298 Hits in 10.9 sec

Heuristic static load-balancing algorithm applied to the fragment molecular orbital method

Yuri Alexeev, Ashutosh Mahajan, Sven Leyffer, Graham Fletcher, Dmitri G. Fedorov
2012 2012 International Conference for High Performance Computing, Networking, Storage and Analysis  
On 163,840 cores of Blue Gene/P, we achieved a parallel efficiency of 80% for an execution of the fragment molecular orbital method applied to model protein-ligand complexes quantummechanically.  ...  We propose a heuristic static load-balancing algorithm, employing fitted benchmarking data, as an alternative to dynamic load balancing.  ...  Government retains for itself, and others acting on its behalf, a paid-up, nonexclusive, irrevocable worldwide license in said article to reproduce, prepare derivative works, distribute copies to the public  ... 
doi:10.1109/sc.2012.62 dblp:conf/sc/AlexeevMLFF12 fatcat:ed4cztal7nhp7ddqnti4ypsvuq

Large-Scale Simulation of Quantum Computational Chemistry on a New Sunway Supercomputer [article]

Honghui Shang, Li Shen, Yi Fan, Zhiqian Xu, Chu Guo, Jie Liu, Wenhao Zhou, Huan Ma, Rongfen Lin, Yuling Yang, Fang Li, Zhuoya Wang (+2 others)
2022 arXiv   pre-print
Embedding Theory with the MPS-based VQE simulator to further extend the simulation range; (3) A three-level parallelization scheme to scale up to 20 million cores; (4) Usage of the Julia script language  ...  The major innovations include: (1) a Matrix Product State (MPS) based VQE simulator to reduce the amount of memory needed and increase the simulation efficiency; (2) a combination of the Density Matrix  ...  This enables high parallel scalability with adapted dynamical load balancing algorithm.  ... 
arXiv:2207.03711v1 fatcat:t6j5li32kvetpmzyadgnkf4w4u

Enabling Department-Scale Supercomputing [chapter]

David S. Greenberg, William E. Hart, Cynthia A. Phillips
1999 IMA Volumes in Mathematics and its Applications  
. of Pi% and development of the algorithms, applications, hardware, systems software and tools needed to implement science-based stockpile stewardship.  ...  Some of these lessons can be applied to these new mini-supercomputers, but in some cases there is still much to be learned.  ...  Acknowledgements We thank all the members of Sandia National Laboratories Massively Parallel Computing Research Laboratory (MPCRL), who have shared their extensive experience, papers, and web pages with  ... 
doi:10.1007/978-1-4612-1516-5_15 fatcat:5p4pp5bxdrevxmh2c2m5fei7ve

Hercules: Reproducing Crashes in Real-World Application Binaries

Van-Thuan Pham, Wei Boon Ng, Konstantin Rubinov, Abhik Roychoudhury
2015 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering  
Such potentially crashing locations can be found by a separate static analysis (or by gleaning crash reports submitted by internal / external users) and serve as the input to our method.  ...  The test input generated by our method serves as a witness of the crash. Our method is particularly suited for binaries of programs which take in complex structured inputs.  ...  The authors would like to thank Kenneth Cheong and Chia Yuan Cho for their constructive comments at various stages of the work.  ... 
doi:10.1109/icse.2015.99 dblp:conf/icse/PhamNRR15 fatcat:tz7epnwtmrcejmipw4zb2vsovm

An automatic performance model-based scheduling tool for coupled climate system models

Nan Ding, Wei Xue, Zhenya Song, Haohuan Fu, Shiming Xu, Weimin Zheng
2018 Journal of Parallel and Distributed Computing  
A heuristic static process scheduling algorithm is applied to the Fragment Molecular Orbital (FMO) Method [23] along with a curve-fitting based performance model.  ...  The solution space of our load balance problem is up to 10 13 , and the overhead of the BB method is beyond the limitation.  ... 
doi:10.1016/j.jpdc.2018.01.002 fatcat:lasxgh5a5jbnvak3gmmcnnbube

D6.4: Report on approaches to Petascaling

Mohammad Jowkar, Carlo Cavazzoni, Xu Guo, Giorgos Goumas
2009 Zenodo  
The approach taken to achieve this goal was to port and optimize several important and highly used applications to different HPC prototypes, so as to achieve as much scalability as possible in the given  ...  The above applications are from the scientific community and were chosen in tasks 6.1 and 6.2 so as to cover a broad range of scientific areas, and are considered to be representative of the European HPC  ...  Acknowledgements The authors wish to express their gratitude to Yvan Fournier, Jerome Bonelle and others in the Code_Saturne development team at EDF for their major contributions to this work.  ... 
doi:10.5281/zenodo.6546112 fatcat:rsmdzoeqbbbdzoe2zkx3czi2ry

Extending the Applicability of Graphlets to Directed Networks

David Aparicio, Pedro Ribeiro, Fernando Silva
2017 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
We compared our tool to other state-of-the art methods and verified that it is the fastest general tool for graphlet counting.  ...  Our implementation addresses this concern by using a state-of-the-art data structure, the g-trie, which is able to greatly reduce the necessary computation.  ...  Our algorithms perform random polling which has been established as an adequate heuristic for dynamic load balancing [57] .  ... 
doi:10.1109/tcbb.2016.2586046 pmid:27362986 fatcat:6hmtqn7abngkzgw53dhm3wnepi

Computational challenges in structural and functional genomics

T. Head-Gordon, J. C. Wooley
2001 IBM Systems Journal  
The goal of fold assignment and comparative modeling is to assign, using computational methods, each new genome sequence to the known protein fold or structure that it most closely resembles.  ...  This paper represents an effort by a research community to define the hard computational biology problems of the future, to define what mixture of basic research directions and practical algorithmic approaches  ...  Acknowledgments We would like to thank all of the following individuals who contributed to the intellectual content of this document.  ... 
doi:10.1147/sj.402.0265 fatcat:xfkz65qoond6zouw6rsbjltwqy

The Arepo public code release [article]

Rainer Weinberger, Volker Springel, Rüdiger Pakmor
2020 arXiv   pre-print
Arepo is a massively distributed-memory parallel code, using the Message Passing Interface (MPI) communication standard and employing a dynamical work-load and memory balancing scheme to allow optimal  ...  This version contains a finite-volume magnetohydrodynamics algorithm on an unstructured, dynamic Voronoi tessellation coupled to a tree-particle-mesh algorithm for the Poisson equation either on a Newtonian  ...  The authors would like to thank the full user base of Arepo for their continued encouragement to realize a public release of the code, and for their long-standing efforts in putting the code to great scientific  ... 
arXiv:1909.04667v2 fatcat:dt5ujxdlejhlvizzdmpfq6afla

Scalable molecular dynamics with NAMD

James C. Phillips, Rosemary Braun, Wei Wang, James Gumbart, Emad Tajkhorshid, Elizabeth Villa, Christophe Chipot, Robert D. Skeel, Laxmikant Kalé, Klaus Schulten
2005 Journal of Computational Chemistry  
methods along with the efficient electrostatics evaluation algorithms employed and temperature and pressure controls used.  ...  This article, directed to novices as well as experts, first introduces concepts and methods used in the NAMD program, describing the classical molecular dynamics force field, equations of motion, and integration  ...  The authors would also like to acknowledge Fatemeh Khalili-Araghi and Marcos Sotomayor for preparing the ubiquitin tetramer and ubiquitin simulations. Free energy calculation development with C.  ... 
doi:10.1002/jcc.20289 pmid:16222654 pmcid:PMC2486339 fatcat:ltac7t3jtrbkngvn33tkmemmta


Greg L. Bryan, Michael L. Norman, Brian W. O'Shea, Tom Abel, John H. Wise, Matthew J. Turk, Daniel R. Reynolds, David C. Collins, Peng Wang, Samuel W. Skillman, Britton Smith, Robert P. Harkness (+16 others)
2014 Astrophysical Journal Supplement Series  
In addition to explaining the algorithms implemented, we present solutions for a wide range of test problems, demonstrate the code's parallel performance, and discuss the Enzo collaboration's code development  ...  This paper describes the open-source code Enzo, which uses block-structured adaptive mesh refinement to provide high spatial and temporal resolution for modeling astrophysical fluid flows.  ...  The first load-balancing option is to move a grid from the processor with the highest computational load to the processor with the lowest load, with the proviso that only grids with load factors less than  ... 
doi:10.1088/0067-0049/211/2/19 fatcat:fmam4dequvaqvm7bpo7jwnqnja


Jaswinder Pal Singh, Wolf-Dietrich Weber, Anoop Gupta
1992 SIGARCH Computer Architecture News  
We expect the current set of applications to act as a nucleus for a suite that will grow with time.  ...  We expect the current set of applications to act as a nucleus for a suite that will grow with time. ev Words and Phrases: parallel application suite, shared memory, documentation, application characteristics  ...  Acknowledgements We would like to thank the following people for running the programs and writing initial versions of the individual application reports: Steve Goldschmidt (MP3D), Margaret Martonosi (LocusRoute  ... 
doi:10.1145/130823.130824 fatcat:3j3igrqrj5dqnjndxqleb5yxee

STARFORGE: Toward a comprehensive numerical model of star cluster formation and feedback [article]

Michael Y. Grudić, Dávid Guszejnov, Philip F. Hopkins, Stella S. R. Offner, Claude-André Faucher-Giguère
2021 arXiv   pre-print
We use the GIZMO code with the MFM mesh-free Lagrangian MHD method, augmented with new algorithms for gravity, timestepping, sink particle formation and accretion, stellar dynamics, and feedback coupling  ...  Modules for mass-injecting feedback (winds, SNe, and jets) inject new gas elements on-the-fly, eliminating the lack of resolution in diffuse feedback cavities otherwise inherent in Lagrangian methods.  ...  We are especially grateful to fellow starsmith Anna Rosen and to the referee Chris Matzner, whose careful readings helped improve the manuscript. MYG is supported by a CIERA Postdoctoral Fellowship.  ... 
arXiv:2010.11254v2 fatcat:xxclx4laa5fjjlqousiidnlxpq

14th International Symposium on Mathematical Programming

1990 Mathematical programming  
to the well known serious steps und null steps of bundle methods a third type of steps is used to generate the model of dom .  ...  If we use a decomposition approach in order to solve a minimization problem we often get an objective function in such a w a y that its domain dom 6 = n is not given explicitely to us.  ...  A s c heme of this type has been implemented on a distributed computational environment, and a static load balancing approach has been chosen for the parallelization scheme, given the subproblem structure  ... 
doi:10.1007/bf01580875 fatcat:3jtclwmntzgjxkqs5uecombdaa

Another Thanks to All JSR Supporters

Vince Zoby
2012 Journal of Spacecraft and Rockets  
Behind this shock, the molecular methane present in the freestream rapidly dissociates into smaller fragments including CH, H, and C.  ...  Nonlinear, discontiuous behavior of fitness Fn To search gioba ptimal desigr Heuristic algorithm To achieve best perform among heuristics Particle swarm mization opt Zatio —— To handle a time-consuming  ... 
doi:10.2514/1.57436 fatcat:6xrmfxntkzgvvidou7b2bktm5u
« Previous Showing results 1 — 15 out of 298 results