@article{ref:Carrier1988,
  title={A fast adaptive multipole algorithm for particle simulations},
  author={Carrier, J and Greengard, Leslie and Rokhlin, Vladimir},
  journal={SIAM Journal on Scientific and Statistical Computing},
  volume={9},
  number={4},
  pages={669--686},
  year={1988},
  publisher={SIAM}
}

@article{ref:Barnes1986,
  title={A hierarchical O (N log N) force-calculation algorithm},
  author={Barnes, Josh and Hut, Piet},
  journal={Nature},
  year={1986},
  publisher={Nature Publishing Group}
}

@article{ref:Reinders2012,
  title={An Overview of Programming for {I}ntel{\textregistered} {X}eon{\textregistered} processors and {I}ntel{\textregistered} {X}eon {P}hi{\textsuperscript{\sf {TM}}} coprocessors},
  author={Reinders, James},
  journal={by Intel Corporation},
  year={2012}
}

@article{ref:Phillips2005,
  title={Scalable molecular dynamics with NAMD},
  author={Phillips, James C and Braun, Rosemary and Wang, Wei and Gumbart, James and Tajkhorshid, Emad and Villa, Elizabeth and Chipot, Christophe and Skeel, Robert D and Kale, Laxmikant and Schulten, Klaus},
  journal={Journal of computational chemistry},
  volume={26},
  number={16},
  pages={1781--1802},
  year={2005},
  publisher={Wiley Online Library}
}

@inproceedings{ref:Kale1993,
  author        = "{Kal\'{e}}, L.V. and Krishnan, S.",
  title         = "{CHARM++: A Portable Concurrent Object Oriented System
                   Based on C++}",
  editor        = "Paepcke, A.",
  fulleditor    = "Paepcke, Andreas",
  pages         = "91--108",
  Month         = "September",
  Year          = "1993",
  booktitle     = "{Proceedings of OOPSLA'93}",
  publisher     = "{ACM Press}",
}

@article{ref:Thacker2006,
  title={A parallel adaptive P$^3$M code with hierarchical particle reordering},
  author={Thacker, Robert J and Couchman, Hugh MP},
  journal={Computer physics communications},
  volume={174},
  number={7},
  pages={540--554},
  year={2006},
  publisher={Elsevier}
}

@techreport{ref:Gonnet2013b,
    title = "QuickSched: Task-based parallelism with dependencies and conflicts",
    author = "Gonnet, Pedro",
    institution = "School of Engineering and Computing Sciences, Durham University",
    year = "2013",
    number = "ECS-TR 2013/06"
    }

@article{ref:Lemson2006,
    title={Halo and Galaxy Formation Histories from the Millennium Simulation: Public release of a VO-oriented and SQL-queryable database for studying the evolution of galaxies in the LambdaCDM cosmogony},
    author={Lemson, Gerard and others},
    journal={arXiv preprint astro-ph/0608019},
    year={2006}
    }

@article{ref:Karypis1998,
    title={A fast and high quality multilevel scheme for partitioning irregular graphs},
    author={Karypis, George and Kumar, Vipin},
    journal={SIAM Journal on scientific Computing},
    volume={20},
    number={1},
    pages={359--392},
    year={1998},
    publisher={SIAM}
    }

@article{ref:Bangerth2007,
    author = 	 {W. Bangerth and R. Hartmann and G. Kanschat},
    title = 	 {{deal.II} -- a General Purpose Object Oriented Finite Element Library},
    journal = 	 {ACM Trans. Math. Softw.},
    year = 	 "2007",
    volume = 	 "33",
    number = 	 "4",
    pages = 	 {24/1--24/27}
    }
      
@inproceedings{ref:Agullo2009,
    title={Numerical linear algebra on emerging architectures: The {PLASMA} and {MAGMA} projects},
    author={Agullo, Emmanuel and Demmel, Jim and Dongarra, Jack and Hadri, Bilel and Kurzak, Jakub and Langou, Julien and Ltaief, Hatem and Luszczek, Piotr and Tomov, Stanimire},
    booktitle={Journal of Physics: Conference Series},
    volume={180},
    number={1},
    pages={012037},
    year={2009},
    organization={IOP Publishing}
    }

@inproceedings{ref:Schaller2013,
    title={On the use of particle based methods for cosmological hydrodynamical simulations},
    author={Schaller, Matthieu and Bower, Richard and Theuns, Tom},
    booktitle={8th International SPHERIC Workshop},
    year="2013",
    }

@misc{ref:Sedov1959,
    title={Similarity and Dimensional Methods in Mechanics (Similarity and Dimensional Methods in Mechanics, New York},
    author={Sedov, LI},
    year={1959},
    publisher={Academic Press}
    }

@article{ref:Blumofe1999,
    title={Scheduling multithreaded computations by work stealing},
    author={Blumofe, Robert D and Leiserson, Charles E},
    journal={Journal of the ACM (JACM)},
    volume={46},
    number={5},
    pages={720--748},
    year={1999},
    publisher={ACM}
    }

@article{ref:Ltaief2012,
    title={Data-driven execution of fast multipole methods},
    author={Ltaief, Hatem and Yokota, Rio},
    journal={arXiv preprint arXiv:1203.0889},
    year={2012}
    }

@book{ref:Reinders2007,
    title={Intel threading building blocks: outfitting {C++} for multi-core processor parallelism},
    author={Reinders, James},
    year={2007},
    publisher={O'Reilly Media, Incorporated}
    }

@book{ref:Snir1998,
    title={{MPI}: The Complete Reference (Vol. 1): Volume 1-The {MPI} Core},
    author={Snir, Marc and Otto, Steve and Huss-Lederman, Steven and Walker, David and Dongarra, Jack},
    volume={1},
    year={1998},
    publisher={MIT press}
    }

@article{ref:Gabriel2004,
    title={{Open MPI}: Goals, concept, and design of a next generation {MPI} implementation},
    author={Gabriel, Edgar and Fagg, Graham and Bosilca, George and Angskun, Thara and Dongarra, Jack and Squyres, Jeffrey and Sahay, Vishal and Kambadur, Prabhanjan and Barrett, Brian and Lumsdaine, Andrew and others},
    journal={Recent Advances in Parallel Virtual Machine and Message Passing Interface},
    pages={353--377},
    year={2004},
    publisher={Springer}
    }

@article{ref:Price2012,
    title={Smoothed particle hydrodynamics and magnetohydrodynamics},
    author={Price, Daniel J},
    journal={Journal of Computational Physics},
    volume={231},
    number={3},
    pages={759--794},
    year={2012},
    publisher={Elsevier}
    }

@article{ref:Duran2009,
    title={A proposal to extend the {OpenMP} tasking model with dependent tasks},
    author={Duran, Alejandro and Ferrer, Roger and Ayguad{\'e}, Eduard and Badia, Rosa M and Labarta, Jesus},
    journal={International Journal of Parallel Programming},
    volume={37},
    number={3},
    pages={292--305},
    year={2009},
    publisher={Springer}
    }

@article{ref:Sod1978,
    title={A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws},
    author={Sod, Gary A},
    journal={Journal of Computational Physics},
    volume={27},
    number={1},
    pages={1--31},
    year={1978},
    publisher={Elsevier}
    }

@article{ref:balsara1995,
    title={Von {N}eumann stability analysis of smoothed particle hydrodynamics--Suggestions for optimal algorithms},
    author={Balsara, Dinshaw S},
    journal={Journal of Computational Physics},
    volume={121},
    number={2},
    pages={357--372},
    year={1995},
    publisher={Elsevier}
    }

@article{ref:Monaghan1983,
    title={Shock simulation by the particle method {SPH}},
    author={Monaghan, JJ and Gingold, RA},
    journal={Journal of Computational Physics},
    volume={52},
    number={2},
    pages={374--389},
    year={1983},
    publisher={Elsevier}
    }

@misc{ref:pthreads,
    title={{IEEE} {S}td 1003.1 c-1995, Threads Extensions},
    author={{IEEE} Portable Applications Standards Committee and others},
    year={1995},
    publisher={IEEE}
    }

@article{ref:Dagum1998,
    title={{OpenMP}: an industry standard {API} for shared-memory programming},
    author={Dagum, Leonardo and Menon, Ramesh},
    journal={Computational Science \& Engineering, IEEE},
    volume={5},
    number={1},
    pages={46--55},
    year={1998},
    publisher={IEEE}
    }

@article{ref:Gingold1977,
    title={Smoothed particle hydrodynamics-theory and application to non-spherical stars},
    author={Gingold, Robert A and Monaghan, Joseph J},
    journal={Monthly notices of the royal astronomical society},
    volume={181},
    pages={375--389},
    year={1977}
    }

@article{ref:Viccione2008,
    title={Defining and optimizing algorithms for neighbouring particle identification in SPH fluid simulations},
    author={Viccione, G and Bovolin, V and Carratelli, E Pugliese},
    journal={International Journal for Numerical Methods in Fluids},
    volume={58},
    number={6},
    pages={625--638},
    year={2008},
    publisher={Wiley Online Library}
    }

@article{ref:Dominguez2011,
    title={Neighbour lists in smoothed particle hydrodynamics},
    author={Dom{\'\i}nguez, JM and Crespo, AJC and G{\'o}mez-Gesteira, M and Marongiu, JC},
    journal={International Journal for Numerical Methods in Fluids},
    volume={67},
    number={12},
    pages={2026--2042},
    year={2011},
    publisher={Wiley Online Library}
    }

@article{ref:Lee1977,
    title={Worst-case analysis for region and partial region searches in multidimensional binary search trees and balanced quad trees},
    author={Lee, Der-Tsai and Wong, CK},
    journal={Acta Informatica},
    volume={9},
    number={1},
    pages={23--29},
    year={1977},
    publisher={Springer}
    }

@article{ref:Meagher1982,
    title={Geometric modeling using octree encoding},
    author={Meagher, Donald},
    journal={Computer Graphics and Image Processing},
    volume={19},
    number={2},
    pages={129--147},
    year={1982},
    publisher={Elsevier}
    }

@article{ref:Bentley1975,
    title={Multidimensional binary search trees used for associative searching},
    author={Bentley, Jon Louis},
    journal={Communications of the ACM},
    volume={18},
    number={9},
    pages={509--517},
    year={1975},
    publisher={ACM}
    }

@article{ref:Wadsley2004,
    title={Gasoline: a flexible, parallel implementation of {TreeSPH}},
    author={Wadsley, JW and Stadel, Joachim and Quinn, Thomas},
    journal={New Astronomy},
    volume={9},
    number={2},
    pages={137--158},
    year={2004},
    publisher={Elsevier}
    }

@article{ref:Springel2005,
    title={The cosmological simulation code {G}adget-2},
    author={Springel, Volker},
    journal={Monthly Notices of the Royal Astronomical Society},
    volume={364},
    number={4},
    pages={1105--1134},
    year={2005},
    publisher={Wiley Online Library}
    }

@article{ref:Hernquist1989,
    title={{TREESPH}-{A} unification of {SPH} with the hierarchical tree method},
    author={Hernquist, Lars and Katz, Neal},
    journal={The Astrophysical Journal Supplement Series},
    volume={70},
    pages={419--446},
    year={1989}
    }
    
@misc{ref:mdcore,
    title = "{\tt mdcore}",
    url = "http://mdcore.sourceforge.net"
    }

@misc{ref:SWIFT,
    title = "{\sc swift}",
    note = "http://swiftsim.sourceforge.net"
    }

@manual{ref:cuda,
    title = "NVIDIA {CUDA} {C} Programming Guide 4.2",
    organization = "NVIDIA Corporation",
    address = "Santa Clara, CA 95050, USA",
    year = "2012"
    }
    
@article{ref:Fomin2011,
    author = {Fomin, Eduard S.},
    title = {Consideration of data load time on modern processors for the {V}erlet table and linked-cell algorithms},
    journal = {Journal of Computational Chemistry},
    volume = {32},
    number = {7},
    doi = {10.1002/jcc.21722},
    pages = {1386--1399},
    year = {2011}
    }
    
@article{ref:Springel2005b,
  title={Simulations of the formation, evolution and clustering of galaxies and quasars},
  author={Springel, Volker and White, Simon DM and Jenkins, Adrian and Frenk, Carlos S and Yoshida, Naoki and Gao, Liang and Navarro, Julio and Thacker, Robert and Croton, Darren and Helly, John and others},
  journal={nature},
  volume={435},
  number={7042},
  pages={629--636},
  year={2005},
  publisher={Nature Publishing Group}
}

@article{ref:Gonnet2012,
    author = "Gonnet, Pedro",
    title = "Pairwise {V}erlet lists: Combining cell lists and {V}erlet lists to improve memory locality and parallelism",
    journal = "Journal of Computational Chemistry",
    volume = "33",
    issue = "1",
    pages = "76--81",
    year = "2012"
    }

@article{ref:Gonnet2013,
    title={Pseudo-{V}erlet lists: a new, compact neighbour list representation},
    author={Gonnet, Pedro},
    journal={Molecular Simulation},
    volume={39},
    number={9},
    pages={721--727},
    year={2013},
    publisher={Taylor \& Francis}
    }
    
@misc{ref:Chalk2014,
    author = "Chalk, Aidan {\relax B. G.} and Townsend, Sam and Gonnet, Pedro",
    title = "Using task-based parallelism directly on {GPU}s",
    howpublished = "Submitted to ACM Transactions on Parallel Computing",
    year = "2014"
    }
    
@article{ref:Harvey2009,
    title={{ACEMD}: accelerating biomolecular dynamics in the microsecond time scale},
    author={Harvey, MJ and Giupponi, G. and Fabritiis, G.D.},
    journal={Journal of Chemical Theory and Computation},
    volume={5},
    number={6},
    pages={1632--1639},
    year={2009},
    publisher={ACS Publications}
    }
    
@article{ref:Stone2007,
    title={Accelerating molecular modeling applications with graphics processors},
    author={Stone, J.E. and Phillips, J.C. and Freddolino, P.L. and Hardy, D.J. and Trabuco, L.G. and Schulten, K.},
    journal={Journal of Computational Chemistry},
    volume={28},
    number={16},
    pages={2618--2640},
    year={2007},
    publisher={Wiley Online Library}
    }
    
@inproceedings{ref:Ganesan2011,
    title={{FENZI}: {GPU}-enabled Molecular Dynamics Simulations of Large Membrane Regions based on the CHARMM force field and PME},
    author={Ganesan, N. and Taufer, M. and Bauer, B. and Patel, S.},
    booktitle={Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW), 2011 IEEE International Symposium on},
    pages={472--480},
    year={2011},
    organization={IEEE}
    }
    
@article{ref:Peters2011,
    title={Fast in-place, comparison-based sorting with {CUDA}: a study with bitonic sort},
    author={Peters, H. and Schulz-Hildebrandt, O. and Luttenberger, N.},
    journal={Concurrency and Computation: Practice and Experience},
    volume={23},
    number={7},
    pages={681--693},
    year={2011},
    publisher={Wiley Online Library}
    }
    
@article{ref:Gonnet2010b,
    author = "Pedro Gonnet",
    title = "Using piecewise polynomials for faster potential function evaluation",
    journal = "Journal of Computational Physics",
    volume = "229",
    number = "2",
    pages = "313--324",
    year = "2010",
    doi = "10.1016/j.jcp.2009.09.028",
    }
    
@article{ref:Verlet1967,
    title = {Computer ``Experiments'' on Classical Fluids. {I}. {T}hermodynamical Properties of {L}ennard-{J}ones Molecules},
    author = {Verlet, Loup},
    journal = {Physical Review},
    volume = {159},
    number = {1},
    pages = {98},
    year = {1967},
    doi = {10.1103/PhysRev.159.98},
    publisher = {American Physical Society}
    }

@article{ref:Gonnet2007,
    author = {Gonnet, Pedro},
    title = {A simple algorithm to accelerate the computation of non-bonded interactions in cell-based molecular dynamics simulations},
    journal = {Journal of Computational Chemistry},
    volume = {28},
    number = {2},
    pages = {570--573},
    year = {2007},
    doi = {10.1002/jcc.20563}
    }

@article{ref:Eastman2010,
    title={Efficient nonbonded interactions for molecular dynamics on a graphics processing unit},
    author={Eastman, P. and Pande, V.S.},
    journal={Journal of computational chemistry},
    volume={31},
    number={6},
    pages={1268--1272},
    year={2010},
    publisher={Wiley Online Library}
    }
    
@article{ref:Friedrichs2009,
    title={Accelerating molecular dynamic simulation on graphics processing units},
    author={Friedrichs, M.S. and Eastman, P. and Vaidyanathan, V. and Houston, M. and Legrand, S. and Beberg, A.L. and Ensign, D.L. and Bruns, C.M. and Pande, V.S.},
    journal={Journal of computational chemistry},
    volume={30},
    number={6},
    pages={864--872},
    year={2009},
    publisher={Wiley Online Library}
    }
    
@article{ref:Anderson2008,
    title={General purpose molecular dynamics simulations fully implemented on graphics processing units},
    author={Anderson, J.A. and Lorenz, C.D. and Travesset, A.},
    journal={Journal of Computational Physics},
    volume={227},
    number={10},
    pages={5342--5359},
    year={2008},
    publisher={Elsevier}
    }

@book{ref:Sanders2010,
    title={{CUDA} by example: an introduction to general-purpose {GPU} programming},
    author={Sanders, J. and Kandrot, E.},
    year={2010},
    publisher={Addison-Wesley Professional}
    }

@article{ref:Geer2005,
    title={Chip makers turn to multicore processors},
    author={Geer, D.},
    journal={Computer},
    volume={38},
    number={5},
    pages={11--13},
    year={2005},
    publisher={IEEE}
    }
    
@book{ref:Allen1989,
    title={Computer simulation of liquids},
    author={Allen, M.P. and Tildesley, D.J.},
    volume={18},
    number={195},
    year={1989},
    publisher={Oxford university press}
    }
    
@article{ref:Stone2010,
    title={{GPU}-accelerated molecular modeling coming of age},
    author={Stone, J.E. and Hardy, D.J. and Ufimtsev, I.S. and Schulten, K.},
    journal={Journal of Molecular Graphics and Modelling},
    volume={29},
    number={2},
    pages={116--125},
    year={2010},
    publisher={Elsevier}
    }

@article{ref:Essmann1995,
    title={A smooth particle mesh {E}wald method},
    author={Essmann, U. and Perera, L. and Berkowitz, M.L. and Darden, T. and Lee, H. and Pedersen, L.G.},
    journal={The Journal of Chemical Physics},
    volume={103},
    pages={8577},
    year={1995}
    }

@article{ref:Rossinelli2011,
    title={Mesh--particle interpolations on graphics processing units and multicore central processing units},
    author={Rossinelli, D. and Conti, C. and Koumoutsakos, P.},
    journal={Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
    volume={369},
    number={1944},
    pages={2164--2175},
    year={2011},
    publisher={The Royal Society}
    }

@book{ref:Blumofe1995,
	number = {8}, 
	year = {1995}, 
	author = {Blumofe, R.D. and Joerg, C.F. and Kuszmaul, B.C. and Leiserson, C.E. and Randall, K.H. and Zhou, Y.}, 
	volume = {30}, 
	publisher = {ACM}, 
	title = {Cilk: An efficient multithreaded runtime system}, 
    }

@manual{ref:QUARK,
	month = {April}, 
	year = {2011}, 
	author = {YarKhan, A. and Kurzak, J. and Dongarra, J.}, 
	address = {Electrical Engineering and Computer Science, Innovative Computing Laboratory, University of Tennessee}, 
	publisher = {University of Tennessee}, 
	title = {QUARK Users' Guide}, 
}

@manual{ref:SMPSuperscalar,
	year = {2008}, 
	publisher = {Barcelona Supercomputing Center}, 
	title = {{SMP} {S}uperscalar ({SMPS}s) User's Manual, {B}arcelona Supercomputing Center}, 
}

@article{ref:Augonnet2011,
	year = {2011}, 
	author = {Augonnet, C\'edric and Thibault, Samuel and Namyst, Raymond and Wacrenier, Pierre-Andr\'e}, 
	journal = {Concurrency and Computation: Practice and Experience, Special Issue: Euro-Par 2009}, 
	volume = {23}, 
	pages = {187--198}, 
	publisher = {John Wiley & Sons, Ltd.}, 
	doi = {10.1002/cpe.1631}, 
	url = {http://hal.inria.fr/inria-00550877}, 
	title = {Star{PU}: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures}, 
}