Filters








6,225 Hits in 5.2 sec

Practical parallel algorithms for dynamic data redistribution, median finding, and selection

D.A. Bader, J. JaJa
Proceedings of International Conference on Parallel Processing  
Practical algorithms needed by our selection algorithm for the dynamic redistribution of data are also discussed.  ...  This paper presents a fast and portable parallel algorithm for nding the median given a set of elements distributed across a parallel machine.  ...  We also acknowledge William Carlson and Jesse Draper from the Center for Computing Science formerly Supercomputing Research C e n ter for writing the parallel compiler AC v ersion 2.6 12 o n which the  ... 
doi:10.1109/ipps.1996.508072 dblp:conf/ipps/BaderJ96 fatcat:jukscwj2wjaqzidkmjpxgnmbpq

Practical algorithms for selection on coarse-grained parallel computers

I. Al-Furiah, S. Aluru, S. Goil, S. Ranka
1997 IEEE Transactions on Parallel and Distributed Systems  
In this paper, we consider the problem of selection on coarse-grained distributed memory parallel computers. We discuss several deterministic and randomized algorithms for parallel selection.  ...  We also consider several algorithms for load balancing needed to keep a balanced distribution of data across processors during the execution of the selection algorithms.  ...  The algorithms can also be used in other problems that require dynamic redistribution of data and where there is no restriction on the assignment of data to processors.  ... 
doi:10.1109/71.605768 fatcat:wdod7y3cxbcxhbtwtlm7iyn46u

Robust Massively Parallel Sorting [article]

Michael Axtmann, Peter Sanders
2020 arXiv   pre-print
At the same time asymptotic analysis provides performance guarantees and guides the selection and configuration of the algorithms.  ...  We investigate distributed memory parallel sorting algorithms that scale to the largest available machines and are robust with respect to input size and distribution of the input elements.  ...  Approximate Median Selection with a Single Reduction Siebert and Wolf [2] consider the case where n = p and propose to select splitters for parallel quicksort using a ternary tree whose leaves are the  ... 
arXiv:1606.08766v4 fatcat:2xj4cxxcvvaojiotf7arypvndu

Implementation and evaluation of an efficient parallel Delaunay triangulation algorithm

Jonathan C. Hardwick
1997 Proceedings of the ninth annual ACM symposium on Parallel algorithms and architectures - SPAA '97  
The Machiavelli toolkit used to transform the nested data parallelism inherent in the divide-and-conquer algorithm into achievable task and data parallelism is also described and compared to previous techniques  ...  Results are presented for a loosely-coupled cluster of workstations, a distributed-memory multicomputer, and a shared-memory multiprocessor.  ...  Finding the median Initially a parallel version of quickmedian 25] was used to nd the median internal point a l o n g the x or y axis.  ... 
doi:10.1145/258492.258516 dblp:conf/spaa/Hardwick97 fatcat:eucj2ma7vbfc3le2ejv7qy24bq

Parallel String Sample Sort [article]

Timo Bingmann, Peter Sanders
2013 arXiv   pre-print
As a synthesis of the best sequential string sorting algorithms and successful parallel sorting algorithms for atomic objects, we propose string sample sort.  ...  The algorithm makes effective use of the memory hierarchy, uses additional word level parallelism, and largely avoids branch mispredictions.  ...  Burstsort dynamically builds a trie data structure for the input strings.  ... 
arXiv:1305.1157v1 fatcat:nbk2iecmsvedng3dghamjnx434

Parallel String Sample Sort [chapter]

Timo Bingmann, Peter Sanders
2013 Lecture Notes in Computer Science  
As a synthesis of the best sequential string sorting algorithms and successful parallel sorting algorithms for atomic objects, we propose string sample sort.  ...  The algorithm makes effective use of the memory hierarchy, uses additional word level parallelism, and largely avoids branch mispredictions.  ...  Burstsort dynamically builds a trie data structure for the input strings.  ... 
doi:10.1007/978-3-642-40450-4_15 fatcat:sgqzjbzmtbddtf326cqlnnu2iy

ParGeo: A Library for Parallel Computational Geometry [article]

Yiqiu Wang, Rahul Yesantharao, Shangdi Yu, Laxman Dhulipala, Yan Gu, Julian Shun
2022 arXiv   pre-print
Third, we present the BDL-tree, a parallel batch-dynamic kd-tree that allows for efficient parallel updates and k-NN queries over dynamically changing point sets.  ...  Second, for the smallest enclosing ball problem, we propose a new sampling-based algorithm to quickly reduce the size of the data set.  ...  We use a parallel maximum-finding algorithm to identify the pivot point. 5 Parallel Batch-Dynamic kd-tree The kd-tree, first proposed by Bentley [16] , is a binary tree data structure that arranges  ... 
arXiv:2207.01834v1 fatcat:4vdrhejamzcejhfyphdt6bhfee

Construction of Higher Education Management Data Analysis Model Based on Association Rules

Fanfei Zhao, Guanqun Zhang, Zhaoli Wang, Xiangyu Hao, Sheng Bin
2022 Scientific Programming  
and technical challenges of the algorithms themselves and the background of the practical application needs of the industry and firstly selects a series of data mining and machine learning algorithms  ...  The research on efficient large-scale distributed parallelized data mining and machine learning methods and algorithms is carried out.  ...  Acknowledgments is work was supported by Jitang College, North China University of Science and Technology.  ... 
doi:10.1155/2022/5414238 fatcat:kkmgu23b4jhv7gjtcpa3ec6ovy

Implementation of a portable nested data-parallel language

Guy E. Blelloch, Jonathan C. Hardwick, Siddhartha Chatterjee, Jay Sipelstein, Marco Zagha
1993 Proceedings of the fourth ACM SIGPLAN symposium on Principles and practice of parallel programming - PPOPP '93  
need for dynamic load-balancing in the median-finding code on the Connection Machine CM-2.  ...  The median-finding results show the benefit of NESL's dynamic memory allocation and dynamic load balancing on the Connection Machines.  ... 
doi:10.1145/155332.155343 dblp:conf/ppopp/BlellochCHSZ93 fatcat:uixs25wepzcv7geh3x2zqn2bk4

Parallel algorithms for personalized communication and sorting with an experimental study (extended abstract)

David R. Helman, David A. Bader, Joseph JáJá
1996 Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures - SPAA '96  
A fundamental challenge for parallel computing is to obtain high-level, architecture independent, algorithms which execute efficiently on general-purpose parallel machines. With  ...  JtiJ& Practical Parallel Algorithms for Dynamic Data Redistribution, Median Finding, and Selection.  ...  Practical Par- allel Algorithms for Personalized Communication and Integer Sorting.  ... 
doi:10.1145/237502.237558 dblp:conf/spaa/HelmanBJ96 fatcat:jtd27sydkvc7fbtjjegmbvhwma

Comparative Study of Sleep Mode Interleaving and Energy Efficiency Substream Allocation Algorithm
English

V. Esakkimuthu Selvi
2014 International Journal of Computer Trends and Technology  
EESA algorithm reduces the energy consumption for receivers. The EESA algorithm transmits the selected sub-streams in bursts, so energy is saved by the receivers.  ...  Second one is Energy efficiency substream selection algorithm.  ...  Then, construct a dynamic programming table for all quality values within the bounds and find the solution sub streams using backtracking.  ... 
doi:10.14445/22312803/ijctt-v9p129 fatcat:xd7gbryk2jgtnpv3ivsk2sn554

Design and Implementation of a Practical Parallel Delaunay Algorithm

G. E. Blelloch, G. L. Miller, J. C. Hardwick, D. Talmor
1999 Algorithmica  
This paper describes the design and implementation of a practical parallel algorithm for Delaunay triangulation that works well on general distributions.  ...  Although there have been many theoretical parallel algorithms for the problem, and some implementations based on bucketing that work well for uniform distributions, there has been little work on implementations  ...  Finding the Median. Initially a parallel version of quickmedian [29] was used to find the median internal point along the x or y axis.  ... 
doi:10.1007/pl00008262 fatcat:fz4tkkuicnb75b467cmparbccy

Efficient Delaunay Tessellation through K-D Tree Decomposition

Dmitriy Morozov, Tom Peterka
2016 SC16: International Conference for High Performance Computing, Networking, Storage and Analysis  
Because resulting point distributions no longer satisfy the assumptions of existing parallel Delaunay algorithms, we develop a new parallel algorithm that adapts to its input and prove its correctness.  ...  The algorithms for computing these tessellations at scale perform poorly when the input data is unbalanced.  ...  ACKNOWLEDGEMENTS We would like to thank Zarija Lukić for providing the Nyx data, Salman Habib and Katrin Heitmann for the HACC data. We are grateful to Janine Bennett for shepherding this paper.  ... 
doi:10.1109/sc.2016.61 dblp:conf/sc/MorozovP16 fatcat:pkf5njjtpbeyvmivwuuk4vttsa

Robust Massively Parallel Sorting

Michael Axtmann, Peter Sanders
2017 2017 Proceedings of the Ninteenth Workshop on Algorithm Engineering and Experiments (ALENEX)  
Asymptotic analysis at the same time provides performance guarantees and guides the selection and configuration of the algorithms.  ...  We investigate distributed memory parallel sorting algorithms that scale to the largest available machines and are robust with respect to input size and distribution of the input elements.  ...  Special thanks go to SAP AG, Ingo Mueller, and Sebastian Schlag for making their 1-factor algorithm [29] available. This research was partially supported by DFG project SA 933/11-1.  ... 
doi:10.1137/1.9781611974768.7 dblp:conf/alenex/Axtmann017 fatcat:npylsyoyzzblxdltie5ze5phoq

PANDA: Extreme Scale Parallel K-Nearest Neighbor on Distributed Architectures

Md. Mostofa Ali Patwary, Nadathur Rajagopalan Satish, Narayanan Sundaram, Jialin Liu, Peter Sadowski, Evan Racah, Suren Byna, Craig Tull, Wahid Bhimji, Prabhat, Pradeep Dubey
2016 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)  
In this paper, we present parallel and highly optimized kd-tree based KNN algorithms (both construction and querying) suitable for distributed architectures.  ...  Although kd-tree based O( n) algorithms have been proposed for computing KNN, due to its inherent sequentiality, linear algorithms are being used in practice.  ...  Local KNN querying The algorithm for finding the k nearest neighbors from a local kd-tree, T is given as pseudo-code in Algorithm 1.  ... 
doi:10.1109/ipdps.2016.57 dblp:conf/ipps/PatwarySSLSRBTB16 fatcat:uf3a5ibozngntcthepaut7frgi
« Previous Showing results 1 — 15 out of 6,225 results