Filters








109,389 Hits in 5.5 sec

Cost Optimization Using Hybrid Evolutionary Algorithm in Cloud Computing

B. Kavitha, P. Varalakshmi
2015 Research Journal of Applied Sciences Engineering and Technology  
The main aim of this research is to design the hybrid evolutionary algorithm for minimizing multiple problems of dynamic resource allocation in cloud computing.  ...  The resource allocation is one of the big problems in the distributed systems when the client wants to decrease the cost for the resource allocation for their task.  ...  A velocity matrix is generated randomly for the initialization matrix and the fitness function is evaluated.  ... 
doi:10.19026/rjaset.10.2428 fatcat:vfugebra5nb6jakkcys765kmq4

LINVIEW

Milos Nikolic, Mohammed ElSeidy, Christoph Koch
2014 Proceedings of the 2014 ACM SIGMOD international conference on Management of data - SIGMOD '14  
We develop a framework, called LINVIEW, for capturing deltas of linear algebra programs and understanding their computational cost.  ...  We develop techniques based on matrix factorizations to contain such epidemics of change.  ...  Table 2 shows the time complexity of hybrid evaluation of the Ti+1 = A Ti + B computation expressed in different iterative models for rank-1 updates to A.  ... 
doi:10.1145/2588555.2610519 dblp:conf/sigmod/NikolicEK14 fatcat:irczeo5myzd4rmfotm4n5jciei

Scaling of ab-initio nuclear physics calculations on multicore computer architectures

Pieter Maris, Masha Sosonkina, James P. Vary, Esmond Ng, Chao Yang
2010 Procedia Computer Science  
For large core counts (typically 5,000 and above), the hybrid version is more efficient than pure MPI.  ...  We discuss the scaling behavior of a state-of-the-art Configuration Interaction code for nuclear physics on modern multicore computer architectures.  ...  . • Lanczos iterations Once we have constructed the matrix (and stored in memory, using CSC format, distributed over all processors), we solve for the lowest eigenvalues using an iterative Lanczos algorithm  ... 
doi:10.1016/j.procs.2010.04.012 fatcat:fbmbg6wzmndttkqnjz3po4d5iq

An iterative algorithm for color space optimization on image segmentation

Mourad Moussa
2021 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
This paper proposes, a novel hybrid color component (HCC) issued from amounts number of color space with iterative manner, in fact traditional images obtained by RGB sensor weren't the effective way in  ...  image processing applications, for this purpose we have propose a supervised algorithm to substitute RGB level by hybrid and suitable color space at the aim to make well representation of the handled  ...  Finally, to evaluate the effectiveness of our proposed approach for hybrid chromatic level section by iterative algorithm, we have used a non-parametric segmentation technique based on Cauchy distribution  ... 
doi:10.12928/telkomnika.v19i1.15122 fatcat:fjnu72wnkjbn5dbzk4izydz5ca

Dynamic Load Balancing of Matrix-Vector Multiplications on Roadrunner Compute Nodes [chapter]

José Carlos Sancho, Darren J. Kerbyson
2009 Lecture Notes in Computer Science  
To achieve this we have designed a new load bal ancing a' lgorithm , which is optimized for the Roadrunner compute nodes, to dynamically distribute computation and associated data between the host and  ...  Results are presented using this approach for sparse and dense matrix-vector multiplications that show load-balancing can improve performance by up to 24% over solely using the accelerators.  ...  Evaluation vVe evaluate our load-balancing technique on a Roadrunner compute node as described in Section 2.  ... 
doi:10.1007/978-3-642-03869-3_19 fatcat:kltkzaj7izcodnx6kbewcztwcy

Designing parallel loop self-scheduling schemes using the hybrid MPI and OpenMP programming model for multi-core grid systems

Chao-Chin Wu, Chao-Tung Yang, Kuan-Chou Lai, Po-Hsun Chiu
2010 Journal of Supercomputing  
Although there have been many studies proposed to employ the hybrid MPI and OpenMP programming model to exploit different levels of parallelism for a distributed system with multi-core computers, none  ...  Therefore, this paper investigates how to employ the hybrid MPI and OpenMP model to design a parallel loop selfscheduling scheme adapted to the multi-core architecture for emerging grid systems.  ...  Acknowledgements The authors would like to thank the National Science Council, Taiwan, for financially supporting this research under Contract No. NSC98-2221-E-018-008-MY2 and NSC98-2220-E-029-004.  ... 
doi:10.1007/s11227-010-0418-y fatcat:3phn3gjn7zgkzbv2qo4zwzdpny

A hybrid iterative method for symmetric indefinite linear systems

D. Calvetti, L. Reichel
1998 Journal of Computational and Applied Mathematics  
This paper presents a new hybrid iterative method for the solution of linear systems of equations with a symmetric indefinite matrix.  ...  These intervals are used to compute suitable iteration parameters for Richardson iteration. We also discuss when to switch between the methods.  ...  The number of matrix-vector product evaluations with the matrix A for the hybrid and CR methods are almost the same.  ... 
doi:10.1016/s0377-0427(98)00048-x fatcat:djhkrzlulbb5jfhqhkpq2ch7ci

PMV: Pre-partitioned Generalized Matrix-Vector Multiplication for Scalable Graph Mining [article]

Chiwan Park, Ha-Myung Park, Minji Yoon, U Kang
2017 arXiv   pre-print
In this paper, we propose PMV (Pre-partitioned generalized Matrix-Vector multiplication), a scalable distributed graph mining method based on generalized matrix-vector multiplication on distributed systems  ...  due to insufficient memory space or the lack of consideration for I/O costs.  ...  PMV vertical has an expected I/O cost C per iteration: en, PMV hybrid executes PMV horizontal for the dense area and PMV vertical for the sparse area.Figure 4dillustrates PMV hybrid on 3 × 3 matrix blocks  ... 
arXiv:1709.09099v1 fatcat:tlqmq47jfbhnzi7i7fpr64jecm

Solving Matrix Equations on Multi-Core and Many-Core Architectures

Peter Benner, Pablo Ezzatti, Hermann Mena, Enrique Quintana-Ortí, Alfredo Remón
2013 Algorithms  
Our experimental results show that this class of hardware provides sufficient computational power to tackle large-scale problems, which only a few years ago would have required a cluster of computers.  ...  We address the numerical solution of Lyapunov, algebraic and differential Riccati equations, via the matrix sign function, on platforms equipped with general-purpose multicore processors and, optionally  ...  Platform Kepler is employed to evaluate the multicore and hybrid CPU-GPU kernels, while the multi-GPU kernels are evaluated in S2050.  ... 
doi:10.3390/a6040857 fatcat:s4gainufkvb53ljdiou5gzwroy

PARALLEL MOM-PO METHOD WITH OUT-OF-CORE TECHNIQUE FOR ANALYSIS OF COMPLEX ARRAYS ON ELECTRICALLY LARGE PLATFORMS

Xun-Wang Zhao, Yu Zhang, Hong-Wei Zhang, Daniel Garcia Donoro, Sio-Weng Ting, Tapan Kumar Sarkar, Chang-Hong Liang
2010 Electromagnetic Waves  
The block-partitioned scheme for the large dense MoM matrix combined with the process-cyclic scheme for the PO discretized triangles is designed to achieve excellent load balance and high parallel efficiency  ...  A Message Passing Interface (MPI) parallel implementation of a hybrid solver that combines the Method of Moments (MoM) with higher order basis functions and Physical Optics (PO) has been successfully used  ...  There is an advantage in using the polynomial basis functions because the intermediate results obtained in evaluating the elements of the impedance matrix for lower order can be used in the computation  ... 
doi:10.2528/pier10072108 fatcat:qiverkew5va4xovoklju4tizpu

Enabling Next-Generation Parallel Circuit Simulation with Trilinos [chapter]

Chris Baker, Erik Boman, Mike Heroux, Eric Keiter, Siva Rajamanickam, Rich Schiek, Heidi Thornquist
2012 Lecture Notes in Computer Science  
Fast-SPICE tools use event-driven simulation techniques and lookup tables for precomputed device evaluations, while hierarchical simulators use circuit-level partitioning algorithms [4, 5] and more efficient  ...  Given the importance of this simulation tool for circuit design verification, many attempts have been made to allow for faster, larger-scale circuit simulation.  ...  Given that Xyce uses Epetra by default, it requires no code modifications to evaluate these hybrid (MPI with OpenMP) linear algebra computations.  ... 
doi:10.1007/978-3-642-29737-3_36 fatcat:hrkojy2vnrfndnywuumhh376xu

An efficient hybrid distributed document clustering algorithm
English

E Judith J, Jayakumari J
2015 Scientific Research and Essays  
framework for distributed computation.  ...  So there is a need for distributed document clustering algorithms to cluster documents using distributed resources.  ...  For experimental evaluation, the dimensions were increased from 50, 100, 150, 200, 250, and 300. The algorithm is repeated for at least about 50 iterations.  ... 
doi:10.5897/sre2014.6107 fatcat:7mou7y4ylvhczi243ld6gbeouu

DE/PSO-aided hybrid linear detectors for MIMO-OFDM systems under correlated arrays

Rafael Masashi Fukuda, David William Marques Guerra, Ricardo Tadashi Kobayashi, Taufik Abrão
2018 Transactions on Emerging Telecommunications Technologies  
The influence of the initial point in the performance improvement and complexity reduction is evaluated numerically.  ...  Hybrid linear-heuristic detectors under different initial solutions provided by linear detectors are considered, namely differential evolution (DE) and particle swarm optimization (PSO).  ...  for conventional algorithms I hyb : # iterations for the hybrid algorithm VI.  ... 
doi:10.1002/ett.3495 fatcat:qjc3djwrpzb5je55dhoqui6cme

Zeroth-order covariance matrix adaptation evolution strategy for single objective bound constrained numerical optimization competition

Yue Ning, Daohong Jian, Hua Wu, Jun Zhou
2022 Proceedings of the Genetic and Evolutionary Computation Conference Companion  
The paper represents a competition entry for the competition on bound constrained single objective numerical optimization at The Genetic and Evolutionary Computation Conference (GECCO) 2022[2] by a hybrid  ...  algorithm named Zeroth-Order Covariance Matrix Adaptation Evolution Strategy (ZO-CMAES).  ...  At the same time, the local solutions can be used as extended information to calculate mean value and covariance matrix for next iteration of CMAES.  ... 
doi:10.1145/3520304.3534053 fatcat:rv62shl3b5f3to3cwdhevc4xqm

Matrix Information Geometry for Signal Detection via Hybrid MPI/OpenMP

Sheng Feng, Xiaoqiang Hua, Yongxian Wang, Qiang Lan, Xiaoqian Zhu
2019 Entropy  
To address these problems, in this paper, a high-performance computing (HPC)-based MIGSD method is proposed, which is implemented using the hybrid message passing interface (MPI) and open multiple processing  ...  matrix.  ...  MPI is the standard for parallel programming in distributed storage architecture computers [33] .  ... 
doi:10.3390/e21121184 fatcat:yeqy2335mne4tih433iqz7w5ym
« Previous Showing results 1 — 15 out of 109,389 results