cluster platform are put forward, and the numerical simulations of the parallelization show that the parallel strategies can be combined to achieve considerable load balancing and good performance.
暂无评论