Filters








89 Hits in 8.7 sec

Dynamic load balancing with enhanced shared-memory parallelism for particle-in-cell codes [article]

Kyle G. Miller, Roman P. Lee, Adam Tableman, Anton Helm, Ricardo A. Fonseca, Viktor K. Decyk, Warren B. Mori
2020 arXiv   pre-print
effects---requires large-scale kinetic simulations using particle-in-cell (PIC) codes.  ...  Furthering our understanding of many of today's interesting problems in plasma physics---including plasma based acceleration and magnetic reconnection with pair production due to quantum electrodynamic  ...  Similar approaches based on rectilinear partitioning are taken in [9, 2, 10] .  ... 
arXiv:2003.10406v1 fatcat:scowk2buxbh67b7onofiqrxabq

The Plasma Simulation Code: A modern particle-in-cell code with patch-based load-balancing

Kai Germaschewski, William Fox, Stephen Abbott, Narges Ahmadi, Kristofor Maynard, Liang Wang, Hartmut Ruhl, Amitava Bhattacharjee
2016 Journal of Computational Physics  
This work describes the Plasma Simulation Code (psc), an explicit, electromagnetic particle-in-cell code with support for different order particle shape functions.  ...  We then describe and analyze in detail a distinguishing feature of psc: patch-based load balancing using space-filling curves which is shown to lead to major efficiency gains over unbalanced methods and  ...  Dynamic load balancing using space filling curves In this work, we present a new patch-based approach to load balancing particle-in-cell simulations and investigate the performance costs and benefits.  ... 
doi:10.1016/j.jcp.2016.05.013 fatcat:kkoik3qiefgdva5hstcmnq7dgu

The Plasma Simulation Code: A modern particle-in-cell code with load-balancing and GPU support [article]

Kai Germaschewski, William Fox, Stephen Abbott, Narges Ahmadi, Kristofor Maynard, Liang Wang, Hartmut Ruhl, Amitava Bhattacharjee
2015 arXiv   pre-print
This paper describes the Plasma Simulation Code (PSC), an explicit, electromagnetic particle-in-cell code with support for different order particle shape functions.  ...  We focus on two distinguishing feature of the code: patch-based load balancing using space-filling curves, and support for Nvidia GPUs, which achieves substantial speed-up of up to more than 6x on the  ...  Dynamic load balancing using space filling curves In this work, we present a new patch-based approach to load balancing particle-in-cell simulations and investigate the performance costs and benefits.  ... 
arXiv:1310.7866v2 fatcat:en5mqq5fnngjnnieg6cjerdqvy

Exploiting Parallelism on Shared Memory in the QED Particle-in-Cell Code PICADOR with Greedy Load Balancing [article]

Iosif Meyerov, Sergei Bastrakov, Aleksei Bashinov, Evgeny Efimenko, Alexander Panov, Elena Panova, Igor Surmin, Valentin Volokitin, Arkady Gonoskov
2019 arXiv   pre-print
State-of-the-art numerical simulations of laser plasma by means of the Particle-in-Cell method are often extremely computationally intensive.  ...  We propose and evaluate a load balancing scheme for shared memory systems, which allows subdividing individual cells of the computational domain into work portions with subsequent dynamic distribution  ...  Our previous work included load balancing on the level of distributed memory based on Cartesian rectilinear partitioning [24] .  ... 
arXiv:1905.08217v1 fatcat:lk2hhvzbgjay5ik4orbqafgxwu

High Performance Computing in Biomedical Applications

S. Bastrakov, I. Meyerov, V. Gergel, A. Gonoskov, A. Gorshkov, E. Efimenko, M. Ivanchenko, M. Kirillin, A. Malova, G. Osipov, V. Petrov, I. Surmin (+1 others)
2013 Procedia Computer Science  
We consider four main fields: plasma simulation, heart activity simulation, brain sensing simulation, molecular dynamics simulation.  ...  The software system is aimed at large-scale simulation on cluster systems with high efficiency and scalability.  ...  Due to the high degree of nonlinearity and geometric complexity of the problem, plasma dynamics research is often based on simulation with the Particle-in-Cell (PIC) method [2] .  ... 
doi:10.1016/j.procs.2013.05.164 fatcat:6hzmpjn35zfihapdwr4l3qyita

Fast parallel Particle-To-Grid interpolation for plasma PIC simulations on the GPU

George Stantchev, William Dorland, Nail Gumerov
2008 Journal of Parallel and Distributed Computing  
Particle-in-Cell (PIC) methods have been widely used for plasma physics simulations in the past three decades.  ...  simulations on inexpensive commodity hardware.  ...  Particle-In-Cell (PIC) methods represent one of several kinetic approaches to plasma simulation.  ... 
doi:10.1016/j.jpdc.2008.05.009 fatcat:p2k4m3pjbverdm466enxk5ibza

Optimization of Parallel Particle-to-Grid Interpolation on Leading Multicore Platforms

Kamesh Madduri, Jimmy Su, Samuel Williams, Leonid Oliker, Ethier, Katherine Yelick
2012 IEEE Transactions on Parallel and Distributed Systems  
Our evaluated kernels are derived from two important numerical computations: a biological simulation of the heart using the Immersed Boundary method, and a Gyrokinetic Particle-in-Cell based application  ...  for studying fusion plasma microturbulence.  ...  , and a Gyrokinetic Particle-in-Cell (PIC) based method for studying plasma microturbulence.  ... 
doi:10.1109/tpds.2012.28 fatcat:ka67zev5grdspa3zjkcls325te

Gyrokinetic particle-in-cell optimization on emerging multi- and manycore platforms

Kamesh Madduri, Eun-Jin Im, Khaled Z. Ibrahim, Samuel Williams, Stéphane Ethier, Leonid Oliker
2011 Parallel Computing  
We also present the first study on tuning gyrokinetic particle-in-cell (PIC) algorithms for graphics processors, using the NVIDIA C2050 (Fermi).  ...  In this work, we examine the efficient multicore optimization of GTC, a petascale gyrokinetic toroidal fusion code for studying plasma microturbulence in tokamak devices.  ...  A closely-related macro-scale parallelization issue is particle load-balancing [19] , and OhHelp [20] is a library for dynamic rebalancing of particles in large parallel PIC simulations.  ... 
doi:10.1016/j.parco.2011.02.001 fatcat:dc6yotxbj5htteiv2z43o4ooje

Memory-efficient optimization of Gyrokinetic particle-to-grid interpolation for multicore processors

Kamesh Madduri, Samuel Williams, Stéphane Ethier, Leonid Oliker, John Shalf, Erich Strohmaier, Katherine Yelicky
2009 Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - SC '09  
We present multicore parallelization strategies for the particleto-grid interpolation step in the Gyrokinetic Toroidal Code (GTC), a 3D particle-in-cell (PIC) application to study turbulent transport in  ...  We implement thirteen different variants for this kernel and identify the best-performing ones given typical PIC parameters such as the grid size, number of particles per cell, and the GTC-specific particle  ...  This work was supported by the ASCR Office in the DOE Office of Science under contract number DE-AC02-05CH11231, Microsoft (Award #024263), Intel (Award #024894), and by matching funding through U.C.  ... 
doi:10.1145/1654059.1654108 dblp:conf/sc/MadduriWEOSSY09 fatcat:cwakndkumzg27ovrzpoycyyl24

Gyrokinetic toroidal simulations on leading multi- and manycore HPC systems

Kamesh Madduri, Khaled Z. Ibrahim, Samuel Williams, Eun-Jin Im, Stephane Ethier, John Shalf, Leonid Oliker
2011 Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11  
The gyrokinetic Particle-in-Cell (PIC) method is a critical computational tool enabling petascale fusion simulation research.  ...  Our optimizations encompass all six GTC sub-routines and include multi-level particle and grid decompositions designed to improve multi-node parallel scaling, particle binning for improved load balance  ...  A closely-related macro-scale parallelization issue is particle load-balancing [7] , and OhHelp [25] is a library for dynamic rebalancing of particles in large parallel PIC simulations.  ... 
doi:10.1145/2063384.2063415 dblp:conf/sc/MadduriIWIESO11 fatcat:g3hyh6mrl5fjzjrmof6fhtee6i

AMReX: Block-Structured Adaptive Mesh Refinement for Multiphysics Applications [article]

Weiqun Zhang, Andrew Myers, Kevin Gott, Ann Almgren, John Bell
2020 arXiv   pre-print
AMReX supports algorithms that solve systems of partial differential equations (PDEs) in simple or complex geometries, and those that use particles and/or particle-mesh operations to represent component  ...  In addition we will highlight the strategy that the AMReX team is pursuing to achieve highly performant code across a range of accelerator-based architectures for a variety of different applications.  ...  Dual grid approach for load balancing In AMReX-based applications that have both mesh data and particle data, the mesh work and particle work have very different requirements for load balancing.  ... 
arXiv:2009.12009v1 fatcat:wxlcgj5rwfhpllwc4nejb6jcae

Particle-Based Plasma Simulations for an Ion Engine Discharge Chamber

Sudhakar Mahalingam, James A. Menart
2010 Journal of Propulsion and Power  
Particle Based Plasma Simulation for an Ion Engine Discharge Chamber.  ...  In this work a complete particle based approach has been taken to model the discharge chamber plasma.This is the first time that simplifying continuum assumptions on the particle motion have not been made  ...  In this work the decomposition partitions are selected based on to maximize the load balancing between the processors.  ... 
doi:10.2514/1.45954 fatcat:4jm5hjs7sndzvlyst3cdnlnegi

Analysis and optimization of gyrokinetic toroidal simulations on homogenous and heterogenous platforms

Khaled Z Ibrahim, Kamesh Madduri, Samuel Williams, Bei Wang, Stephane Ethier, Leonid Oliker
2013 The international journal of high performance computing applications  
The Gyrokinetic Toroidal Code (GTC) uses the particle-in-cell method to efficiently simulate plasma microturbulence.  ...  We introduce cell access analysis to better manage locality vs. synchronization tradeoffs on CPU and GPU-based architectures.  ...  A closely-related macro-scale parallelization issue is particle load-balancing [7] , and OhHelp [25] is a library for dynamic rebalancing of particles in large parallel PIC simulations.  ... 
doi:10.1177/1094342013492446 fatcat:q5jedu5u2nctbdch6p5lc7adna

Specification Of Hpc Hardware And Program Components To Enable Further Optimized Mappings

Carlchristian Helmut Johannes Eckert, Wolfgang E Nagel, Jerónimo Castrillón
2016 Zenodo  
Load balancing is one of the key problems in distributed computing.  ...  In order to find good domain decompositions, the characteristics of hardware and software must be known to the partitioning algorithm.  ...  An Exemplary Particle In Cell Simulation This section will outline existing load balancing challenges that motivated this thesis.  ... 
doi:10.5281/zenodo.163329 fatcat:mkb4ewc4nvdfrcclwlqzrbg7ry

FDPrior: A force-directed based parallel partitioning algorithm for three dimensional integrated circuits on GPGPU

Wan-Jing Chen, Hsien-Kai Kuo, Tsou-Han Chiu, Bo-Cheng Charles Lai
2011 Proceedings of 2011 International Symposium on VLSI Design, Automation and Test  
The purpose of our research is providing a new field of vision in the partition problem of 3DICs.  ...  By adopting the N-body simulation scheme and novel techniques to reduce synchronization overhead, FDPrior successfully exposes the massive parallelism on the multi-core GPGPU architecture.  ...  N-Body simulation phase simulates the movement of each mobile cell based on the forces impacted on it. as the force equations.  ... 
doi:10.1109/vdat.2011.5783580 fatcat:uotrz3tyybbyxmtsagov6ntdmm
« Previous Showing results 1 — 15 out of 89 results