1@article{Brown:2010, 2 Author = {{Brown}, J.}, 3 Journal = {Journal of Scientific Computing}, 4 Volume = 45, 5 Month = oct, 6 Title = {Efficient Nonlinear Solvers for Nodal High-Order Finite Elements in 3D}, 7 Year = 2010, 8 doi = {10.1007/s10915-010-9396-8}, 9} 10 11@misc{C99-lang, 12 title={ISO/IEC 9899: 1999 Programming Languages-C}, 13 author={{International Standards Organisation}}, 14 year={1999}, 15 publisher={American National Standards Institute, New York} 16} 17 18@article{CEED-ECP-paper, 19 author = {Kolev, Tzanio and 20 Fischer, Paul and 21 Min, Misun and 22 Dongarra, Jack and 23 Brown, Jed and 24 Dobrev, Veselin and 25 Warburton, Tim and 26 Tomov, Stanimire and 27 Shephard, Mark S. and 28 Abdelfattah, Ahmad and 29 Barra, Valeria and 30 Beams, Natalie and 31 Camier, Jean-Sylvain and 32 Chalmers, Noel and 33 Dudouit, Yohann and 34 Karakus, Ali and 35 Karlin, Ian and 36 Kerkemeier, Stefan and 37 Lan, Yu-Hsiang and 38 Medina, David and 39 Merzari, Elia and 40 Obabko, Aleksandr and 41 Pazner, Will and 42 Rathnayake, Thilina and 43 Smith, Cameron W. and 44 Spies, Lukas and 45 Swirydowicz, Kasia and 46 Thompson, Jeremy and 47 Tomboulides, Ananias and 48 Tomov, Vladimir}, 49 title = {Efficient Exascale Discretizations: High-Order Finite Element Methods}, 50 journal = {International Journal of High Performance Computing Applications}, 51 year = {2021}, 52 doi = {10.1177/10943420211020803} 53} 54 55@misc{CEEDMS25, 56 author = {Brown, Jed and 57 Abdelfattah, Ahmad and 58 Barra, Valeria and 59 Dobrev, Veselin and 60 Dudouit, Yohann and 61 Fischer, Paul and 62 Kolev, Tzanio and 63 Medina, David and 64 Min, Misun and 65 Ratnayaka, Thilina and 66 Smith, Cameron and 67 Thompson, Jeremy and 68 Tomov, Stanimire and 69 Tomov, Vladimir and 70 Warburton, Tim}, 71 title = {{CEED ECP Milestone Report: Public release of CEED 72 2.0}}, 73 year = 2019, 74 publisher = {Zenodo}, 75 doi = {10.5281/zenodo.2641316} 76} 77 78@misc{CEEDMS34, 79 author = {Kolev, Tzanio and 80 Fischer, Paul and 81 Abdelfattah, Ahmad and 82 Ananthan, Shreyas and 83 Barra, Valeria and 84 Beams, Natalie and 85 Bleile, Ryan and 86 Brown, Jed and 87 Carson, Robert and 88 Camier, Jean-Sylvain and 89 Churchfield, Matthew and 90 Dobrev, Veselin and 91 Dongarra, Jack and 92 Dudouit, Yohann and 93 Karakus, Ali and 94 Kerkemeier, Stefan and 95 Lan, YuHsiang and 96 Medina, David and 97 Merzari, Elia and 98 Min, Misun and 99 Parker, Scott and 100 Ratnayaka, Thilina and 101 Smith, Cameron and 102 Sprague, Michael and 103 Stitt, Thomas and 104 Thompson, Jeremy and 105 Tomboulides, Ananias and 106 Tomov, Stanimire and 107 Tomov, Vladimir and 108 Vargas, Arturo and 109 Warburton, Tim and 110 Weiss, Kenneth}, 111 title = {{CEED ECP Milestone Report: Improve performance and 112 capabilities of CEED-enabled ECP applications on 113 Summit/Sierra}}, 114 year = 2020, 115 publisher = {Zenodo}, 116 doi = {10.5281/zenodo.3860804} 117} 118 119@misc{CEEDwebsite, 120 title = "CEED", 121 url = "https://ceed.exascaleproject.org/", 122 year = "2021" 123} 124 125@misc{CUDAwebsite, 126 title = "CUDA", 127 url = "https://developer.nvidia.com/about-cuda", 128 year = "2021" 129} 130 131@article{Fischer2020scalability, 132 title={Scalability of high-performance PDE solvers}, 133 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}, 134 journal={The International Journal of High Performance Computing Applications}, 135 year={2020}, 136 doi = "10.1177/1094342020915762" 137} 138 139@book{Fortran77-lang, 140 title={Standard {X3}. 9-1978, Programming Language {Fortran} (revision of {ANSI X2}. 9-1966)}, 141 author={ANSI}, 142 journal={New York: ANSI}, 143 year={1978} 144} 145 146@misc{HIPwebsite, 147 title = "HIP", 148 url = "https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-GUIDE.html", 149 year = "2021" 150} 151 152@article{Julia-lang, 153 title={Julia: A fresh approach to numerical computing}, 154 author={Bezanson, Jeff and Edelman, Alan and Karpinski, Stefan and Shah, Viral B}, 155 journal={SIAM {R}eview}, 156 volume={59}, 157 number={1}, 158 pages={65--98}, 159 year={2017}, 160 publisher={SIAM}, 161 doi={10.1137/141000671} 162} 163 164@misc{libceed-user-manual, 165 author = {Abdelfattah, Ahmad and 166 Barra, Valeria and 167 Beams, Natalie and 168 Brown, Jed and 169 Camier, Jean-Sylvain and 170 Dobrev, Veselin and 171 Dudouit, Yohann and 172 Ghaffari, Leila and 173 Kolev, Tzanio and 174 Medina, David and 175 Pazner, Will and 176 Rathnayake, Thilina and 177 Thompson, Jeremy L and 178 Tomov, Stanimire}, 179 title = {libCEED User Manual}, 180 month = mar, 181 year = 2021, 182 publisher = {Zenodo}, 183 version = {0.8}, 184 doi = {10.5281/zenodo.4895340} 185} 186 187@InProceedings{libceed-paper-proc-scipy-2020, 188 author = {Valeria Barra and Jed Brown and Jeremy Thompson and Yohann Dudouit}, 189 title = {{H}igh-performance operator evaluations with ease of use: lib{C}{E}{E}{D}'s {P}ython interface}, 190 booktitle = {{P}roceedings of the 19th {P}ython in {S}cience {C}onference}, 191 pages = {85 - 90}, 192 year = {2020}, 193 editor = {{M}eghann {A}garwal and {C}hris {C}alloway and {D}illon {N}iederhut and {D}avid {S}hupe}, 194 doi = {10.25080/Majora-342d178e-00c} 195} 196 197@misc{LIBXSMM, 198 title = "{LIBXSMM development site}", 199 url = "http://github.com/hfp/libxsmm", 200 year = "2021" 201} 202 203@misc{MAGMAwebsite, 204 title = "{MAGMA development site}", 205 url = "https://bitbucket.org/icl/magma", 206 year = "2021" 207} 208 209@misc{MFEMlibrary, 210 title = "{MFEM}: {Modular Finite Element Methods Library}", 211 url = "https://mfem.org/", 212 year = "2021", 213 doi = "10.11578/dc.20171025.1248" 214} 215 216@article{mfem-paper, 217 title = {{MFEM}: A Modular Finite Element Library}, 218 author = {R. Anderson and J. Andrej and A. Barker and J. Bramwell and J.-S. Camier and 219 J. Cerveny V. Dobrev and Y. Dudouit and A. Fisher and Tz. Kolev and W. Pazner and 220 M. Stowell and V. Tomov and I. Akkerman and J. Dahm and D. Medina and S. Zampini}, 221 journal = {Computers \& Mathematics with Applications}, 222 doi = {10.1016/j.camwa.2020.06.009}, 223 year = {2020} 224} 225 226@misc{Nekwebsite, 227 title = "Nek5000", 228 url = "https://nek5000.mcs.anl.gov/", 229 year = "2021" 230} 231 232@inproceedings{Numba, 233author = {Lam, Siu Kwan and Pitrou, Antoine and Seibert, Stanley}, 234title = {Numba: A LLVM-Based Python JIT Compiler}, 235year = {2015}, 236isbn = {9781450340052}, 237publisher = {Association for Computing Machinery}, 238address = {New York, NY, USA}, 239doi = {10.1145/2833157.2833162}, 240abstract = {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].}, 241booktitle = {Proceedings of the Second Workshop on the LLVM Compiler Infrastructure in HPC}, 242articleno = {7}, 243numpages = {6}, 244keywords = {compiler, LLVM, Python}, 245location = {Austin, Texas}, 246series = {LLVM '15} 247} 248 249@Article{NumPy, 250 title = {Array programming with {NumPy}}, 251 author = {Charles R. Harris and K. Jarrod Millman and St{'{e}}fan J. 252 van der Walt and Ralf Gommers and Pauli Virtanen and David 253 Cournapeau and Eric Wieser and Julian Taylor and Sebastian 254 Berg and Nathaniel J. Smith and Robert Kern and Matti Picus 255 and Stephan Hoyer and Marten H. van Kerkwijk and Matthew 256 Brett and Allan Haldane and Jaime Fern{'{a}}ndez del 257 R{'{\i}}o and Mark Wiebe and Pearu Peterson and Pierre 258 G{'{e}}rard-Marchant and Kevin Sheppard and Tyler Reddy and 259 Warren Weckesser and Hameer Abbasi and Christoph Gohlke and 260 Travis E. Oliphant}, 261 year = {2020}, 262 month = sep, 263 journal = {Nature}, 264 volume = {585}, 265 number = {7825}, 266 pages = {357--362}, 267 doi = {10.1038/s41586-020-2649-2}, 268 publisher = {Springer Science and Business Media {LLC}} 269} 270 271@misc{NVRTCwebsite, 272 title = "NVRTC", 273 url = "https://docs.nvidia.com/cuda/nvrtc/index.html", 274 year = "2021" 275} 276 277@misc{OCCAwebsite, 278 title = "{OCCA} development site", 279 url = "http://github.com/libocca/occa", 280 year = "2021" 281} 282 283@article{Orszag:1980, 284 title = "Spectral methods for problems in complex geometries", 285 journal = "Journal of Computational Physics", 286 volume = "37", 287 pages = "70 - 92", 288 year = "1980", 289 doi = "10.1016/0021-9991(80)90005-4", 290 author = "Steven A Orszag" 291} 292 293@TechReport{PETScUserManual, 294 author = {Satish Balay and Shrirang Abhyankar and Mark~F. Adams and Jed Brown and Peter Brune 295 and Kris Buschelman and Lisandro Dalcin and Alp Dener and Victor Eijkhout and William~D. Gropp 296 and Dmitry Karpeyev and Dinesh Kaushik and Matthew~G. Knepley and Dave~A. May and Lois Curfman McInnes 297 and Richard Tran Mills and Todd Munson and Karl Rupp and Patrick Sanan 298 and Barry~F. Smith and Stefano Zampini and Hong Zhang and Hong Zhang}, 299 title = {{PETS}c Users Manual}, 300 institution = {Argonne National Laboratory}, 301 year = 2021, 302 number = {ANL-95/11 - Revision 3.15} 303} 304 305@misc{Python-lang, 306 title = "Python", 307 url = "https://www.python.org/", 308 year = "2021", 309} 310 311@misc{Rust-lang, 312 title = "Rust", 313 url = "https://www.rust-lang.org/", 314 year = "2021", 315} 316 317@misc{python-cffi, 318 title = "C Foreign Function Interface for {Python}", 319 url = "https://cffi.readthedocs.io", 320 year = "2021", 321} 322 323@article{straka1993numerical, 324 title={Numerical solutions of a non-linear density current: A benchmark solution and comparisons}, 325 author={Straka, Jerry M and Wilhelmson, Robert B and Wicker, Louis J and Anderson, John R and Droegemeier, Kelvin K}, 326 journal={International Journal for Numerical Methods in Fluids}, 327 volume={17}, 328 number={1}, 329 pages={1--22}, 330 year={1993}, 331 publisher={Wiley Online Library}, 332 doi={10.1002/fld.1650170103} 333} 334 335@book{deville2002highorder, 336 title={High-order methods for incompressible fluid flow}, 337 author={Deville, Michel O and Fischer, Paul F and Mund, Ernest H}, 338 year={2002}, 339 publisher={Cambridge University Press}, 340 isbn={0-521-45309-7} 341} 342 343@article{gropp2014using, 344 title={Using {MPI}: Portable Parallel Programming with the Message-Passing Interface}, 345 author={Gropp, William and Lusk, Ewing and Skjellum, Anthony}, 346 year={2014}, 347 publisher={The MIT Press}, 348 isbn={9780262527392} 349} 350 351@article{libMeshPaper, 352 author = {Benjamin S. Kirk and John W. Peterson and Roy H. Stogner and Graham F. Carey}, 353 title = {{\texttt{libMesh}: A C++ Library for Parallel Adaptive Mesh Refinement/Coarsening Simulations}}, 354 journal = {Engineering with Computers}, 355 volume = 22, 356 number = {3--4}, 357 pages = {237--254}, 358 year = 2006, 359 doi = {10.1007/s00366-006-0049-3} 360} 361@book{LoggMardalWells2012, 362 title = {Automated Solution of Differential Equations by the Finite Element Method: The {FEniCS} book}, 363 author = {Anders Logg and Kent-Andre Mardal and Garth N. Wells and others}, 364 editor = {Anders Logg and Kent-Andre Mardal and Garth N. Wells}, 365 volume = {84}, 366 year = {2012}, 367 publisher = {Springer}, 368 doi = {10.1007/978-3-642-23099-8}, 369 isbn = {978-3-642-23098-1} 370} 371 372@article{dealII92, 373 title = {The \texttt{deal.II} Library, Version 9.2}, 374 author = {Daniel Arndt and Wolfgang Bangerth and Bruno Blais and 375 Thomas C. Clevenger and Marc Fehling and Alexander V. Grayver and 376 Timo Heister and Luca Heltai and Martin Kronbichler and Matthias Maier and 377 Peter Munch and Jean-Paul Pelteret and Reza Rastak and 378 Ignacio Thomas and Bruno Turcksin and Zhuoran Wang and David Wells}, 379 journal = {Journal of Numerical Mathematics}, 380 publisher = {De Gruyter}, 381 year = {2020}, 382 volume = {28}, 383 number = {3}, 384 pages = {131-146}, 385 DOI = {10.1515/jnma-2020-0043}, 386 url = {https://dealii.org/deal92-preprint.pdf} 387} 388 389@misc{kruppcomparison, 390 title="{CPU-GPU-MIC} Comparision Charts", 391 author={Karl Rupp}, 392 url={https://github.com/karlrupp/cpu-gpu-mic-comparison}, 393 year={2020} 394} 395 396@article{williams2009roofline, 397 title={Roofline: an insightful visual performance model for multicore architectures}, 398 author={Williams, Samuel and Waterman, Andrew and Patterson, David}, 399 journal={Communications of the ACM}, 400 volume={52}, 401 number={4}, 402 pages={65--76}, 403 year={2009}, 404 publisher={ACM}, 405 doi={10.1145/1498765.1498785} 406} 407 408@article{babuska1994hpfem, 409 title={The $p$ and $h-p$ versions of the finite element method, basic principles and properties}, 410 author={Babu{\v{s}}ka, Ivo and Suri, Manil}, 411 journal={SIAM Review}, 412 volume={36}, 413 number={4}, 414 pages={578--632}, 415 year={1994}, 416 publisher={SIAM}, 417 doi={10.1137/1036141} 418} 419 420@article{lottes2005hms, 421 title={Hybrid Multigrid/{Schwarz} Algorithms for the Spectral Element Method}, 422 author={Lottes, J.W. and Fischer, P.F.}, 423 journal={Journal of Scientific Computing}, 424 volume={24}, 425 number={1}, 426 pages={45--78}, 427 year={2005}, 428 publisher={Springer}, 429 doi={10.1007/s10915-004-4787-3} 430} 431 432@article{zhang2021petscsf, 433 title={The {PetscSF} Scalable Communication Layer}, 434 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}, 435 journal={IEEE Transactions on Parallel and Distributed Systems}, 436 archivePrefix={arXiv}, 437 eprint={2102.13018}, 438 year={2021}, 439 doi={10.1109/TPDS.2021.3084070} 440} 441