A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf
.
Filters
Petascale molecular dynamics simulation using the fast multipole method on K computer
2014
Computer Physics Communications
In this paper, we report all-atom simulations of molecular crowding -a result from the full node simulation on the "K computer", which is a 10-PFLOPS supercomputer in Japan. ...
The capability of this machine enables us to perform simulation of crowded cellular environments, which are more realistic compared to conventional MD simulations where proteins are simulated in isolation ...
Acknowledgments This work was partially supported by the Integrated Simulation of Living Matter Project, commissioned by the Ministry of Education, Culture, Sports, Science and Technology, Japan. ...
doi:10.1016/j.cpc.2014.06.004
fatcat:acapkiuimngrrij465nsxd3er4
FFT, FMM, and Multigrid on the Road to Exascale: performance challenges and opportunities
[article]
2018
arXiv
pre-print
FFT, FMM, and multigrid methods are widely used fast and highly scalable solvers for elliptic PDEs. ...
However, emerging large-scale computing systems are introducing challenges in comparison to current petascale computers. ...
Acknowledgments The authors would like to thank Prof. David Keyes (KAUST) for many insightful discussions. ...
arXiv:1810.11883v1
fatcat:hisugmi2zrc53g2hx3suw5hzae
COMPASS, the COMmunity petascale project for accelerator science and simulation, a broad computational accelerator physics initiative
2007
Journal of Physics, Conference Series
COMPASS, the Community Petascale Project for Accelerator Science and Simulation, is a broad, four-office (HEP, NP, BES, ASCR) effort to develop computational tools for the prediction and performance enhancement ...
In SciDAC-2 these tools will be petascale enabled to allow the inclusion of an unprecedented level of physics for detailed prediction. use of the large computing facilities extant and future to the accelerator ...
Near-term plans are to extend the technique to electrons and ions, with parameters relevant to the RHIC-II cooler, to include the effects of magnetic fields, to use a fast multipole method to calculate ...
doi:10.1088/1742-6596/78/1/012009
fatcat:uvqqwx22eberjftssh6u35jdi4
Fast multipole networks
[article]
2020
arXiv
pre-print
Fast multipole networks (FMNs) enable both ends within a unified framework. ...
FMNs can be organized very efficiently in a distributed way from local information and are ideally suited for motion planning using artificial potentials. ...
The FMM's remarkable scaling performance has enabled petascale simulations of turbulence [45] , molecular dynamics [32] , and cosmological dynamics [35] , and will also enable future exascale simulations ...
arXiv:1904.04869v3
fatcat:7lg7goxqjrfxrdi345q6hxojdq
Hierarchical N-body Simulations with Autotuning for Heterogeneous Systems
2012
Computing in science & engineering (Print)
With the current hybridization of treecodes and FMMs, combined with auto-tuning capabilities on heterogeneous architectures, the flexibility of fast N-body methods has been greatly enhanced. ...
These features are a requirement to developing a black-box software library for fast N-body algorithms on heterogeneous systems, which is our immediate goal. ...
Acknowledgements We're grateful for the support from the US National Science Foundation and the Office of Naval Research. Recent grant numbers are NSF OCI-0946441, and ONR award #N00014-11-1-0356. ...
doi:10.1109/mcse.2012.1
fatcat:qhfjkfnvtfde5iguma5b4gb2fm
ATIP/A*CRC Workshop on Accelerator Technologies for High-Performance Computing: Does Asia Lead the Way? Programme Handbook
[article]
2012
Zenodo
Information Program (ATIP) and the Agency for Science, Technology and Research (A*STAR) Computational Resource Centre (A*CRC), this workshop in Singapore focus on the practical aspects of scientific and ...
Some tutorial sessions arranged by vendors will be conducted on the third and fourth day. ...
and Technology is a brand new graduate university on Okinawa, Japan. ...
doi:10.5281/zenodo.3977457
fatcat:v2aftckqinasxk5ugdw27vinpa
A Performance Model for the Communication in Fast Multipole Methods on HPC Platforms
[article]
2014
arXiv
pre-print
The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics, but has recently been extended to a wider range of problems, including ...
In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on inter-node communication. ...
Her research interests include fast algorithms for particle-based simulations, fast algorithms on parallel computers and GPUs, design of parallel numerical algorithms, parallel programming models and performance ...
arXiv:1405.6362v1
fatcat:5x7zvskpl5h6bilnpqg73oq72u
Architectural Constraints to Attain 1 Exaflop/s for Three Scientific Application Classes
2011
2011 IEEE International Parallel & Distributed Processing Symposium
The application classes being considered in this paper areclassical molecular dynamics, cosmological simulations and unstructured grid computations (finite element solvers). ...
The first Teraflop/s computer, the ASCI Red, became operational in 1997, and it took more than 11 years for a Petaflop/s performance machine, the IBM Roadrunner, to appear on the Top500 list. ...
The authors would like to thank Prof. Tom Quinn from the University of Washington for discussions about cosmological simulations. ...
doi:10.1109/ipdps.2011.18
dblp:conf/ipps/BhateleJGWGK11
fatcat:czw7yzjuk5fbzn7fezlfsg7x2e
Some essential techniques for developing efficient petascale applications
2008
Journal of Physics, Conference Series
It will be a substantial challenge to make existing parallel CSE applications run efficiently on them, and even more challenging to design new applications that can effectively leverage the large computational ...
Multiple PetaFLOPS class machines will appear during the coming year, and many multi-PetaFLOPS machines are on the anvil. ...
Instead, they tend to use techniques such as adaptive and dynamic mesh refinements, sophisticated algorithms such as Barnes-Hut or Fast Multipole Method, and are therefore more challenging to parallelize ...
doi:10.1088/1742-6596/125/1/012036
fatcat:i57rn27hjnf7vontusg47p74km
Multimillion Atom Simulations of Nanostructured Materials on Parallel Computers
2000
Progress of Theoretical Physics Supplement
Ten million atom molecular dynamics simulations are performed to determine atomic-level stress distributions in a 54 nm nanopixel on a 0.1 µm silicon substrate. ...
Multiresolution molecular-dynamics approach for multimillion atom simulations has been used to investigate structural properties, mechanical failure in ceramic materials, and atomiclevel stresses in nanoscale ...
Acknowledgements This research has been partially supported by the US DOE, NSF, AFOSR, ARO, NASA, USC-LSU MURI (DARPA and AFOSR), Austrian FWF, and LEQSF. ...
doi:10.1143/ptps.138.175
fatcat:yghgribokbes3npa6yzftd6yxe
Communication Complexity of the Fast Multipole Method and its Algebraic Variants
2014
Supercomputing Frontiers and Innovations
We present a new communication complexity estimate for fast multipole methods on such architectures. ...
A convergence of the mathematical theories of the fast multipole and H-matrix methods has been underway for over a decade. ...
systems that are expected by the end of the decade, and (2) enabling KAUST's scientific and engineering simulation campaigns to exploit today's state-of-the-practice petascale systems. ...
doi:10.14529/jsfi140104
fatcat:s4dd4w2bjzfhlmjpvjujsn7tfy
Tinker-HP: a massively parallel molecular dynamics package for multiscale simulations of large complex systems with advanced point dipole polarizable force fields
2018
Chemical Science
Tinker-HP is massively parallel software dedicated to polarizable molecular dynamics. ...
Acknowledgements This work was made possible thanks to the French state funds managed by the CalSimLab LABEX and the ANR within the Investissements d'Avenir program (reference ANR-11-IDEX-0004-02) and ...
through support of the Direction Générale ...
doi:10.1039/c7sc04531j
pmid:29732110
pmcid:PMC5909332
fatcat:7gur7v4oyvhg3ok77car6sr3hq
Communication Complexity of the Fast Multipole Method and its Algebraic Variants
[article]
2014
arXiv
pre-print
We present a new communication complexity estimate for fast multipole methods on such architectures. ...
A convergence of the mathematical theories of the fast multipole and H-matrix methods has been underway for over a decade. ...
systems that are expected by the end of the decade, and (2) enabling KAUST's scientific and engineering simulation campaigns to exploit today's stateof-the-practice petascale systems. ...
arXiv:1406.1974v1
fatcat:vphxhdgr6fbmzhcrw2uo726moq
A performance model for the communication in fast multipole methods on high-performance computing platforms
2016
The international journal of high performance computing applications
The fast multipole method (FMM) was originally developed for accelerating N -body problems in astrophysics and molecular dynamics, but has recently been extended to a wider range of problems, including ...
We focus on the communication part only; the efficiency of the computational kernels are beyond the scope of the present study but see, e.g., [3] . ...
He joined the King Abdullah University of Science and Technology (KAUST) as a research scientist, where he continued to work on fast multipole methods. ...
doi:10.1177/1094342016634819
fatcat:eplnkqcy2jbwrbc7xqdr4mcajm
Bioexcel Deliverable 1.3 - Roadmap Of Future Hardware And Long-Term Development Plan For Each Pilot Application
2017
Zenodo
Bio-molecular simulation scientists require effective and usable simulation software that runs well on the hardware resources they can access now. ...
Future hardware development will have a significant impact on all areas of scientific computing including the Life Sciences. ...
The fast multipole method (FMM) provides better formal scaling as O(#particles) both for computation and communication (unlike N(log)N for FFT methods). ...
doi:10.5281/zenodo.574605
fatcat:tyevo2n3vbbeto4agkn7uouiiq
« Previous
Showing results 1 — 15 out of 52 results