@article{Brown:2010,
  Author = {{Brown}, J.},
  Journal = {Journal of Scientific Computing},
  Volume = 45,
  Month = oct,
  Title = {Efficient Nonlinear Solvers for Nodal High-Order Finite Elements in 3D},
  Year = 2010,
  doi = {10.1007/s10915-010-9396-8},
}

@misc{C99-lang,
  title={ISO/IEC 9899: 1999 Programming Languages-C},
  author={{International Standards Organisation}},
  year={1999},
  publisher={American National Standards Institute, New York}
}

@article{CEED-ECP-paper,
  author  = {Kolev, Tzanio and
             Fischer, Paul and
             Min, Misun and
             Dongarra, Jack and
             Brown, Jed and
             Dobrev, Veselin and
             Warburton, Tim and
             Tomov, Stanimire and
             Shephard, Mark S. and
             Abdelfattah, Ahmad and
             Barra, Valeria and
             Beams, Natalie and
             Camier, Jean-Sylvain and
             Chalmers, Noel and
             Dudouit, Yohann and
             Karakus, Ali and
             Karlin, Ian and
             Kerkemeier, Stefan and
             Lan, Yu-Hsiang and
             Medina, David and
             Merzari, Elia and
             Obabko, Aleksandr and
             Pazner, Will and
             Rathnayake, Thilina and
             Smith, Cameron W. and
             Spies, Lukas and
             Swirydowicz, Kasia and
             Thompson, Jeremy and
             Tomboulides, Ananias and
             Tomov, Vladimir},
  title   = {Efficient Exascale Discretizations: High-Order Finite Element Methods},
  journal = {International Journal of High Performance Computing Applications},
  year    = {2021},
  doi     = {10.1177/10943420211020803}
}

@misc{CEEDMS25,
  author       = {Brown, Jed and
                  Abdelfattah, Ahmad and
                  Barra, Valeria and
                  Dobrev, Veselin and
                  Dudouit, Yohann and
                  Fischer, Paul and
                  Kolev, Tzanio and
                  Medina, David and
                  Min, Misun and
                  Ratnayaka, Thilina and
                  Smith, Cameron and
                  Thompson, Jeremy and
                  Tomov, Stanimire and
                  Tomov, Vladimir and
                  Warburton, Tim},
  title        = {{CEED ECP Milestone Report: Public release of CEED
                   2.0}},
  year         = 2019,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.2641316}
}

@misc{CEEDMS34,
  author       = {Kolev, Tzanio and
                  Fischer, Paul and
                  Abdelfattah, Ahmad and
                  Ananthan, Shreyas and
                  Barra, Valeria and
                  Beams, Natalie and
                  Bleile, Ryan and
                  Brown, Jed and
                  Carson, Robert and
                  Camier, Jean-Sylvain and
                  Churchfield, Matthew and
                  Dobrev, Veselin and
                  Dongarra, Jack and
                  Dudouit, Yohann and
                  Karakus, Ali and
                  Kerkemeier, Stefan and
                  Lan, YuHsiang and
                  Medina, David and
                  Merzari, Elia and
                  Min, Misun and
                  Parker, Scott and
                  Ratnayaka, Thilina and
                  Smith, Cameron and
                  Sprague, Michael and
                  Stitt, Thomas and
                  Thompson, Jeremy and
                  Tomboulides, Ananias and
                  Tomov, Stanimire and
                  Tomov, Vladimir and
                  Vargas, Arturo and
                  Warburton, Tim and
                  Weiss, Kenneth},
  title        = {{CEED ECP Milestone Report: Improve performance and
                   capabilities of CEED-enabled ECP applications on
                   Summit/Sierra}},
  year         = 2020,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.3860804}
}

@misc{CEEDwebsite,
  title = "CEED",
  url = "https://ceed.exascaleproject.org/",
  year = "2021"
}

@misc{CUDAwebsite,
  title = "CUDA",
  url = "https://developer.nvidia.com/about-cuda",
  year = "2021"
}

@article{Fischer2020scalability,
  title={Scalability of high-performance PDE solvers},
  author={Paul Fischer and Misun Min and Thilina Rathnayake and Som Dutta and Tzanio Kolev and Veselin Dobrev and Jean-Sylvain Camier and Martin Kronbichler and Tim Warburton and Kasia Świrydowicz and Jed Brown},
  journal={The International Journal of High Performance Computing Applications},
  year={2020},
  doi = "10.1177/1094342020915762"
}

@book{Fortran77-lang,
  title={Standard {X3}. 9-1978, Programming Language {Fortran} (revision of {ANSI X2}. 9-1966)},
  author={ANSI},
  journal={New York: ANSI},
  year={1978}
}

@misc{HIPwebsite,
  title = "HIP",
  url = "https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-GUIDE.html",
  year = "2021"
}

@article{Julia-lang,
  title={Julia: A fresh approach to numerical computing},
  author={Bezanson, Jeff and Edelman, Alan and Karpinski, Stefan and Shah, Viral B},
  journal={SIAM {R}eview},
  volume={59},
  number={1},
  pages={65--98},
  year={2017},
  publisher={SIAM},
  doi={10.1137/141000671}
}

@misc{libceed-user-manual,
  author       = {Abdelfattah, Ahmad and
                  Barra, Valeria and
                  Beams, Natalie and
                  Brown, Jed and
                  Camier, Jean-Sylvain and
                  Dobrev, Veselin and
                  Dudouit, Yohann and
                  Ghaffari, Leila and
                  Kolev, Tzanio and
                  Medina, David and
                  Pazner, Will and
                  Rathnayake, Thilina and
                  Thompson, Jeremy L and
                  Tomov, Stanimire},
  title        = {libCEED User Manual},
  month        = mar,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {0.8},
  doi          = {10.5281/zenodo.4895340}
}

@InProceedings{libceed-paper-proc-scipy-2020,
  author    = {Valeria Barra and Jed Brown and Jeremy Thompson and Yohann Dudouit},
  title     = {{H}igh-performance operator evaluations with ease of use: lib{C}{E}{E}{D}'s {P}ython interface},
  booktitle = {{P}roceedings of the 19th {P}ython in {S}cience {C}onference},
  pages     = {85 - 90},
  year      = {2020},
  editor    = {{M}eghann {A}garwal and {C}hris {C}alloway and {D}illon {N}iederhut and {D}avid {S}hupe},
  doi       = {10.25080/Majora-342d178e-00c}
}

@misc{LIBXSMM,
  title = "{LIBXSMM development site}",
  url = "http://github.com/hfp/libxsmm",
  year = "2021"
}

@misc{MAGMAwebsite,
  title = "{MAGMA development site}",
  url = "https://bitbucket.org/icl/magma",
  year = "2021"
}

@misc{MFEMlibrary,
  title = "{MFEM}: {Modular Finite Element Methods Library}",
  url = "https://mfem.org/",
  year = "2021",
  doi = "10.11578/dc.20171025.1248"
}

@article{mfem-paper,
  title   = {{MFEM}: A Modular Finite Element Library},
  author  = {R. Anderson and J. Andrej and A. Barker and J. Bramwell and J.-S. Camier and
             J. Cerveny V. Dobrev and Y. Dudouit and A. Fisher and Tz. Kolev and W. Pazner and
             M. Stowell and V. Tomov and I. Akkerman and J. Dahm and D. Medina and S. Zampini},
  journal = {Computers \& Mathematics with Applications},
  doi     = {10.1016/j.camwa.2020.06.009},
  year    = {2020}
}

@misc{Nekwebsite,
  title = "Nek5000",
  url = "https://nek5000.mcs.anl.gov/",
  year = "2021"
}

@inproceedings{Numba,
author = {Lam, Siu Kwan and Pitrou, Antoine and Seibert, Stanley},
title = {Numba: A LLVM-Based Python JIT Compiler},
year = {2015},
isbn = {9781450340052},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
doi = {10.1145/2833157.2833162},
abstract = {Dynamic, interpreted languages, like Python, are attractive for domain-experts and scientists experimenting with new ideas. However, the performance of the interpreter is often a barrier when scaling to larger data sets. This paper presents a just-in-time compiler for Python that focuses in scientific and array-oriented computing. Starting with the simple syntax of Python, Numba compiles a subset of the language into efficient machine code that is comparable in performance to a traditional compiled language. In addition, we share our experience in building a JIT compiler using LLVM[1].},
booktitle = {Proceedings of the Second Workshop on the LLVM Compiler Infrastructure in HPC},
articleno = {7},
numpages = {6},
keywords = {compiler, LLVM, Python},
location = {Austin, Texas},
series = {LLVM '15}
}

@Article{NumPy,
 title         = {Array programming with {NumPy}},
 author        = {Charles R. Harris and K. Jarrod Millman and St{'{e}}fan J.
                 van der Walt and Ralf Gommers and Pauli Virtanen and David
                 Cournapeau and Eric Wieser and Julian Taylor and Sebastian
                 Berg and Nathaniel J. Smith and Robert Kern and Matti Picus
                 and Stephan Hoyer and Marten H. van Kerkwijk and Matthew
                 Brett and Allan Haldane and Jaime Fern{'{a}}ndez del
                 R{'{\i}}o and Mark Wiebe and Pearu Peterson and Pierre
                 G{'{e}}rard-Marchant and Kevin Sheppard and Tyler Reddy and
                 Warren Weckesser and Hameer Abbasi and Christoph Gohlke and
                 Travis E. Oliphant},
 year          = {2020},
 month         = sep,
 journal       = {Nature},
 volume        = {585},
 number        = {7825},
 pages         = {357--362},
 doi           = {10.1038/s41586-020-2649-2},
 publisher     = {Springer Science and Business Media {LLC}}
}

@misc{NVRTCwebsite,
  title = "NVRTC",
  url = "https://docs.nvidia.com/cuda/nvrtc/index.html",
  year = "2021"
}

@misc{OCCAwebsite,
  title = "{OCCA} development site",
  url = "http://github.com/libocca/occa",
  year = "2021"
}

@article{Orszag:1980,
  title = "Spectral methods for problems in complex geometries",
  journal = "Journal of Computational Physics",
  volume = "37",
  pages = "70 - 92",
  year = "1980",
  doi = "10.1016/0021-9991(80)90005-4",
  author = "Steven A Orszag"
}

@TechReport{PETScUserManual,
  author = {Satish Balay and Shrirang Abhyankar and Mark~F. Adams and Jed Brown and Peter Brune
            and Kris Buschelman and Lisandro Dalcin and Alp Dener and Victor Eijkhout and William~D. Gropp
            and Dmitry Karpeyev and Dinesh Kaushik and Matthew~G. Knepley and Dave~A. May and Lois Curfman McInnes
            and Richard Tran Mills and Todd Munson and Karl Rupp and Patrick Sanan
            and Barry~F. Smith and Stefano Zampini and Hong Zhang and Hong Zhang},
  title  = {{PETS}c Users Manual},
  institution = {Argonne National Laboratory},
  year   = 2021,
  number = {ANL-95/11 - Revision 3.15}
}

@misc{Python-lang,
  title = "Python",
  url = "https://www.python.org/",
  year = "2021",
}

@misc{Rust-lang,
  title = "Rust",
  url = "https://www.rust-lang.org/",
  year = "2021",
}

@misc{python-cffi,
  title = "C Foreign Function Interface for {Python}",
  url = "https://cffi.readthedocs.io",
  year = "2021",
}

@article{straka1993numerical,
  title={Numerical solutions of a non-linear density current: A benchmark solution and comparisons},
  author={Straka, Jerry M and Wilhelmson, Robert B and Wicker, Louis J and Anderson, John R and Droegemeier, Kelvin K},
  journal={International Journal for Numerical Methods in Fluids},
  volume={17},
  number={1},
  pages={1--22},
  year={1993},
  publisher={Wiley Online Library},
  doi={10.1002/fld.1650170103}
}

@book{deville2002highorder,
  title={High-order methods for incompressible fluid flow},
  author={Deville, Michel O and Fischer, Paul F and Mund, Ernest H},
  year={2002},
  publisher={Cambridge University Press},
  isbn={0-521-45309-7}
}

@article{gropp2014using,
  title={Using {MPI}: Portable Parallel Programming with the Message-Passing Interface},
  author={Gropp, William and Lusk, Ewing and Skjellum, Anthony},
  year={2014},
  publisher={The MIT Press},
  isbn={9780262527392}
}

@article{libMeshPaper,
  author = {Benjamin S. Kirk and John W. Peterson and Roy H. Stogner and Graham F. Carey},
  title = {{\texttt{libMesh}: A C++ Library for Parallel Adaptive Mesh Refinement/Coarsening Simulations}},
  journal = {Engineering with Computers},
  volume = 22,
  number = {3--4},
  pages = {237--254},
  year = 2006,
  doi = {10.1007/s00366-006-0049-3}
}
@book{LoggMardalWells2012,
  title  = {Automated Solution of Differential Equations by the Finite Element Method: The {FEniCS} book},
  author = {Anders Logg and Kent-Andre Mardal and Garth N. Wells and others},
  editor = {Anders Logg and Kent-Andre Mardal and Garth N. Wells},
  volume = {84},
  year = {2012},
  publisher = {Springer},
  doi = {10.1007/978-3-642-23099-8},
  isbn = {978-3-642-23098-1}
}

@article{dealII92,
  title     = {The \texttt{deal.II} Library, Version 9.2},
  author    = {Daniel Arndt and Wolfgang Bangerth and Bruno Blais and
               Thomas C. Clevenger and Marc Fehling and Alexander V. Grayver and
               Timo Heister and Luca Heltai and Martin Kronbichler and Matthias Maier and
               Peter Munch and Jean-Paul Pelteret and Reza Rastak and
               Ignacio Thomas and Bruno Turcksin and Zhuoran Wang and David Wells},
  journal   = {Journal of Numerical Mathematics},
  publisher = {De Gruyter},
  year      = {2020},
  volume    = {28},
  number    = {3},
  pages     = {131-146},
  DOI       = {10.1515/jnma-2020-0043},
  url       = {https://dealii.org/deal92-preprint.pdf}
}

@misc{kruppcomparison,
  title="{CPU-GPU-MIC} Comparision Charts",
  author={Karl Rupp},
  url={https://github.com/karlrupp/cpu-gpu-mic-comparison},
  year={2020}
}

@article{williams2009roofline,
  title={Roofline: an insightful visual performance model for multicore architectures},
  author={Williams, Samuel and Waterman, Andrew and Patterson, David},
  journal={Communications of the ACM},
  volume={52},
  number={4},
  pages={65--76},
  year={2009},
  publisher={ACM},
  doi={10.1145/1498765.1498785}
}

@article{babuska1994hpfem,
  title={The $p$ and $h-p$ versions of the finite element method, basic principles and properties},
  author={Babu{\v{s}}ka, Ivo and Suri, Manil},
  journal={SIAM Review},
  volume={36},
  number={4},
  pages={578--632},
  year={1994},
  publisher={SIAM},
  doi={10.1137/1036141}
}

@article{lottes2005hms,
  title={Hybrid Multigrid/{Schwarz} Algorithms for the Spectral Element Method},
  author={Lottes, J.W. and Fischer, P.F.},
  journal={Journal of Scientific Computing},
  volume={24},
  number={1},
  pages={45--78},
  year={2005},
  publisher={Springer},
  doi={10.1007/s10915-004-4787-3}
}

@article{zhang2021petscsf,
  title={The {PetscSF} Scalable Communication Layer},
  author={Zhang, Junchao and Brown, Jed and Balay, Satish and Faibussowitsch, Jacob and Knepley, Matthew and Marin, Oana and Mills, Richard Tran and Munson, Todd and Smith, Barry F and Zampini, Stefano},
  journal={IEEE Transactions on Parallel and Distributed Systems},
  archivePrefix={arXiv},
  eprint={2102.13018},
  year={2021},
  doi={10.1109/TPDS.2021.3084070}
}