Filters








22,726 Hits in 6.9 sec

A new deterministic parallel sorting algorithm with an experimental evaluation

David R. Helman, Joseph JáJá, David A. Bader
1998 ACM Journal of Experimental Algorithmics  
We i n troduce a new deterministic parallel sorting algorithm based on the regular sampling approach.  ...  However, unlike our randomized sorting algorithm, the performance and memory requirements of our regular sorting algorithm can be deterministically guaranteed. 1 is a read or write operation.  ...  We a c knowledge the use of the UMIACS 16-node IBM SP-2-TN2, which w as provided by a n IBM Shared University Research a ward and an NSF Academic Research Infrastructure Grant No. CDA9401151.  ... 
doi:10.1145/297096.297128 fatcat:ftdbgmdglzcnrgvjartv55feba

Deterministic Sample Sort For GPUs [article]

Frank Dehne, Hamidreza Zaboli
2010 arXiv   pre-print
We present and evaluate GPU Bucket Sort, a parallel deterministic sample sort algorithm for many-core GPUs. Our method is considerably faster than Thrust Merge (Satish et.al., Proc.  ...  IPDPS 2009), the best comparison-based sorting algorithm for GPUs, and it is as fast as the new randomized sample sort for GPUs by Leischner et.al. (to appear in Proc. IPDPS 2010).  ...  Our experimental evaluation indicates that GPU Bucket Sort is considerably faster than Thrust Merge [14] , the best comparison-based sorting algorithm for GPUs, and it is exactly as fast as the new Randomized  ... 
arXiv:1002.4464v1 fatcat:zjrpreh2szcqdbtd733clf4l4e

Scalejoin: A deterministic, disjoint-parallel and skew-resilient stream join

Vincenzo Gulisano, Yiannis Nikolakopoulos, Marina Papatriantafilou, Philippas Tsigas
2015 2015 IEEE International Conference on Big Data (Big Data)  
In this paper we present ScaleJoin, an algorithmic construction for deterministic and parallel stream joins that guarantees all the above properties, thus filling in a gap in the existing state-of-the  ...  Key to the novelty of ScaleJoin is a new data structure, Scalegate, and its lock-free implementation.  ...  Framework Programme (FP7/2007-2013) through the EXCESS Project (www.excessproject.eu) under grant agreement 611183 and by the Swedish Research Council (Vetenskapsrådet) project "Fine-grain synchronization in parallel  ... 
doi:10.1109/bigdata.2015.7363751 dblp:conf/bigdataconf/GulisanoNPT15 fatcat:lyfum5v6prh4lkzxrbz7ozxavy

ScaleJoin: a Deterministic, Disjoint-Parallel and Skew-Resilient Stream Join

Vincenzo Gulisano, Yiannis Nikolakopoulos, Marina Papatriantafilou, Philippas Tsigas
2016 IEEE Transactions on Big Data  
In this paper we present ScaleJoin, an algorithmic construction for deterministic and parallel stream joins that guarantees all the above properties, thus filling in a gap in the existing state-of-the  ...  Key to the novelty of ScaleJoin is a new data structure, Scalegate, and its lock-free implementation.  ...  Framework Programme (FP7/2007-2013) through the EXCESS Project (www.excessproject.eu) under grant agreement 611183 and by the Swedish Research Council (Vetenskapsrådet) project "Fine-grain synchronization in parallel  ... 
doi:10.1109/tbdata.2016.2624274 fatcat:zgtpwcswefcdfh5gu52kc5l2be

BSP Sorting: An experimental Study [article]

Alexandros V. Gerbessiotis, Constantinos J. Siniolakis
2014 arXiv   pre-print
The deterministic algorithm uses deterministic regular oversampling and parallel sample sorting and is augmented to handle duplicate keys transparently with optimal asymptotic efficiency.  ...  The randomized algorithm is sample-sort based and uses oversampling and the ideas introduced with the deterministic algorithm.  ...  Under the same realistic assumptions as [21] , a new deterministic sorting algorithm is introduced in [22] , and a bound of (1 + (⌊ζ(1 − ζ −1 )⌋((1 − ζ −1 )/2) + o(1))(n lg n/p) and O(gζn p ) + O(L ζ  ... 
arXiv:1408.6729v1 fatcat:goqadgestvcg3leeutsfwwufhy

Efficient techniques for clustering and scheduling onto embedded multiprocessors

V. Kianzad, S.S. Bhattacharyya
2006 IEEE Transactions on Parallel and Distributed Systems  
We evaluate a number of leading clustering and merging algorithms using a set of benchmarks with diverse structures.  ...  We present an experimental setup for comparing the single-step against the two-step scheduling approach.  ...  We present a general framework for the performance comparison of guided random-search algorithms against deterministic algorithms and an experimental setup for the comparison of one-step against two-step  ... 
doi:10.1109/tpds.2006.87 fatcat:kpk5w5cirrbgziy6wdbxtise7u

A two-pass exact algorithm for selection on Parallel Disk Systems

Tian Mi, Sanguthevar Rajasekaran
2013 2013 IEEE Symposium on Computers and Communications (ISCC)  
We have compared our RSS algorithm with two other algorithms in the literature, namely, the Deterministic Sampling Selection and QuickSelect on the Parallel Disks Systems.  ...  The parallel selection has also become an important fundamental operation, especially after parallel databases were introduced.  ...  Rajasekaran, et al., have presented a deterministic algorithm with a run time of on any p-node network, and a randomized algorithm with an expected run time of [18] , where is the time needed for collecting  ... 
doi:10.1109/iscc.2013.6755015 pmid:25374478 pmcid:PMC4217089 dblp:conf/iscc/MiR13 fatcat:zxxoauobrndhpbcb5lm6jt5y7a

Performance of Parallel K-Means Algorithms in Java

Libero Nigro
2022 Algorithms  
This paper describes a novel approach to parallel K-means which, today, is based on commodity multicore machines with shared memory.  ...  K-means is a well-known clustering algorithm often used for its simplicity and potential efficiency. Its properties and limitations have been investigated by many works reported in the literature.  ...  Section 4 describes some experimental results and a performance comparison of the developed solutions, together with an indication of limitations of the approach.  ... 
doi:10.3390/a15040117 fatcat:dpm4luyivjac7lk4vpx5k7rlji

Data-Streaming and Concurrent Data-Object Co-design: Overview and Algorithmic Challenges [chapter]

Vincenzo Gulisano, Yiannis Nikolakopoulos, Marina Papatriantafilou, Philippas Tsigas
2015 Lecture Notes in Computer Science  
suitable for a set of functions and identify new key challenges to improve data-stream processing through co-design with fine-grain efficient synchronization combined with the data exchange.  ...  the new problems in the massive-data research domain, with applications in e.g. cyberphysical systems.  ...  A basic requirement for an algorithmic implementation of the ScaleGate is to maintain items in a sorted manner.  ... 
doi:10.1007/978-3-319-24024-4_15 fatcat:mz75ythl4bfwvlyj3erhruw7fe

An optimization approach for load balancing in parallel link discovery

Mohamed Ahmed Sherif, Axel-Cyrille Ngonga Ngomo
2015 Proceedings of the 11th International Conference on Semantic Systems - SEMANTICS '15  
We combine this approach with the Orchid algorithm for geo-spatial linking and evaluate it on real and artificial datasets.  ...  In this paper, we thus present a novel load balancing technique for link discovery on parallel hardware based on particle-swarm optimization.  ...  Parallel Orchid We began by evaluating the speedup gained by using parallel implementations of Orchid algorithm.  ... 
doi:10.1145/2814864.2814872 dblp:conf/i-semantics/SherifN15 fatcat:7bk3wmb7ubfw3njbds6r2w7tym

GPGPU-Compatible Archive Based Stochastic Ranking Evolutionary Algorithm (G-ASREA) for Multi-Objective Optimization [chapter]

Deepak Sharma, Pierre Collet
2010 Parallel Problem Solving from Nature, PPSN XI  
In this paper, a GPGPU (general purpose graphics processing unit) compatible Archived based Stochastic Ranking Evolutionary Algorithm (G-ASREA) is proposed, that ranks the population with respect to an  ...  Experiments compare G-ASREA with a CPU version of ASREA and NSGA-II on ZDT test functions for a wide range of population sizes.  ...  Description of the Algorithm ASREA is an archive-based MOEA that starts with evaluating a random initial population (ini pop).  ... 
doi:10.1007/978-3-642-15871-1_12 dblp:conf/ppsn/SharmaC10 fatcat:fgkqfu4vyvdczpkx6sry3sj4ie

Reproducible Efficient Parallel SAT Solving [chapter]

Hidetomo Nabeshima, Katsumi Inoue
2020 Lecture Notes in Computer Science  
In this paper, we propose a new reproducible and efficient parallel SAT solving algorithm.  ...  The experimental results show that our reproducible parallel SAT solver has comparable performance to non-deterministic parallel SAT solvers even in a many-core environment.  ...  Experimental Results We have developed a new deterministic parallel SAT solver called ManyGlucose based on Glucose-syrup 4.1, which implements the delayed clause exchange and three types of periods (one  ... 
doi:10.1007/978-3-030-51825-7_10 fatcat:tmh6hoyqsngc5kuaqlznuctfry

Page 1300 of Mathematical Reviews Vol. , Issue 2003B [page]

2003 Mathematical Reviews  
In this paper, a new parallel algorithm for computing path expressions, named parallel cascade semijoin (PCSJ), is proposed.  ...  ; Shenyang) ; Yu, Ge (PRC-SHEN-IIS; Shenyang) Performance evaluation of a parallel cascade semijoin algorithm for computing path expressions in object database systems.  ... 

Deterministic galois

Donald Nguyen, Andrew Lenharth, Keshav Pingali
2014 Proceedings of the 19th international conference on Architectural support for programming languages and operating systems - ASPLOS '14  
Evaluation of this approach on a collection of benchmarks from the PARSEC, PBBS, and Lonestar suites shows that it delivers deterministic execution with substantially less overhead than other systems in  ...  To remedy this, we propose a new approach, based on the Galois programming model, in which (i) the programming model permits the writing of non-deterministic programs and (ii) the runtime system executes  ...  To evaluate the quality of our deterministic programs, we compare their performance with handwritten deterministic parallel programs from the PBBS benchmark suite [7] .  ... 
doi:10.1145/2541940.2541964 dblp:conf/asplos/NguyenLP14 fatcat:gi46n67iqbeyxb5iyhqoofpb4y

Crowd Database Operators [chapter]

Beth Trushkowsky
2016 Encyclopedia of Database Systems  
They are alternate implementations of traditional relational operators, like sort or select, for use in hybrid human/machine query processing systems like crowd database systems.  ...  One strategy to achieve a crowd-based sort is to replace the comparator method used in a traditional sorting algorithm with a method that asks people to evaluate the comparison, in a comparison task, to  ...  They explore both a deterministic setting, in which humans do not make mistakes, as well as an uncertain setting in which each item may need multiple evaluations to deduce correctness.  ... 
doi:10.1007/978-1-4899-7993-3_80660-1 fatcat:ztjfybgutrfhnj3sjwk73ngt2i
« Previous Showing results 1 — 15 out of 22,726 results