mybibfile.bib

@article{Dirac1953888,
  title   = "The {L}orentz transformation and absolute time",
  journal = "Physica",
  volume  = "19",
  number  = "1-–12",
  pages   = "888--896",
  year    = "1953",
  doi     = "10.1016/S0031-8914(53)80099-6",
  author  = "P.A.M. Dirac"
}

@article{Feynman1963118,
  title   = "The theory of a general quantum system interacting with a linear dissipative system",
  journal = "Annals of Physics",
  volume  = "24",
  pages   = "118--173",
  year    = "1963",
  doi     = "10.1016/0003-4916(63)90068-X",
  author  = "R.P Feynman and F.L {Vernon Jr.}"
}

@article{AdamsHirvijokiKnepleyBrownIsaacMills2017,
  title    = {Landau Collision Integral Solver with Adaptive Mesh Refinement on Emerging Architectures},
  author   = {Mark F. Adams and Eero Hirvijoki and Matthew G. Knepley and Jed Brown and Tobin Isaac and Richard Mills},
  journal  = {SIAM Journal on Scientific Computing},
  volume   = {39},
  number   = {6},
  pages    = {C452--C465},
  doi      = {10.1137/17M1118828},
  year     = {2017}
}

@article{OSUMicro,
  title={{OSU} Microbenchmarks v5.6.2},
  author={Panda, DK and others},
  journal={http://mvapich.cse.ohio-state.edu/benchmarks/},
  year = {2019},
}

@incollection{petsc-msk2013,
	Author = {Victor Minden and Barry F. Smith and Matthew G. Knepley},
	Booktitle = {{GPU} Solutions to Multi-scale Problems in Science and Engineering},
	Editor = {David A. Yuen and Long Wang and Xuebin Chi and Lennart Johnsson and Wei Ge and Yaolin Shi},
	Isbn = {978-3-642-16404-0},
	Pages = {131--140},
	Publisher = {Springer Berlin Heidelberg},
	Series = {Lecture Notes in Earth System Sciences},
	Title = {Preliminary Implementation of {PETSc} Using {GPUs}},
	doi = {10.1007/978-3-642-16405-7_7},
	Year = {2013},
	}

@techreport{osti_1614879,
title = {Evaluation of {PETSc} on a Heterogeneous Architecture, the {OLCF} {S}ummit System: Part {I}: Vector Node Performance},
author = {Morgan, Hannah Mairs and Mills, Richard Tran and Smith, Barry},
abstractNote = {Our goal is to report on the basic performance of {PETSc} vector operations on a single node of the Oakridge Leadership Facility System Summit. We describe the Summit system and present data collected from several vector operations. Limited analysis is also presented.},
institution = {Argonne National Laboratory},
doi = {10.2172/1614879},
number = {ANL-19/41},
place = {United States},
year = {2020}
}

@INPROCEEDINGS{SNIR,
author={N. {Dryden} and N. {Maruyama} and T. {Moon} and T. {Benson} and A. {Yoo} and M. {Snir} and B. {Van Essen}},
booktitle={2018 IEEE/ACM Machine Learning in HPC Environments (MLHPC)},
title={Aluminum: An Asynchronous, {GPU}-Aware Communication Library Optimized for Large-Scale Training of Deep Neural Networks on {HPC} Systems},
year={2018},
volume={},
number={},
pages={1-13},
doi={10.1109/MLHPC.2018.8638639},
ISSN={null},
month={Nov}
}

@TechReport{petsc-user-ref,
       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   = 2020,
       number = {ANL-95/11 - Revision 3.14},
       note    = {https://www.mcs.anl.gov/petsc}
}

@TechReport{sf-tech-report,
       author = {Junchao Zhang and Richard Tran Mills and Barry F. Smith},
       title  = {Evaluation of {PETSc} on a Heterogeneous Architecture, the {OLCF} {S}ummit System: Part {II}: Basic Communication Performance},
       institution = {Argonne National Laboratory},
       year   = 2020,
       number = {ANL-20/76},
}



@article{KSPHPDDM,
    Author = {Jolivet, Pierre and Roman, Jose E. and Zampini, Stefano},
    Title = {{KSPHPDDM} and {PCHPDDM}: Extending {PETSc} with Robust Overlapping {Schwarz} Preconditioners and Advanced {Krylov} Methods},
    Year = {2020},
    Journal = {submitted for publication},
    note = {, https://github.com/prj-/jolivet2020petsc}
}

@misc{THRUST,
  title={Thrust: Code at the speed of light},
  author={Nathan Bell and Jared Hoberock},
  year={2020},
  note={https://github.com/NVIDIA/thrust},
}

@misc{OPENFOAM,
  title={{OpenFOAM}},
  author={{The OpenFOAM Foundation}},
  year={2020},
  note={https://openfoam.org/}
}

@misc{PETSc4FOAM,
  title={{PETSc4FOAM}},
  author={Simone Bna and Mark Olesen and Stefano Zampini},
  year={2020},
  note={https://develop.openfoam.com/modules/external-solver}
}

@misc{OpenFOAMLid,
  title={{OpenFOAM HPC} benchmark suite: {3D} Lid Driven cavity flow},
  author={},
  year={2020},
  note={https://develop.openfoam.com/committees/hpc/-/tree/develop/Lid\_driven\_cavity-3d/M},
}


@inproceedings{PCTELESCOPE,
author = {May, Dave A. and Sanan, Patrick and Rupp, Karl and Knepley, Matthew G. and Smith, Barry F.},
title = {Extreme-Scale Multigrid Components within {PETSc}},
year = {2016},
isbn = {9781450341264},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
//doi = {10.1145/2929908.2929913},
booktitle = {Proceedings of the Platform for Advanced Scientific Computing Conference},
articleno = {5},
pages={1-12},
keywords = {preconditioning, agglomeration, coarse-level solver, parallel computing, GPU, multigrid, HPC},
location = {Lausanne, Switzerland},
series = {PASC '16}
}

@misc{NVSHMEM,
  title={{NVIDIA} {OpenSHMEM} Library ({NVSHMEM}) Documentation},
  author={NVIDIA},
  year={2020},
  note={https://docs.nvidia.com/hpc-sdk/nvshmem/api/docs/introduction.html},
}

@misc{NCCL,
  title={{NVIDIA} Collective Communication Library ({NCCL}) Documentation},
  author={NVIDIA},
  year={2020},
  note={https://docs.nvidia.com/deeplearning/nccl/archives/nccl\_278/user-guide/docs/index.html},
}

@misc{OpenSHMEM,
  title={{OpenSHMEM} Application Programming Interface V1.5},
  author={{Open Source Software Solutions, Inc.}},
  year={2020},
  note={http://www.openshmem.org/},
}

@article{BLIS7,
   author      = {Field G. {V}an~{Z}ee and Devangi N. Parikh and Robert A. van~de~{G}eijn},
   title       = {Supporting Mixed-domain Mixed-precision Matrix Multiplication within the {BLIS} Framework},
   journal     = {ACM Transactions on Mathematical Software},
   year = {2019},
   note        = {, submitted}
}

@article{KOKKOS,
  title = {Kokkos: Enabling manycore performance portability through polymorphic memory access patterns},
  journal = {Journal of Parallel and Distributed Computing},
  volume = {74},
  number = {12},
  pages = {3202--3216},
  year = {2014},
  note = {{D}omain-Specific Languages and High-Level Frameworks for High-Performance Computing},
  issn = {0743-7315},
  doi = {10.1016/j.jpdc.2014.07.003},
  author = {H. Carter Edwards and Christian R. Trott and Daniel Sunderland}
}

@inproceedings{RAJA,
  title={{RAJA}: Portable performance for large-scale scientific applications},
  author={Beckingsale, David A and Burmark, Jason and Hornung, Rich and Jones, Holger and Killian, William and Kunen, Adam J and Pearce, Olga and Robinson, Peter and Ryujin, Brian S and Scogland, Thomas RW},
  booktitle={2019 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)},
  pages={71--81},
  year={2019},
  organization={IEEE}
}

@misc{SYCL,
  title={{SYCL} Specification: Generic heterogeneous computing for modern {C++}},
  author={{Khronos SYCL Working Group}},
  year={2020},
  note={https://www.khronos.org/-registry/SYCL/specs/sycl-2020-provisional.pdf},
}

@misc{DPC++,
  title={Data Parallel {C++}: Mastering {DPC++} for Programming of Heterogeneous Systems using {C++} and {SYCL}},
  author={Reinders, James and Ashbaugh, Ben and Brodman, James and Kinsner, Michael and Pennycook, John and Tian, Xinmin},
  year={2020},
  publisher={Apress}
}

@article{VIENNACL,
  title={Vienna{CL}---linear algebra library for multi-and many-core architectures},
  author={Rupp, Karl and Tillet, Philippe and Rudolf, Florian and Weinbub, Josef and Morhammer, Andreas and Grasser, Tibor and Jungel, Ansgar and Selberherr, Siegfried},
  journal={SIAM Journal on Scientific Computing},
  volume={38},
  number={5},
  pages={S412--S439},
  year={2016},
  publisher={SIAM}
}

@article{OPENCL,
  title={{OpenCL}: A parallel programming standard for heterogeneous computing systems},
  author={Stone, John E and Gohara, David and Shi, Guochun},
  journal={Computing in science \& engineering},
  volume={12},
  number={3},
  pages={66--73},
  year={2010},
  publisher={IEEE Computer Society}
}

@misc{CUDA,
  title={{CUDA C++} Programming Guide},
  author={{NVIDA}},
  year={2020},
  note={https://docs.nvidia.com/cuda/-pdf/CUDA\_C\_Programming\_Guide.pdf}
}

@misc{HIP,
  title={{HIP} Programming Guide},
  author={{AMD}},
  year={2020},
  note={https://rocmdocs.amd.com/en/latest/-Programming\_Guides/HIP-GUIDE.html}
}

@article{Karl2020preparing,
  title={Preparing sparse solvers for exascale computing},
  author={Anzt, Hartwig and Boman, Erik and Falgout, Rob and Ghysels, Pieter and Heroux, Michael and Li, Xiaoye and Curfman McInnes, Lois and Tran Mills, Richard and Rajamanickam, Sivasankaran and Rupp, Karl and others},
  journal={Philosophical Transactions of the Royal Society A},
  volume={378},
  number={2166},
  pages={20190053},
  year={2020},
  publisher={The Royal Society Publishing}
}

@article{ChangPerformanceSpectrum,
  title={A performance spectrum for parallel computational frameworks that solve {PDEs}},
  author={Chang, J and Nakshatrala, KB and Knepley, Matthew G and Johnsson, L},
  journal={Concurrency and Computation: Practice and Experience},
  volume={30},
  number={11},
  pages={e4401},
  year={2018},
  publisher={Wiley Online Library}
}

@article{ChangTASSpectrum,
  title={Comparative study of finite element methods using the Time-Accuracy-Size ({TAS}) spectrum analysis},
  author={Chang, Justin and Fabien, Maurice S and Knepley, Matthew G and Mills, Richard T},
  journal={SIAM Journal on Scientific Computing},
  volume={40},
  number={6},
  pages={C779--C802},
  year={2018},
  publisher={SIAM}
}

@article{blanchard2020mixed,
  title={Mixed precision block fused multiply-add: {E}rror analysis and application to {GPU} Tensor Cores},
  author={Blanchard, Pierre and Higham, Nicholas J and Lopez, Florent and Mary, Th{\'e}o and Pranesh, Srikara},
  journal={SIAM Journal on Scientific Computing},
  volume={42},
  number={3},
  pages={C124--C141},
  year={2020},
  publisher={SIAM}
}

@article{zachariadis2020accelerating,
  title={Accelerating sparse matrix--matrix multiplication with {GPU} Tensor Cores},
  author={Zachariadis, Orestis and Satpute, Nitin and G{\'o}mez-Luna, Juan and Olivares, Joaqu{\'\i}n},
  journal={Computers \& Electrical Engineering},
  volume={88},
  pages={106848},
  year={2020},
  publisher={Elsevier}
}

@inproceedings{haidar2018harnessing,
  title={Harnessing {GPU} tensor cores for fast {FP16} arithmetic to speed up mixed-precision iterative refinement solvers},
  author={Haidar, Azzam and Tomov, Stanimire and Dongarra, Jack and Higham, Nicholas J},
  booktitle={SC18: International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages={603--613},
  year={2018},
  organization={IEEE}
}

@inproceedings{bkmms2012,
  author    = {Jed Brown and Matthew G. Knepley and David A. May and Lois C. McInnes and Barry F. Smith},
  title     = {Composable linear solvers for multiphysics},
  booktitle = {Proceeedings of the 11th {International Symposium on Parallel and Distributed Computing} ({ISPDC} 2012)},
  year      = {2012},
//doi       = {10.1109/ISPDC.2012.16},
  publisher = {IEEE Computer Society},
  pages     = {55--62},
}

@article{byrd1994representations,
  title={Representations of quasi-Newton matrices and their use in limited memory methods},
  author={Byrd, Richard H and Nocedal, Jorge and Schnabel, Robert B},
  journal={Mathematical Programming},
  volume={63},
  number={1-3},
  pages={129--156},
  year={1994},
  publisher={Springer}
}

@article{erway2017solving,
  title={On solving large-scale limited-memory quasi-Newton equations},
  author={Erway, Jennifer B and Marcia, Roummel F},
  journal={Linear Algebra and its Applications},
  volume={515},
  pages={196--225},
  year={2017},
  publisher={Elsevier}
}

@article{filippone2017GPGPUSpMV,
author = {Filippone, Salvatore and Cardellini, Valeria and Barbieri, Davide and Fanfarillo, Alessandro},
title = {Sparse Matrix-Vector Multiplication on {GPGPUs}},
year = {2017},
issue_date = {March 2017},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {43},
number = {4},
issn = {0098-3500},
doi = {10.1145/3017994},
journal = {ACM Trans. Math. Softw.},
month = jan,
articleno = {30},
numpages = {49},
keywords = {Sparse matrices, {GPU} programming}
}