检索结果-内蒙古大学图书馆

作者： Yang, Chaoran Bland, Wesley Mellor-Crummey, John Balaji, Pavan Department of Computer Science Rice University United States Math. and Comp. Sci. Division Argonne National Laboratory United States Mathematics and Computer Science Division Argonne National Laboratory United States

The past decade has seen the advent of a number of parallel programming models such as Coarray Fortran (CAF), Unified Parallel C, X10, and Chapel. Despite the productivity gains promised by these models, most parallel scientific applications still rely on MPI as their data movement model. One reason for this trend is that it is hard for users to incrementally adopt these new programming models in existing MPI applications. Because each model use its own runtime system, they duplicate resources and are potentially error-prone. Such independent runtime systems were deemed necessary because MPI was considered insufficient in the past to play this role for these languages. The recently released MPI-3, however, adds several new capabilities that now provide all of the functionality needed to act as a runtime, including a much more comprehensive one-sided communication framework. In this paper, we investigate how MPI-3 can form a runtime system for one example programming model, CAF, with a broader goal of enabling a single application to use both MPI and CAF with the highest level of interoperability. © 2014 ACM.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Multiple translational containment: Approximate and exact algorithms 6

Multiple translational containment: Approximate and exact al...

引用

6th Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 1995

作者： Daniels, Karen Milenkovict, Victor J. Harvard University Division of Applied Sciences United States University of Miami Department of Math and Computer Science United States

ISBN: (纸本)0898713498

We present exact algorithms for finding a solution to the two-dimensional translational containment problem: find translations for k polygons which place them inside a polygonal container without overlApplng. We also give an approximate algorithm: given any ϵ, it finds a set of translations such that no point of any polygon is more than 2ϵ inside the boundary of any other polygon or outside the container. The term &CN denotes a containment problem in which the κ polygons are convex and the container is nonconvex, and fcNN denotes nonconvex polygons and container. The polygons have up to m vertices, and the container has n vertices, where n > m (typically). We give exact algorithms for the following: 2CN in O(mnlogn) time, 3CN in O(m3ralogn) time, and ANN in O((mti)2κ+1LP(2κmn, + k2m2)) time, where LP(a, 6) is the time to solve a linear program with o variables and 6 constraints. We present an approximate algorithm for κNN whose running time is O((1/ϵ)κ log (1/ϵ)κ5slog s), where s is the largest number of vertices of any polygon that can generated by applying a certain set of operations to the input. We have no polynomial bound on s, but, in practice, it is usually not more than quadratic in n.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Portable, MPI-interoperable Coarray Fortran 14

Portable, MPI-interoperable Coarray Fortran

引用

2014 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2014

ISBN: (纸本)9781450326568

The past decade has seen the advent of a number of parallel programming models such as Coarray Fortran (CAF), Unified Parallel C, X10, and Chapel. Despite the productivity gains promised by these models, most parallel scientific applications still rely on MPI as their data movement model. One reason for this trend is that it is hard for users to incrementally adopt these new programming models in existing MPI applications. Because each model use its own runtime system, they duplicate resources and are potentially errorprone. Such independent runtime systems were deemed necessary because MPI was considered insufficient in the past to play this role for these languages. The recently released MPI-3, however, adds several new capabilities that now provide all of the functionality needed to act as a runtime, including a much more comprehensive one-sided communication framework. In this paper, we investigate how MPI-3 can form a runtime system for one example programming model, CAF, with a broader goal of enabling a single application to use both MPI and CAF with the highest level of interoperability. Copyright © 2014 ACM.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Applying Big Data Based Deep Learning System to Intrusion Detection

引用

Big Data Mining and Analytics 2020年第3期3卷 181-195页

作者： Wei Zhong Ning Yu Chunyu Ai Division of Math and Computer Science University of South Carolina UpstateSpartanburgSC 29303USA Department of Computing Sciences State University of New York College at BrockportBrockportNY 14420USA

With vast amounts of data being generated daily and the ever increasing interconnectivity of the world’s internet infrastructures,a machine learning based Intrusion Detection Systems(IDS)has become a vital component to protect our economic and national *** shallow learning and deep learning strategies adopt the single learning model approach for intrusion *** single learning model approach may experience problems to understand increasingly complicated data distribution of intrusion ***,the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of *** order to further enhance the performance of machine learning based IDS,we propose the Big Data based Hierarchical Deep Learning System(BDHDLS).BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the *** deep learning model in the BDHDLS concentrates its efforts to learn the unique data distribution in one *** strategy can increase the detection rate of intrusive attacks as compared to the previous single learning model *** on parallel training strategy and big data techniques,the model construction time of BDHDLS is reduced substantially when multiple machines are deployed.

关键词： intrusion detection deep learning convolution neural network fully connected feedforward neural network multi-level clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Multiclass fuzzy clustering support vector machines for protein local structure prediction

Multiclass fuzzy clustering support vector machines for prot...

引用

7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE

作者： Zhong, Wei He, Jieyue Pan, Yi Division of Math and Computer Science USC Upstate Spartanburg SC 29303 United States Department of Computer Science and Engineering Southeast University Nanjing 210096 China Department of Computer Science Georgia State University Atlanta GA 30303 United States

ISBN: (纸本)1424415098

Local protein structure prediction is a central task in bioinformatics research. Local protein structure prediction can be transformed into the multiclass problem for huge datasets. In previous study, multiclass Clustering Support Vector Machines (CSVMs) was proposed for local protein structure prediction. The greedy algorithm is utilized to select the next closest class if CSVM modeled for the assigned class predicts the sequence segment as negative. However, the greedy algorithm may not be optimal. If all CSVM predict the sequence segment as negative, this sequence segment cannot be classified. In order to further improve performance of the multiclass problem, we propose Fuzzy Clustering Support Vector Machines (FCSVMs) in this study. The FCSVMs model calculates the class membership value of the given sequence segment for each class and assigns the representative structure of the finally selected class to the sequence segment. Values of the fuzzy membership function are based on testing accuracy of decision function outputs from FCSVMs. Under this mechanism, values of different fuzzy membership functions can be compared. FCSVMs are built specifically for each class partitioned intelligently by the clustering algorithm. This feature makes learning tasks for each FCSVM more specific and simpler. Furthermore, FCSVM modeled for each class can be easily parallelized to handle the complex multiclass problems for huge datasets. Using fuzzy membership functions, all sequence segments can be classified. Compared with the conventional clustering algorithm and CSVMs, testing accuracy for local structure prediction has been improved noticeably when the FCSVMs model is applied. ©2007 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Column-based strip packing using ordered and compliant containment 1st

Column-based strip packing using ordered and compliant conta...

引用

1st ACM Workshop on Applied Computational Geometry, WACG 1996 held as part of 2nd Federated Computing Research Conference, FCRC 1996

作者： Daniels, Karen Milenkovic, Victor J. Harvard University and University of Miami Division of Applied Sciences United States University of Miami Department of Math and Computer Science United States

ISBN: (纸本)354061785X

The oriented strip packingproblem is very important to manufacturing industries: given a strip of fixed width and a set of many (> 100) nonconvex polygons with 1, 2, 4, or 8 orientations permitted for each polygon, find a set of translations and orientations for the polygons that places them without overlapping into the strip of minimum length. Heuristics are given for two versions of strip packing: 1) translation-only and 2) oriented. The first heuristic uses an algorithm we have previously developed for translational containment: given polygons P1, P2…., Pk and a fixed container C, find translations for the polygons that place them into C without overlapping. The containment algorithm is practica] for k ≤ 10. Two new containment algorithms are presented for use in the second packing heuristic. The first, an ordered containment algorithm, solves containment in time which is only linear in k when the polygons are a) "long" with respect to one dimension of the container and b) ordered with respect to the other dimension. The second algorithm solves compliant containment: given polygons P1, P2,..., Pi+k and a container C such that polygons P1, P2,…, Pi are already placed into C, find translations for Pi+l, Pi+2,…, Pi+k and a nonoverlapping translationa] motion of P1, P2,…, Pi that allows all l + k polygons to fit into the container without overlapping. The performance of the heuristics is compared to the performance of commercial software and/or human experts. The results demonstrate that fast containment algorithms for modest values of k (k ≤ 10) are very useful in the development of heuristics for oriented strip packing of many (k >> 10) polygons. © Springer-Verlag Berlin Heidelberg 1996.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Real-Time Evolution and Deployment of Neuromorphic Computing at the Edge 12

Real-Time Evolution and Deployment of Neuromorphic Computing...

引用

12th International Green and Sustainable Computing Conference, IGSC 2021

作者： Schuman, Catherine D. Young, Steven R. Maldonado, Bryan P. Kaul, Brian C. Oak Ridge National Laboratory Computer Science and Math Division Oak RidgeTN United States Oak Ridge National Laboratory Energy and Transportation Science Division Oak RidgeTN United States

ISBN: (纸本)9781665478519

Extremely low power neuromorphic systems are well-suited for deployment to the edge for many applications. In many use cases of neuromorphic computing for control, a spiking neural network is trained off-line using a simulation and then deployed to a neuromorphic system at the edge, where it will operate without ongoing training or learning. However, it may be desirable to continue training or learning at the edge to refine or adapt to the real-world system. In this work, we propose an approach for performing real-time evolutionary optimization for spiking neural networks for neuromorphic deployment at the edge. In particular, we propose a combination of simulation and real-world evaluations, along with feedback from the real-world environment, to train spiking neural networks for continuous deployment to the edge. We show that the real-time evolution at the edge approach achieves comparable performance to an evolution approach that requires constant evaluation in the realworld environment. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Parallel components for PDEs and optimization: Some issues and experiences

Parallel components for PDEs and optimization: Some issues a...

引用

作者： Norris, Boyana Balay, Satish Benson, Steven Freitag, Lori Hovland, Paul McInnes, Lois Smith, Barry Math. and Computer Science Division Argonne National Laboratory 9700 S. Cass Avenue Argonne IL 60439 United States

High-performance simulations in computational science often involve the combined software contributions of multidisciplinary teams of scientists, engineers, mathematicians, and computer scientists. One goal of component-based software engineering in large-scale scientific simulations is to help manage such complexity by enabling better interoperability among codes developed by different groups. This paper discusses recent work on building component interfaces and implementations in parallel numerical toolkits for mesh manipulations, discretization, linear algebra, and optimization. We consider several motivating applications involving partial differential equations and unconstrained minimization to demonstrate this approach and evaluate performance. © 2002 Elsevier science B.V. All rights reserved.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Fairness in scheduling 6

Fairness in scheduling

引用

6th Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 1995

作者： Ajtai, Miklos Aspnes, James Naor, Moni Rabani, Yuval Schulman, Leonard J. Waarts, Orli IBM Research Division Almaden Research Center United States Dept. of Computer Science Yale University United States Dept. of Applied Math and Computer Science Weizmann Institute Israel ICSI Berkeley Lab. for Computer Science MIT United States Department of Computer Science University of Toronto TorontoONM5S 1A4 Canada Computer Science Division U.C. Berkeley United States

ISBN: (纸本)0898713498

On-line machine scheduling has been studied extensively, but the fundamental issue of fairness in scheduling is still mostly open. In this paper we explore the issue in settings where there are long living processes which should be repeatedly scheduled for various tasks throughout the lifetime of a system. For any such instance we develop a notion of desired load of a process, which is a function of the tasks it participates in. The unfairness of a system is the maximum, taken over all processes, of the difference between the desired load and the actual load. An example of such a setting is the carpooi problem suggested by Fagin and Williams [17]. In this problem, a set of n people form a carpooi. On each day a subset of the people arrive and one of them is designated as the driver. A scheduling rule is required so that the driver will be determined in a 'fair' way. We investigate this problem under various assumptions on the input distribution. We also show that the carpooi problems can capture several other problems of fairness in scheduling.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Falkon: A Fast and Light-weight tasK executiON framework 07

Falkon: A Fast and Light-weight tasK executiON framework

引用

2007 ACM/IEEE Conference on Supercomputing, SC'07

作者： Raicu, Loan Zhao, Yong Dumitrescu, Catalin Foster, Ian Wilde, Mike Department of Computer Science University of Chicago IL United States Computation Institute University of Chicago Argonne National Laboratory United States Math and Computer Science Division Argonne National Laboratory Argonne IL United States

ISBN: (纸本)9781595937643

To enable the rapid execution of many tasks on compute clusters, we have developed Falkon, a Fast and Light-weight tasK executiON framework. Falkon integrates (1) multi-level scheduling to separate resource acquisition (via, e.g., requests to batch schedulers) from task dispatch, and (2) a streamlined dispatcher. Falkon's integration of multi-level scheduling and streamlined dispatchers delivers performance not provided by any other system. We describe Falkon architecture and implementation, and present performance results for both microbenchmarks and applications. Microbenchmarks show that Falkon throughput (487 tasks/sec) and scalability (to 54,000 executors and 2,000,000 tasks processed in just 112 minutes) are one to two orders of magnitude better than other systems used in production Grids. Large-scale astronomy and medical applications executed under Falkon by the Swift parallel programming system achieve up to 90% reduction in end-to-end run time, relative to versions that execute tasks via separate scheduler submissions. (c) 2007 ACM.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：