As a representation of high connected objects, graphs receive a arising attention. By virtue of the interconnection of graph data, current general-purpose parallel data processing systems misfit effectively graph proc...
详细信息
ISBN:
(纸本)9781509021291
As a representation of high connected objects, graphs receive a arising attention. By virtue of the interconnection of graph data, current general-purpose parallel data processing systems misfit effectively graph processing. thus, a wide spectrum of dedicated graph processing system emerged. In this paper, we give a guidance of classical types of graph processing system. We discuss key features and the according challenges of graph processing from the aspect of graph data, graph algorithm as well as the computation implementation. then we specify four strategies that should be taken into account when designing a graph processing systems. In the last part of our paper we make a comparison of present typical graph processing systems and specify their suitable application area.
A simplified dynamical model of the international market for greenhouse gases emissions permits is considered. A procedure for constructing optimal strategies of Russia's behavior is suggested. A possibility of ob...
详细信息
ISBN:
(纸本)9783540681052
A simplified dynamical model of the international market for greenhouse gases emissions permits is considered. A procedure for constructing optimal strategies of Russia's behavior is suggested. A possibility of obtaining algorithm's input data from integrated assessment models is discussed. A specific numerical analysis is performed.
Chip multiprocessors (CMP) are widely used for high performance computing and are being configured in a hierarchical manner to compose a CMP compute node in a parallel system. OpenMP parallel programming within such a...
详细信息
ISBN:
(纸本)9781424449231
Chip multiprocessors (CMP) are widely used for high performance computing and are being configured in a hierarchical manner to compose a CMP compute node in a parallel system. OpenMP parallel programming within such a CMP node can take advantage of the globally shared address space and on-chip high inter-core bandwidth and low inter-core latency. In this paper, we use OpenMP to parallelize a sequential earthquake simulation code for modeling spontaneous dynamic earthquake rupture along geometrically complex faults on two CMP systems, IBM POWER5+ system and SUN Opteron server. the experimental results indicate that the OpenMP implementation has the accurate output results and the good scalability on the two CMP systems. Further, we apply the optimization techniques such as large page and processor binding to the OpenMP implementation to achieve up to 7.05% performance improvement on the CMP systems without any code modification.
System-on-a-chip (SOC) is the best solution to meet withthe requirement of the state-of-the-art electronic products such as portable mobile terminals and digital cameras in the terms of performance, cost and reliabil...
详细信息
ISBN:
(纸本)078037889X
System-on-a-chip (SOC) is the best solution to meet withthe requirement of the state-of-the-art electronic products such as portable mobile terminals and digital cameras in the terms of performance, cost and reliability. To design a high performance SOC chip with high flexibility, embedded DSP or CPU cores are essential component. In this paper, starting with a briefly review on the major features of main-stream DSP processors developed since 1980's, we discuss the special requirement in design of embedded DSP cores, and present a new reconfigurable parallel architecture of high performance embedded DSP core with vector processing ability for media and mobile communication signal processing.
this paper presents different aspects of parallelization of a problem of processing color digital images in order to generate linguistic description of their content. A parallel architecture of an intelligent image re...
详细信息
ISBN:
(纸本)9783319780245;9783319780238
this paper presents different aspects of parallelization of a problem of processing color digital images in order to generate linguistic description of their content. A parallel architecture of an intelligent image recognition system is proposed. Fuzzy classification and inference is performed in parallel, based on the CIE chromaticity color model and granulation approach. In addition, the parallelization concerns e.g. processing a large collection of images or parts of a single image.
In order to improve the processing speed of highly complex video coding that involves high data rate and large amount of computation, a parallel video coding system optimization (PVCSO) method is proposed in this pape...
详细信息
this paper describes a parallel numerical library based on Co-array Fortran syntax in combination withthe object-oriented features of Fortran 95. It defines distributed data structures based on an abstract object cal...
详细信息
ISBN:
(纸本)3540341412
this paper describes a parallel numerical library based on Co-array Fortran syntax in combination withthe object-oriented features of Fortran 95. It defines distributed data structures based on an abstract object called a vector map. It uses co-array syntax, embedded in methods associated with distributed objects, for communication between those objects based on information in the vector map. It applies a finite difference operator to the shallow water equations to illustrate how to use the library to calculate solutions for partial differential equations.
Development and simulation of artificial biological models require a considerable computational complexity which can be surmounted using Modern Graphic processing Units (GPUs), since these devices adopt parallel multi...
详细信息
ISBN:
(纸本)9781538606865
Development and simulation of artificial biological models require a considerable computational complexity which can be surmounted using Modern Graphic processing Units (GPUs), since these devices adopt parallel multi-core architecture which favors the inherently data-parallel nature. In this paper, we present an extended version of our hybrid model presented in [1], [2], based on a high tuning CUDA parameter (Compute Unified Device Architecture) for the parallel evolutionary strategy (ES) and a recurrent neural network (RNN), called PEvoRNN. this proposal takes the advantages of the GPU memory hierarchy effective use, the best parallelism management by investigating tuning CUDA parameters and the optimal GPU-based coding, to generate optimal trajectories of a humanoid robot using GPU Accelerator at multiple levels. PEvoRNN represents a controller which monitors the movement and the evolution of a 3D humanoid robot simulated on the open dynamic engine simulator (ODE). Moreover, this proposal makes feasible and tractable the integration of multiple complex evolutionary methods for heterogeneous training locomotion process. the effectiveness of the proposed parallel tuned evolutionary training technique was validated for real movements in terms of a promising speedup, since this field requires powerful computational resources.
the computer algebra of parallel modular operations with a square diapason for a variable is described. the base set of the algebra is a finite dimension metric space of modular integer vectors. Two metrics are introd...
详细信息
the proceedings contain 33 papers. the topics discussed include: description and recognition of symmetrical and freely oriented images based on parallel shift technology;the web visualization of real signals;making a ...
ISBN:
(纸本)9781538675007
the proceedings contain 33 papers. the topics discussed include: description and recognition of symmetrical and freely oriented images based on parallel shift technology;the web visualization of real signals;making a tactile painting of the painting 'capturing Vasil Levski at the Kakrinsko Hanche' for blind users;and cyber security resilience based on static factors as a part of converged security.
暂无评论