14,549 Hits in 4.0 sec

Comparative Study: MD Simulation with different Load Balancing Technique on Heterogeneous Environment

Jitesh M., Sudershan Deshmukh
2016 International Journal of Computer Applications  
MD simulation are used for deeper understating of fluid flows, chemical reaction, and other phenomena due to molecular interaction.  ...  Authors discuss several important issues in porting a large molecular dynamics code for use on parallel hybrid machines.  ...  They provides algorithm for efficient short range force calculation on hybrid high performance machines and provide approach for dynamic load balancing of work between CPU and accelerator cores and provide  ... 
doi:10.5120/ijca2016908137 fatcat:3katg4x3znd6tosdsfob2xzecm

Optimizing molecular dynamics simulations with product lines

Rui C. Silva, João L. Sobral
2011 Proceedings of the 5th Workshop on Variability Modeling of Software-Intensive Systems - VaMoS '11  
Developed features encapsulate common optimization methods in molecular dynamics simulations and target platform mappings.  ...  This paper presents a case study of using product-lines to address the variability of optimization methods and target platform mappings in high-performance molecular dynamics simulations.  ...  One of most popular molecular dynamics packages, GROMACS, aims to provide high performance on both a single (multi-core) machine and on clusters of machines.  ... 
doi:10.1145/1944892.1944911 dblp:conf/vamos/SilvaS11 fatcat:iaiakwczxbahpejomeivx4jzae

Hybrid Message-Passing and Shared-Memory Programming in a Molecular Dynamics Application On Multicore Clusters

Martin J. Chorley, David W. Walker, Martyn F. Guest, Jack Dongarra, Bernard Tourancheau
2009 The international journal of high performance computing applications  
A molecular dynamics application has been parallelized using both MPI and hybrid MPI/OpenMP programming models.  ...  Hybrid programming, whereby shared memory and message passing programming techniques are combined within a single parallel application, has often been discussed as a method for increasing code performance  ...  Hybrid Version The hybrid version of the Molecular Dynamics code used in this paper was created by adding OpenMP parallelization on top of the original MPI parallel code.  ... 
doi:10.1177/1094342009106188 fatcat:n7b3rvelknglzmmg6fn7l572vq

Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters

Martin J. Chorley, David W. Walker
2010 Journal of Computational Science  
DL POLY, a large scale Molecular Dynamics application programmed using message passing programming, has been modified to add a layer of shared memory threading and the performance analysed on two multi-core  ...  On larger core counts the hybrid model performs better than pure MPI, with reduced communication time decreasing the overall runtime.  ...  The previous work with a simpler molecular dynamics code did not show any benefit to the hybrid model on an Infiniband connection; benefits were only seen on slower interconnects.  ... 
doi:10.1016/j.jocs.2010.05.001 fatcat:ka5i325ekbgzdiftveuas4e4pi

Molecular Dynamics on FPGA Based Accelerated Processing Units

Mihaela Maliţa, David Mihǎiţǎ, Gheorghe M. Ştefan, N. Mastorakis, V. Mladenov, A. Bulucea
2017 MATEC Web of Conferences  
One of the main problems in providing the amount of computation requested by the Molecular Dynamic domain is to offer an appropriate architectural environment for solving all the aspects of the intense  ...  The Martini water example, running on a cycle accurate simulator, is used to evaluate the speed-up and the energy.  ...  We selected, for investigating how the Molecular Dynamics can be accelerated using hybrid computation, the Gromacs 1 system whose main idea is to limit the interactions of each particle p i to a small  ... 
doi:10.1051/matecconf/201712504012 fatcat:oncbo2qpifftzhthnswplh32ru

Impact of Kernel-Assisted MPI Communication over Scientific Applications: CPMD and FFTW [chapter]

Teng Ma, Aurelien Bouteiller, George Bosilca, Jack J. Dongarra
2011 Lecture Notes in Computer Science  
This paper investigates the impact of kernel-assisted MPI communication, over two scientific applications: 1) Car-Parrinello molecular dynamics(CPMD), a chemical molecular dynamics application, and 2)  ...  Our experiments indicate that the quality of the collective communication implementation on a specific machine plays a critical role on the overall application performance.  ...  Applications Car-Parrinello Molecular Dynamics(CPMD) is a plane wave/pseudo-potential implementation of density functional theory, particularly designed for ab-initio molecular dynamic [3] .  ... 
doi:10.1007/978-3-642-24449-0_28 fatcat:bnkvbrne4jebram52epyspqhre

A hybrid algorithm for parallel molecular dynamics simulations

Chris M. Mangiardi, R. Meyer
2017 Computer Physics Communications  
This article describes algorithms for the hybrid parallelization and SIMD vectorization of molecular dynamics simulations with short-range forces.  ...  Results are shown that were obtained on multi-core systems with Sandy Bridge and Haswell processors as well as systems with Xeon Phi many-core processors.  ...  On shared-memory systems, molecular dynamics simulations can also be parallelized using thread-based parallel APIs like OpenMP or Threading Building Blocks.  ... 
doi:10.1016/j.cpc.2017.05.020 fatcat:3nu6fwylhfftxc5q33qmeq7ily

Data I/O Optimization in GROMACS Using the Global Arrays Toolkit

Valentin Pavlov, Peicho Petkov
2012 Zenodo  
In MPI multiprocessing environments, data I/O in the GROMACS molecular dynamics package is handled by the master node.  ...  Our results indicate that the approach works and we present the simulation of a large bio-molecular system (lignocellulose) on an IBM Blue Gene/P machine.  ...  Jeremy Smith from the Centre for Molecular Biophysics at the Oak Ridge National Laboratory for providing the lignocellulose data file.  ... 
doi:10.5281/zenodo.6241896 fatcat:ll3svx4d6vabrpgya3gbindwym

Multicore Challenges and Benefits for High Performance Scientific Computing

Ida M.B. Nielsen, Curtis L. Janssen
2008 Scientific Programming  
We will illustrate these ideas with a hybrid distributed memory matrix multiply and a quantum chemistry algorithm for energy computation using Møller–Plesset perturbation theory.  ...  We will here discuss the architecture of parallel computers constructed from many multicore chips as well as techniques for managing the complexity of programming such computers, including the hybrid message-passing  ...  The system memory typically employs Dynamic Random Access Memory (DRAM) technology, which is substantially slower than the memory cache.  ... 
doi:10.1155/2008/450818 fatcat:iiybzql5jbegnh3mfdyuisezdq


2006 International Journal of Modern Physics C  
We demonstrate weak and strong scaling of our classical molecular dynamics code SPaSM on Livermore's BlueGene/L architecture containing 131 072 IBM PowerPC440 processors.  ...  As computational power is increasing, molecular dynamics simulations are becoming more important in materials science, chemistry, physics, and other fields of science.  ...  Evolution of the literature fraction of MD related publications (i.e., molecular dynamics is a keyword or in the abstract).  ... 
doi:10.1142/s0129183106010182 fatcat:osjiz7epsngftf46ru2272p2hi

Acceleration of an Asynchronous Message Driven Programming Paradigm on IBM Blue Gene/Q

Sameer Kumar, Yanhua Sun, Laximant V. Kale
2013 2013 IEEE 27th International Symposium on Parallel and Distributed Processing  
We demonstrate the benefits of our techniques via two benchmarks, 3D Fast Fourier Transform, and the molecular dynamics application NAMD.  ...  IBM Blue Gene/Q is the next generation Blue Gene machine that can scale to tens of Peta Flops with 16 cores and 64 hardware threads per node.  ...  This work was supported in part by a NIH Grant PHS 5 P41 RR05969-04 for Molecular Dynamics.  ... 
doi:10.1109/ipdps.2013.83 dblp:conf/ipps/KumarSK13 fatcat:fgndfvqhtvc4hkgqa2iuzihlhm

A Parallel Iterative Method for Computing Molecular Absorption Spectra [article]

Peter Koval, Dietrich Foerster, Olivier Coulaud
2010 arXiv   pre-print
The implementation of our method uses hybrid MPI and OpenMP parallelization in which load balancing and memory access are optimized.  ...  To validate our approach and to establish benchmarks, we compute spectra of large molecules on various types of parallel machines.  ...  We acknowledge useful correspondence on the SIESTA code by Daniel Sanchez-Portal (DIPC, San Sebastian) and also by Andrei Postnikov (Verlaine University, Metz).  ... 
arXiv:1005.5340v1 fatcat:pbgbudva3ve55j3qpfroupcnpq

Parallel atomistic simulations

Grant S. Heffelfinger
2000 Computer Physics Communications  
Others have employed the Ewald sum with replicated data in the NPT ensemble on a shared memory machine and workstation clusters [37] .  ...  Because this approach is essentially a hybridization of Monte Carlo and molecular dynamics simulation methods, the parallel algorithm developed for the method combined spatial decomposition molecular dynamics  ... 
doi:10.1016/s0010-4655(00)00050-3 fatcat:kj2ce3cjzvgf5khzk4t3qqyz7m

A Hybrid Imperative and Functional Molecular Mechanics Application

Thomas Deboni, John Feo, Doug Peters
1996 Scientific Programming  
Imperative programs have been written that attempt this on shared and distributed memory machines.  ...  the resulting hybrid code.  ...  Merely reordering the operations in a molecular dynamics computation can affect the results, and imperative language compilers on different machines will almost certainly emit different operation sequences  ... 
doi:10.1155/1996/915618 fatcat:sqs436sv3nfnzo4iysqza3scim

Early experiences scaling VMD molecular visualization and analysis jobs on blue waters

John E. Stone, Barry Isralewitz, Klaus Schulten
2013 2013 Extreme Scaling Workshop (xsw 2013)  
We report ongoing progress on porting, tuning, and scaling up the popular molecular visualization and analysis program VMD on the NSF Blue Waters petascale supercomputer.  ...  Petascale molecular dynamics simulations provide a powerful tool for probing the dynamics of cellular processes at atomic and nanosecond resolution not achievable by experimental methods alone.  ...  The authors wish to thank NCSA, NVIDIA, and Cray for providing system software enabling GPU-accelerated OpenGL rasterization on the Blue Waters XK7 nodes, per our requests.  ... 
doi:10.1109/xsw.2013.10 fatcat:czjno62d5ngb3dnmapwqq5yk6q
« Previous Showing results 1 — 15 out of 14,549 results