Filters








1,000 Hits in 6.4 sec

Parallel skeletons for structured composition

John Darlington, Yi-ke Guo, Hing Wing To, Jin Yang
1995 Proceedings of the fifth ACM SIGPLAN symposium on Principles and practice of parallel programming - PPOPP '95  
In this paper, we propose a straightforward solution to the problems of compositional parallel programming by using skeletons as the uniform mechanism for structured composition.  ...  The ability to compose skeletons provides us with the essential tools for building further and more complex application-oriented skeletons specifying important aspects of parallel computation.  ...  Special thanks are due to Moustafa Ghanem for his helpful comments on earlier drafts.  ... 
doi:10.1145/209936.209940 dblp:conf/ppopp/DarlingtonGTY95 fatcat:beq2snzg4rgbfhahfkbyki4auq

Parallel skeletons for structured composition

John Darlington, Yi-ke Guo, Hing Wing To, Jin Yang
1995 SIGPLAN notices  
In this paper, we propose a straightforward solution to the problems of compositional parallel programming by using skeletons as the uniform mechanism for structured composition.  ...  The ability to compose skeletons provides us with the essential tools for building further and more complex application-oriented skeletons specifying important aspects of parallel computation.  ...  Special thanks are due to Moustafa Ghanem for his helpful comments on earlier drafts.  ... 
doi:10.1145/209937.209940 fatcat:jqejakzecbdfzigi5irti5xhuu

Covariate selection with iterative principal component analysis for predicting physical soil properties

Matthew R. Levi, Craig Rasmussen
2014 Geoderma  
An iterative principal component analysis (iPCA) data reduction routine of reflectance and elevation covariate layers was combined with a conditioned Latin Hypercube field sample design to effectively  ...  This research demonstrates the efficacy of coupling data reduction, sample design, and geostatistical techniques for effective spatial prediction of soil physical properties in a semiarid ecosystem.  ...  The authors would like to thank the handling editor and two anonymous reviewers for their helpful comments that greatly improved the manuscript.  ... 
doi:10.1016/j.geoderma.2013.12.013 fatcat:f7ezwj3tyja55c3ascu4kxwdwy

Empirical analysis of overheads in cluster environments

Brian K. Schmidt, Vaidy S. Sunderam
1994 Concurrency Practice and Experience  
In an attempt to gain some insight into the nature of these overheads, and to propose strategies to alleviate them, empirical measurements of native communication performance as well as application execution  ...  Interestingly, we find that agenda parallelism and load balancing strategies contribute significantly more to better performance than improved communications or system tuning.  ...  Figure 10 : 10 Comparison of PVM datagram and stream protocols for sorting. Figure 11 : 11 Predicted vs. measured time for sorting on a hypercube.  ... 
doi:10.1002/cpe.4330060102 fatcat:zkhdwir7djcxpc2g7z2sfoxqt4

Fault Tolerance in Interconnection Network-a Survey

Laxminath Tripathy, Devashree Tripathy, C.R. Tripathy
2015 Research Journal of Applied Sciences Engineering and Technology  
This study makes an extensive survey of various methods of fault tolerance for interconnection networks those are used in large scale parallel processing.  ...  Interconnection networks are used to provide communication between processors and memory modules in a parallel computing environment.  ...  Balanced Varietal Hypercube (BVH), suitable for massively parallel systems. The topology being a hybrid structures of Balanced Hypercube and Varietal Hypercube.  ... 
doi:10.19026/rjaset.11.1708 fatcat:kg63d4zn4bcqfkydcvm6y3nooi

Application Specific Customization and Scalability of Soft Multiprocessors

Deepak Unnikrishnan, Jia Zhao, Russell Tessier
2009 2009 17th IEEE Symposium on Field Programmable Custom Computing Machines  
The power consumption for 9 and 16 processor designs for Bitonic sort show mostly linear growth.  ...  Figure 18 : 18 Hypercube topology for 16 processors Figure 21 shows 21 an overview of the proposed design flow for the soft multiprocessor synthesis framework.  ... 
doi:10.1109/fccm.2009.41 dblp:conf/fccm/UnnikrishnanZT09 fatcat:7cjy7ltl4rcyzlo7e2p4hdecdq

Principal component pyramids for manifold learning in hand shape recognition

Mohamed Farouk, Alistair Sutherland
2018 ICT Express  
2.20 shows an MLP network with one hidden layer.  ...  Nonlinear Principal Component Analysis Studying nonlinear manifolds using a manifold learning technique is an important issue in pattern recognition.  ... 
doi:10.1016/j.icte.2018.04.009 fatcat:ldjt75n3jvevjotzu5dowcklou

Critical issues in the design of a fault-tolerant multiprocessor database server

S.O. Hvasshovd, T. Saeter, O. Torbjornsen
1991 [1991] Proceedings Pacific Rim International Symposium on Fault Tolerant Systems  
Critical design issues when designing a fault-tolerant multiprocessor database server are identied as: 1) System design must be based on components with well dened states and state transitions. 2) Component  ...  The communication protocol should be optimized for the actual application (a DBMS in this case). 7) The communication system should be central in internode error detection and reconguration of a fault-tolerant  ...  The Design of a Fault-Tolerant Communication System The hypercube is a much used interconnection topology for parallel shared-nothing multicomputers ( [32] , [41] , [10] ).  ... 
doi:10.1109/rfts.1991.212941 fatcat:chspq2z6mvarpoqunipf5gggzu

XMulator: A Listener-Based Integrated Simulation Platform for Interconnection Networks

A. Nayebi, S. Meraji, A. Shamaei, H. Sarbazi-Azad
2007 First Asia International Conference on Modelling & Simulation (AMS'07)  
It is so desirable to attach newly designed components to the existing models and to exploit detailed results.  ...  This paper presents XMulator, an object-oriented listener-based simulation environment for evaluating multicomputer interconnection networks.  ...  Listener-Based Integration The method applied for integration of components in a component-based simulator has a great impact on extensibility and maintainability of a simulator [4, 19] .  ... 
doi:10.1109/ams.2007.112 dblp:conf/asiams/NayebiMSS07 fatcat:txwoalcorjgtfldjlhraylpruu

Ultracomputers

Jacob T. Schwartz
1980 ACM Transactions on Programming Languages and Systems  
A number of basic algorithms for these "ultracomputers" are presented, and physical design considerations are discussed in a preliminary fashion.  ...  A class of parallel processors potentially involving thousands of individual processing elements is described.  ...  This encouraging remark should apply, for example, to finite-element computations, where requirements for communication are modest and the necessary pattern of communications is known in advance.  ... 
doi:10.1145/357114.357116 fatcat:7ualqw566vhkvfafgghni66vgy

EdgeFrame

Per Fuchs, Peter Boncz, Bogdan Ghit
2020 Proceedings of the 3rd Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA)  
scalable Worst-Case-Optimal Join (WCOJ) that is especially useful for matching of complex and cyclical patterns in large graphs.  ...  Our choice to forego shuffle-or communication-based WCOJ is motivated by our analysis of the Shares algorithm for distributed WCOJ, that was proven communication-optimal, but which we show to quickly deteriorate  ...  Figure 1 : 1 An overview of the three layers in a Leapfrog TrieJoin algorithm for the triangle query. The arrows show the dependencies among components (a).  ... 
doi:10.1145/3398682.3399162 dblp:conf/sigmod/FuchsBG20 fatcat:bevufz4e35cxbm5kjuhwk6kpma

A compiler-based communication analysis approach for multiprocessor systems

Shuyi Shao, A.K. Jones, R. Melhem
2006 Proceedings 20th IEEE International Parallel & Distributed Processing Symposium  
In this paper we describe a compiler framework which can identify communication patterns for MPIbased parallel applications.  ...  Our compiler is capable of detecting both static and persistent communication patterns within an application.  ...  The communication compiling component is designed for connection-oriented networks with the goal of reducing the communication overhead.  ... 
doi:10.1109/ipdps.2006.1639322 dblp:conf/ipps/ShaoJM06 fatcat:q2wpua6l5bak3oyestbua3zmbm

Sorting Integers on the AP1000 [article]

Lex Weaver, Andrew Lynes
2000 arXiv   pre-print
This document describes the implementation of a radix based algorithm for sorting positive integers on a Fujitsu AP1000 Supercomputer, which was constructed as an entry in the Joint Symposium on Parallel  ...  Brief consideration is also given to a full radix sort conducted in parallel across the machine.  ...  An analysis of the data sets quickly revealed that they were designed to provide a thorough test of any parallel integer sorting program.  ... 
arXiv:cs/0004013v1 fatcat:5sl7aps7mbcq5pph6lon3jppjm

EFFICIENT IDENTIFICATION OF FACES IN VIDEO STREAMS USING LOW-POWER MULTI-CORE DEVICES [chapter]

Donavan Prieur, Eric Granger, Yvon Savaria, Claude Thibeault
2015 Handbook of Pattern Recognition and Computer Vision  
Experimental results obtained using real-world video data show that implementing fuzzy ARTMAP networks optimized using multi-objective PSO on low-power parallel processors allows to significantly reduce  ...  In this paper, fuzzy ARTMAP networks co-jointly optimized for accuracy and efficiency are implemented and compared for one-against-many face matching using the Intel Core i3-530, the Intel Atom N270 and  ...  During enrolment, one or more input patterns acquired for an individual are employed to design his facial template or model, and stores in a database.  ... 
doi:10.1142/9789814656535_0023 fatcat:ncorik52mnblli4cko5cllhwya

ARMI

Steven Saunders, Lawrence Rauchwerger
2003 SIGPLAN notices  
ARMI is used by STAPL, our generic parallel library, to provide a portable, user transparent communication layer.  ...  The library is an advanced implementation of the RMI protocol and handles low-level details such as scheduling incoming communication and aggregating outgoing communication to coarsen parallelism when  ...  Three common communication patterns result: 1. data parallel -the same operation needs to be applied in parallel, possibly with a parallel reduction at the end.  ... 
doi:10.1145/966049.781534 fatcat:2vikxlc7rjb3zp22tx6cehhrgm
« Previous Showing results 1 — 15 out of 1,000 results