23 Hits in 6.0 sec

Petascale turbulence simulation using a highly parallel fast multipole method on GPUs

Rio Yokota, L.A. Barba, Tetsu Narumi, Kenji Yasuoka
2013 Computer Physics Communications  
The simulations use a vortex particle method to solve the Navier-Stokes equations, with a highly parallel fast multipole method (FMM) as numerical engine, and match the current record in mesh size for  ...  This paper reports large-scale direct numerical simulations of homogeneous-isotropic fluid turbulence, achieving sustained performance of 1.08 petaflop/s on gpu hardware using single precision.  ...  Parallel fast multipole method on GPUs It is common that algorithms with low complexity (sparse linear algebra, fft) have low arithmetic intensity, while algorithms with high arithmetic intensity (dense  ... 
doi:10.1016/j.cpc.2012.09.011 fatcat:zdbjrn6ga5cmlkcw7mlo77kif4

Hierarchical N-body Simulations with Autotuning for Heterogeneous Systems

Rio Yokota, Lorena Barba
2012 Computing in science & engineering (Print)  
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.  ...  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.  ...  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

FMM-based vortex method for simulation of isotropic turbulence on GPUs, compared with a spectral method

Rio Yokota, L.A. Barba
2013 Computers & Fluids  
The fact that it uses the fast multipole method (FMM)--a hierarchical algorithm for N-body problems with highly scalable parallel implementations--as numerical engine makes it a potentially good candidate  ...  The vortex method uses an FMM code (exaFMM) that runs on GPU hardware using CUDA, while the spectral code (hit3d) runs on CPU only.  ...  We acknowledge the use of the hit3D pseudospectral DNS code for isotropic turbulence, and appreciate greatly their authors for their open-source policy; the code is available via Google code at http://  ... 
doi:10.1016/j.compfluid.2012.08.002 fatcat:5ukhafrvkndg3gynpey5ygq4ey

ATIP/A*CRC Workshop on Accelerator Technologies for High-Performance Computing: Does Asia Lead the Way? Programme Handbook [article]

Michalewicz Marek, Kahaner David
2012 Zenodo  
Three of these five systems boast GPU accelerators.  ...  STAR) Computational Resource Centre (A*CRC), this workshop in Singapore focus on the practical aspects of scientific and engineering applications, experiences with program development, porting, tuning,  ...  brand new graduate university on Okinawa, Japan.  ... 
doi:10.5281/zenodo.3977457 fatcat:v2aftckqinasxk5ugdw27vinpa

Literature Review of Accelerated CFD Simulation Methods towards Online Application

Md Lokman Hosain, Rebei Bel Fdhila
2015 Energy Procedia  
As a next step one of these methods will be implemented and coupled to CFD simulation of cooling impinging jets used to control the heat transfer and temperature behavior of a hot flat surface in a hot  ...  They provide high accuracy however, the simulation time is too long and this limit its generalized use dramatically as for control purposes.  ...  Recently, a petascale turbulence near real-time simulation was done by Yokota, R., et. al., in [25] using GPU architecture.  ... 
doi:10.1016/j.egypro.2015.07.714 fatcat:cb5vmlvhjfhr7mxf2iq45hlqca

D7.1.2: Applications Enabling for Capability Science

Jussi Enkovaara
2012 Zenodo  
The WP7 "Enabling Petascale Applications: Efficient Use of Tier-0 Systems" in PRACE-1IP is responsible for providing petascaling support to European researchers for PRACE Tier-0 systems.  ...  Projects have been largely successful, and in most cases the application code is now ready for petascale production usage.  ...  The first one was to improve the use of FFT's, while the second was to try a different method to solve the equation based on the Fast Multipole Method.  ... 
doi:10.5281/zenodo.6553000 fatcat:tkhkg7sq5feonf2w5spxqkvcbq

Abstractions and Middleware for Petascale Computing and Beyond

Ivo F. Sbalzarini
2010 International Journal of Distributed Systems and Technologies  
We outline the structure and functionality of such a middleware and demonstrate its feasibility on the example of the parallel particle-mesh library (PPM).  ...  As high-performance computing moves to the petascale and beyond, a number of algorithmic and software challenges need to be addressed.  ...  In summary, the abstractions and middleware presented in this paper provide a starting point that has already led to highly scalable and easy-to-implement parallel simulations .  ... 
doi:10.4018/jdst.2010040103 fatcat:yihhihij7rblbo3jzknckjeglu

Exascale applications: skin in the game

Francis Alexander, Ann Almgren, John Bell, Amitava Bhattacharjee, Jacqueline Chen, Phil Colella, David Daniel, Jack DeSlippe, Lori Diachin, Erik Draeger, Anshu Dubey, Thom Dunning (+39 others)
2020 Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences  
on the field of play under discussion'.  ...  As noted in Wikipedia, skin in the game refers to having 'incurred risk by being involved in achieving a goal', where 'skin is a synecdoche for the person involved, and game is the metaphor for actions  ...  The authors would like to extend a special thanks to the many computer and computational science researchers (hundreds of them) who have committed their time, talents, experience and passion to the ECP  ... 
doi:10.1098/rsta.2019.0056 pmid:31955678 fatcat:6gijc65k2fa5lirhdkiudbie5q

Accelerated application development: The ORNL Titan experience

Wayne Joubert, Rick Archibald, Mark Berrill, W. Michael Brown, Markus Eisenbach, Ray Grout, Jeff Larkin, John Levesque, Bronson Messer, Matt Norman, Bobby Philip, Ramanan Sankaran (+2 others)
2015 Computers & electrical engineering  
Titan, which began planning in 2009 and was deployed for general use in 2013, was the first multi-petaflop system based on accelerator hardware.  ...  The use of computational accelerators such as NVIDIA GPUs and Intel Xeon Phi processors is now widespread in the high performance computing community, with many applications delivering impressive performance  ...  Acknowledgments The CAAR project was a large-scale effort requiring the participation of many individuals.  ... 
doi:10.1016/j.compeleceng.2015.04.008 fatcat:ir4nljoznvfvrbg3vdcjtggxc4

Solvers for O (N) Electronic Structure in the Strong Scaling Limit [article]

Nicolas Bock and Matt Challacombe and Laxmikant V. Kalé
2015 arXiv   pre-print
We present a hybrid OpenMP/Charm++ framework for solving the O (N) Self-Consistent-Field eigenvalue problem with parallelism in the strong scaling regime, P≫N, where P is the number of cores, and N a measure  ...  Comput. 35 C72, 2013], and involves a recursive, task-parallel algorithm, often employed by generalized N-Body solvers, to occlusion and culling of negligible products in the case of matrices with decay  ...  Taiji, 42 TFlops Hierarchical N-body Simulations on GPUs with Applications in Both Astrophysics and Turbulence, 2009. ACM Gordon Bell Prize. [76] William W. Hargrove, Forrest M.  ... 
arXiv:1403.7458v7 fatcat:75dqzyl2xbflhdvh5x6zsmfasq

PIC methods in astrophysics: Simulations of relativistic jets and kinetic physics in astrophysical systems [article]

Kenichi Nishikawa, Ioana Dutan, Christoph Köhn, Yosuke Mizuno
2021 arXiv   pre-print
Finally, we give an outlook of the future simulations of jets associated to neutron stars, black holes and their merging and discuss the future of PIC simulations in the light of petascale and exascale  ...  We review a plethora of astrophysical phenomena such as relativistic jets, instabilities, magnetic reconnection, pulsars, as well as PIC simulations of laser-plasma physics (until 2021) emphasizing the  ...  Simulations were performed using Pleiades and Endeavor facilities at NASA Advanced Supercomputing (NAS: s2004), using Comet at The San Diego Supercomputer Center (SDSC), Bridges at The Pittsburgh Supercomputing  ... 
arXiv:2008.02105v3 fatcat:5uttdaqnrjekbemtgaxwliafua


Max P. Katz, Michael Zingale, Alan C. Calder, F. Douglas Swesty, Ann S. Almgren, Weiqun Zhang
2016 Astrophysical Journal  
This is the first paper in a series describing simulations of these systems using a hydrodynamics code with adaptive mesh refinement.  ...  To date there have been relatively few self-consistent simulations of merging white dwarf systems using mesh-based hydrodynamics.  ...  CASTRO is highly parallel and is designed for large-scale use on modern supercomputers; see Section 5 for information on how CASTRO performs for our problem.  ... 
doi:10.3847/0004-637x/819/2/94 fatcat:p5xaktcrgncsjdcoyyrp6buxgm

Performance Benchmarking of Fast Multipole Methods Thesis by

Noha Al-Harthi, Noha Al-Harthi
2013 unpublished
The fast multipole method (FMM) was originally developed as a fast algorithm for approximating the N-body interactions that appear in astrophysics, molecular dynamics, and vortex based fluid dynamics simulations  ...  Performance Benchmarking of Fast Multipole Methods Noha Ahmed Al-Harthi The current trends in computer architecture are shifting towards smaller byte/flop ratios, while available parallelism is increasing  ...  One on the algorithms that is expected to have a major role towards exascale is the fast multipole method (FMM).  ... 

Welcome from the SHAXC-2 Organizing Committee Aims and Scope SHAXC-2 Organizing Committee

David Keyes, David Keyes, George Turkiyyah
2014 unpublished
There is evidence (e.g., in the form of many Gordon Bell Prizes) that fast multipole methods and their treecode cousins fare well on emerging architectures.  ...  Fast multipole methods, H-matrices, sparse grids, multigrid, and fast transforms are critical to the optimal performance of many scientific codes.  ...  Acknowledgements A. Litvinenko is a member of the KAUST SRI Center for Uncertainty Quantification in Computational Science and Engineering.  ... 

A Smooth Partition of Unity Finite Element Method for Vortex Particle Regularization

Matthias Kirchhart, Shinnosuke Obi
2017 SIAM Journal on Scientific Computing  
In order to use the spaces on general domains, we propose a fictitious domain formulation, together with a new high-order accurate stabilization.  ...  We present a new class of C^∞-smooth finite element spaces on Cartesian grids, based on a partition of unity approach.  ...  express his gratitude to Sven Groß, Arnold Reusken, and all the members of the DROPS team at the Lehrstuhl für Numerische Mathematik (LNM) at RWTH Aachen University, Germany, with whom he previously worked on  ... 
doi:10.1137/17m1116258 fatcat:suextwqkfbgddok2hvzskya5a4
« Previous Showing results 1 — 15 out of 23 results