Understanding of the human brain functioning currently represents a challenging problem. In contrast to usual serial computers and complicated hierarchically organized artificial man-made systems, decentralized, paral...
详细信息
ISBN:
(数字)9783110269208
ISBN:
(纸本)9783110268355
Understanding of the human brain functioning currently represents a challenging problem. In contrast to usual serial computers and complicated hierarchically organized artificial man-made systems, decentralized, parallel and distributed information processing principles are inherent to the brain. Besides adaptation and learning, which play a crucial role in brain functioning, oscillatory neural activity, synchronization and resonance accompany the brain work. Neural-like oscillatory network models, designed by the authors for imageprocessing, allow to elucidate the capabilities of dynamical, synchronization-based types of imageprocessing, presumably exploited by the brain. The oscillatory network models, studied by means of computer modeling and qualitative analysis, are presented and discussed in the book. Some other problems of paralleldistributed information processing are also considered, such as a recall process from network memory for large-scale recurrent associative memory neural networks, performance of oscillatory networks of associative memory, dynamical oscillatory network methods of imageprocessing with synchronization-based performance, optical parallel information processing based on the nonlinear optical phenomenon of photon echo, and modeling random electric fields of quasi-monochromatic polarized light beams using systems of superposed stochastic oscillators. This makes the book highly interesting to researchers dealing with various aspects of parallel information processing.
A large variety of methods based on Partial Differential Equations (PDE) use the interface propagation. For their flexibility these methods are being more and more applied to various problems ranging from physics, flu...
详细信息
ISBN:
(纸本)0780376633
A large variety of methods based on Partial Differential Equations (PDE) use the interface propagation. For their flexibility these methods are being more and more applied to various problems ranging from physics, fluid mechanics to control theory and computer vision. The solution of the PDE-based interface evolution is in itself a complex iterative computational task involving a great number of iterations (unknown a priori). Therefore, these applications are very demanding on the hardware and their real-time implementation is still a challenging problem. An efficient implementation could be done by using a specific parallel architecture. This paper proposes an original, entirely parallel algorithm to solve the Eikonal equation. Which is the base of applications using a weighted distance function. This algorithm allows the parallel implementation of active contours methods or continuous watershed on a specific hardware.
Computed tomography (CT) image reconstruction algorithms via graphic processing unit (GPU) have recently attracted much public attention. These methods often adopt cached texture memory to reduce GPU's high memory...
详细信息
ISBN:
(纸本)9781424479948
Computed tomography (CT) image reconstruction algorithms via graphic processing unit (GPU) have recently attracted much public attention. These methods often adopt cached texture memory to reduce GPU's high memory latency. However, these texture-based methods still have low efficiency because of their low cache hit rates. By studying threads' execution model on GPU, this paper proposes an accelerating scheme based on the degree of streaming multiprocessor level parallelism. This parallel strategy could make simultaneously executing threads in each multiprocessor have closer localities of memory accesses to improve the utilization of cached texture memory. Experiment results indicate that our accelerating scheme could reduce the computing time by 20%-30% for both forward-and backward-projections on GPU.
Advances in storage and high-speed broadband communication,network technologies are making it feasible to design and implement distributed scalable Video-on-Demand structure networks. In this paper;a hierarchical stru...
详细信息
ISBN:
(纸本)0769507689
Advances in storage and high-speed broadband communication,network technologies are making it feasible to design and implement distributed scalable Video-on-Demand structure networks. In this paper;a hierarchical structure for a server network is proposed to support a metropolitan TV-Anytime service. A key issue, how to map the media assets onto such a hierarchical sen,er network, is addressed in this paper: The definition and heuristic methods for the solution of this new combinatorial optimization problem are presented. The mapping problem studied here addresses the management of media assets taking the storage capacity: communication bandwidth limitation and access pattern into account. The methods presented in this payer are based on parallel simulated annealing and are verified by the use of a set of benchmark instances. The results show that the methods provide a near to optimal performance in terms of the Quality of Service (QoS).
In this paper, it is shown that, through the use of model- integrated program synthesis (MIPS), parallel real-time implementations of imageprocessing data flows can be synthesized from high level graphical specificat...
详细信息
Exact segmentation of the brain tumor is one of the imperative tasks in medical imageprocessing and its analysis as it deals with extracting the information of the tumorous region from the brain MRI sequences. Automa...
详细信息
ISBN:
(纸本)9781728106465
Exact segmentation of the brain tumor is one of the imperative tasks in medical imageprocessing and its analysis as it deals with extracting the information of the tumorous region from the brain MRI sequences. Automated segmentation and detection of brain tumors from the brain MRI is an exigent issue caused by the texture, size, shape, and location. In this paper, a significant method of brain tumor segmentation from the FLAIR MRI sequences is by classifying local window followed by parallel fuzzy c means clustering. Fuzzy c- means methods have shown their efficiency in extracting a variety of objects in several medical imageprocessing applications. However, one of the major issues of these algorithms is high computational requirements at the time of dealing with large data set. Nowadays, NVIDIA's GPU plays an extremely essential role in implementing such time-consuming algorithms to reduce the time complexity. Our experiments based on NCI-MICCAI BRATS 2017 FLAIR MRI of HGG (High-Grade Glioma) demonstrate the efficiency of the implemented parallel algorithm. For the segmentation of tumorous region, a mechanism of sliding window is implemented on CPU (host) in which a 45 X 45 sized window is taken to classify whether that particular window is having tumor region or not. For perfect segmentation at the GPU (device) side, fuzzy c means technique is used to get the exact location of the tumor. Approx 17.6 speed up obtained, for the BRATS data sets over the implementation of the algorithm on CPU. Apart from speed up significant dice similarity coefficients are obtained which shows the efficient segmentation in the reasonable time.
Previous proposals for the application of discrete Event methods to parallelization of sequential software have been based on the optimistic execution strategy. In this paper we present a new method which avoids optim...
详细信息
ISBN:
(纸本)0818682272
Previous proposals for the application of discrete Event methods to parallelization of sequential software have been based on the optimistic execution strategy. In this paper we present a new method which avoids optimistic execution. This is motivated by the observation that the control structure of a sequential program constitutes a temporal co-ordinate system which is exogenous to the program execution. The method employs a logical time mechanism and provides adaptive synchronisation for the distributed execution. Hence Data dependent and/or conditional parallelism is released without the risk of coherency violation. The paper begins with a brief introduction to parallel discrete event simulation paradigm. Efficient coarse grain mapping of conventional programs onto this paradigm is then discussed.
The lack of a single system image Operating System (OS) for clusters restricts their use for parallelprocessing. We propose an approach for building an efficient single system image cluster operating system. The prop...
详细信息
The lack of a single system image Operating System (OS) for clusters restricts their use for parallelprocessing. We propose an approach for building an efficient single system image cluster operating system. The proposed system implements distributed services performing global and dynamic resource management to offer high performance, high availability and ease of use and programming. The programming API of the OS running on each cluster node is kept unmodified but the high level OS services can take benefit of all cluster resources. Our approach has been validated by a prototype based on Linux. Our prototype comprises of a limited kernel patch and a set of modules extending the kernel to implement the cluster distributed services. Existing applications running on symmetric multiprocessors (SMP) on top of Linux can be executed on top of our cluster OS without modification. (C) 2003 Elsevier B.V. All rights reserved.
High efficiency in parallel adaptive integration is difficult to achieve. Dependencies between integration regions are dynamic and therefore dynamic region redistribution is necessary. In our approach, we employ a con...
详细信息
ISBN:
(纸本)9780769530895
High efficiency in parallel adaptive integration is difficult to achieve. Dependencies between integration regions are dynamic and therefore dynamic region redistribution is necessary. In our approach, we employ a control infrastructure designed to support parallel application global state monitoring. It includes monitors (called synchronizers), which observe application global states and take control decisions based on predicates computed on global states. Region redistribution strategy Is implemented inside the monitors. The most and least loaded processes are selected and ordered to level their loads by region exchange. The paper shows that this strategy can work well, underlining some important factors, which influence the performance. Two methods' which aim at eliminating excessive region transfers, are presented. It is also shown, that good parallel efficiency can be obtained easier if interprocessor network supports efficient transmissions of large data packets. The problem of finding an optimal communication frequency between computing processes has been much reduced - it is enough if processes report their local load reasonably often.
Fault simulation is a time-consuming process that requires customized methods and techniques to accelerate it. Multi-threading and Multi-core approaches are two promising techniques that can be exploited to accelerate...
详细信息
ISBN:
(纸本)9781665414555
Fault simulation is a time-consuming process that requires customized methods and techniques to accelerate it. Multi-threading and Multi-core approaches are two promising techniques that can be exploited to accelerate the fault simulation process by using different parts of the hardware at the same time. However, an efficient parallelization is obtained only by the refinement of software with respect to the hardware platform. In this paper, a parallel multi-thread fault simulation technique is proposed to accelerate the simulation process on multi-core platforms. In this approach, the gate input values are independently assigned to each thread. Each input value carries the information of several parallel simulation processes. This provides a multithread parallel fault simulation environment. The experimental results show that the proposed technique can efficiently use the hardware platform. In a single-core platform. the proposed technique can reduce the time by 25% while in a dual-core increasing the thread approximately halves the execution time.
暂无评论