195,521 Hits in 6.0 sec

A massively parallel algorithm for three-dimensional device simulation

D.M. Webber, E. Tomacruz, R. Guerrieri, T. Toyabe, A. Sangiovanni-Vincentelli
1991 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
This paper explores the issue of whether massively parallel computers are suitable for this problem.  ...  Results are demonstrated on a wide variety of devices and mesh sizes.  ...  ACKNOWLEDGMENT The authors wish to thank Alan Torres, Eugene Loh, and Terry Dontje of Thinking Machines Corporation for the use of the Los Alamos Connection Machines.  ... 
doi:10.1109/43.85767 fatcat:tntxgt2oivfibjolyikh3qiqia

GPU-based N-1 Static Security Analysis Algorithm with Preconditioned Conjugate Gradient Method

Meng Fu, Gan Zhou, Jiahao Zhao, Yanjun Feng, Huan He, Kai Liang
2020 IEEE Access  
Second, it proposes a GPU-based batch-PCG solver, which packages a massive number of PCG subtasks into a large-scale problem to achieve a higher degree of parallelism and better coalesced memory accesses  ...  Case studies on a practical 10828-bus system show that the GPU-based N-1 SSA algorithm with the batch-PCG solver is 4.90 times faster than a sequential algorithm on an 8-core CPU.  ...  BATCH-PCG SOLVER FOR MASSIVE NUMBERS OF SLSES 1) OVERALL DESIGN Focusing on the demand for solving massive numbers of SLSEs from the SSA problem, this section proposes a novel batch-PCG solver to solve  ... 
doi:10.1109/access.2020.3004713 fatcat:k6wbjj6elngvfi2r376fudpibq

Massively parallel computation using a splitting-up operator method for three-dimensional device simulation

S. Odanaka, T. Nogi
1995 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
In large-scale simulations of greater than 100000 grid nodes, the high parallel efficiency level over 90% can be achieved using a new-type massively parallel computer: ADENART with up to 256 processors  ...  A splitting-up operator method is proposed for incomplete factorization of sparse matrices arising from semiconductor device equations, suitable for parallel computations.  ...  ACKNOWLEDGMENT The authors would like to thank Dr. T. Takemoto, H. Ezaki, Y. Mano, Y. Terui, and Dr. H. Kadota for their encouragement through this work. The authors also wish to thank A.  ... 
doi:10.1109/43.391730 fatcat:glwx4rk3srfmrmedfgswbdzqva

A Note on Massively Parallel Implementation of FETI for the Solution of Contact Problems

David Horak, Vaclav Hapla, Jakub Kruzik, Radim Sojka, Martin Cermak, Jiri Tomcala, Marek Pecha, Zdenek Dostal
2017 Advances in Electrical and Electronic Engineering  
The paper deals with a solution of large multibody contact problems using massively parallel computers and domain decomposition methods.  ...  The paper describes the ingredients essential for efficient massively parallel implementation that increases the parallel scalability beyond the limit mentioned above.  ...  Acknowledgment The authors acknowledge the support of the Czech Science Foundation (GACR) project no. 15-18274S.  ... 
doi:10.15598/aeee.v15i2.2321 fatcat:oaz7qbr24vgjfo4jt2eprdyuiu

Toward Exascale Computing Systems: An Energy Efficient Massive Parallel Computational Model

Muhammad Usman, Fathy Alburaei, Aiiad Ahmad, Abdullah
2018 International Journal of Advanced Computer Science and Applications  
Massive parallelism is one of these challenges, which requires a novel energy-efficient parallel programming (PP) model for providing the massively parallel performance.  ...  The proposed model is considered an initial and leading model for obtaining massively parallel performance in an Exascale computing system.  ...  for exascale computing systems through massive parallelism.  ... 
doi:10.14569/ijacsa.2018.090217 fatcat:u3yli4s5v5cgbm5l3ck7cgw42a

Hemispherical Projection for Progressive Radiosity Calculation on Massively Parallel Architectures [article]

C Renaud, F Bricout, E Lepretre
1993 Eurographics Workshop on Graphics Hardware  
This paper describes a massively parallel implementation of the progressive radiosityalgorithm.  ...  Our algorithm is based on an hemispherical projection approach, which provides an accurate from factor approximation.  ...  A massively parallel approach The projection of a patch onto a plane divided into several sampling elements is implPcitly a massively parallel operation.  ... 
doi:10.2312/eggh/eggh93/081-092 dblp:conf/egh/RenaudBL93 fatcat:nkfknivq3bdhfkk2ywo5qolkxi

Massively parallel factorizations of polynomials with many non-commuting variables

Jean-Christophe Hohl
1997 Theoretical Computer Science  
It allows full use of the massively parallel programmation of the CM200.  ...  We give here an effective massively parallel algorithm allowing factorization of polynomials with non-commuting variables and integer coefficients.  ...  Indeed, in the first case, we apply one parallel Euclid algorithm and in the second case p -1. The GCD processing time grows with the degree of the searched factor.  ... 
doi:10.1016/s0304-3975(96)00108-9 fatcat:gzhrn2mt4fexzfj3fv5gjkul4i

Dispelling the Myths of Parallel Computing

Patrick H. Madden
2013 IEEE design & test  
Editors' notes: Professor Patrick Madden presents his (agnostic) take on parallel computing.  ...  We believe that having an agnostic view allows us to focus on the deficiencies of the systems we are building, so we can improve on them.  ...  One might expect that massive parallelism would allow for much faster path computations; in reality, the scalable parallel solution is far slower.  ... 
doi:10.1109/mdt.2012.2230391 fatcat:32ugd2vfhfhkvp62lxmfkktqsq

A Fast Algorithm for Massively Parallel, Long-Term, Simulation of Complex Molecular Dynamics Systems [chapter]

Amir Fijany, Tahir Çağın, Andres Jaramillo-Botero, William Goddard
1998 Advances in Parallel Computing  
In order to achieve such a significant improvement in the computational efficiency, in addition to massively parallel platforms, new algorithms are needed to allow efficient long-term MD simulation.  ...  MD simulation of very large systems are currently being performed by using massively parallel architectures.  ...  A In addition to the optimal computational cost, the CMM has been also shown to be very e cient for massively parallel implementation rnl The simplest and most widely used MD methods employ Cartesian coordinates  ... 
doi:10.1016/s0927-5452(98)80065-8 fatcat:req4zwgepzeuhka3itgzvignbe

A Secured Large Heterogeneous HPC Cluster System using Massive Parallel Programming Model with Accelerated GPUs

Khalid Alsubhi
2020 International Journal of Advanced Computer Science and Applications  
that at what level [9], the software framework is adoptable to achieve massive parallelism for Exascale computing systems.  ...  This study proposes a non-blocking, overlapping and GPU computation based tri-hybird model (OpenMP, CUDA and MPI) model that provide a massive parallelism through different granularity levels.  ...  through on-chip parallelism.  ... 
doi:10.14569/ijacsa.2020.0110549 fatcat:52wvtjts55ahzi3iwp4jgjrd2a

Scalable Massively Parallel Artificial Neural Networks

Lyle N. Long, Ankur Gupta
2008 Journal of Aerospace Computing Information and Communication  
An object-oriented, massively-parallel ANN (Artificial Neural Network) software package SPANN (Scalable Parallel Artificial Neural Network) has been developed and is described here.  ...  MPI was used to parallelize the C++ code. Only the neurons on the edges of the domains were involved in communication, in order to reduce the communication costs and maintain scalability.  ...  Acknowledgments The authors would like to thank the NASA Advanced Supercomputing Division (NAS) for the use of the Columbia supercomputer [28].  ... 
doi:10.2514/1.31026 fatcat:2rbtisn6mvhwpjr3y3zqn3xyfa

A Massively Parallel Algorithm for the Three-Dimensional Navier-Stokes-Boussinesq Simulations of the Atmospheric Phenomena [chapter]

Maciej Paszyński, Leszek Siwik, Krzysztof Podsiadło, Peter Minev
2020 Lecture Notes in Computer Science  
The computation of the one time step takes 3 min on a Linux cluster.  ...  The computational cost is linear O(N ) over each sub-domain, and near to O(N/c) in parallel over 1024 processors, where N is the number of unknowns and c is the number of cores.  ...  Thus, if well parallelized, the parallel factorization cost is near to O(N/c) in every time step, where N is the number of unknowns and c is the number of cores.  ... 
doi:10.1007/978-3-030-50371-0_8 fatcat:oa5wsntsbvbwdbjgx6ybg3zqwm

Fast massively parallel progressive radiosity on the MP-1

Christophe Renaud, François Rousselle
1997 Parallel Computing  
The aim of this paper is to present a method for the parallelisation of the progressive refinement radiosity algorithm on a massively parallel SIMD machine.  ...  The parallel scheme we propose uses a disk projection area for form factors estimate and decreases dramatically the computation times. PI1 SOl67-Sl91(97)00033-1 !m C. Renaud, .  ...  A massively parallel approach Our goal is to develop an efficient SIMD implementation of the disk projection algorithm as the heart of a massively parallel progressive radiosity approach.  ... 
doi:10.1016/s0167-8191(97)00033-1 fatcat:tjjknwzoo5gi7jgt6upwb76oj4

Page 1567 of Mathematical Reviews Vol. , Issue 93c [page]

1993 Mathematical Reviews  
We show that it is possible to use the subspace method with a good throughput or speed-up on massively parallel architectures like the CM2.  ...  This method is the most frequently used one for very large eigenproblems and it is also well adapted to massively parallel architectures.  ... 

Massively Parallel Multigrid for the Simulation of Skin Permeation on Anisotropic Tetrakaidecahedral Cell Geometries [chapter]

Sebastian Reiter, Arne Nägel, Andreas Vogel, Gabriel Wittum
2018 High Performance Computing in Science and Engineering ' 17  
Furthermore, we show how those meshes can be used in scalable massively parallel multigrid based computations of permeation processes in the skin.  ...  Numerical simulation based on mathematical models is an important pillar for enhancing the understanding of permeation processes in the skin.  ...  Acknowledgements This work has been supported by the DFG in the German Priority Programme 1648-Software for Exascale Computing in the project Exasolvers (WI 1037/24-2) and by the German Ministry of Economics  ... 
doi:10.1007/978-3-319-68394-2_27 fatcat:7jqj5rmhivhh5gue4wgiy5icpe
« Previous Showing results 1 — 15 out of 195,521 results