sample-bibliography.bib

%%% ====================================================================
%%%  BibTeX-file{
%%%     author          = "Gerry Murray",
%%%     version         = "1.2",
%%%     date            = "2 April 2012",
%%%     filename        = "acmsmall-sample-bibfile.bib",
%%%     address         = "ACM, NY",
%%%     email           = "murray at hq.acm.org",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "ACM Reference Format, bibliography, citation, references",
%%%     supported       = "yes",
%%%     docstring       = "This BibTeX database file contains 'bibdata' entries
%%%                        that 'match' the examples provided in the Specifications Document
%%%                        AND, also, 'legacy'-type bibs. It should assist authors in 
%%%                        choosing the 'correct' at-bibtype and necessary bib-fields
%%%                        so as to obtain the appropriate ACM Reference Format output. 
%%%			   It also contains many 'Standard Abbreviations'. "
%%%  }
%%% ====================================================================

% Journals

% First the Full Name is given, then the abbreviation used in the AMS Math
% Reviews, with an indication if it could not be found there.
% Note the 2nd overwrites the 1st, so swap them if you want the full name.

 %{AMS}
 @String{AMSTrans = "American Mathematical Society Translations" }
 @String{AMSTrans = "Amer. Math. Soc. Transl." }
 @String{BullAMS = "Bulletin of the American Mathematical Society" }
 @String{BullAMS = "Bull. Amer. Math. Soc." }
 @String{ProcAMS = "Proceedings of the American Mathematical Society" }
 @String{ProcAMS = "Proc. Amer. Math. Soc." }
 @String{TransAMS = "Transactions of the American Mathematical Society" }
 @String{TransAMS = "Trans. Amer. Math. Soc." }

 %ACM
 @String{CACM = "Communications of the {ACM}" }
 @String{CACM = "Commun. {ACM}" }
 @String{CompServ = "Comput. Surveys" }
 @String{JACM = "J. ACM" }
 @String{ACMMathSoft = "{ACM} Transactions on Mathematical Software" }
 @String{ACMMathSoft = "{ACM} Trans. Math. Software" }
 @String{SIGNUM = "{ACM} {SIGNUM} Newsletter" }
 @String{SIGNUM = "{ACM} {SIGNUM} Newslett." }

 @String{AmerSocio = "American Journal of Sociology" }
 @String{AmerStatAssoc = "Journal of the American Statistical Association" }
 @String{AmerStatAssoc = "J. Amer. Statist. Assoc." }
 @String{ApplMathComp = "Applied Mathematics and Computation" }
 @String{ApplMathComp = "Appl. Math. Comput." }
 @String{AmerMathMonthly = "American Mathematical Monthly" }
 @String{AmerMathMonthly = "Amer. Math. Monthly" }
 @String{BIT = "{BIT}" }
 @String{BritStatPsych = "British Journal of Mathematical and Statistical
          Psychology" }
 @String{BritStatPsych = "Brit. J. Math. Statist. Psych." }
 @String{CanMathBull = "Canadian Mathematical Bulletin" }
 @String{CanMathBull = "Canad. Math. Bull." }
 @String{CompApplMath = "Journal of Computational and Applied Mathematics" }
 @String{CompApplMath = "J. Comput. Appl. Math." }
 @String{CompPhys = "Journal of Computational Physics" }
 @String{CompPhys = "J. Comput. Phys." }
 @String{CompStruct = "Computers and Structures" }
 @String{CompStruct = "Comput. \& Structures" }
 @String{CompJour = "The Computer Journal" }
 @String{CompJour = "Comput. J." }
 @String{CompSysSci = "Journal of Computer and System Sciences" }
 @String{CompSysSci = "J. Comput. System Sci." }
 @String{Computing = "Computing" }
 @String{ContempMath = "Contemporary Mathematics" }
 @String{ContempMath = "Contemp. Math." }
 @String{Crelle = "Crelle's Journal" }
 @String{GiornaleMath = "Giornale di Mathematiche" }
 @String{GiornaleMath = "Giorn. Mat." } % didn't find in AMS MR., ibid.

 %IEEE
 @String{Computer = "{IEEE} Computer" }
 @String{IEEETransComp = "{IEEE} Transactions on Computers" }
 @String{IEEETransComp = "{IEEE} Trans. Comput." }
 @String{IEEETransAC = "{IEEE} Transactions on Automatic Control" }
 @String{IEEETransAC = "{IEEE} Trans. Automat. Control" }
 @String{IEEESpec = "{IEEE} Spectrum" } % didn't find in AMS MR
 @String{ProcIEEE = "Proceedings of the {IEEE}" }
 @String{ProcIEEE = "Proc. {IEEE}" } % didn't find in AMS MR
 @String{IEEETransAeroElec = "{IEEE} Transactions on Aerospace and Electronic
     Systems" }
 @String{IEEETransAeroElec = "{IEEE} Trans. Aerospace Electron. Systems" }

 @String{IMANumerAna = "{IMA} Journal of Numerical Analysis" }
 @String{IMANumerAna = "{IMA} J. Numer. Anal." }
 @String{InfProcLet = "Information Processing Letters" }
 @String{InfProcLet = "Inform. Process. Lett." }
 @String{InstMathApp = "Journal of the Institute of Mathematics and
     its Applications" }
 @String{InstMathApp = "J. Inst. Math. Appl." }
 @String{IntControl = "International Journal of Control" }
 @String{IntControl = "Internat. J. Control" }
 @String{IntNumerEng = "International Journal for Numerical Methods in
     Engineering" }
 @String{IntNumerEng = "Internat. J. Numer. Methods Engrg." }
 @String{IntSuper = "International Journal of Supercomputing Applications" }
 @String{IntSuper = "Internat. J. Supercomputing Applic." } % didn't find
%% in AMS MR
 @String{Kibernetika = "Kibernetika" }
 @String{JResNatBurStand = "Journal of Research of the National Bureau
     of Standards" }
 @String{JResNatBurStand = "J. Res. Nat. Bur. Standards" }
 @String{LinAlgApp = "Linear Algebra and its Applications" }
 @String{LinAlgApp = "Linear Algebra Appl." }
 @String{MathAnaAppl = "Journal of Mathematical Analysis and Applications" }
 @String{MathAnaAppl = "J. Math. Anal. Appl." }
 @String{MathAnnalen = "Mathematische Annalen" }
 @String{MathAnnalen = "Math. Ann." }
 @String{MathPhys = "Journal of Mathematical Physics" }
 @String{MathPhys = "J. Math. Phys." }
 @String{MathComp = "Mathematics of Computation" }
 @String{MathComp = "Math. Comp." }
 @String{MathScand = "Mathematica Scandinavica" }
 @String{MathScand = "Math. Scand." }
 @String{TablesAidsComp = "Mathematical Tables and Other Aids to Computation" }
 @String{TablesAidsComp = "Math. Tables Aids Comput." }
 @String{NumerMath = "Numerische Mathematik" }
 @String{NumerMath = "Numer. Math." }
 @String{PacificMath = "Pacific Journal of Mathematics" }
 @String{PacificMath = "Pacific J. Math." }
 @String{ParDistComp = "Journal of Parallel and Distributed Computing" }
 @String{ParDistComp = "J. Parallel and Distrib. Comput." } % didn't find
%% in AMS MR
 @String{ParComputing = "Parallel Computing" }
 @String{ParComputing = "Parallel Comput." }
 @String{PhilMag = "Philosophical Magazine" }
 @String{PhilMag = "Philos. Mag." }
 @String{ProcNAS = "Proceedings of the National Academy of Sciences
                    of the USA" }
 @String{ProcNAS = "Proc. Nat. Acad. Sci. U. S. A." }
 @String{Psychometrika = "Psychometrika" }
 @String{QuartMath = "Quarterly Journal of Mathematics, Oxford, Series (2)" }
 @String{QuartMath = "Quart. J. Math. Oxford Ser. (2)" }
 @String{QuartApplMath = "Quarterly of Applied Mathematics" }
 @String{QuartApplMath = "Quart. Appl. Math." }
 @String{RevueInstStat = "Review of the International Statisical Institute" }
 @String{RevueInstStat = "Rev. Inst. Internat. Statist." }

 %SIAM
 @String{JSIAM = "Journal of the Society for Industrial and Applied
     Mathematics" }
 @String{JSIAM = "J. Soc. Indust. Appl. Math." }
 @String{JSIAMB = "Journal of the Society for Industrial and Applied
     Mathematics, Series B, Numerical Analysis" }
 @String{JSIAMB = "J. Soc. Indust. Appl. Math. Ser. B Numer. Anal." }
 @String{SIAMAlgMeth = "{SIAM} Journal on Algebraic and Discrete Methods" }
 @String{SIAMAlgMeth = "{SIAM} J. Algebraic Discrete Methods" }
 @String{SIAMAppMath = "{SIAM} Journal on Applied Mathematics" }
 @String{SIAMAppMath = "{SIAM} J. Appl. Math." }
 @String{SIAMComp = "{SIAM} Journal on Computing" }
 @String{SIAMComp = "{SIAM} J. Comput." }
 @String{SIAMMatrix = "{SIAM} Journal on Matrix Analysis and Applications" }
 @String{SIAMMatrix = "{SIAM} J. Matrix Anal. Appl." }
 @String{SIAMNumAnal = "{SIAM} Journal on Numerical Analysis" }
 @String{SIAMNumAnal = "{SIAM} J. Numer. Anal." }
 @String{SIAMReview = "{SIAM} Review" }
 @String{SIAMReview = "{SIAM} Rev." }
 @String{SIAMSciStat = "{SIAM} Journal on Scientific and Statistical
     Computing" }
 @String{SIAMSciStat = "{SIAM} J. Sci. Statist. Comput." }

 @String{SoftPracExp = "Software Practice and Experience" }
 @String{SoftPracExp = "Software Prac. Experience" } % didn't find in AMS MR
 @String{StatScience = "Statistical Science" }
 @String{StatScience = "Statist. Sci." }
 @String{Techno = "Technometrics" }
 @String{USSRCompMathPhys = "{USSR} Computational Mathematics and Mathematical
     Physics" }
 @String{USSRCompMathPhys = "{U. S. S. R.} Comput. Math. and Math. Phys." }
 @String{VLSICompSys = "Journal of {VLSI} and Computer Systems" }
 @String{VLSICompSys = "J. {VLSI} Comput. Syst." }
 @String{ZAngewMathMech = "Zeitschrift fur Angewandte Mathematik und
     Mechanik" }
 @String{ZAngewMathMech = "Z. Angew. Math. Mech." }
 @String{ZAngewMathPhys = "Zeitschrift fur Angewandte Mathematik und Physik" }
 @String{ZAngewMathPhys = "Z. Angew. Math. Phys." }

% Publishers % ================================================= |

 @String{Academic = "Academic Press" }
 @String{ACMPress = "{ACM} Press" }
 @String{AdamHilger = "Adam Hilger" }
 @String{AddisonWesley = "Addison-Wesley" }
 @String{AllynBacon = "Allyn and Bacon" }
 @String{AMS = "American Mathematical Society" }
 @String{Birkhauser = "Birkha{\"u}ser" }
 @String{CambridgePress = "Cambridge University Press" }
 @String{Chelsea = "Chelsea" }
 @String{ClaredonPress = "Claredon Press" }
 @String{DoverPub = "Dover Publications" }
 @String{Eyolles = "Eyolles" }
 @String{HoltRinehartWinston = "Holt, Rinehart and Winston" }
 @String{Interscience = "Interscience" }
 @String{JohnsHopkinsPress = "The Johns Hopkins University Press" }
 @String{JohnWileySons = "John Wiley and Sons" }
 @String{Macmillan = "Macmillan" }
 @String{MathWorks = "The Math Works Inc." }
 @String{McGrawHill = "McGraw-Hill" }
 @String{NatBurStd = "National Bureau of Standards" }
 @String{NorthHolland = "North-Holland" }
 @String{OxfordPress = "Oxford University Press" }  %address Oxford or London?
 @String{PergamonPress = "Pergamon Press" }
 @String{PlenumPress = "Plenum Press" }
 @String{PrenticeHall = "Prentice-Hall" }
 @String{SIAMPub = "{SIAM} Publications" }
 @String{Springer = "Springer-Verlag" }
 @String{TexasPress = "University of Texas Press" }
 @String{VanNostrand = "Van Nostrand" }
 @String{WHFreeman = "W. H. Freeman and Co." }

%Entries
@inproceedings{sc14charm,
  title="{Parallel Programming with Migratable Objects: Charm++ in Practice}",
  author={Acun, Bilge and Gupta, Abhishek and Jain, Nikhil and Langer, Akhil and Menon, Harshitha and Mikida, Eric and Ni, Xiang and Robson, Michael and Sun, Yanhua and Totoni, Ehsan and Wesolowski, Lukasz and Kal\'e, Laxmikant},
 series = {SC},
 year = {2014},
}

@article{AlOmairy2015,
	author = {Rabab Al-Omairy and Guillermo Miranda and Hatem Ltaief and Rosa Badia and Xavier Martorell and Jesus Labarta and David Keyes},
	title = {Dense Matrix Computations on NUMA Architectures with Distance-Aware Work Stealing},
	journal = {Supercomputing Frontiers and Innovations (SuperFRI)},
	volume = {2},
	number = {1},
	year = {2015},
	keywords = {},
	abstract = {We employ the dynamic runtime system OmpSs to decrease the overhead of data motion in the now ubiquitous non-uniform memory access (NUMA) high concurrency environment of multicore processors. The dense numerical linear algebra algorithms of Cholesky factorization and symmetric matrix inversion are employed as representative benchmarks. Work stealing occurs within an innovative NUMA-aware scheduling policy to reduce data movement between NUMA nodes. The overall approach achieves separation of concerns by abstracting the complexity of the hardware from the end users so that high productivity can be achieved. Performance results on a large NUMA system outperform the state-of-the-art existing implementations up to a two fold speedup for the Cholesky factorization, as well as the symmetric matrix inversion, while the OmpSs-enabled code maintains strong similarity to its original sequential version.},	
}

@ARTICLE{Unat2017localitysurvey,
author={D. Unat and A. Dubey and T. Hoefler and J. Shalf and M. Abraham and M. Bianco and B. L. Chamberlain and R. Cledat and H. C. Edwards and others},
journal={IEEE Transactions on Parallel and Distributed Systems (TPDS)},
title={Trends in Data Locality Abstractions for {HPC} Systems},
year={2017},
volume={28},
number={10},
keywords={cache storage;data flow analysis;data structures;parallel processing;programming languages;software libraries;HPC systems;application developers;data locality abstractions;data movement;data structures;energy consumption;energy performance;high performance computing;languages;libraries;runtime systems;Arrays;Distributed databases;Layout;Libraries;Market research;Parallel processing;Data locality;data layout;high-performance computing;locality-aware runtimes;programming abstractions},
doi={10.1109/TPDS.2017.2703149},
ISSN={1045-9219},}

@INPROCEEDINGS{Cheriere2015hetdist,
author={N. Cheriere and E. Saule},
booktitle={Proceedings of International Parallel and Distributed Processing Symposium Workshop (IPDPSW)},
title={Considerations on Distributed Load Balancing for Fully Heterogeneous Machines: Two Particular Cases},
year={2015},
volume={},
number={},
keywords={parallel programming;pattern clustering;probability;processor scheduling;resource allocation;GPU-accelerated clusters;approximation ratio;decentralized scheduling algorithms;distributed algorithms;distributed load balancing;fully heterogeneous machines;heterogeneous systems;homogeneous clusters;parallel systems;probability density function;work-stealing algorithms;Approximation algorithms;Approximation methods;Clustering algorithms;Load management;Processor scheduling;Program processors;Scheduling;Approximation Algorithms;Decentralized Algorithms;Load-Balancing;Unrelated Machine Scheduling},
doi={10.1109/IPDPSW.2015.36},
ISSN={},
address={Hyderab, India},
publisher={IEEE},}

@INPROCEEDINGS{Beri2015hetws,
author={T. Beri and S. Bansal and S. Kumar},
booktitle={Proceedings of International Parallel and Distributed Processing Symposium Workshop (IPDPSW)},
title={ProSteal: A Proactive Work Stealer for Bulk Synchronous Tasks Distributed on a Cluster of Heterogeneous Machines with Multiple Accelerators},
year={2015},
address={Hyderab, India},
publisher={IEEE},
volume={},
number={},
keywords={graphics processing units;parallel programming;resource allocation;shared memory systems;GPUs;ProSteal;Unicorn;bulk synchronous tasks;compute-communication overlap;half steal strategy;healthy steal success rate;heterogeneous machines;load balancing technique;many-core accelerators;multiple CPUs;multiple accelerators;proactive work stealer;random victim selection;remote data transfers;shared memory parallel programming;termination detection;Convolution;Data transfer;Graphics processing units;Load management;Matrix decomposition;Performance evaluation;Pipelines;Heterogeneous Architectures;High Performance Computing;Hybrid CPU-GPU Clusters;Multi Scheduling;Work Stealing},
doi={10.1109/IPDPSW.2015.7},
ISSN={},}

@INPROCEEDINGS{Paudel2013wslocal,
author={J. Paudel and O. Tardieu and J. N. Amaral},
booktitle={Proceedings of International Conference on Parallel Processing (ICPP)},
title={On the Merits of Distributed Work-Stealing on Selective Locality-Aware Tasks},
year={2013},
volume={},
number={},
keywords={distributed shared memory systems;performance evaluation;resource allocation;scheduling;Cowichan suites;Lonestar suites;X10;application-level task locality;asynchronous partitioned global address space programming model;distributed memory cluster;distributed shared-memory systems;distributed work-stealing;migration across nodes;performance evaluation;processor cluster;scheduler;selective locality-aware tasks;work-stealing load-balancing algorithms;work-stealing strategy;Distributed databases;Instruction sets;Parallel processing;Runtime;Sociology;Statistics;APGAS;Distributed Work Stealing;Performance;X10},
doi={10.1109/ICPP.2013.19},
ISSN={0190-3918},
address={Lyon, France},
publisher={IACC},}

@INPROCEEDINGS{Jeannot2016topo,
author={E. Jeannot and G. Mercier and F. Tessier},
booktitle={Proceedings of International Workshop on Communication Optimizations in HPC (COMHPC)},
title={Topology and Affinity Aware Hierarchical and Distributed Load-Balancing in Charm++},
year={2016},
volume={},
number={},
keywords={object-oriented programming;parallel machines;parallel programming;resource allocation;topology;trees (mathematics);LibTopoMap;TreeMatch;charm++;distributed load-balancing;parallel supercomputers;topology-aware load balancing;Central Processing Unit;Conferences;Load management;Network topology;Optimization;Runtime;Topology},
ISSN={},
address={Salt Lake City, USA},
publisher={ACM},}

@inproceedings{Diener2017locality,
 author = {Diener, Matthias and White, Sam and Kal\'e, Laxmikant V. and Campbell, Michael and Bodony, Daniel J. and Freund, Jonathan B.},
 title = {Improving the Memory Access Locality of Hybrid MPI Applications},
 booktitle = {Proceedings of the 24th European MPI Users' Group Meeting},
 series = {EuroMPI '17},
 year = {2017},
 isbn = {978-1-4503-4849-2},
 location = {Chicago, Illinois},
 pages = {11:1--11:10},
 articleno = {11},
 numpages = {10},
 acmid = {3127038},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {AMPI, MPI, OpenMp, hybrid applications, load balancing, memory access locality},
}

@inproceedings{penna:15,
	author   = {Pedro H. Penna and
                M\'arcio Catro and
                Henrique C. Freitas and
                Fran\c{c}ois Broquedis and
                Jean-Fran\c{c}ois M\'ehaut},
	editor    = {Sociedade Brasileira de Computa\c{c}ão},
	title     = {Uma Metodologia Baseada em Simula\c{c}ão e Algoritmo Gen\'etico para Explora\c{c}ão de Estrat\'egias de Escalonamento de La\c{c}os},
	booktitle = {XV Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD-SSC)},
	year      = {2015}
}

@INPROCEEDINGS{schedmatters2016,
author={J. Benson and T. Estrada and A. L. Rosenberg and M. Taufer},
booktitle={Proceedings of International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)},
title={Scheduling Matters: Area-Oriented Heuristic for Resource Management},
year={2016},
volume={},
number={},
keywords={cloud computing;scheduling;workflow management software;DAG workflow;area-oriented heuristic;capacity planning;cost reduction;resource management;resource utilization;Capacity planning;Context;Optimization;Processor scheduling;Resource management;Schedules;Scheduling},
ISSN={},
address={Los Angeles, USA},
publisher={IEEE},}

@misc{packdrop,
    author = "Student T",
    title  = "His Bacharel Thesis Title",
    howpublished = "Thesis (B. Sc.) - Universidade Federal de Santa Catarina",
    year     = "2017",
    month    = "12",
    note     = "Florian\'opolis, Santa Catarina",
}

@inproceedings{trahay2009scalable,
 title={A scalable and generic task scheduling system for communication libraries},
 author={Trahay, Fran{\c{c}}ois and Denis, Alexandre},
 booktitle={Proceedings of International Conference on Cluster Computing (CLUSTER)},
 year={2009},
 publisher={IEEE},
 address = {New Orleans, USA}
}

@article{simgrid,
  hal_id = {hal-01017319},
  title = {Versatile, Scalable, and Accurate Simulation of Distributed Applications and Platforms},
  author = {Casanova, Henri and Giersch, Arnaud and Legrand, Arnaud and Quinson, Martin and Suter, Fr{\'e}d{\'e}ric},
  publisher = {Elsevier},
  pages = {2899-2917},
  journal = {Journal of Parallel and Distributed Computing},
  volume = {74},
  number = {10},
  year = {2014},
  month = Jun,
  pdf = {http://hal.inria.fr/hal-01017319/PDF/simgrid3-journal.pdf},
}

@article{Gustafson1988,
 author = {Gustafson, John L.},
 title = {Reevaluating Amdahl's Law},
 journal = {Commun. ACM},
 issue_date = {May 1988},
 volume = {31},
 number = {5},
 month = may,
 year = {1988},
 issn = {0001-0782},
 pages = {532--533},
 numpages = {2},
 acmid = {42415},
 publisher = {ACM},
 address = {New York, NY, USA}
} 



@inproceedings{changa,
 author = {Jetley, Pritish and Wesolowski, Lukasz and Gioachin, Filippo and Kal{\'e}, Laxmikant V. and Quinn, Thomas R.},
 title = {Scaling Hierarchical N-body Simulations on GPU Clusters},
 booktitle = {Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis},
 series = {SC '10},
 year = {2010},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA}
}

@INPROCEEDINGS{IPDPS13:LULESH,
AUTHOR="Ian Karlin and Abhinav Bhatele and Jeff Keasler and Bradford L. Chamberlain and Jonathan Cohen and Zachary DeVito and Riyaz Haque and Dan Laney and Edward Luke and Felix Wang and David Richards and others",
TITLE="Exploring Traditional and Emerging Parallel Programming Models using a Proxy Application",
BOOKTITLE="Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS)",
ADDRESS="Boston, USA",
publisher = "IEEE",
YEAR=2013
}

@INPROCEEDINGS{namd,
        author = "Chao Mei and Yanhua Sun and Gengbin Zheng and
Eric J. Bohm and Laxmikant V.~Kal{\'e} and James C. Phillips and Chris Harrison",
        title = "Enabling and Scaling Biomolecular Simulations of 100~Million Atoms on Petascale Machines with a Multicore-optimized Message-driven Runtime",
        booktitle = "Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)",
        year = "2011",
        address = "Seattle, USA",
        publisher = "IEEE/ACM",
}

@article{padoin2017energy,
title = "Using Power Demand and Residual Load Imbalance in the Load Balancing to Save Energy of Parallel Systems",
journal = "Procedia Computer Science",
volume = "108",
address = {Z\"urich, Switzerland},
year = "2017",
publisher="Elsevier",
author = "Edson Luiz Padoin and Víctor Martínez and Philippe O.A. Navaux and Jean-François Méhaut",
keywords = "Energy Consumption, Load Balancing, DVFS, Power Demand, Energy Saving"
}


@INPROCEEDINGS{exapower2015,
author={J. Mair and Z. Huang and D. Eyers and Y. Chen},
booktitle={Proceedings of International Symposium on Cluster, Cloud and Grid Computing (CCGrid)},
title={Quantifying the Energy Efficiency Challenges of Achieving Exascale Computing},
year={2015},
address={Shenzhen, China},
publisher={IEEE/ACM},
keywords={parallel machines;performance evaluation;power aware computing;Green500 supercomputer list;PαPW metric;Top500 supercomputer list;energy efficiency;exascale computing;exascale supercomputer design;performance objective;power consumption;power efficiency scalability evaluation;power objective;Computer architecture;Market research;Power measurement;Program processors;Scalability;Servers;Supercomputers},
doi={10.1109/CCGrid.2015.130},
}

@INPROCEEDINGS{olam,
author={C. Osthoff and R. P. Souto and P. L. S. Dias and J. Panetta and P. Lopes},
booktitle={2012 31st International Conference of the Chilean Computer Science Society},
title={Atmospheric Model Cluster Performance Evaluation on Hybrid MPI/OpenMP/Cuda Programming Model Platform},
year={2012},
pages={216-222},
keywords={atmospheric techniques;geophysics computing;graphics processing units;message passing;multi-threading;multiprocessing systems;parallel architectures;Cuda kernels;MPI process;OLAM MPI parallel implementation;OpenMP thread;atmospheric model cluster performance evaluation;cluster core;global numerical simulation model;hybrid MPI/OpenMP/Cuda programming model platform;hybrid multicore/GPU cluster environment;multicore system;ocean-land-atmosphere model;parallel performance;programming models;Atmospheric modeling;Computational modeling;Graphics processing units;Kernel;Multicore processing;Numerical models;Performance evaluation;Atmospheric Numerical Simulation Model;Cluster;GPU;High Performance Computing;Multicore},
month={Nov},}

@article{ondes3d,
title = "High-performance finite-element simulations of seismic wave propagation in three-dimensional nonlinear inelastic geological media ",
journal = "Parallel Computing ",
volume = "36",
number = "5–6",
pages = "308 - 325",
year = "2010",
note = "Parallel Matrix Algorithms and Applications ",
author = "Fabrice Dupros and Florent De Martin and Evelyne Foerster and Dimitri Komatitsch and Jean Roman",
}

@inbook{petascale,
    author   = {Dunning, T. H. and
                Schulten, K. and
                Tromp, J. and
                Ostriker, J. P. and
                Droegemeier, K. and
                Xue, M. and
                Fussell, P.},
    title    = {Science and Engineering in the Petascale Era},
    booktitle= {Computing in Science and Engineering},
    issue    = {5},
    volume   = {11},
    year     = {2009},
    publisher= {IEEE},
}

@article{binlpt,
	author = {Pedro Henrique Penna and M\'arcio Castro and Patricia Plentz and Henrique C. Freitas and Fran\c{c}ois Broquedis and Jean-Fran\c{c}ois M\'ehaut},
	title = {BinLPT: A Novel Workload-Aware Loop Scheduler for Irregular Parallel Loops},
	journal = {Proceedings of Brazilian Symposium in High Performance Computing (WSCAD)},
	year = {2017},
	keywords = {},
	abstract = {Workload-aware loop schedulers were introduced to deliver better performance than classical strategies, but they present limitations on workload estimation, chunk scheduling and integrability with applications. Targeting these challenges, in this work we propose a novel workload-aware loop scheduler that is called BinLPT and it is based on three features. First, it relies on some user-supplied estimation of the workload of the target parallel loop. Second, BinLPT uses a greedy bin packing heuristic to adaptively partition the iteration space in several chunks. The maximum number of chunks to be produced is a parameter that may be fine-tuned. Third, it schedules chunks of iterations using a hybrid scheme based on the LPT rule and on-demand scheduling. We integrated BinLPT in OpenMP, and we evaluated its performance in a large-scale NUMA machine using a synthetic kernel and 3D N-Body Simulations. Our results revealed that BinLPT improves performance over OpenMP’s strategies by up to 45.13% and 37.15% in the synthetic and application kernels, respectively.},
	address={Campinas, Brazil},
	publisher={SBC},
}


@article{francesquini:14,
	author  = {Francesquini, Emilio and
	           Castro, M\'arcio and
	           Penna, Pedro H. and
	           Dupros, Fabrice and
	           de Freitas, Henrique Cota and
	           Navaux, Philippe Olivier Alexandre and
	           M\'ehaut, Jean-Fran\c{c}ois},
	journal = {Journal of Parallel and Distributed Computing (JPDC)},
	pages   = {32--48},
	title   = {On the Energy Efficiency and Performance of Irregular Applications on Multicore, NUMA and Manycore Platforms},
	volume  = {76},
	year    = {2014}
}


	
@article{olivier:12,
	author     = {Olivier, Stephen L and
	              Porterfield, Allan K and
	              Wheeler, Kyle B and
	              Spiegel, Michael and
	              Prins, Jan F},
	title      = {OpenMP Task Scheduling Strategies for Multicore NUMA Systems},
	journal    = {Int. J. High Perform. Comput. Appl.},
	volume     = {26},
	year       = {2012},
	pages      = {110--124},
	publisher  = {Sage Publications, Inc.},
}

@inproceedings{ding:13,
	author    = {Wei Ding and
	             Yuanrui Zhang and
	             Kandemir, M. and
	             Srinivas, J. and
	             Yedlapalli, P.},
	booktitle = {IEEE/ACM International Symposium on Code Generation and Optimization (CGO)},
	title     = {Locality-aware Mapping and Scheduling for Multicores},
	year      = {2013},
	pages     = {1-12},
	address = {Shenzhen, China},
}

@Inproceedings{loadbalancing,
author="Becker, Aaron
and Zheng, Gengbin
and Kal{\'e}, Laxmikant V.",
editor="Padua, David",
title="Load Balancing, Distributed Memory",
bookTitle="Encyclopedia of Parallel Computing",
series={},
year="2011",
publisher="Springer US",
address="Boston, MA",
pages="1043--1051",
}

@article{hybrid,
  title={Periodic hierarchical load balancing for large supercomputers},
  author={Zheng, Gengbin and Bhatel{\'e}, Abhinav and Meneses, Esteban and Kal{\'e}, Laxmikant V},
  journal={International Journal of High Performance Computing Applications (IJHPCA)},
  volume={25},
  number={4},
  year={2011},
  publisher={Sage Publications},
  address = {London, UK}
}

@InProceedings{Janjic2013,
author="Janjic, Vladimir and Hammond, Kevin",
title="How to be a Successful Thief",
bookTitle="Proceedings of International Conference on Parallel Processing (EuroPar)",
year="2013",
publisher="Springer",
address="Berlin, Germany",
abstract="Work Stealing has proved to be an effective method for load balancing regular divide-and-conquer (D{\&}C) applications on heterogeneous distributed systems, but there have been relatively few attempts to adapt it to address irregular D{\&}C applications. For such applications, it is essential to have a mechanism that can estimate dynamic system load during the execution of the applications. In this paper, we evaluate a number of work-stealing algorithms on a set of generic Unbalanced Tree Search (UTS) benchmarks. We present a novel Feudal Stealing work-stealing algorithm and show, using simulations, that it delivers consistently better speedups than other work-stealing algorithms for irregular D{\&}C applications on high-latency heterogeneous distributed systems. Compared to the best known work-stealing algorithm for high-latency distributed systems, we achieve improvements of between 9{\%} and 48{\%} for irregular D{\&}C applications.",
}

@article{Yang18wssurvey,
  author    = {Jixiang Yang and
               Qingbi He},
  title     = {Scheduling Parallel Computations by Work Stealing: {A} Survey},
  journal   = {International Journal of Parallel Programming (IJPP)},
  volume    = {46},
  number    = {2},
  year      = {2018},
  timestamp = {Wed, 21 Mar 2018 17:07:01 +0100},
}

@PHDTHESIS{MenonPHD,
        author="Harshitha Menon",
        title="Adaptive Load Balancing for {HPC} Applications",
        year="2016",
        school = {Department of Computer Science, University of Illinois at Urbana-Champaign},
}

@inproceedings{lifflander2012work,
  title="{Work Stealing and Persistence-based Load Balancers for Iterative Overdecomposed Applications}",
  author={Lifflander, Jonathan and Krishnamoorthy, Sriram and Kal\'e, Laxmikant V},
  booktitle={Proceedings of the 21st international symposium on High-Performance Parallel and Distributed Computing},
  pages={137--148},
  year={2012},
  organization={ACM}
}


@INPROCEEDINGS{hwtopo,
author={L. L. Pilla and P. O. A. Navaux and C. P. Ribeiro and P. Coucheney and F. Broquedis and B. Gaujal and J.-F. Méhaut},
booktitle={Proceedings of International Conference on Parallel and Distributed Systems (ICPADS)},
title={Asymptotically Optimal Load Balancing for Hierarchical Multi-Core Systems},
year={2012},
volume={},
number={},
keywords={multiprocessing systems;parallel machines;resource allocation;topology;CHARM++ Parallel System;NUMA design;asymptotically optimal load balancing;cache subsystem;hierarchical core topology;hierarchical multicore systems;high processing power;machine architecture;machine topology characteristics;memory subsystem;multicore machines;parallel application communication patterns;parallel machines;topology aware load balancing algorithm;Algorithm design and analysis;Benchmark testing;Libraries;Load management;Multicore processing;Runtime;Topology;algorithm;hierarchical architecture;load balancing;multi-core;performance evaluation},
doi={10.1109/ICPADS.2012.41},
ISSN={1521-9097},
address={Singapore},
publisher={IEEE},}

@INPROCEEDINGS{Zheng2010,
author={G. Zheng and E. Meneses and A. Bhatele and L. V. Kal\'e},
booktitle={2010 39th International Conference on Parallel Processing Workshops},
title={Hierarchical Load Balancing for Charm++ Applications on Large Supercomputers},
year={2010},
pages={436-444},
keywords={mainframes;parallel machines;parallel processing;resource allocation;Blue Gene-P machine;Charm++ applications;automatic dynamic hierarchical load balancing method;centralized load balancing algorithms;measurement-based load balancing framework;parallel machines;supercomputers;Databases;Lead;Load management;Load modeling;Memory management;Program processors;Scalability;hierarchical algorithms;load balancing;scalability},
month={Sept},}

@inbook {commaware,
title = {An Overview of Topology Mapping Algorithms and Techniques in High-Performance Computing},
author = {Hoefler, Torsten and Jeannot, Emmanuel and Mercier, Guillaume},
editor = {Jeannot, Emmanuel and Zilinskas, Julius},
publisher = {John Wiley \& Sons, Inc.},
keywords = {high-performance computing (HPC), mapping enforcement techniques, physical topology, topology mapping algorithms, virtual topology},
booktitle = {High-Performance Computing on Complex Environments},
year = {2014},
}
@INPROCEEDINGS{Bathele2011graph,
author={A. Bhatele and L. V. Kal\'e},
booktitle={2011 IEEE International Conference on High Performance Computing and Communications},
title={Heuristic-Based Techniques for Mapping Irregular Communication Graphs to Mesh Topologies},
year={2011},
volume={},
number={},
pages={765-771},
ISSN={},
month={Sept},
}

@INPROCEEDINGS{pskel,
author={A. D. Pereira and M. Castro and M. A. R. Dantas and R. C. O. Rocha and L. F. W. Góes},
booktitle={2017 International Conference on High Performance Computing Simulation (HPCS)},
title={Extending OpenACC for Efficient Stencil Code Generation and Execution by Skeleton Frameworks},
year={2017},
volume={},
number={},
pages={719-726},
keywords={graphics processing units;parallel programming;program compilers;software performance evaluation;OpenACC extensions;OpenACC programming model;abstract accelerator model;accelerator devices;code execution;efficient stencil code generation;general-purpose approach;least common denominator;optimization;parallel skeleton frameworks;performance improvement;stencil applications;stencil extensions;work-partitioning;Computer architecture;Graphics processing units;Jacobian matrices;Optimization;Programming;Runtime;Skeleton;CUDA;OpenACC;skeleton frameworks;source-to-source compilation;stencil},
doi={10.1109/HPCS.2017.110},
ISSN={},
month={July},}

@phdthesis{pillaphd,
    author = {La\'ercio Lima Pilla},
    title = {Topology-Aware Load Balancing for Performance Portability over Parallel High Performance Systems},
    school = {Universidade Federal do Rio Grande do Sul},
    year = {2014},
    month ={4},
    address = {Porto Alegre, Rio Grande do Sul},
}

@PHDTHESIS{GengbinThesis,
        author="Gengbin Zheng",
        title="Achieving high performance on extremely large parallel machines: performance prediction and load balancing",
        year="2005",
        school = {Department of Computer Science, University of Illinois at Urbana-Champaign},
}

@Article{ZoltanManual,
   author = {E. G. Boman and U. V. Catalyurek and C. Chevalier and K. D. Devine},
   title = {The {Z}oltan and {I}sorropia Parallel Toolkits for Combinatorial Scientific Computing: Partitioning, Ordering, and Coloring},
   journal = {Scientific Programming},
   year = {2012},
   volume = {20},
   number = {2},
   pages = {129--150}
} 

@Inbook{tiling,
author="Irigoin, Fran{\c{c}}ois",
editor="Padua, David",
title="Tiling",
bookTitle="Encyclopedia of Parallel Computing",
year="2011",
publisher="Springer US",
address="Boston, MA",
pages="2040--2049",
}

@Inproceedings{ZoltanParHypRepart07,
   title = {Hypergraph-based Dynamic Load Balancing for Adaptive Scientific Computations},
   author = {U. V. Catalyurek and E. G. Boman and K. D. Devine and D. Bozdag and R. T. Heaphy and L. A. Riesen},
   booktitle = {Proceedings of International Parallel and Distributed Processing Symposium (IPDPS)},
   publisher = {IEEE},
   year = {2007},
   address={Long Beach, USA},
}

@INPROCEEDINGS{Deveci2015,
author={M. Deveci and K. Kaya and B. U\c{c}ar and U. V. Catalyurek},
booktitle={Proceedings of International Parallel and Distributed Processing Symposium (IPDPS)},
title={Fast and High Quality Topology-Aware Task Mapping},
year={2015},
publisher={IEEE},
address={Hyderabad, India},
keywords={multiprocessor interconnection networks;network topology;parallel machines;communicating tasks;communication hops;communication-only application;concurrently executable tasks;exascale-capable supercomputers;interconnection networks;link contentions;parallel SpMV kernel;parallel applications;topology-aware task-mapping methods;Complexity theory;Heuristic algorithms;Measurement;Network topology;Partitioning algorithms;Program processors;Topology;Task mapping;communication graph;partitioning},
}


@inproceedings{nuco,
  title={A hierarchical approach for load balancing on parallel multi-core systems},
  author={Pilla, Laercio L and Ribeiro, Christiane Pousa and Cordeiro, Daniel and Mei, Chao and Bhatele, Abhinav and Navaux, Philippe OA and Broquedis, Francois and M\'haut, Jean-Francois and Kal\'e, Laxmikant V},
  booktitle={Parallel Processing (ICPP), 2012 41st International Conference on},
  pages={118--127},
  year={2012},
  organization={IEEE}
}


@inproceedings{grapevine,
 Author = {Menon, Harshitha and Kal{\'e}, Laxmikant},
 title = {A Distributed Dynamic Load Balancer for Iterative Applications},
 booktitle = {Proceedings of International Conference for High Performance Computing, Networking, Storage and Analysis (SC)},
 series = {},
 year = 2013,
 location = {Denver, Colorado},
 articleno = {15},
 numpages = {11},
 publisher = {ACM},
 address = {Denver, USA},
 keywords = {distributed load balancer, epidemic algorithm, load balancing}
} 

@article{MigPFrighi,
title = "MigPF: Towards on self-organizing process rescheduling of Bulk-Synchronous Parallel applications",
journal = "Future Generation Computer Systems",
volume = "78",
pages = "272 - 286",
year = "2018",
issn = "0167-739X",
doi = "https://doi.org/10.1016/j.future.2016.05.004",
url = "http://www.sciencedirect.com/science/article/pii/S0167739X16301145",
author = "Rodrigo da Rosa Righi and Roberto de Quadros Gomes and Vinicius Facco Rodrigues and Cristiano André da Costa and Antonio Marcos Alberti and Laércio Lima Pilla and Philippe Olivier Alexandre Navaux",
keywords = "Bulk Synchronous Parallel, Process migration, Load balancing, Self-organizing"
}

@article{diffus,
  title={Strategies for dynamic load balancing on highly parallel computers},
  author={Willebeek-LeMair, Marc H and Reeves, Anthony P.},
  journal={IEEE Transactions on Parallel and Distributed Systems (TPDS)},
  volume={4},
  number={9},
  year={1993},
  publisher={IEEE}
}

@Inbook{stapl,
author="Rauchwerger, Lawrence
and Arzu, Francisco
and Ouchi, Koji",
editor="O'Hallaron, David R.",
title="Standard Templates Adaptive Parallel Library (STAPL)",
bookTitle="Languages, Compilers, and Run-Time Systems for Scalable Computers: 4th International Workshop, LCR' 98 Pittsburgh, PA, USA, May 28--30, 1998 Selected Papers",
year="1998",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="402--409",
}

@techreport{namd0,
  author	= "Abhinav Bhatele and Sameer Kumar and Chao Mei and James C. Phillips and Gengbin Zheng and Laxmikant V. Kal\'e",
  title		= "{NAMD: A Portable and Highly Scalable Program for Biomolecular Simulations}",
  year		= "2009",
  month		= "February",
  institution	= "Department of Computer Science, University of Illinois at Urbana-Champaign"
}

@article{CharmLOTR,
  title={Power, Reliability, and Performance: One System to Rule them All},
  author={Acun, Bilge and Langer, Akhil and Meneses, Esteban and Menon, Harshitha and Sarood, Osman and Totoni, Ehsan and Kal{\'e}, Laxmikant V},
  journal={Computer},
  volume={49},
  number={10},
  year={2016},
  publisher={IEEE}
}

@inproceedings{amr:langer12,
  author        = "Akhil Langer and Jonathan Lifflander and Phil Miller and  Kuo-Chuan Pan and and Laxmikant V. Kal\'e and Paul Ricker",
  title         = "{Scalable Algorithms for Distributed-Memory Adaptive Mesh Refinement}",
  booktitle     = "Proceedings of the 24th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2012)",
  month         = "October",
  year          = "2012",
  address       = "New York, USA",
}

@mastersthesis{metabalancer,
	author = "Harshitha Menon",
	title = {Meta-Balancer: Automated load balancing based on application behavior},
	year = "2012",
	school = {Dept. of Computer Science, University of Illinois},
	note = "http://charm.cs.uiuc.edu/newPapers/12-41"
}

@book{npcomplete,
 author = {Garey, Michael R. and Johnson, David S.},
 title = {Computers and Intractability: A Guide to the Theory of NP-Completeness},
 year = {1979},
 publisher = {W. H. Freeman \& Co.},
 address = {New York, USA},
 pages={90}
} 

@inproceedings{gossip,
 author = {Demers, Alan and Greene, Dan and Hauser, Carl and Irish, Wes and Larson, John and Shenker, Scott and Sturgis, Howard and Swinehart, Dan and Terry, Doug},
 title = {Epidemic Algorithms for Replicated Database Maintenance},
 booktitle = {Proceedings of Symposium on Principles of Distributed Computing (PODC)},
 year = {1987},
 address = {Vancouver, Canada},
 numpages = {12},
 publisher = {ACM},}


@inproceedings{Castro-Penna-WSCAD:2017,
address = {Campinas, Brazil},
author = {Penna, Pedro Henrique and Castro, M{\'{a}}rcio and Plentz, Patricia Della M{\'{e}}a and Freitas, Henrique Cota and Broquedis, Fran{\c{c}}ois and M{\'{e}}haut, Jean-Fran{\c{c}}ois},
booktitle = {Proceedings of Brazilian Symposium on High Performance Computing (WSCAD)},
issn = {2358-6613},
publisher = {SBC},
title = {{BinLPT}: A Workload-Aware Parallel Loop Scheduler for Large-Scale Multicore Platforms},
year = {2017},
}

@ARTICLE{stenciltiling,
author={I. Z. Reguly and G. R. Mudalige and M. B. Giles},
journal={IEEE Transactions on Parallel and Distributed Systems (TPDS)},
title={Loop Tiling in Large-Scale Stencil Codes at Run-Time with OPS},
year={2018},
volume={29},
number={4},
keywords={Navier-Stokes equations;computational fluid dynamics;distributed memory systems;optimisation;optimising compilers;parallel architectures;parallel machines;parallel processing;parallel programming;program compilers;program control structures;shared memory systems;Cloverleaf 2D/3D proxy applications;OPS;OPS applications;PDE applications;compilation units;compilers;compressible Navier-Stokes solver OpenSBLI;data locality improving optimisation;data movement;delayed execution;distributed-memory systems;execution paths;grid point;large-scale stencil codes;linear solver TeaLeaf;loop nest data access information;loop tiling;memory size 16.0 GByte;optimisations;prior research;run-time analysis;run-time parameters;shared-memory;stencil DSL;Algorithm design and analysis;Computer architecture;DSL;Electronic mail;Libraries;Optimization;Schedules;DSL;OPS;cache blocking;memory locality;stencil;structured mesh;tiling},
doi={10.1109/TPDS.2017.2778161},
ISSN={1045-9219},
}