A comparison is made between the probabilistic domain decomposition (DD) method and a certain deterministic DD method for solving linear elliptic boundary-value problems. Since in the deterministic approach the CPU ti...
详细信息
ISBN:
(纸本)9783540744658
A comparison is made between the probabilistic domain decomposition (DD) method and a certain deterministic DD method for solving linear elliptic boundary-value problems. Since in the deterministic approach the CPU time is affected by intercommunications among the processors, it turns out that the probabilistic method performs better, especially when the number of subdomains (hence, of processors) is increased. this fact is clearly illustrated by some examples. the probabilistic DD algorithm has been implemented in an MPI environment, in order to exploit distributed computer architectures. Scalability and fault-tolerance of the probabilistic DD algorithm are emphasized.
Monitoring traffic intersections in real time is an important part towards Intelligent Transportation System. A road surveillance system using background subtraction and threshold segmentation calculated traffic param...
详细信息
ISBN:
(纸本)0769529097
Monitoring traffic intersections in real time is an important part towards Intelligent Transportation System. A road surveillance system using background subtraction and threshold segmentation calculated traffic parameters. First an improved background establish and updating algorithm was applied to setup a robust background filtering illumination disturbance. then a self-adaptive max variance threshold algorithm was adopted to determine the threshold. third, a fast region growing algorithm was employed to border vehicles in some rectangles fixed their edges. Finally, algorithms were mentioned to calculate traffic parameters including traffic flux, average speed and duty ratio of road. the experimental results show that the system is adapted to monitor a multi-lane road near an urban intersection.
Tiled architectures are emerging as an architectural platform that allows high levels of instruction level parallelism. Traditional compiler parallelization techniques are usually employed to generate programs for the...
详细信息
Computational morphology is a core component in many different types of natural language processing, such as the alignment techniques. this paper describes a method for morphological processing. Based on both rules an...
详细信息
ISBN:
(纸本)0769529097
Computational morphology is a core component in many different types of natural language processing, such as the alignment techniques. this paper describes a method for morphological processing. Based on both rules and statistical models, a lemmatizer is constructed to analyze the English inflectional morphology, and automatically derives the lemmas of the words. the rule model incorporates data from various corpora, machine-readable dictionaries, and an empirical metamorphose rule set, and the statistical model applies mainly the maximum entropy principles to deal with unknown words and ambiguous cases effectively. the knowledge used in our lemmatizer is convenient to update to support the development of natural language processing. Experiments show that the lemmatizer has a wide coverage and high accuracy.
作者：
Li, LiUSTB
Informat Engn Sch Beijing Peoples R China
Query Expansion technology can reduce word mismatch between query and related documents, improve retrieval precision through adding similar or related terms to original query. In the algorithm proposed in this paper, ...
详细信息
ISBN:
(纸本)9780769529097
Query Expansion technology can reduce word mismatch between query and related documents, improve retrieval precision through adding similar or related terms to original query. In the algorithm proposed in this paper, terms or phrases which have closely related sense are added to the original query and express users' query intention more precisely. this algorithm costs O(L) time which is independent of the SER-Base, and this is very practical for highly real-time search engine.
Programming using message passing or distributed shared memory are the two major parallel programming paradigms on clusters. However these two models have high programming complexity, produce less maintainable paralle...
详细信息
ISBN:
(纸本)9780769530499
Programming using message passing or distributed shared memory are the two major parallel programming paradigms on clusters. However these two models have high programming complexity, produce less maintainable parallel code, and are not suitable for multi-core multiprocessor clusters. While object-oriented programming is dominant in serial programming, it has not been well exploited in parallel programming. In this paper we propose an innovative automatic parallelization framework that employs past experience to parallelize serial programs and outputs the parallel code in the form of objects. Supported by a data-driven runtime environment, each parallel task is managed as a thread, exploiting the multiple processing cores on a cluster node. Based on this proposed framework, we have implemented a proof-of-concept parallelizer called PJava to parallelize Java code. the performance benefit of this framework is evaluated through case studies by comparing the execution time of the automatically generated PJava code to that of handcrafted JOPI (a Java dialect of MPI) code.
Many sorting algorithms have been studied in the past, but there are only a few algorithmsthat can effectively exploit both SIMD instructions and thread-level parallelism. In this paper, we propose a new parallel sor...
详细信息
As various multimedia communication services are increasingly required by Internet users, several signaling protocols have been proposed for the efficient control of multimedia communication services. However, the mod...
详细信息
the proceedings contain 14 papers. the topics discussed include: parallelization schemes for memory optimization on the cell processor: a case study of image processing algorithm;an on-chip cache design for vector pro...
the proceedings contain 14 papers. the topics discussed include: parallelization schemes for memory optimization on the cell processor: a case study of image processing algorithm;an on-chip cache design for vector processors;improving the accuracy of snoop filtering using stream registers;data prefetching and address pre-calculation through instruction pre-execution with two-step physical register deallocation;building a large instruction window through ROB compression;code-size conscious pipelining of imperfectly nested loops;improving disk bandwidth-bound applications through main memory compression;broadcast filtering-aware task assignment techniques for low-power MPSoCs;reducing leakage in power-saving capable caches for embedded systems by using a filter cache;analysis of static and dynamic energy consumption in NUCA caches: initial results;and a power-aware shared cache mechanism based on locality assessment of memory reference for CMPs.
We propose strategies to efficiently execute a query workload, which consists of multiple related queries submitted against a scientific dataset, on a distributed-memory system in the presence of partial dataset repli...
详细信息
ISBN:
(纸本)9781424415595
We propose strategies to efficiently execute a query workload, which consists of multiple related queries submitted against a scientific dataset, on a distributed-memory system in the presence of partial dataset replicas. Partial replication re-organizes and re-distributes one or more subsets of a dataset across the storage system to reduce I/O overheads and increase I/O parallelism. Our work targets a class of queries, called range queries, in which the query predicate specifies lower and upper bounds on the values of all or a subset of attributes of a dataset. Data elements whose attribute values fall into the specified bounds are retrieved from the dataset. If we think of the attributes of a dataset forming multi-dimensional space, where each attribute corresponds to one of the dimensions, a range query defines a bounding box in this multidimensional space. We evaluate our strategies in two scenarios involving range queries. the first scenario represents the case in which queries have overlapping regions of interest, such as those arising from an exploratory analysis of the dataset by multiple users. In the second scenario, queries represent adjacent rectilinear sections that capture an irregular subregion in the multi-dimensional space. this scenario corresponds to a case where the user wants to query and retrieve a spatial feature from the dataset. We propose cost models and an algorithm for optimizing such queries. Our results using queries for subsetting and analysis of medical image datasets show that effective use of partial replicas can result in reduction in query execution times.
暂无评论