BibTeX records: Antonio J. Peña

download as .bib file

@inproceedings{DBLP:conf/cc/MatsumuraGP23,
  author       = {Kazuaki Matsumura and
                  Simon Garcia De Gonzalo and
                  Antonio J. Pe{\~{n}}a},
  editor       = {Clark Verbrugge and
                  Ondrej Lhot{\'{a}}k and
                  Xipeng Shen},
  title        = {A Symbolic Emulator for Shuffle Synthesis on the {NVIDIA} {PTX} Code},
  booktitle    = {Proceedings of the 32nd {ACM} {SIGPLAN} International Conference on
                  Compiler Construction, {CC} 2023, Montr{\'{e}}al, QC, Canada,
                  February 25-26, 2023},
  pages        = {110--121},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3578360.3580253},
  doi          = {10.1145/3578360.3580253},
  timestamp    = {Mon, 20 Feb 2023 14:33:53 +0100},
  biburl       = {https://dblp.org/rec/conf/cc/MatsumuraGP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/UsmanIFP23,
  author       = {Muhammad Usman and
                  Sergio Iserte and
                  Roger Ferrer and
                  Antonio J. Pe{\~{n}}a},
  title        = {OpenMP Offloading to {DPU}},
  booktitle    = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2023
                  - Workshops, Santa Fe, NM, USA, October 31, 2023},
  pages        = {64--65},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/CLUSTERWorkshops61457.2023.00027},
  doi          = {10.1109/CLUSTERWORKSHOPS61457.2023.00027},
  timestamp    = {Wed, 06 Dec 2023 13:14:05 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/UsmanIFP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/UsmanIFP23,
  author       = {Muhammad Usman and
                  Sergio Iserte and
                  Roger Ferrer and
                  Antonio Jos{\'{e}} Pe{\~{n}}a},
  title        = {{DPU} Offloading Programming with the OpenMP {API}},
  booktitle    = {Proceedings of the {SC} '23 Workshops of The International Conference
                  on High Performance Computing, Network, Storage, and Analysis, {SC-W}
                  2023, Denver, CO, USA, November 12-17, 2023},
  pages        = {884--891},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3624062.3624165},
  doi          = {10.1145/3624062.3624165},
  timestamp    = {Tue, 28 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/UsmanIFP23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11389,
  author       = {Kazuaki Matsumura and
                  Simon Garcia De Gonzalo and
                  Antonio J. Pe{\~{n}}a},
  title        = {A Symbolic Emulator for Shuffle Synthesis on the {NVIDIA} {PTX} Code},
  journal      = {CoRR},
  volume       = {abs/2301.11389},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2301.11389},
  doi          = {10.48550/ARXIV.2301.11389},
  eprinttype    = {arXiv},
  eprint       = {2301.11389},
  timestamp    = {Tue, 31 Jan 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2301-11389.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-13002,
  author       = {Kazuaki Matsumura and
                  Simon Garcia De Gonzalo and
                  Antonio J. Pe{\~{n}}a},
  title        = {{ACC} Saturator: Automatic Kernel Optimization for Directive-Based
                  {GPU} Code},
  journal      = {CoRR},
  volume       = {abs/2306.13002},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.13002},
  doi          = {10.48550/ARXIV.2306.13002},
  eprinttype    = {arXiv},
  eprint       = {2306.13002},
  timestamp    = {Tue, 27 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-13002.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cluster/JordaVP22,
  author       = {Marc Jord{\`{a}} and
                  Pedro Valero{-}Lara and
                  Antonio J. Pe{\~{n}}a},
  title        = {cuConv: {CUDA} implementation of convolution for {CNN} inference},
  journal      = {Clust. Comput.},
  volume       = {25},
  number       = {2},
  pages        = {1459--1473},
  year         = {2022},
  url          = {https://doi.org/10.1007/s10586-021-03494-y},
  doi          = {10.1007/S10586-021-03494-Y},
  timestamp    = {Thu, 23 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cluster/JordaVP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/Lloret-Talavera22,
  author       = {Guillermo Lloret{-}Talavera and
                  Marc Jord{\`{a}} and
                  Harald Servat and
                  Fabian Boemer and
                  Chetan Chauhan and
                  Shigeki Tomishima and
                  Nilesh N. Shah and
                  Antonio J. Pe{\~{n}}a},
  title        = {Enabling Homomorphically Encrypted Inference for Large {DNN} Models},
  journal      = {{IEEE} Trans. Computers},
  volume       = {71},
  number       = {5},
  pages        = {1145--1155},
  year         = {2022},
  url          = {https://doi.org/10.1109/TC.2021.3076123},
  doi          = {10.1109/TC.2021.3076123},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tc/Lloret-Talavera22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/ZhaiSP22,
  author       = {Jidong Zhai and
                  Min Si and
                  Antonio J. Pe{\~{n}}a},
  title        = {Guest Editorial},
  journal      = {{IEEE} Trans. Parallel Distributed Syst.},
  volume       = {33},
  number       = {11},
  pages        = {2644--2647},
  year         = {2022},
  url          = {https://doi.org/10.1109/TPDS.2022.3166681},
  doi          = {10.1109/TPDS.2022.3166681},
  timestamp    = {Mon, 13 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tpds/ZhaiSP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/JordaRALP22,
  author       = {Marc Jord{\`{a}} and
                  Siddharth Rai and
                  Eduard Ayguad{\'{e}} and
                  Jes{\'{u}}s Labarta and
                  Antonio J. Pe{\~{n}}a},
  title        = {ecoHMEM: Improving Object Placement Methodology for Hybrid Memory
                  Systems in {HPC}},
  booktitle    = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2022,
                  Heidelberg, Germany, September 5-8, 2022},
  pages        = {278--288},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/CLUSTER51413.2022.00040},
  doi          = {10.1109/CLUSTER51413.2022.00040},
  timestamp    = {Wed, 26 Oct 2022 19:40:32 +0200},
  biburl       = {https://dblp.org/rec/conf/cluster/JordaRALP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/KorakitisGG0MP22,
  author       = {Orestis Korakitis and
                  Simon Garcia De Gonzalo and
                  Nicolas Guidotti and
                  Jo{\~{a}}o Pedro Barreto and
                  Jos{\'{e}} C. Monteiro and
                  Antonio J. Pe{\~{n}}a},
  editor       = {Jaejin Lee and
                  Kunal Agrawal and
                  Michael F. Spear},
  title        = {Towards OmpSs-2 and OpenACC interoperation},
  booktitle    = {PPoPP '22: 27th {ACM} {SIGPLAN} Symposium on Principles and Practice
                  of Parallel Programming, Seoul, Republic of Korea, April 2 - 6, 2022},
  pages        = {433--434},
  publisher    = {{ACM}},
  year         = {2022},
  url          = {https://doi.org/10.1145/3503221.3508401},
  doi          = {10.1145/3503221.3508401},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/KorakitisGG0MP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/waccpd-ws/KorakitisGGBMP22,
  author       = {Orestis Korakitis and
                  Simon Garcia de Gonzalo and
                  Nicolas Guidotti and
                  Jo{\~{a}}o Barreto and
                  Jos{\'{e}} Monteiro and
                  Antonio J. Pe{\~{n}}a},
  title        = {OmpSs-2 and OpenACC Interoperation},
  booktitle    = {9th Workshop on Accelerator Programming Using Directives, WACCPD@SC
                  2022, Dallas, TX, USA, November 13-18, 2022},
  pages        = {11--21},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/WACCPD56842.2022.00007},
  doi          = {10.1109/WACCPD56842.2022.00007},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/waccpd-ws/KorakitisGGBMP22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/IserteMQP21,
  author       = {Sergio Iserte and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Antonio J. Pe{\~{n}}a},
  title        = {DMRlib: Easy-Coding and Efficient Resource Management for Job Malleability},
  journal      = {{IEEE} Trans. Computers},
  volume       = {70},
  number       = {9},
  pages        = {1443--1457},
  year         = {2021},
  url          = {https://doi.org/10.1109/TC.2020.3022933},
  doi          = {10.1109/TC.2020.3022933},
  timestamp    = {Thu, 16 Sep 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tc/IserteMQP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/GuidottiCBMRFMP21,
  author       = {Nicolas Guidotti and
                  Pedro Ceyrat and
                  Jo{\~{a}}o Barreto and
                  Jos{\'{e}} Monteiro and
                  Rodrigo Rodrigues and
                  Ricardo Fonseca and
                  Xavier Martorell and
                  Antonio J. Pe{\~{n}}a},
  editor       = {Leonel Sousa and
                  Nuno Roma and
                  Pedro Tom{\'{a}}s},
  title        = {Particle-In-Cell Simulation Using Asynchronous Tasking},
  booktitle    = {Euro-Par 2021: Parallel Processing - 27th International Conference
                  on Parallel and Distributed Computing, Lisbon, Portugal, September
                  1-3, 2021, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {12820},
  pages        = {482--498},
  publisher    = {Springer},
  year         = {2021},
  url          = {https://doi.org/10.1007/978-3-030-85665-6\_30},
  doi          = {10.1007/978-3-030-85665-6\_30},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/GuidottiCBMRFMP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/MatsumuraGP21,
  author       = {Kazuaki Matsumura and
                  Simon Garcia de Gonzalo and
                  Antonio J. Pe{\~{n}}a},
  title        = {{JACC:} An OpenACC Runtime Framework with Kernel-Level and Multi-GPU
                  Parallelization},
  booktitle    = {28th {IEEE} International Conference on High Performance Computing,
                  Data, and Analytics, HiPC 2021, Bengaluru, India, December 17-20,
                  2021},
  pages        = {182--191},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/HiPC53243.2021.00032},
  doi          = {10.1109/HIPC53243.2021.00032},
  timestamp    = {Mon, 31 Jan 2022 09:34:30 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/MatsumuraGP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/ToledoVVP21,
  author       = {Leonel Toledo and
                  Pedro Valero{-}Lara and
                  Jeffrey S. Vetter and
                  Antonio J. Pe{\~{n}}a},
  title        = {Static Graphs for Coding Productivity in OpenACC},
  booktitle    = {28th {IEEE} International Conference on High Performance Computing,
                  Data, and Analytics, HiPC 2021, Bengaluru, India, December 17-20,
                  2021},
  pages        = {364--369},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/HiPC53243.2021.00050},
  doi          = {10.1109/HIPC53243.2021.00050},
  timestamp    = {Sat, 19 Mar 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/ToledoVVP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-16139,
  author       = {Guillermo Lloret{-}Talavera and
                  Marc Jord{\`{a}} and
                  Harald Servat and
                  Fabian Boemer and
                  Chetan Chauhan and
                  Shigeki Tomishima and
                  Nilesh N. Shah and
                  Antonio J. Pe{\~{n}}a},
  title        = {Enabling Homomorphically Encrypted Inference for Large {DNN} Models},
  journal      = {CoRR},
  volume       = {abs/2103.16139},
  year         = {2021},
  url          = {https://arxiv.org/abs/2103.16139},
  eprinttype    = {arXiv},
  eprint       = {2103.16139},
  timestamp    = {Wed, 07 Apr 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2103-16139.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-16234,
  author       = {Marc Jord{\`{a}} and
                  Pedro Valero{-}Lara and
                  Antonio J. Pe{\~{n}}a},
  title        = {cuConv: {A} {CUDA} Implementation of Convolution for {CNN} Inference},
  journal      = {CoRR},
  volume       = {abs/2103.16234},
  year         = {2021},
  url          = {https://arxiv.org/abs/2103.16234},
  eprinttype    = {arXiv},
  eprint       = {2103.16234},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2103-16234.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-12485,
  author       = {Nicolas Guidotti and
                  Pedro Ceyrat and
                  Jo{\~{a}}o Barreto and
                  Jos{\'{e}} Monteiro and
                  Rodrigo Rodrigues and
                  Ricardo Fonseca and
                  Xavier Martorell and
                  Antonio J. Pe{\~{n}}a},
  title        = {Particle-In-Cell Simulation using Asynchronous Tasking},
  journal      = {CoRR},
  volume       = {abs/2106.12485},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.12485},
  eprinttype    = {arXiv},
  eprint       = {2106.12485},
  timestamp    = {Wed, 23 Feb 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-12485.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-14340,
  author       = {Kazuaki Matsumura and
                  Simon Garcia De Gonzalo and
                  Antonio J. Pe{\~{n}}a},
  title        = {{JACC:} An OpenACC Runtime Framework with Kernel-Level and Multi-GPU
                  Parallelization},
  journal      = {CoRR},
  volume       = {abs/2110.14340},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.14340},
  eprinttype    = {arXiv},
  eprint       = {2110.14340},
  timestamp    = {Fri, 29 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-14340.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/PenaS20,
  author       = {Antonio J. Pe{\~{n}}a and
                  Min Si},
  title        = {Guest editorial: Special Issue on Applications and System Software
                  for Hybrid Exascale Systems},
  journal      = {Parallel Comput.},
  volume       = {91},
  year         = {2020},
  url          = {https://doi.org/10.1016/j.parco.2019.102583},
  doi          = {10.1016/J.PARCO.2019.102583},
  timestamp    = {Fri, 27 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/PenaS20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/CastelloGSBQP20,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Rafael Mayo Gual and
                  Sangmin Seo and
                  Pavan Balaji and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Antonio J. Pe{\~{n}}a},
  title        = {Analysis of Threading Libraries for High Performance Computing},
  journal      = {{IEEE} Trans. Computers},
  volume       = {69},
  number       = {9},
  pages        = {1279--1292},
  year         = {2020},
  url          = {https://doi.org/10.1109/TC.2020.2970706},
  doi          = {10.1109/TC.2020.2970706},
  timestamp    = {Mon, 02 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tc/CastelloGSBQP20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-05872,
  author       = {Harald Servat and
                  Jes{\'{u}}s Labarta and
                  Hans{-}Christian Hoppe and
                  Judit Gim{\'{e}}nez and
                  Antonio J. Pe{\~{n}}a},
  title        = {Understanding Memory Access Patterns Using the {BSC} Performance Tools},
  journal      = {CoRR},
  volume       = {abs/2005.05872},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.05872},
  eprinttype    = {arXiv},
  eprint       = {2005.05872},
  timestamp    = {Thu, 14 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-05872.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-05910,
  author       = {Sergio Iserte and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Vicen{\c{c}} Beltran and
                  Antonio J. Pe{\~{n}}a},
  title        = {{DMR} {API:} Improving cluster productivity by turning applications
                  into malleable},
  journal      = {CoRR},
  volume       = {abs/2005.05910},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.05910},
  eprinttype    = {arXiv},
  eprint       = {2005.05910},
  timestamp    = {Wed, 07 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-05910.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-06332,
  author       = {Pedro Valero{-}Lara and
                  Ra{\"{u}}l Sirvent and
                  Antonio J. Pe{\~{n}}a and
                  Jes{\'{u}}s Labarta},
  title        = {MPI+OpenMP Tasking Scalability for Multi-Morphology Simulations of
                  the Human Brain},
  journal      = {CoRR},
  volume       = {abs/2005.06332},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.06332},
  eprinttype    = {arXiv},
  eprint       = {2005.06332},
  timestamp    = {Thu, 14 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-06332.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/access/JordaVP19,
  author       = {Marc Jord{\`{a}} and
                  Pedro Valero{-}Lara and
                  Antonio J. Pe{\~{n}}a},
  title        = {Performance Evaluation of cuDNN Convolution Algorithms on {NVIDIA}
                  Volta GPUs},
  journal      = {{IEEE} Access},
  volume       = {7},
  pages        = {70461--70473},
  year         = {2019},
  url          = {https://doi.org/10.1109/ACCESS.2019.2918851},
  doi          = {10.1109/ACCESS.2019.2918851},
  timestamp    = {Fri, 05 Jul 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/access/JordaVP19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/IserteMBCMP19,
  author       = {Sergio Iserte and
                  H{\'{e}}ctor Mart{\'{\i}}nez and
                  Sergio Barrachina and
                  Maribel Castillo and
                  Rafael Mayo and
                  Antonio J. Pe{\~{n}}a},
  title        = {Dynamic reconfiguration of noniterative scientific applications: {A}
                  case study with {HPG} aligner},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {33},
  number       = {5},
  year         = {2019},
  url          = {https://doi.org/10.1177/1094342018802347},
  doi          = {10.1177/1094342018802347},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ijhpca/IserteMBCMP19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/Valero-LaraSPL19,
  author       = {Pedro Valero{-}Lara and
                  Ra{\"{u}}l Sirvent and
                  Antonio J. Pe{\~{n}}a and
                  Jes{\'{u}}s Labarta},
  title        = {MPI+OpenMP tasking scalability for multi-morphology simulations of
                  the human brain},
  journal      = {Parallel Comput.},
  volume       = {84},
  pages        = {50--61},
  year         = {2019},
  url          = {https://doi.org/10.1016/j.parco.2019.03.006},
  doi          = {10.1016/J.PARCO.2019.03.006},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/Valero-LaraSPL19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/SalaTPPBL19,
  author       = {Kevin Sala and
                  Xavier Teruel and
                  Josep M. P{\'{e}}rez and
                  Antonio J. Pe{\~{n}}a and
                  Vicen{\c{c}} Beltran and
                  Jes{\'{u}}s Labarta},
  title        = {Integrating blocking and non-blocking {MPI} primitives with task-based
                  programming models},
  journal      = {Parallel Comput.},
  volume       = {85},
  pages        = {153--166},
  year         = {2019},
  url          = {https://doi.org/10.1016/j.parco.2018.12.008},
  doi          = {10.1016/J.PARCO.2018.12.008},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/SalaTPPBL19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Pena19,
  author       = {Antonio J. Pe{\~{n}}a},
  title        = {Introduction to AsHES 2019},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPSW} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
  pages        = {460},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/IPDPSW.2019.00086},
  doi          = {10.1109/IPDPSW.2019.00086},
  timestamp    = {Wed, 16 Oct 2019 14:14:51 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/Pena19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdcat/ToledoPCV19,
  author       = {Leonel Toledo and
                  Antonio J. Pe{\~{n}}a and
                  Sandra Catal{\'{a}}n and
                  Pedro Valero{-}Lara},
  title        = {Tasking in Accelerators: Performance Evaluation},
  booktitle    = {20th International Conference on Parallel and Distributed Computing,
                  Applications and Technologies, {PDCAT} 2019, Gold Coast, Australia,
                  December 5-7, 2019},
  pages        = {127--132},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/PDCAT46702.2019.00034},
  doi          = {10.1109/PDCAT46702.2019.00034},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/pdcat/ToledoPCV19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/sc/2019,
  editor       = {Michela Taufer and
                  Pavan Balaji and
                  Antonio J. Pe{\~{n}}a},
  title        = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
                  November 17-19, 2019},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3295500},
  doi          = {10.1145/3295500},
  isbn         = {978-1-4503-6229-0},
  timestamp    = {Sat, 09 Nov 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/2019.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-03271,
  author       = {Kevin Sala and
                  Xavier Teruel and
                  Josep M. P{\'{e}}rez and
                  Antonio J. Pe{\~{n}}a and
                  Vicen{\c{c}} Beltran and
                  Jes{\'{u}}s Labarta},
  title        = {Integrating Blocking and Non-Blocking {MPI} Primitives with Task-Based
                  Programming Models},
  journal      = {CoRR},
  volume       = {abs/1901.03271},
  year         = {2019},
  url          = {http://arxiv.org/abs/1901.03271},
  eprinttype    = {arXiv},
  eprint       = {1901.03271},
  timestamp    = {Thu, 22 Aug 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1901-03271.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/Valero-LaraMSMP18,
  author       = {Pedro Valero{-}Lara and
                  Ivan Mart{\'{\i}}nez{-}P{\'{e}}rez and
                  Ra{\"{u}}l Sirvent and
                  Xavier Martorell and
                  Antonio J. Pe{\~{n}}a},
  title        = {cuThomasBatch and cuThomasVBatch, {CUDA} Routines to compute batch
                  of tridiagonal systems on {NVIDIA} GPUs},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {30},
  number       = {24},
  year         = {2018},
  url          = {https://doi.org/10.1002/cpe.4909},
  doi          = {10.1002/CPE.4909},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/Valero-LaraMSMP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/CastelloMSBBP18,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Rafael Mayo and
                  Kevin Sala and
                  Vicen{\c{c}} Beltran and
                  Pavan Balaji and
                  Antonio J. Pe{\~{n}}a},
  title        = {On the adequacy of lightweight thread approaches for high-level parallel
                  programming models},
  journal      = {Future Gener. Comput. Syst.},
  volume       = {84},
  pages        = {22--31},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.future.2018.02.016},
  doi          = {10.1016/J.FUTURE.2018.02.016},
  timestamp    = {Mon, 02 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/fgcs/CastelloMSBBP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/ChandrasekaranP18,
  author       = {Sunita Chandrasekaran and
                  Antonio J. Pe{\~{n}}a},
  title        = {Special issue on applications for the heterogeneous computing era
                  2017},
  journal      = {Parallel Comput.},
  volume       = {77},
  pages        = {125--127},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.parco.2018.06.002},
  doi          = {10.1016/J.PARCO.2018.06.002},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/ChandrasekaranP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/ServatLHGP18,
  author       = {Harald Servat and
                  Jes{\'{u}}s Labarta and
                  Hans{-}Christian Hoppe and
                  Judit Gim{\'{e}}nez and
                  Antonio J. Pe{\~{n}}a},
  title        = {Understanding memory access patterns using the {BSC} performance tools},
  journal      = {Parallel Comput.},
  volume       = {78},
  pages        = {1--14},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.parco.2018.06.007},
  doi          = {10.1016/J.PARCO.2018.06.007},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/ServatLHGP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/IserteMQBP18,
  author       = {Sergio Iserte and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Vicen{\c{c}} Beltran and
                  Antonio J. Pe{\~{n}}a},
  title        = {{DMR} {API:} Improving cluster productivity by turning applications
                  into malleable},
  journal      = {Parallel Comput.},
  volume       = {78},
  pages        = {54--66},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.parco.2018.07.006},
  doi          = {10.1016/J.PARCO.2018.07.006},
  timestamp    = {Thu, 24 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/pc/IserteMQBP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tjs/CastelloPMPQB18,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Antonio J. Pe{\~{n}}a and
                  Rafael Mayo and
                  Judit Planas and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Pavan Balaji},
  title        = {Exploring the interoperability of remote {GPGPU} virtualization using
                  rCUDA and directive-based programming models},
  journal      = {J. Supercomput.},
  volume       = {74},
  number       = {11},
  pages        = {5628--5642},
  year         = {2018},
  url          = {https://doi.org/10.1007/s11227-016-1791-y},
  doi          = {10.1007/S11227-016-1791-Y},
  timestamp    = {Mon, 02 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tjs/CastelloPMPQB18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/SiPHBTI18,
  author       = {Min Si and
                  Antonio J. Pe{\~{n}}a and
                  Jeff R. Hammond and
                  Pavan Balaji and
                  Masamichi Takagi and
                  Yutaka Ishikawa},
  title        = {Dynamic Adaptable Asynchronous Progress Model for {MPI} {RMA} Multiphase
                  Applications},
  journal      = {{IEEE} Trans. Parallel Distributed Syst.},
  volume       = {29},
  number       = {9},
  pages        = {1975--1989},
  year         = {2018},
  url          = {https://doi.org/10.1109/TPDS.2018.2815568},
  doi          = {10.1109/TPDS.2018.2815568},
  timestamp    = {Fri, 02 Oct 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tpds/SiPHBTI18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/ChandrasekaranP18,
  author       = {Sunita Chandrasekaran and
                  Antonio J. Pe{\~{n}}a and
                  Min Si},
  title        = {Introduction to AsHES 2018},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPS} Workshops 2018, Vancouver, BC, Canada, May 21-25,
                  2018},
  pages        = {520},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPSW.2018.00089},
  doi          = {10.1109/IPDPSW.2018.00089},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/ChandrasekaranP18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Rivas-GomezPMLM18,
  author       = {Sergio Rivas{-}Gomez and
                  Antonio J. Pe{\~{n}}a and
                  David Moloney and
                  Erwin Laure and
                  Stefano Markidis},
  title        = {Exploring the Vision Processing Unit as Co-Processor for Inference},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPS} Workshops 2018, Vancouver, BC, Canada, May 21-25,
                  2018},
  pages        = {589--598},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPSW.2018.00098},
  doi          = {10.1109/IPDPSW.2018.00098},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/Rivas-GomezPMLM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/Valero-LaraSPML18,
  author       = {Pedro Valero{-}Lara and
                  Ra{\"{u}}l Sirvent and
                  Antonio J. Pe{\~{n}}a and
                  Xavier Martorell and
                  Jes{\'{u}}s Labarta},
  title        = {MPI+OpenMP Tasking Scalability for the Simulation of the Human Brain:
                  Human Brain Project},
  booktitle    = {Proceedings of the 25th European {MPI} Users' Group Meeting, Barcelona,
                  Spain, September 23-26, 2018},
  pages        = {5:1--5:8},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3236367.3236373},
  doi          = {10.1145/3236367.3236373},
  timestamp    = {Wed, 25 Sep 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/pvm/Valero-LaraSPML18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/SalaBFTPPHBL18,
  author       = {Kevin Sala and
                  Jorge Bell{\'{o}}n and
                  Pau Farr{\'{e}} and
                  Xavier Teruel and
                  Josep M. P{\'{e}}rez and
                  Antonio J. Pe{\~{n}}a and
                  Daniel J. Holmes and
                  Vicen{\c{c}} Beltran and
                  Jes{\'{u}}s Labarta},
  title        = {Improving the Interoperability between {MPI} and Task-Based Programming
                  Models},
  booktitle    = {Proceedings of the 25th European {MPI} Users' Group Meeting, Barcelona,
                  Spain, September 23-26, 2018},
  pages        = {6:1--6:11},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3236367.3236382},
  doi          = {10.1145/3236367.3236382},
  timestamp    = {Fri, 27 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/SalaBFTPPHBL18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-04150,
  author       = {Sergio Rivas{-}Gomez and
                  Antonio J. Pe{\~{n}}a and
                  David Moloney and
                  Erwin Laure and
                  Stefano Markidis},
  title        = {Exploring the Vision Processing Unit as Co-processor for Inference},
  journal      = {CoRR},
  volume       = {abs/1810.04150},
  year         = {2018},
  url          = {http://arxiv.org/abs/1810.04150},
  eprinttype    = {arXiv},
  eprint       = {1810.04150},
  timestamp    = {Tue, 30 Oct 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1810-04150.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/ChandrasekaranP17,
  author       = {Sunita Chandrasekaran and
                  Antonio J. Pe{\~{n}}a},
  title        = {Special Issue on Topics on Heterogeneous Computing},
  journal      = {Parallel Comput.},
  volume       = {68},
  pages        = {1--2},
  year         = {2017},
  url          = {https://doi.org/10.1016/j.parco.2017.08.001},
  doi          = {10.1016/J.PARCO.2017.08.001},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/ChandrasekaranP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/ServatPLMHL17,
  author       = {Harald Servat and
                  Antonio J. Pe{\~{n}}a and
                  Germ{\'{a}}n Llort and
                  Estanislao Mercadal and
                  Hans{-}Christian Hoppe and
                  Jes{\'{u}}s Labarta},
  title        = {Automating the Application Data Placement in Hybrid Memory Systems},
  booktitle    = {2017 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2017, Honolulu, HI, USA, September 5-8, 2017},
  pages        = {126--136},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/CLUSTER.2017.50},
  doi          = {10.1109/CLUSTER.2017.50},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/ServatPLMHL17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/CastelloSMBQP17,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Sangmin Seo and
                  Rafael Mayo and
                  Pavan Balaji and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Antonio J. Pe{\~{n}}a},
  editor       = {Francisco F. Rivera and
                  Tom{\'{a}}s F. Pena and
                  Jos{\'{e}} Carlos Cabaleiro},
  title        = {{GLT:} {A} Unified {API} for Lightweight Thread Libraries},
  booktitle    = {Euro-Par 2017: Parallel Processing - 23rd International Conference
                  on Parallel and Distributed Computing, Santiago de Compostela, Spain,
                  August 28 - September 1, 2017, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {10417},
  pages        = {470--481},
  publisher    = {Springer},
  year         = {2017},
  url          = {https://doi.org/10.1007/978-3-319-64203-1\_34},
  doi          = {10.1007/978-3-319-64203-1\_34},
  timestamp    = {Mon, 02 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/CastelloSMBQP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/Valero-LaraMPMS17,
  author       = {Pedro Valero{-}Lara and
                  Ivan Mart{\'{\i}}nez{-}P{\'{e}}rez and
                  Antonio J. Pe{\~{n}}a and
                  Xavier Martorell and
                  Ra{\"{u}}l Sirvent and
                  Jes{\'{u}}s Labarta},
  editor       = {Petros Koumoutsakos and
                  Michael Lees and
                  Valeria V. Krzhizhanovskaya and
                  Jack J. Dongarra and
                  Peter M. A. Sloot},
  title        = {cuHinesBatch: Solving Multiple Hines systems on GPUs Human Brain Project\({}^{\mbox{*}}\)},
  booktitle    = {International Conference on Computational Science, {ICCS} 2017, 12-14
                  June 2017, Zurich, Switzerland},
  series       = {Procedia Computer Science},
  volume       = {108},
  pages        = {566--575},
  publisher    = {Elsevier},
  year         = {2017},
  url          = {https://doi.org/10.1016/j.procs.2017.05.145},
  doi          = {10.1016/J.PROCS.2017.05.145},
  timestamp    = {Thu, 08 Jul 2021 16:04:01 +0200},
  biburl       = {https://dblp.org/rec/conf/iccS/Valero-LaraMPMS17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/CastelloSMBQP17,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Sangmin Seo and
                  Rafael Mayo and
                  Pavan Balaji and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Antonio J. Pe{\~{n}}a},
  title        = {{GLTO:} On the Adequacy of Lightweight Thread Approaches for OpenMP
                  Implementations},
  booktitle    = {46th International Conference on Parallel Processing, {ICPP} 2017,
                  Bristol, United Kingdom, August 14-17, 2017},
  pages        = {60--69},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICPP.2017.15},
  doi          = {10.1109/ICPP.2017.15},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/CastelloSMBQP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/Garcia-FloresAP17,
  author       = {Victor Garcia{-}Flores and
                  Eduard Ayguad{\'{e}} and
                  Antonio J. Pe{\~{n}}a},
  title        = {Efficient Data Sharing on Heterogeneous Systems},
  booktitle    = {46th International Conference on Parallel Processing, {ICPP} 2017,
                  Bristol, United Kingdom, August 14-17, 2017},
  pages        = {121--130},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICPP.2017.21},
  doi          = {10.1109/ICPP.2017.21},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/Garcia-FloresAP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icppw/IserteMQBP17,
  author       = {Sergio Iserte and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Vicen{\c{c}} Beltran and
                  Antonio J. Pe{\~{n}}a},
  title        = {Efficient Scalable Computing through Flexible Applications and Adaptive
                  Workloads},
  booktitle    = {46th International Conference on Parallel Processing Workshops, {ICPP}
                  Workshops 2017, Bristol, United Kingdom, August 14-17, 2017},
  pages        = {180--189},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICPPW.2017.36},
  doi          = {10.1109/ICPPW.2017.36},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icppw/IserteMQBP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icppw/ServatLHGP17,
  author       = {Harald Servat and
                  Jes{\'{u}}s Labarta and
                  Hans{-}Christian Hoppe and
                  Judit Gim{\'{e}}nez and
                  Antonio J. Pe{\~{n}}a},
  title        = {Integrating Memory Perspective into the {BSC} Performance Tools},
  booktitle    = {46th International Conference on Parallel Processing Workshops, {ICPP}
                  Workshops 2017, Bristol, United Kingdom, August 14-17, 2017},
  pages        = {231--232},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICPPW.2017.42},
  doi          = {10.1109/ICPPW.2017.42},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icppw/ServatLHGP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/PenaBCM17,
  author       = {Antonio J. Pe{\~{n}}a and
                  Vicen{\c{c}} Beltran and
                  Carsten Clauss and
                  Thomas Moschny},
  editor       = {William D. Gropp and
                  Pete Beckman and
                  Zhiyuan Li and
                  Francisco J. Cazorla},
  title        = {Supporting automatic recovery in offloaded distributed programming
                  models through {MPI-3} techniques},
  booktitle    = {Proceedings of the International Conference on Supercomputing, {ICS}
                  2017, Chicago, IL, USA, June 14-16, 2017},
  pages        = {22:1--22:10},
  publisher    = {{ACM}},
  year         = {2017},
  url          = {https://doi.org/10.1145/3079079.3079093},
  doi          = {10.1145/3079079.3079093},
  timestamp    = {Wed, 25 Sep 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ics/PenaBCM17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispass/Gomez-LunaHCGGJ17,
  author       = {Juan G{\'{o}}mez{-}Luna and
                  Izzat El Hajj and
                  Li{-}Wen Chang and
                  Victor Garcia{-}Flores and
                  Simon Garcia De Gonzalo and
                  Thomas B. Jablin and
                  Antonio J. Pe{\~{n}}a and
                  Wen{-}mei W. Hwu},
  title        = {Chai: Collaborative heterogeneous applications for integrated-architectures},
  booktitle    = {2017 {IEEE} International Symposium on Performance Analysis of Systems
                  and Software, {ISPASS} 2017, Santa Rosa, CA, USA, April 24-25, 2017},
  pages        = {43--54},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ISPASS.2017.7975269},
  doi          = {10.1109/ISPASS.2017.7975269},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ispass/Gomez-LunaHCGGJ17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppam/Valero-LaraMSMP17,
  author       = {Pedro Valero{-}Lara and
                  Ivan Mart{\'{\i}}nez{-}P{\'{e}}rez and
                  Ra{\"{u}}l Sirvent and
                  Xavier Martorell and
                  Antonio J. Pe{\~{n}}a},
  editor       = {Roman Wyrzykowski and
                  Jack J. Dongarra and
                  Ewa Deelman and
                  Konrad Karczewski},
  title        = {{NVIDIA} GPUs Scalability to Solve Multiple (Batch) Tridiagonal Systems
                  Implementation of cuThomasBatch},
  booktitle    = {Parallel Processing and Applied Mathematics - 12th International Conference,
                  {PPAM} 2017, Lublin, Poland, September 10-13, 2017, Revised Selected
                  Papers, Part {I}},
  series       = {Lecture Notes in Computer Science},
  volume       = {10777},
  pages        = {243--253},
  publisher    = {Springer},
  year         = {2017},
  url          = {https://doi.org/10.1007/978-3-319-78024-5\_22},
  doi          = {10.1007/978-3-319-78024-5\_22},
  timestamp    = {Wed, 25 Sep 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppam/Valero-LaraMSMP17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/pvm/2017,
  editor       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  William Gropp and
                  Rajeev Thakur},
  title        = {Proceedings of the 24th European {MPI} Users' Group Meeting, EuroMPI/USA
                  2017, Chicago, IL, USA, September 25-28, 2017},
  publisher    = {{ACM}},
  year         = {2017},
  url          = {http://dl.acm.org/citation.cfm?id=3127024},
  isbn         = {978-1-4503-4849-2},
  timestamp    = {Thu, 24 Aug 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/pvm/2017.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/PenaB16,
  author       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji},
  title        = {A data-oriented profiler to assist in data partitioning and distribution
                  for heterogeneous memory in {HPC}},
  journal      = {Parallel Comput.},
  volume       = {51},
  pages        = {46--55},
  year         = {2016},
  url          = {https://doi.org/10.1016/j.parco.2015.10.006},
  doi          = {10.1016/J.PARCO.2015.10.006},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/PenaB16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/AjiPBF16,
  author       = {Ashwin M. Aji and
                  Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  Wu{-}chun Feng},
  title        = {MultiCL: Enabling automatic scheduling for task-parallel workloads
                  in OpenCL},
  journal      = {Parallel Comput.},
  volume       = {58},
  pages        = {37--55},
  year         = {2016},
  url          = {https://doi.org/10.1016/j.parco.2016.05.006},
  doi          = {10.1016/J.PARCO.2016.05.006},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/AjiPBF16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/CastelloPSMBQ16,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Antonio J. Pe{\~{n}}a and
                  Sangmin Seo and
                  Rafael Mayo and
                  Pavan Balaji and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  title        = {A Review of Lightweight Thread Approaches for High Performance Computing},
  booktitle    = {2016 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2016, Taipei, Taiwan, September 12-16, 2016},
  pages        = {471--480},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/CLUSTER.2016.12},
  doi          = {10.1109/CLUSTER.2016.12},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/CastelloPSMBQ16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/GhoshHPBGC16,
  author       = {Sayan Ghosh and
                  Jeff R. Hammond and
                  Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  Assefaw Hadish Gebremedhin and
                  Barbara M. Chapman},
  title        = {One-Sided Interface for Matrix Operations Using {MPI-3} {RMA:} {A}
                  Case Study with Elemental},
  booktitle    = {45th International Conference on Parallel Processing, {ICPP} 2016,
                  Philadelphia, PA, USA, August 16-19, 2016},
  pages        = {185--194},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/ICPP.2016.28},
  doi          = {10.1109/ICPP.2016.28},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/GhoshHPBGC16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iiswc/GarciaGGRAP16,
  author       = {Victor Garcia and
                  Juan G{\'{o}}mez{-}Luna and
                  Thomas Grass and
                  Alejandro Rico and
                  Eduard Ayguad{\'{e}} and
                  Antonio J. Pe{\~{n}}a},
  title        = {Evaluating the effect of last-level cache sharing on integrated {GPU-CPU}
                  systems with heterogeneous applications},
  booktitle    = {2016 {IEEE} International Symposium on Workload Characterization,
                  {IISWC} 2016, Providence, RI, USA, September 25-27, 2016},
  pages        = {168--177},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/IISWC.2016.7581277},
  doi          = {10.1109/IISWC.2016.7581277},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iiswc/GarciaGGRAP16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/ReanoSGPMQD15,
  author       = {Carlos Rea{\~{n}}o and
                  Federico Silla and
                  Adri{\'{a}}n Castell{\'{o}} and
                  Antonio J. Pe{\~{n}}a and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Jos{\'{e}} Duato},
  title        = {Improving the user experience of the rCUDA remote {GPU} virtualization
                  framework},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {27},
  number       = {14},
  pages        = {3746--3770},
  year         = {2015},
  url          = {https://doi.org/10.1002/cpe.3409},
  doi          = {10.1002/CPE.3409},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/concurrency/ReanoSGPMQD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/SiPHBI15,
  author       = {Min Si and
                  Antonio J. Pe{\~{n}}a and
                  Jeff R. Hammond and
                  Pavan Balaji and
                  Yutaka Ishikawa},
  title        = {Scaling NWChem with Efficient and Portable Asynchronous Communication
                  in {MPI} {RMA}},
  booktitle    = {15th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
                  Computing, CCGrid 2015, Shenzhen, China, May 4-7, 2015},
  pages        = {811--816},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CCGrid.2015.48},
  doi          = {10.1109/CCGRID.2015.48},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/SiPHBI15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/PenaB15,
  author       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji},
  title        = {Understanding Data Access Patterns Using Object-Differentiated Memory
                  Profiling},
  booktitle    = {15th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
                  Computing, CCGrid 2015, Shenzhen, China, May 4-7, 2015},
  pages        = {1143--1146},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CCGrid.2015.42},
  doi          = {10.1109/CCGRID.2015.42},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/PenaB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/RaffenettiPB15,
  author       = {Ken Raffenetti and
                  Antonio J. Pe{\~{n}}a and
                  Pavan Balaji},
  title        = {Toward Implementing Robust Support for Portals 4 Networks in {MPICH}},
  booktitle    = {15th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
                  Computing, CCGrid 2015, Shenzhen, China, May 4-7, 2015},
  pages        = {1173--1176},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CCGrid.2015.79},
  doi          = {10.1109/CCGRID.2015.79},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/RaffenettiPB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/AjiPBF15,
  author       = {Ashwin Mandayam Aji and
                  Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  Wu{-}chun Feng},
  title        = {Automatic Command Queue Scheduling for Task-Parallel Workloads in
                  OpenCL},
  booktitle    = {2015 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2015, Chicago, IL, USA, September 8-11, 2015},
  pages        = {42--51},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CLUSTER.2015.15},
  doi          = {10.1109/CLUSTER.2015.15},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/AjiPBF15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/GimenoPMBQ15,
  author       = {Adri{\'{a}}n Castell{\'{o}} and
                  Antonio J. Pe{\~{n}}a and
                  Rafael Mayo and
                  Pavan Balaji and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  title        = {Exploring the Suitability of Remote {GPGPU} Virtualization for the
                  OpenACC Programming Model Using rCUDA},
  booktitle    = {2015 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2015, Chicago, IL, USA, September 8-11, 2015},
  pages        = {92--95},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CLUSTER.2015.23},
  doi          = {10.1109/CLUSTER.2015.23},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/GimenoPMBQ15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/SiPHBTI15,
  author       = {Min Si and
                  Antonio J. Pe{\~{n}}a and
                  Jeff R. Hammond and
                  Pavan Balaji and
                  Masamichi Takagi and
                  Yutaka Ishikawa},
  title        = {Casper: An Asynchronous Progress Model for {MPI} {RMA} on Many-Core
                  Architectures},
  booktitle    = {2015 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
  pages        = {665--676},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/IPDPS.2015.35},
  doi          = {10.1109/IPDPS.2015.35},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/SiPHBTI15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/PenaBB15,
  author       = {Antonio J. Pe{\~{n}}a and
                  Wesley Bland and
                  Pavan Balaji},
  editor       = {Jackie Kern and
                  Jeffrey S. Vetter},
  title        = {{VOCL-FT:} introducing techniques for efficient soft error coprocessor
                  recovery},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2015, Austin, TX, USA, November
                  15-20, 2015},
  pages        = {71:1--71:12},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2807591.2807640},
  doi          = {10.1145/2807591.2807640},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/PenaBB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/PenaRSMQD14,
  author       = {Antonio J. Pe{\~{n}}a and
                  Carlos Rea{\~{n}}o and
                  Federico Silla and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Jos{\'{e}} Duato},
  title        = {A complete and efficient CUDA-sharing solution for {HPC} clusters},
  journal      = {Parallel Comput.},
  volume       = {40},
  number       = {10},
  pages        = {574--588},
  year         = {2014},
  url          = {https://doi.org/10.1016/j.parco.2014.09.011},
  doi          = {10.1016/J.PARCO.2014.09.011},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/pc/PenaRSMQD14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/PenaB14,
  author       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji},
  title        = {Toward the efficient use of multiple explicitly managed memory subsystems},
  booktitle    = {2014 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2014, Madrid, Spain, September 22-26, 2014},
  pages        = {123--131},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/CLUSTER.2014.6968756},
  doi          = {10.1109/CLUSTER.2014.6968756},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/PenaB14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/ReanoSPSSGQD14,
  author       = {Carlos Rea{\~{n}}o and
                  Federico Silla and
                  Antonio J. Pe{\~{n}}a and
                  Gilad Shainer and
                  Scot Schultz and
                  Adri{\'{a}}n Castell{\'{o}} and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Jos{\'{e}} Duato},
  title        = {Boosting the performance of remote {GPU} virtualization using InfiniBand
                  connect-IB and PCIe 3.0},
  booktitle    = {2014 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2014, Madrid, Spain, September 22-26, 2014},
  pages        = {266--267},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/CLUSTER.2014.6968737},
  doi          = {10.1109/CLUSTER.2014.6968737},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/ReanoSPSSGQD14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icppw/PenaB14,
  author       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji},
  title        = {A Framework for Tracking Memory Accesses in Scientific Applications},
  booktitle    = {43rd International Conference on Parallel Processing Workshops, {ICPPW}
                  2014, Minneapolis, MN, USA, September 9-12, 2014},
  pages        = {235--244},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/ICPPW.2014.40},
  doi          = {10.1109/ICPPW.2014.40},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icppw/PenaB14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/SiPBTI14,
  author       = {Min Si and
                  Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  Masamichi Takagi and
                  Yutaka Ishikawa},
  editor       = {Arndt Bode and
                  Michael Gerndt and
                  Per Stenstr{\"{o}}m and
                  Lawrence Rauchwerger and
                  Barton P. Miller and
                  Martin Schulz},
  title        = {{MT-MPI:} multithreaded {MPI} for many-core environments},
  booktitle    = {2014 International Conference on Supercomputing, ICS'14, Muenchen,
                  Germany, June 10-13, 2014},
  pages        = {125--134},
  publisher    = {{ACM}},
  year         = {2014},
  url          = {https://doi.org/10.1145/2597652.2597658},
  doi          = {10.1145/2597652.2597658},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ics/SiPBTI14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/PenaA13,
  author       = {Antonio J. Pe{\~{n}}a and
                  Sadaf R. Alam},
  title        = {Evaluation of Inter- and Intra-node Data Transfer Efficiencies between
                  {GPU} Devices and their Impact on Scalable Applications},
  booktitle    = {13th {IEEE/ACM} International Symposium on Cluster, Cloud, and Grid
                  Computing, CCGrid 2013, Delft, Netherlands, May 13-16, 2013},
  pages        = {144--151},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/CCGrid.2013.15},
  doi          = {10.1109/CCGRID.2013.15},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/PenaA13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/ReanoMQSDP13,
  author       = {Carlos Rea{\~{n}}o and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Federico Silla and
                  Jos{\'{e}} Duato and
                  Antonio J. Pe{\~{n}}a},
  title        = {Influence of InfiniBand {FDR} on the performance of remote {GPU} virtualization},
  booktitle    = {2013 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2013, Indianapolis, IN, USA, September 23-27, 2013},
  pages        = {1--8},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/CLUSTER.2013.6702662},
  doi          = {10.1109/CLUSTER.2013.6702662},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/ReanoMQSDP13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/PenaCDBTG13,
  author       = {Antonio J. Pe{\~{n}}a and
                  Ralf G. Correa Carvalho and
                  James Dinan and
                  Pavan Balaji and
                  Rajeev Thakur and
                  William Gropp},
  editor       = {Jack J. Dongarra and
                  Javier Garc{\'{\i}}a Blas and
                  Jes{\'{u}}s Carretero},
  title        = {Analysis of topology-dependent {MPI} performance on Gemini networks},
  booktitle    = {20th European {MPI} Users's Group Meeting, EuroMPI '13, Madrid, Spain
                  - September 15 - 18, 2013},
  pages        = {61--66},
  publisher    = {{ACM}},
  year         = {2013},
  url          = {https://doi.org/10.1145/2488551.2488564},
  doi          = {10.1145/2488551.2488564},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/pvm/PenaCDBTG13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/ReanoPSDMQ12,
  author       = {Carlos Rea{\~{n}}o and
                  Antonio J. Pe{\~{n}}a and
                  Federico Silla and
                  Jos{\'{e}} Duato and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  title        = {CU2rCU: Towards the complete rCUDA remote {GPU} virtualization and
                  sharing solution},
  booktitle    = {19th International Conference on High Performance Computing, HiPC
                  2012, Pune, India, December 18-22, 2012},
  pages        = {1--10},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/HiPC.2012.6507485},
  doi          = {10.1109/HIPC.2012.6507485},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/ReanoPSDMQ12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/DuatoPSFMQ11,
  author       = {Jos{\'{e}} Duato and
                  Antonio J. Pe{\~{n}}a and
                  Federico Silla and
                  Juan Carlos Fern{\'{a}}ndez and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  title        = {Enabling {CUDA} acceleration within virtual machines using rCUDA},
  booktitle    = {18th International Conference on High Performance Computing, HiPC
                  2011, Bengaluru, India, December 18-21, 2011},
  pages        = {1--10},
  publisher    = {{IEEE} Computer Society},
  year         = {2011},
  url          = {https://doi.org/10.1109/HiPC.2011.6152718},
  doi          = {10.1109/HIPC.2011.6152718},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/DuatoPSFMQ11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/DuatoPSMQ11,
  author       = {Jos{\'{e}} Duato and
                  Antonio J. Pe{\~{n}}a and
                  Federico Silla and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  editor       = {Guang R. Gao and
                  Yu{-}Chee Tseng},
  title        = {Performance of {CUDA} Virtualized Remote GPUs in High Performance
                  Clusters},
  booktitle    = {International Conference on Parallel Processing, {ICPP} 2011, Taipei,
                  Taiwan, September 13-16, 2011},
  pages        = {365--374},
  publisher    = {{IEEE} Computer Society},
  year         = {2011},
  url          = {https://doi.org/10.1109/ICPP.2011.58},
  doi          = {10.1109/ICPP.2011.58},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/DuatoPSMQ11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ieeehpcs/DuatoPSMQ10,
  author       = {Jos{\'{e}} Duato and
                  Antonio J. Pe{\~{n}}a and
                  Federico Silla and
                  Rafael Mayo and
                  Enrique S. Quintana{-}Ort{\'{\i}}},
  editor       = {Waleed W. Smari and
                  John P. McIntire},
  title        = {rCUDA: Reducing the number of GPU-based accelerators in high performance
                  clusters},
  booktitle    = {Proceedings of the 2010 International Conference on High Performance
                  Computing {\&} Simulation, {HPCS} 2010, June 28 - July 2, 2010,
                  Caen, France},
  pages        = {224--231},
  publisher    = {{IEEE}},
  year         = {2010},
  url          = {https://doi.org/10.1109/HPCS.2010.5547126},
  doi          = {10.1109/HPCS.2010.5547126},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ieeehpcs/DuatoPSMQ10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/DuatoIMPQS09,
  author       = {Jos{\'{e}} Duato and
                  Francisco D. Igual and
                  Rafael Mayo and
                  Antonio J. Pe{\~{n}}a and
                  Enrique S. Quintana{-}Ort{\'{\i}} and
                  Federico Silla},
  editor       = {Hai{-}Xiang Lin and
                  Michael Alexander and
                  Martti Forsell and
                  Andreas Kn{\"{u}}pfer and
                  Radu Prodan and
                  Leonel Sousa and
                  Achim Streit},
  title        = {An Efficient Implementation of {GPU} Virtualization in High Performance
                  Clusters},
  booktitle    = {Euro-Par 2009 - Parallel Processing Workshops, HPPC, HeteroPar, PROPER,
                  ROIA, UNICORE, VHPC, Delft, The Netherlands, August 25-28, 2009, Revised
                  Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {6043},
  pages        = {385--394},
  publisher    = {Springer},
  year         = {2009},
  url          = {https://doi.org/10.1007/978-3-642-14122-5\_44},
  doi          = {10.1007/978-3-642-14122-5\_44},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/DuatoIMPQS09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics