BibTeX records: John D. Owens

download as .bib file

@inproceedings{DBLP:conf/ipps/OwensH24,
  author       = {John D. Owens and
                  Bruce Hoppe},
  title        = {Helping Faculty Teach Software Performance Engineering},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2024 - Workshop, San Francisco, CA, USA, May 27-31, 2024},
  pages        = {338--341},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/IPDPSW63119.2024.00078},
  doi          = {10.1109/IPDPSW63119.2024.00078},
  timestamp    = {Wed, 07 Aug 2024 14:14:07 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/OwensH24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-11591,
  author       = {Toluwanimi O. Odemuyiwa and
                  Joel S. Emer and
                  John D. Owens},
  title        = {The {EDGE} Language: Extended General Einsums for Graph Algorithms},
  journal      = {CoRR},
  volume       = {abs/2404.11591},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.11591},
  doi          = {10.48550/ARXIV.2404.11591},
  eprinttype    = {arXiv},
  eprint       = {2404.11591},
  timestamp    = {Wed, 22 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-11591.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-12674,
  author       = {Zhongyi Lin and
                  Ning Sun and
                  Pallab Bhattacharya and
                  Xizhou Feng and
                  Louis Feng and
                  John D. Owens},
  title        = {Towards Universal Performance Modeling for Machine Learning Training
                  on Multi-GPU Platforms},
  journal      = {CoRR},
  volume       = {abs/2404.12674},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.12674},
  doi          = {10.48550/ARXIV.2404.12674},
  eprinttype    = {arXiv},
  eprint       = {2404.12674},
  timestamp    = {Wed, 22 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-12674.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apocs/AwadAPFO23,
  author       = {Muhammad A. Awad and
                  Saman Ashkiani and
                  Serban D. Porumbescu and
                  Martin Farach{-}Colton and
                  John D. Owens},
  editor       = {Jie Gao},
  title        = {Analyzing and Implementing {GPU} Hash Tables},
  booktitle    = {2023 Symposium on Algorithmic Principles of Computer Systems, {APOCS}
                  2023, Florence, Italy, January 25, 2023},
  pages        = {33--50},
  publisher    = {{SIAM}},
  year         = {2023},
  url          = {https://doi.org/10.1137/1.9781611977578.ch3},
  doi          = {10.1137/1.9781611977578.CH3},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/apocs/AwadAPFO23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asplos/OdemuyiwaMPHTCJ23,
  author       = {Toluwanimi O. Odemuyiwa and
                  Hadi Asghari Moghaddam and
                  Michael Pellauer and
                  Kartik Hegde and
                  Po{-}An Tsai and
                  Neal Clayton Crago and
                  Aamer Jaleel and
                  John D. Owens and
                  Edgar Solomonik and
                  Joel S. Emer and
                  Christopher W. Fletcher},
  editor       = {Tor M. Aamodt and
                  Natalie D. Enright Jerger and
                  Michael M. Swift},
  title        = {Accelerating Sparse Data Orchestration via Dynamic Reflexive Tiling},
  booktitle    = {Proceedings of the 28th {ACM} International Conference on Architectural
                  Support for Programming Languages and Operating Systems, Volume 3,
                  {ASPLOS} 2023, Vancouver, BC, Canada, March 25-29, 2023},
  pages        = {18--32},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3582016.3582064},
  doi          = {10.1145/3582016.3582064},
  timestamp    = {Tue, 21 Mar 2023 11:08:23 +0100},
  biburl       = {https://dblp.org/rec/conf/asplos/OdemuyiwaMPHTCJ23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hopc/OdemuyiwaMPHTCJ23,
  author       = {Toluwanimi O. Odemuyiwa and
                  Hadi Asghari Moghaddam and
                  Michael Pellauer and
                  Kartik Hegde and
                  Po{-}An Tsai and
                  Neal Clayton Crago and
                  Aamer Jaleel and
                  John D. Owens and
                  Edgar Solomonik and
                  Joel S. Emer and
                  Christopher W. Fletcher},
  editor       = {Laxman Dhulipala and
                  Yihan Sun},
  title        = {Accelerating Sparse Data Orchestration via Dynamic Reflexive Tiling
                  (Extended Abstract)},
  booktitle    = {Proceedings of the 2023 {ACM} Workshop on Highlights of Parallel Computing,
                  {HOPC} 2023, Orlando, FL, USA, 16 June 2023},
  pages        = {15--16},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3597635.3598031},
  doi          = {10.1145/3597635.3598031},
  timestamp    = {Fri, 21 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/hopc/OdemuyiwaMPHTCJ23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/GeilPO23,
  author       = {Afton Geil and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Maximum Clique Enumeration on the {GPU}},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2023 - Workshops, St. Petersburg, FL, USA, May 15-19, 2023},
  pages        = {234--244},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/IPDPSW59300.2023.00047},
  doi          = {10.1109/IPDPSW59300.2023.00047},
  timestamp    = {Wed, 09 Aug 2023 16:25:12 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/GeilPO23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/WapmanTPO23,
  author       = {Jonathan D. Wapman and
                  Sean Treichler and
                  Serban D. Porumbescu and
                  John D. Owens},
  editor       = {Quan Chen and
                  Zhiyi Huang and
                  Min Si},
  title        = {Harmonic {CUDA:} Asynchronous Programming on GPUs},
  booktitle    = {Proceedings of the 14th International Workshop on Programming Models
                  and Applications for Multicores and Manycores, PMAM@PPoPP 2023, Montreal,
                  QC, Canada, 25 February 2023 - 1 March 2023},
  pages        = {39--49},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3582514.3582517},
  doi          = {10.1145/3582514.3582517},
  timestamp    = {Sat, 11 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ppopp/WapmanTPO23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/OsamaPO23,
  author       = {Muhammad Osama and
                  Serban D. Porumbescu and
                  John D. Owens},
  editor       = {Maryam Mehri Dehnavi and
                  Milind Kulkarni and
                  Sriram Krishnamoorthy},
  title        = {A Programming Model for {GPU} Load Balancing},
  booktitle    = {Proceedings of the 28th {ACM} {SIGPLAN} Annual Symposium on Principles
                  and Practice of Parallel Programming, PPoPP 2023, Montreal, QC, Canada,
                  25 February 2023 - 1 March 2023},
  pages        = {79--91},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3572848.3577434},
  doi          = {10.1145/3572848.3577434},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/OsamaPO23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/OsamaMCGO23,
  author       = {Muhammad Osama and
                  Duane Merrill and
                  Cris Cecka and
                  Michael Garland and
                  John D. Owens},
  editor       = {Maryam Mehri Dehnavi and
                  Milind Kulkarni and
                  Sriram Krishnamoorthy},
  title        = {Stream-K: Work-Centric Parallel Decomposition for Dense Matrix-Matrix
                  Multiplication on the {GPU}},
  booktitle    = {Proceedings of the 28th {ACM} {SIGPLAN} Annual Symposium on Principles
                  and Practice of Parallel Programming, PPoPP 2023, Montreal, QC, Canada,
                  25 February 2023 - 1 March 2023},
  pages        = {429--431},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3572848.3577479},
  doi          = {10.1145/3572848.3577479},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/OsamaMCGO23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-03598,
  author       = {Muhammad Osama and
                  Duane Merrill and
                  Cris Cecka and
                  Michael Garland and
                  John D. Owens},
  title        = {Stream-K: Work-centric Parallel Decomposition for Dense Matrix-Matrix
                  Multiplication on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/2301.03598},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2301.03598},
  doi          = {10.48550/ARXIV.2301.03598},
  eprinttype    = {arXiv},
  eprint       = {2301.03598},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2301-03598.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-04792,
  author       = {Muhammad Osama and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {A Programming Model for {GPU} Load Balancing},
  journal      = {CoRR},
  volume       = {abs/2301.04792},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2301.04792},
  doi          = {10.48550/ARXIV.2301.04792},
  eprinttype    = {arXiv},
  eprint       = {2301.04792},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2301-04792.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-10410,
  author       = {Matthew Drescher and
                  Muhammad A. Awad and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {{BOBA:} {A} Parallel Lightweight Graph Reordering Algorithm with Heavyweight
                  Implications},
  journal      = {CoRR},
  volume       = {abs/2306.10410},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.10410},
  doi          = {10.48550/ARXIV.2306.10410},
  eprinttype    = {arXiv},
  eprint       = {2306.10410},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-10410.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-00496,
  author       = {Cameron Shinn and
                  Collin McCarthy and
                  Saurav Muralidharan and
                  Muhammad Osama and
                  John D. Owens},
  title        = {The Sparsity Roofline: Understanding the Hardware Limits of Sparse
                  Neural Networks},
  journal      = {CoRR},
  volume       = {abs/2310.00496},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2310.00496},
  doi          = {10.48550/ARXIV.2310.00496},
  eprinttype    = {arXiv},
  eprint       = {2310.00496},
  timestamp    = {Wed, 18 Oct 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-00496.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pacmcgit/SeitzFPO22,
  author       = {Kerry A. Seitz and
                  Theresa Foley and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Supporting Unified Shader Specialization by Co-opting {C++} Features},
  journal      = {Proc. {ACM} Comput. Graph. Interact. Tech.},
  volume       = {5},
  number       = {3},
  pages        = {25:1--25:17},
  year         = {2022},
  url          = {https://doi.org/10.1145/3543866},
  doi          = {10.1145/3543866},
  timestamp    = {Sun, 20 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pacmcgit/SeitzFPO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/toms/YangBO22,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {GraphBLAST: {A} High-Performance Linear Algebra-based Graph Framework
                  on the {GPU}},
  journal      = {{ACM} Trans. Math. Softw.},
  volume       = {48},
  number       = {1},
  pages        = {1:1--1:51},
  year         = {2022},
  url          = {https://doi.org/10.1145/3466795},
  doi          = {10.1145/3466795},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/toms/YangBO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/AwadPO22,
  author       = {Muhammad A. Awad and
                  Serban D. Porumbescu and
                  John D. Owens},
  editor       = {Andreas Kl{\"{o}}ckner and
                  Jos{\'{e}} Moreira},
  title        = {A {GPU} Multiversion B-Tree},
  booktitle    = {Proceedings of the International Conference on Parallel Architectures
                  and Compilation Techniques, {PACT} 2022, Chicago, Illinois, October
                  8-12, 2022},
  pages        = {481--493},
  publisher    = {{ACM}},
  year         = {2022},
  url          = {https://doi.org/10.1145/3559009.3569681},
  doi          = {10.1145/3559009.3569681},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/IEEEpact/AwadPO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/LinFALLKKO22,
  author       = {Zhongyi Lin and
                  Louis Feng and
                  Ehsan K. Ardestani and
                  Jaewon Lee and
                  John Lundell and
                  Changkyu Kim and
                  Arun Kejariwal and
                  John D. Owens},
  title        = {Building a Performance Model for Deep Learning Recommendation Model
                  Training on GPUs},
  booktitle    = {29th {IEEE} International Conference on High Performance Computing,
                  Data, and Analytics, HiPC 2022, Bengaluru, India, December 18-21,
                  2022},
  pages        = {48--58},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/HiPC56025.2022.00019},
  doi          = {10.1109/HIPC56025.2022.00019},
  timestamp    = {Wed, 03 May 2023 17:27:40 +0200},
  biburl       = {https://dblp.org/rec/conf/hipc/LinFALLKKO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/ChenBPBYO22,
  author       = {Yuxin Chen and
                  Benjamin Brock and
                  Serban D. Porumbescu and
                  Aydin Bulu{\c{c}} and
                  Katherine A. Yelick and
                  John D. Owens},
  title        = {Atos: {A} Task-Parallel {GPU} Scheduler for Graph Analytics},
  booktitle    = {Proceedings of the 51st International Conference on Parallel Processing,
                  {ICPP} 2022, Bordeaux, France, 29 August 2022 - 1 September 2022},
  pages        = {50:1--50:11},
  publisher    = {{ACM}},
  year         = {2022},
  url          = {https://doi.org/10.1145/3545008.3545056},
  doi          = {10.1145/3545008.3545056},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icpp/ChenBPBYO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/OsamaPO22,
  author       = {Muhammad Osama and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Essentials of Parallel Graph Analytics},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} Workshops 2022, Lyon, France, May 30 - June 3, 2022},
  pages        = {314--317},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/IPDPSW55747.2022.00061},
  doi          = {10.1109/IPDPSW55747.2022.00061},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/OsamaPO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispass/LinFALLKKO22,
  author       = {Zhongyi Lin and
                  Louis Feng and
                  Ehsan K. Ardestani and
                  Jaewon Lee and
                  John Lundell and
                  Changkyu Kim and
                  Arun Kejariwal and
                  John D. Owens},
  title        = {Building a Performance Model for Deep Learning Recommendation Model
                  Training on GPUs},
  booktitle    = {International {IEEE} Symposium on Performance Analysis of Systems
                  and Software, {ISPASS} 2022, Singapore, May 22-24, 2022},
  pages        = {227--229},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ISPASS55109.2022.00030},
  doi          = {10.1109/ISPASS55109.2022.00030},
  timestamp    = {Mon, 04 Jul 2022 17:06:18 +0200},
  biburl       = {https://dblp.org/rec/conf/ispass/LinFALLKKO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ChenBPBYO22,
  author       = {Yuxin Chen and
                  Benjamin Brock and
                  Serban D. Porumbescu and
                  Aydin Bulu{\c{c}} and
                  Katherine A. Yelick and
                  John D. Owens},
  editor       = {Felix Wolf and
                  Sameer Shende and
                  Candace Culhane and
                  Sadaf R. Alam and
                  Heike Jagode},
  title        = {Scalable Irregular Parallelism with GPUs: Getting CPUs Out of the
                  Way},
  booktitle    = {{SC22:} International Conference for High Performance Computing, Networking,
                  Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
  pages        = {50:1--50:16},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/SC41404.2022.00055},
  doi          = {10.1109/SC41404.2022.00055},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/ChenBPBYO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/crc/22/KepnerABBF0H0LMMMOYZM22,
  author       = {Jeremy Kepner and
                  Peter Aaltonen and
                  David A. Bader and
                  Aydin Bulu{\c{c}} and
                  Franz Franchetti and
                  John Gilbert and
                  Shana Hutchison and
                  Manoj Kumar and
                  Andrew Lumsdaine and
                  Henning Meyerhenke and
                  Scott McMillan and
                  Jos{\'{e}} E. Moreira and
                  John D. Owens and
                  Carl Yang and
                  Marcin Zalewski and
                  Timothy G. Mattson},
  editor       = {David A. Bader},
  title        = {Introduction to GraphBLAS},
  booktitle    = {Massive Graph Analytics},
  pages        = {507--524},
  publisher    = {Chapman and Hall/CRC},
  year         = {2022},
  url          = {https://doi.org/10.1201/9781003033707-24},
  doi          = {10.1201/9781003033707-24},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/books/crc/22/KepnerABBF0H0LMMMOYZM22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-07821,
  author       = {Zhongyi Lin and
                  Louis Feng and
                  Ehsan K. Ardestani and
                  Jaewon Lee and
                  John Lundell and
                  Changkyu Kim and
                  Arun Kejariwal and
                  John D. Owens},
  title        = {Building a Performance Model for Deep Learning Recommendation Model
                  Training on GPUs},
  journal      = {CoRR},
  volume       = {abs/2201.07821},
  year         = {2022},
  url          = {https://arxiv.org/abs/2201.07821},
  eprinttype    = {arXiv},
  eprint       = {2201.07821},
  timestamp    = {Tue, 01 Feb 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2201-07821.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08200,
  author       = {Muhammad Osama and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Essentials of Parallel Graph Analytics},
  journal      = {CoRR},
  volume       = {abs/2212.08200},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.08200},
  doi          = {10.48550/ARXIV.2212.08200},
  eprinttype    = {arXiv},
  eprint       = {2212.08200},
  timestamp    = {Tue, 22 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-08200.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/MahmoudPO21,
  author       = {Ahmed H. Mahmoud and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {RXMesh: a {GPU} mesh data structure},
  journal      = {{ACM} Trans. Graph.},
  volume       = {40},
  number       = {4},
  pages        = {104:1--104:16},
  year         = {2021},
  url          = {https://doi.org/10.1145/3450626.3459748},
  doi          = {10.1145/3450626.3459748},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/MahmoudPO21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/LinGO21,
  author       = {Zhongyi Lin and
                  Evangelos Georganas and
                  John D. Owens},
  editor       = {Leonel Sousa and
                  Nuno Roma and
                  Pedro Tom{\'{a}}s},
  title        = {Towards Flexible and Compiler-Friendly Layer Fusion for CNNs on Multicore
                  CPUs},
  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        = {232--248},
  publisher    = {Springer},
  year         = {2021},
  url          = {https://doi.org/10.1007/978-3-030-85665-6\_15},
  doi          = {10.1007/978-3-030-85665-6\_15},
  timestamp    = {Thu, 16 Sep 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/LinGO21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-07232,
  author       = {Muhammad A. Awad and
                  Saman Ashkiani and
                  Serban D. Porumbescu and
                  Martin Farach{-}Colton and
                  John D. Owens},
  title        = {Better {GPU} Hash Tables},
  journal      = {CoRR},
  volume       = {abs/2108.07232},
  year         = {2021},
  url          = {https://arxiv.org/abs/2108.07232},
  eprinttype    = {arXiv},
  eprint       = {2108.07232},
  timestamp    = {Fri, 20 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2108-07232.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-14682,
  author       = {Kerry A. Seitz Jr. and
                  Theresa Foley and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Unified Shader Programming in {C++}},
  journal      = {CoRR},
  volume       = {abs/2109.14682},
  year         = {2021},
  url          = {https://arxiv.org/abs/2109.14682},
  eprinttype    = {arXiv},
  eprint       = {2109.14682},
  timestamp    = {Mon, 04 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-14682.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-00132,
  author       = {Yuxin Chen and
                  Benjamin Brock and
                  Serban D. Porumbescu and
                  Aydin Bulu{\c{c}} and
                  Katherine A. Yelick and
                  John D. Owens},
  title        = {Atos: {A} Task-Parallel {GPU} Dynamic Scheduling Framework for Dynamic
                  Irregular Computations},
  journal      = {CoRR},
  volume       = {abs/2112.00132},
  year         = {2021},
  url          = {https://arxiv.org/abs/2112.00132},
  eprinttype    = {arXiv},
  eprint       = {2112.00132},
  timestamp    = {Tue, 07 Dec 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2112-00132.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/AbdelkaderBEMMO20,
  author       = {Ahmed Abdelkader and
                  Chandrajit L. Bajaj and
                  Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Scott A. Mitchell and
                  John D. Owens and
                  Ahmad A. Rushdi},
  title        = {VoroCrust: Voronoi Meshing Without Clipping},
  journal      = {{ACM} Trans. Graph.},
  volume       = {39},
  number       = {3},
  pages        = {23:1--23:16},
  year         = {2020},
  url          = {https://doi.org/10.1145/3337680},
  doi          = {10.1145/3337680},
  timestamp    = {Sat, 08 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tog/AbdelkaderBEMMO20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/AwadAPO20,
  author       = {Muhammad A. Awad and
                  Saman Ashkiani and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Dynamic Graphs on the {GPU}},
  booktitle    = {2020 {IEEE} International Parallel and Distributed Processing Symposium
                  (IPDPS), New Orleans, LA, USA, May 18-22, 2020},
  pages        = {739--748},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/IPDPS47924.2020.00081},
  doi          = {10.1109/IPDPS47924.2020.00081},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/AwadAPO20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LiuWOL20,
  author       = {Weitang Liu and
                  Xiaoyun Wang and
                  John D. Owens and
                  Yixuan Li},
  editor       = {Hugo Larochelle and
                  Marc'Aurelio Ranzato and
                  Raia Hadsell and
                  Maria{-}Florina Balcan and
                  Hsuan{-}Tien Lin},
  title        = {Energy-based Out-of-distribution Detection},
  booktitle    = {Advances in Neural Information Processing Systems 33: Annual Conference
                  on Neural Information Processing Systems 2020, NeurIPS 2020, December
                  6-12, 2020, virtual},
  year         = {2020},
  url          = {https://proceedings.neurips.cc/paper/2020/hash/f5496252609c43eb8a3d147ab9b9c006-Abstract.html},
  timestamp    = {Tue, 19 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/LiuWOL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-01527,
  author       = {Leyuan Wang and
                  John D. Owens},
  title        = {Fast Gunrock Subgraph Matching {(GSM)} on GPUs},
  journal      = {CoRR},
  volume       = {abs/2003.01527},
  year         = {2020},
  url          = {https://arxiv.org/abs/2003.01527},
  eprinttype    = {arXiv},
  eprint       = {2003.01527},
  timestamp    = {Tue, 10 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2003-01527.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-03759,
  author       = {Weitang Liu and
                  Xiaoyun Wang and
                  John D. Owens and
                  Yixuan Li},
  title        = {Energy-based Out-of-distribution Detection},
  journal      = {CoRR},
  volume       = {abs/2010.03759},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.03759},
  eprinttype    = {arXiv},
  eprint       = {2010.03759},
  timestamp    = {Tue, 13 Oct 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-03759.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tiv/LinYOOM19,
  author       = {Zhongyi Lin and
                  Matthew Yih and
                  Jeffrey M. Ota and
                  John D. Owens and
                  Pinar Muyan{-}{\"{O}}z{\c{c}}elik},
  title        = {Benchmarking Deep Learning Frameworks and Investigating {FPGA} Deployment
                  for Traffic Sign Classification and Detection},
  journal      = {{IEEE} Trans. Intell. Veh.},
  volume       = {4},
  number       = {3},
  pages        = {385--395},
  year         = {2019},
  url          = {https://doi.org/10.1109/TIV.2019.2919458},
  doi          = {10.1109/TIV.2019.2919458},
  timestamp    = {Sun, 10 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tiv/LinYOOM19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/SeitzJFPO19,
  author       = {Kerry A. Seitz Jr. and
                  Theresa Foley and
                  Serban D. Porumbescu and
                  John D. Owens},
  title        = {Staged metaprogramming for shader system development},
  journal      = {{ACM} Trans. Graph.},
  volume       = {38},
  number       = {6},
  pages        = {202:1--202:15},
  year         = {2019},
  url          = {https://doi.org/10.1145/3355089.3356554},
  doi          = {10.1145/3355089.3356554},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/SeitzJFPO19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpec/WangLYO19,
  author       = {Xiaoyun Wang and
                  Zhongyi Lin and
                  Carl Yang and
                  John D. Owens},
  title        = {Accelerating {DNN} Inference with GraphBLAS and the {GPU}},
  booktitle    = {2019 {IEEE} High Performance Extreme Computing Conference, {HPEC}
                  2019, Waltham, MA, USA, September 24-26, 2019},
  pages        = {1--6},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/HPEC.2019.8916498},
  doi          = {10.1109/HPEC.2019.8916498},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpec/WangLYO19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpec/WangO19,
  author       = {Leyuan Wang and
                  John D. Owens},
  title        = {Fast BFS-Based Triangle Counting on GPUs},
  booktitle    = {2019 {IEEE} High Performance Extreme Computing Conference, {HPEC}
                  2019, Waltham, MA, USA, September 24-26, 2019},
  pages        = {1--6},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/HPEC.2019.8916434},
  doi          = {10.1109/HPEC.2019.8916434},
  timestamp    = {Sun, 08 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpec/WangO19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/OsamaTYBO19,
  author       = {Muhammad Osama and
                  Minh Truong and
                  Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {Graph Coloring on the {GPU}},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPSW} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
  pages        = {231--240},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/IPDPSW.2019.00046},
  doi          = {10.1109/IPDPSW.2019.00046},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/OsamaTYBO19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/AwadAJFO19,
  author       = {Muhammad A. Awad and
                  Saman Ashkiani and
                  Rob Johnson and
                  Martin Farach{-}Colton and
                  John D. Owens},
  editor       = {Jeffrey K. Hollingsworth and
                  Idit Keidar},
  title        = {Engineering a high-performance {GPU} B-Tree},
  booktitle    = {Proceedings of the 24th {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA,
                  February 16-20, 2019},
  pages        = {145--157},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3293883.3295706},
  doi          = {10.1145/3293883.3295706},
  timestamp    = {Sun, 12 Jun 2022 19:46:08 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/AwadAJFO19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BrockCYOBY19,
  author       = {Benjamin A. Brock and
                  Yuxin Chen and
                  Jiakun Yan and
                  John D. Owens and
                  Aydin Bulu{\c{c}} and
                  Katherine A. Yelick},
  title        = {{RDMA} vs. {RPC} for Implementing Distributed Data Structures},
  booktitle    = {9th {IEEE/ACM} Workshop on Irregular Applications: Architectures and
                  Algorithms, IA3@SC 2019, Denver, CO, USA, November 18, 2019},
  pages        = {17--22},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/IA349570.2019.00009},
  doi          = {10.1109/IA349570.2019.00009},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/BrockCYOBY19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-08767,
  author       = {Ahmed Abdelkader and
                  Chandrajit L. Bajaj and
                  Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Scott A. Mitchell and
                  John D. Owens and
                  Ahmad A. Rushdi},
  title        = {VoroCrust: Voronoi Meshing Without Clipping},
  journal      = {CoRR},
  volume       = {abs/1902.08767},
  year         = {2019},
  url          = {http://arxiv.org/abs/1902.08767},
  eprinttype    = {arXiv},
  eprint       = {1902.08767},
  timestamp    = {Sat, 23 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1902-08767.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-01407,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {GraphBLAST: {A} High-Performance Linear Algebra-based Graph Framework
                  on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1908.01407},
  year         = {2019},
  url          = {http://arxiv.org/abs/1908.01407},
  eprinttype    = {arXiv},
  eprint       = {1908.01407},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1908-01407.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-02127,
  author       = {Leyuan Wang and
                  John D. Owens},
  title        = {Fast BFS-Based Triangle Counting on GPUs},
  journal      = {CoRR},
  volume       = {abs/1909.02127},
  year         = {2019},
  url          = {http://arxiv.org/abs/1909.02127},
  eprinttype    = {arXiv},
  eprint       = {1909.02127},
  timestamp    = {Mon, 16 Sep 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1909-02127.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-02158,
  author       = {Benjamin Brock and
                  Yuxin Chen and
                  Jiakun Yan and
                  John D. Owens and
                  Aydin Bulu{\c{c}} and
                  Katherine A. Yelick},
  title        = {{RDMA} vs. {RPC} for Implementing Distributed Data Structures},
  journal      = {CoRR},
  volume       = {abs/1910.02158},
  year         = {2019},
  url          = {http://arxiv.org/abs/1910.02158},
  eprinttype    = {arXiv},
  eprint       = {1910.02158},
  timestamp    = {Wed, 09 Oct 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1910-02158.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-09228,
  author       = {Weitang Liu and
                  Lifeng Wei and
                  James Sharpnack and
                  John D. Owens},
  title        = {Unsupervised Object Segmentation with Explicit Localization Module},
  journal      = {CoRR},
  volume       = {abs/1911.09228},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.09228},
  eprinttype    = {arXiv},
  eprint       = {1911.09228},
  timestamp    = {Tue, 03 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-09228.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cacm/Owens18,
  author       = {John D. Owens},
  title        = {Technical perspective: Graphs, betweenness centrality, and the {GPU}},
  journal      = {Commun. {ACM}},
  volume       = {61},
  number       = {8},
  pages        = {84},
  year         = {2018},
  url          = {https://doi.org/10.1145/3230483},
  doi          = {10.1145/3230483},
  timestamp    = {Wed, 21 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/cacm/Owens18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/compgeom/AbdelkaderBEMMO18,
  author       = {Ahmed Abdelkader and
                  Chandrajit L. Bajaj and
                  Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Scott A. Mitchell and
                  John D. Owens and
                  Ahmad A. Rushdi},
  editor       = {Bettina Speckmann and
                  Csaba D. T{\'{o}}th},
  title        = {Sampling Conditions for Conforming Voronoi Meshing by the VoroCrust
                  Algorithm},
  booktitle    = {34th International Symposium on Computational Geometry, SoCG 2018,
                  June 11-14, 2018, Budapest, Hungary},
  series       = {LIPIcs},
  volume       = {99},
  pages        = {1:1--1:16},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik},
  year         = {2018},
  url          = {https://doi.org/10.4230/LIPIcs.SoCG.2018.1},
  doi          = {10.4230/LIPICS.SOCG.2018.1},
  timestamp    = {Wed, 16 Jun 2021 12:03:35 +0200},
  biburl       = {https://dblp.org/rec/conf/compgeom/AbdelkaderBEMMO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/compgeom/AbdelkaderBEMMO18a,
  author       = {Ahmed Abdelkader and
                  Chandrajit L. Bajaj and
                  Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Scott A. Mitchell and
                  John D. Owens and
                  Ahmad A. Rushdi},
  editor       = {Bettina Speckmann and
                  Csaba D. T{\'{o}}th},
  title        = {VoroCrust Illustrated: Theory and Challenges (Multimedia Exposition)},
  booktitle    = {34th International Symposium on Computational Geometry, SoCG 2018,
                  June 11-14, 2018, Budapest, Hungary},
  series       = {LIPIcs},
  volume       = {99},
  pages        = {77:1--77:4},
  publisher    = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik},
  year         = {2018},
  url          = {https://doi.org/10.4230/LIPIcs.SoCG.2018.77},
  doi          = {10.4230/LIPICS.SOCG.2018.77},
  timestamp    = {Wed, 16 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/compgeom/AbdelkaderBEMMO18a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/YangBO18,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  editor       = {Marco Aldinucci and
                  Luca Padovani and
                  Massimo Torquati},
  title        = {Design Principles for Sparse Matrix Multiplication on the {GPU}},
  booktitle    = {Euro-Par 2018: Parallel Processing - 24th International Conference
                  on Parallel and Distributed Computing, Turin, Italy, August 27-31,
                  2018, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {11014},
  pages        = {672--687},
  publisher    = {Springer},
  year         = {2018},
  url          = {https://doi.org/10.1007/978-3-319-96983-1\_48},
  doi          = {10.1007/978-3-319-96983-1\_48},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/YangBO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/YangBO18,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {Implementing Push-Pull Efficiently in GraphBLAS},
  booktitle    = {Proceedings of the 47th International Conference on Parallel Processing,
                  {ICPP} 2018, Eugene, OR, USA, August 13-16, 2018},
  pages        = {89:1--89:11},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3225058.3225122},
  doi          = {10.1145/3225058.3225122},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icpp/YangBO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/AshkianiFO18,
  author       = {Saman Ashkiani and
                  Martin Farach{-}Colton and
                  John D. Owens},
  title        = {A Dynamic Hash Table for the {GPU}},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2018, Vancouver, BC, Canada, May 21-25, 2018},
  pages        = {419--429},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPS.2018.00052},
  doi          = {10.1109/IPDPS.2018.00052},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/AshkianiFO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/AshkianiLFAO18,
  author       = {Saman Ashkiani and
                  Shengren Li and
                  Martin Farach{-}Colton and
                  Nina Amenta and
                  John D. Owens},
  title        = {{GPU} {LSM:} {A} Dynamic Dictionary Data Structure for the {GPU}},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2018, Vancouver, BC, Canada, May 21-25, 2018},
  pages        = {430--440},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPS.2018.00053},
  doi          = {10.1109/IPDPS.2018.00053},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/AshkianiLFAO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/GeilFO18,
  author       = {Afton Geil and
                  Martin Farach{-}Colton and
                  John D. Owens},
  title        = {Quotient Filters: Approximate Membership Queries on the {GPU}},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2018, Vancouver, BC, Canada, May 21-25, 2018},
  pages        = {451--462},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPS.2018.00055},
  doi          = {10.1109/IPDPS.2018.00055},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/GeilFO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/PanPO18,
  author       = {Yuechao Pan and
                  Roger Pearce and
                  John D. Owens},
  title        = {Scalable Breadth-First Search on a {GPU} Cluster},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2018, Vancouver, BC, Canada, May 21-25, 2018},
  pages        = {1090--1101},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPS.2018.00118},
  doi          = {10.1109/IPDPS.2018.00118},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/PanPO18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/itsc/YihOOM18,
  author       = {Matthew Yih and
                  Jeffrey M. Ota and
                  John D. Owens and
                  Pinar Muyan{-}{\"{O}}z{\c{c}}elik},
  editor       = {Wei{-}Bin Zhang and
                  Alexandre M. Bayen and
                  Javier J. S{\'{a}}nchez Medina and
                  Matthew J. Barth},
  title        = {{FPGA} versus {GPU} for Speed-Limit-Sign Recognition},
  booktitle    = {21st International Conference on Intelligent Transportation Systems,
                  {ITSC} 2018, Maui, HI, USA, November 4-7, 2018},
  pages        = {843--850},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ITSC.2018.8569462},
  doi          = {10.1109/ITSC.2018.8569462},
  timestamp    = {Wed, 16 Oct 2019 14:14:57 +0200},
  biburl       = {https://dblp.org/rec/conf/itsc/YihOOM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ivs/LinOOM18,
  author       = {Zhongyi Lin and
                  Jeffrey M. Ota and
                  John D. Owens and
                  Pinar Muyan{-}{\"{O}}z{\c{c}}elik},
  title        = {Benchmarking Deep Learning Frameworks with FPGA-suitable Models on
                  a Traffic Sign Dataset},
  booktitle    = {2018 {IEEE} Intelligent Vehicles Symposium, {IV} 2018, Changshu, Suzhou,
                  China, June 26-30, 2018},
  pages        = {1197--1203},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/IVS.2018.8500685},
  doi          = {10.1109/IVS.2018.8500685},
  timestamp    = {Wed, 16 Oct 2019 14:14:57 +0200},
  biburl       = {https://dblp.org/rec/conf/ivs/LinOOM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-03922,
  author       = {Yuechao Pan and
                  Roger Pearce and
                  John D. Owens},
  title        = {Scalable Breadth-First Search on a {GPU} Cluster},
  journal      = {CoRR},
  volume       = {abs/1803.03922},
  year         = {2018},
  url          = {http://arxiv.org/abs/1803.03922},
  eprinttype    = {arXiv},
  eprint       = {1803.03922},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1803-03922.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-06078,
  author       = {Ahmed Abdelkader and
                  Chandrajit L. Bajaj and
                  Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Scott A. Mitchell and
                  John D. Owens and
                  Ahmad A. Rushdi},
  title        = {Sampling Conditions for Conforming Voronoi Meshing by the VoroCrust
                  Algorithm},
  journal      = {CoRR},
  volume       = {abs/1803.06078},
  year         = {2018},
  url          = {http://arxiv.org/abs/1803.06078},
  eprinttype    = {arXiv},
  eprint       = {1803.06078},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1803-06078.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-08601,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {Design Principles for Sparse Matrix Multiplication on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1803.08601},
  year         = {2018},
  url          = {http://arxiv.org/abs/1803.08601},
  eprinttype    = {arXiv},
  eprint       = {1803.08601},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1803-08601.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03327,
  author       = {Carl Yang and
                  Aydin Bulu{\c{c}} and
                  John D. Owens},
  title        = {Implementing Push-Pull Efficiently in GraphBLAS},
  journal      = {CoRR},
  volume       = {abs/1804.03327},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.03327},
  eprinttype    = {arXiv},
  eprint       = {1804.03327},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-03327.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-06926,
  author       = {Leyuan Wang and
                  Yangzihao Wang and
                  Carl Yang and
                  John D. Owens},
  title        = {A Comparative Study on Exact Triangle Counting Algorithms on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1804.06926},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.06926},
  eprinttype    = {arXiv},
  eprint       = {1804.06926},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-06926.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-07706,
  author       = {Weitang Liu and
                  Emad Barsoum and
                  John D. Owens},
  title        = {Object Localization and Motion Transfer learning with Capsules},
  journal      = {CoRR},
  volume       = {abs/1805.07706},
  year         = {2018},
  url          = {http://arxiv.org/abs/1805.07706},
  eprinttype    = {arXiv},
  eprint       = {1805.07706},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1805-07706.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/AbdelkaderMRMOE17,
  author       = {Ahmed Abdelkader and
                  Ahmed H. Mahmoud and
                  Ahmad A. Rushdi and
                  Scott A. Mitchell and
                  John D. Owens and
                  Mohamed S. Ebeida},
  title        = {A Constrained Resampling Strategy for Mesh Improvement},
  journal      = {Comput. Graph. Forum},
  volume       = {36},
  number       = {5},
  pages        = {189--201},
  year         = {2017},
  url          = {https://doi.org/10.1111/cgf.13256},
  doi          = {10.1111/CGF.13256},
  timestamp    = {Mon, 18 Sep 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/AbdelkaderMRMOE17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/Muyan-OzcelikO17,
  author       = {Pinar Muyan{-}{\"{O}}z{\c{c}}elik and
                  John D. Owens},
  title        = {Methods for multitasking among real-time embedded compute tasks running
                  on the {GPU}},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {29},
  number       = {15},
  year         = {2017},
  url          = {https://doi.org/10.1002/cpe.4118},
  doi          = {10.1002/CPE.4118},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/Muyan-OzcelikO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/AshkianiDMO17,
  author       = {Saman Ashkiani and
                  Andrew A. Davidson and
                  Ulrich Meyer and
                  John D. Owens},
  title        = {{GPU} Multisplit: An Extended Study of a Parallel Algorithm},
  journal      = {{ACM} Trans. Parallel Comput.},
  volume       = {4},
  number       = {1},
  pages        = {2:1--2:44},
  year         = {2017},
  url          = {https://doi.org/10.1145/3108139},
  doi          = {10.1145/3108139},
  timestamp    = {Sat, 25 Apr 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/topc/AshkianiDMO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/WangPDWYWOYLRO17,
  author       = {Yangzihao Wang and
                  Yuechao Pan and
                  Andrew A. Davidson and
                  Yuduo Wu and
                  Carl Yang and
                  Leyuan Wang and
                  Muhammad Osama and
                  Chenshan Yuan and
                  Weitang Liu and
                  Andy T. Riffel and
                  John D. Owens},
  title        = {Gunrock: {GPU} Graph Analytics},
  journal      = {{ACM} Trans. Parallel Comput.},
  volume       = {4},
  number       = {1},
  pages        = {3:1--3:49},
  year         = {2017},
  url          = {https://doi.org/10.1145/3108140},
  doi          = {10.1145/3108140},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/topc/WangPDWYWOYLRO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/PanWWYO17,
  author       = {Yuechao Pan and
                  Yangzihao Wang and
                  Yuduo Wu and
                  Carl Yang and
                  John D. Owens},
  title        = {Multi-GPU Graph Analytics},
  booktitle    = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
  pages        = {479--490},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/IPDPS.2017.117},
  doi          = {10.1109/IPDPS.2017.117},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/PanWWYO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/WangBO17,
  author       = {Yangzihao Wang and
                  Sean Baxter and
                  John D. Owens},
  title        = {Mini-Gunrock: {A} Lightweight Graph Analytics Framework on the {GPU}},
  booktitle    = {2017 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPS} Workshops 2017, Orlando / Buena Vista, FL, USA,
                  May 29 - June 2, 2017},
  pages        = {616--626},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/IPDPSW.2017.116},
  doi          = {10.1109/IPDPSW.2017.116},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/WangBO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangPDWYWOYLRO17,
  author       = {Yangzihao Wang and
                  Yuechao Pan and
                  Andrew A. Davidson and
                  Yuduo Wu and
                  Carl Yang and
                  Leyuan Wang and
                  Muhammad Osama and
                  Chenshan Yuan and
                  Weitang Liu and
                  Andy T. Riffel and
                  John D. Owens},
  title        = {Gunrock: {GPU} Graph Analytics},
  journal      = {CoRR},
  volume       = {abs/1701.01170},
  year         = {2017},
  url          = {http://arxiv.org/abs/1701.01170},
  eprinttype    = {arXiv},
  eprint       = {1701.01170},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/WangPDWYWOYLRO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AshkianiDMO17,
  author       = {Saman Ashkiani and
                  Andrew A. Davidson and
                  Ulrich Meyer and
                  John D. Owens},
  title        = {{GPU} Multisplit},
  journal      = {CoRR},
  volume       = {abs/1701.01189},
  year         = {2017},
  url          = {http://arxiv.org/abs/1701.01189},
  eprinttype    = {arXiv},
  eprint       = {1701.01189},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/AshkianiDMO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AshkianiLFAO17,
  author       = {Saman Ashkiani and
                  Shengren Li and
                  Martin Farach{-}Colton and
                  Nina Amenta and
                  John D. Owens},
  title        = {{GPU} {LSM:} {A} Dynamic Dictionary Data Structure for the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1707.05354},
  year         = {2017},
  url          = {http://arxiv.org/abs/1707.05354},
  eprinttype    = {arXiv},
  eprint       = {1707.05354},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/AshkianiLFAO17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-11246,
  author       = {Saman Ashkiani and
                  Martin Farach{-}Colton and
                  John D. Owens},
  title        = {A Dynamic Hash Table for the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1710.11246},
  year         = {2017},
  url          = {http://arxiv.org/abs/1710.11246},
  eprinttype    = {arXiv},
  eprint       = {1710.11246},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1710-11246.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/EbeidaRAMYEOBM16,
  author       = {Mohamed S. Ebeida and
                  Ahmad A. Rushdi and
                  Muhammad A. Awad and
                  Ahmed H. Mahmoud and
                  Dong{-}Ming Yan and
                  Shawn A. English and
                  John D. Owens and
                  Chandrajit L. Bajaj and
                  Scott A. Mitchell},
  title        = {Disk Density Tuning of a Maximal Random Packing},
  journal      = {Comput. Graph. Forum},
  volume       = {35},
  number       = {5},
  pages        = {259--269},
  year         = {2016},
  url          = {https://doi.org/10.1111/cgf.12981},
  doi          = {10.1111/CGF.12981},
  timestamp    = {Mon, 15 Jun 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/EbeidaRAMYEOBM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/WangBO16,
  author       = {Leyuan Wang and
                  Sean Baxter and
                  John D. Owens},
  title        = {Fast parallel skew and prefix-doubling suffix array construction on
                  the {GPU}},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {28},
  number       = {12},
  pages        = {3466--3484},
  year         = {2016},
  url          = {https://doi.org/10.1002/cpe.3867},
  doi          = {10.1002/CPE.3867},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/WangBO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/KemalDO16,
  author       = {Jonathan Y. Kemal and
                  Roger L. Davis and
                  John D. Owens},
  title        = {Multidisciplinary simulation acceleration using multiple shared memory
                  graphical processing units},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {30},
  number       = {4},
  pages        = {486--508},
  year         = {2016},
  url          = {https://doi.org/10.1177/1094342016639114},
  doi          = {10.1177/1094342016639114},
  timestamp    = {Thu, 12 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijhpca/KemalDO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cns/GeganAOG16,
  author       = {Ross K. Gegan and
                  Vishal Ahuja and
                  John D. Owens and
                  Dipak Ghosal},
  title        = {Real-time GPU-based timing channel detection using entropy},
  booktitle    = {2016 {IEEE} Conference on Communications and Network Security, {CNS}
                  2016, Philadelphia, PA, USA, October 17-19, 2016},
  pages        = {296--305},
  publisher    = {{IEEE}},
  year         = {2016},
  url          = {https://doi.org/10.1109/CNS.2016.7860497},
  doi          = {10.1109/CNS.2016.7860497},
  timestamp    = {Wed, 16 Oct 2019 14:14:55 +0200},
  biburl       = {https://dblp.org/rec/conf/cns/GeganAOG16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/WangWYO16,
  author       = {Leyuan Wang and
                  Yangzihao Wang and
                  Carl Yang and
                  John D. Owens},
  editor       = {Toyotaro Suzumura and
                  Dario Garcia{-}Gasulla and
                  Miyuru Dayarathna},
  title        = {A Comparative Study on Exact Triangle Counting Algorithms on the {GPU}},
  booktitle    = {Proceedings of the {ACM} Workshop on High Performance Graph Processing,
                  HPGP@HPDC 2016, Kyoto, Japan, May 31, 2016},
  pages        = {1--8},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2915516.2915521},
  doi          = {10.1145/2915516.2915521},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpdc/WangWYO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpec/KepnerABBFGHKLM16,
  author       = {Jeremy Kepner and
                  Peter Aaltonen and
                  David A. Bader and
                  Aydin Bulu{\c{c}} and
                  Franz Franchetti and
                  John R. Gilbert and
                  Dylan Hutchison and
                  Manoj Kumar and
                  Andrew Lumsdaine and
                  Henning Meyerhenke and
                  Scott McMillan and
                  Carl Yang and
                  John D. Owens and
                  Marcin Zalewski and
                  Timothy G. Mattson and
                  Jos{\'{e}} E. Moreira},
  title        = {Mathematical foundations of the GraphBLAS},
  booktitle    = {2016 {IEEE} High Performance Extreme Computing Conference, {HPEC}
                  2016, Waltham, MA, USA, September 13-15, 2016},
  pages        = {1--9},
  publisher    = {{IEEE}},
  year         = {2016},
  url          = {https://doi.org/10.1109/HPEC.2016.7761646},
  doi          = {10.1109/HPEC.2016.7761646},
  timestamp    = {Tue, 07 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/hpec/KepnerABBFGHKLM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/WangDPWRO16,
  author       = {Yangzihao Wang and
                  Andrew A. Davidson and
                  Yuechao Pan and
                  Yuduo Wu and
                  Andy Riffel and
                  John D. Owens},
  editor       = {Rafael Asenjo and
                  Tim Harris},
  title        = {Gunrock: a high-performance graph processing library on the {GPU}},
  booktitle    = {Proceedings of the 21st {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, PPoPP 2016, Barcelona, Spain, March
                  12-16, 2016},
  pages        = {11:1--11:12},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2851141.2851145},
  doi          = {10.1145/2851141.2851145},
  timestamp    = {Sun, 12 Jun 2022 19:46:08 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/WangDPWRO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/AshkianiDMO16,
  author       = {Saman Ashkiani and
                  Andrew A. Davidson and
                  Ulrich Meyer and
                  John D. Owens},
  editor       = {Rafael Asenjo and
                  Tim Harris},
  title        = {{GPU} multisplit},
  booktitle    = {Proceedings of the 21st {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, PPoPP 2016, Barcelona, Spain, March
                  12-16, 2016},
  pages        = {12:1--12:13},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2851141.2851169},
  doi          = {10.1145/2851141.2851169},
  timestamp    = {Sun, 12 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/AshkianiDMO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/Muyan-OzcelikO16,
  author       = {Pinar Muyan{-}{\"{O}}z{\c{c}}elik and
                  John D. Owens},
  editor       = {Pavan Balaji and
                  Kai{-}Cheung Leung},
  title        = {Multitasking Real-time Embedded {GPU} Computing Tasks},
  booktitle    = {Proceedings of the 7th International Workshop on Programming Models
                  and Applications for Multicores and Manycores, PMAM@PPoPP 2016, Barcelona,
                  Spain, March 12-16, 2016},
  pages        = {78--87},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2883404.2883408},
  doi          = {10.1145/2883404.2883408},
  timestamp    = {Sun, 12 Jun 2022 19:46:08 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/Muyan-OzcelikO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/AshkianiAO16,
  author       = {Saman Ashkiani and
                  Nina Amenta and
                  John D. Owens},
  editor       = {Christian Scheideler and
                  Seth Gilbert},
  title        = {Parallel Approaches to the String Matching Problem on the {GPU}},
  booktitle    = {Proceedings of the 28th {ACM} Symposium on Parallelism in Algorithms
                  and Architectures, {SPAA} 2016, Asilomar State Beach/Pacific Grove,
                  CA, USA, July 11-13, 2016},
  pages        = {275--285},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2935764.2935800},
  doi          = {10.1145/2935764.2935800},
  timestamp    = {Tue, 06 Nov 2018 16:59:33 +0100},
  biburl       = {https://dblp.org/rec/conf/spaa/AshkianiAO16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KepnerABBFGHKLM16,
  author       = {Jeremy Kepner and
                  Peter Aaltonen and
                  David A. Bader and
                  Aydin Bulu{\c{c}} and
                  Franz Franchetti and
                  John R. Gilbert and
                  Dylan Hutchison and
                  Manoj Kumar and
                  Andrew Lumsdaine and
                  Henning Meyerhenke and
                  Scott McMillan and
                  Jos{\'{e}} E. Moreira and
                  John D. Owens and
                  Carl Yang and
                  Marcin Zalewski and
                  Timothy G. Mattson},
  title        = {Mathematical Foundations of the GraphBLAS},
  journal      = {CoRR},
  volume       = {abs/1606.05790},
  year         = {2016},
  url          = {http://arxiv.org/abs/1606.05790},
  eprinttype    = {arXiv},
  eprint       = {1606.05790},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/KepnerABBFGHKLM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/PatneyTSO15,
  author       = {Anjul Patney and
                  Stanley Tzeng and
                  Kerry A. Seitz Jr. and
                  John D. Owens},
  title        = {Piko: a framework for authoring programmable graphics pipelines},
  journal      = {{ACM} Trans. Graph.},
  volume       = {34},
  number       = {4},
  pages        = {147:1--147:13},
  year         = {2015},
  url          = {https://doi.org/10.1145/2766973},
  doi          = {10.1145/2766973},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/PatneyTSO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aipr/ShashkovMRNOJ15,
  author       = {Mikhail M. Shashkov and
                  Jason Mak and
                  Shawn Recker and
                  Connie S. Nguyen and
                  John D. Owens and
                  Kenneth I. Joy},
  title        = {Efficient dense reconstruction using geometry and image consistency
                  constraints},
  booktitle    = {2015 {IEEE} Applied Imagery Pattern Recognition Workshop, {AIPR} 2015,
                  Washington, DC, USA, October 13-15, 2015},
  pages        = {1--7},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/AIPR.2015.7444539},
  doi          = {10.1109/AIPR.2015.7444539},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/aipr/ShashkovMRNOJ15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/WangBO15,
  author       = {Leyuan Wang and
                  Sean Baxter and
                  John D. Owens},
  editor       = {Jesper Larsson Tr{\"{a}}ff and
                  Sascha Hunold and
                  Francesco Versaci},
  title        = {Fast Parallel Suffix Array on the {GPU}},
  booktitle    = {Euro-Par 2015: Parallel Processing - 21st International Conference
                  on Parallel and Distributed Computing, Vienna, Austria, August 24-28,
                  2015, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {9233},
  pages        = {573--587},
  publisher    = {Springer},
  year         = {2015},
  url          = {https://doi.org/10.1007/978-3-662-48096-0\_44},
  doi          = {10.1007/978-3-662-48096-0\_44},
  timestamp    = {Sun, 12 Nov 2023 02:07:45 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/WangBO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iiswc/WuWPYO15,
  author       = {Yuduo Wu and
                  Yangzihao Wang and
                  Yuechao Pan and
                  Carl Yang and
                  John D. Owens},
  title        = {Performance Characterization of High-Level Programming Models for
                  {GPU} Graph Analytics},
  booktitle    = {2015 {IEEE} International Symposium on Workload Characterization,
                  {IISWC} 2015, Atlanta, GA, USA, October 4-6, 2015},
  pages        = {66--75},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/IISWC.2015.13},
  doi          = {10.1109/IISWC.2015.13},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iiswc/WuWPYO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/YangWO15,
  author       = {Carl Yang and
                  Yangzihao Wang and
                  John D. Owens},
  title        = {Fast Sparse Matrix and Sparse Vector Multiplication Algorithm on the
                  {GPU}},
  booktitle    = {2015 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshop, {IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
  pages        = {841--847},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/IPDPSW.2015.77},
  doi          = {10.1109/IPDPSW.2015.77},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/YangWO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/WangDPWRO15,
  author       = {Yangzihao Wang and
                  Andrew A. Davidson and
                  Yuechao Pan and
                  Yuduo Wu and
                  Andy Riffel and
                  John D. Owens},
  editor       = {Albert Cohen and
                  David Grove},
  title        = {Gunrock: a high-performance graph processing library on the {GPU}},
  booktitle    = {Proceedings of the 20th {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, PPoPP 2015, San Francisco, CA, USA,
                  February 7-11, 2015},
  pages        = {265--266},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2688500.2688538},
  doi          = {10.1145/2688500.2688538},
  timestamp    = {Sun, 12 Jun 2022 19:46:08 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/WangDPWRO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/si3d/WeberWO15,
  author       = {Thomas Weber and
                  Michael Wimmer and
                  John D. Owens},
  editor       = {John Keyser and
                  Pedro V. Sander and
                  Kartic Subr and
                  Li{-}Yi Wei},
  title        = {Parallel Reyes-style adaptive subdivision with bounded memory usage},
  booktitle    = {Proceedings of the 19th Symposium on Interactive 3D Graphics and Games,
                  San Francisco, CA, USA, February 27 - March 01, 2015},
  pages        = {39--45},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2699276.2699289},
  doi          = {10.1145/2699276.2699289},
  timestamp    = {Wed, 26 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/si3d/WeberWO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/daglib/p/EbeidaMPDTAMO15,
  author       = {Mohamed S. Ebeida and
                  Scott A. Mitchell and
                  Anjul Patney and
                  Andrew A. Davidson and
                  Stanley Tzeng and
                  Muhammad A. Awad and
                  Ahmed H. Mahmoud and
                  John D. Owens},
  editor       = {Coral Calero and
                  Mario Piattini},
  title        = {Exercises in High-Dimensional Sampling: Maximal Poisson-Disk Sampling
                  and \emph{k}-d Darts},
  booktitle    = {Green in Software Engineering},
  pages        = {221--238},
  publisher    = {Springer},
  year         = {2015},
  url          = {https://doi.org/10.1007/978-3-662-44900-4\_13},
  doi          = {10.1007/978-3-662-44900-4\_13},
  timestamp    = {Sat, 19 Oct 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/books/daglib/p/EbeidaMPDTAMO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangDPWRO15,
  author       = {Yangzihao Wang and
                  Andrew A. Davidson and
                  Yuechao Pan and
                  Yuduo Wu and
                  Andy Riffel and
                  John D. Owens},
  title        = {Gunrock: {A} High-Performance Graph Processing Library on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1501.05387},
  year         = {2015},
  url          = {http://arxiv.org/abs/1501.05387},
  eprinttype    = {arXiv},
  eprint       = {1501.05387},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/WangDPWRO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PanWWYO15,
  author       = {Yuechao Pan and
                  Yangzihao Wang and
                  Yuduo Wu and
                  Carl Yang and
                  John D. Owens},
  title        = {Multi-GPU Graph Analytics},
  journal      = {CoRR},
  volume       = {abs/1504.04804},
  year         = {2015},
  url          = {http://arxiv.org/abs/1504.04804},
  eprinttype    = {arXiv},
  eprint       = {1504.04804},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/PanWWYO15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/EbeidaPMDDO14,
  author       = {Mohamed S. Ebeida and
                  Anjul Patney and
                  Scott A. Mitchell and
                  Keith R. Dalbey and
                  Andrew A. Davidson and
                  John D. Owens},
  title        = {\emph{k}-d Darts: Sampling by \emph{k}-dimensional flat searches},
  journal      = {{ACM} Trans. Graph.},
  volume       = {33},
  number       = {1},
  pages        = {3:1--3:16},
  year         = {2014},
  url          = {https://doi.org/10.1145/2522528},
  doi          = {10.1145/2522528},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tog/EbeidaPMDDO14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/accv/MakHROJ14,
  author       = {Jason Mak and
                  Mauricio Hess{-}Flores and
                  Shawn Recker and
                  John D. Owens and
                  Kenneth I. Joy},
  editor       = {C. V. Jawahar and
                  Shiguang Shan},
  title        = {A Comparative Study of GPU-Accelerated Multi-view Sequential Reconstruction
                  Triangulation Methods for Large-Scale Scenes},
  booktitle    = {Computer Vision - {ACCV} 2014 Workshops - Singapore, Singapore, November
                  1-2, 2014, Revised Selected Papers, Part {I}},
  series       = {Lecture Notes in Computer Science},
  volume       = {9008},
  pages        = {254--269},
  publisher    = {Springer},
  year         = {2014},
  url          = {https://doi.org/10.1007/978-3-319-16628-5\_19},
  doi          = {10.1007/978-3-319-16628-5\_19},
  timestamp    = {Tue, 14 May 2019 10:00:50 +0200},
  biburl       = {https://dblp.org/rec/conf/accv/MakHROJ14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cosn/GeilWO14,
  author       = {Afton Geil and
                  Yangzihao Wang and
                  John D. Owens},
  editor       = {Alessandra Sala and
                  Ashish Goel and
                  Krishna P. Gummadi},
  title        = {WTF, GPU! computing twitter's who-to-follow on the {GPU}},
  booktitle    = {Proceedings of the second {ACM} conference on Online social networks,
                  {COSN} 2014, Dublin, Ireland, October 1-2, 2014},
  pages        = {63--68},
  publisher    = {{ACM}},
  year         = {2014},
  url          = {https://doi.org/10.1145/2660460.2660481},
  doi          = {10.1145/2660460.2660481},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cosn/GeilWO14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/DavidsonBGO14,
  author       = {Andrew A. Davidson and
                  Sean Baxter and
                  Michael Garland and
                  John D. Owens},
  title        = {Work-Efficient Parallel {GPU} Methods for Single-Source Shortest Paths},
  booktitle    = {2014 {IEEE} 28th International Parallel and Distributed Processing
                  Symposium, Phoenix, AZ, USA, May 19-23, 2014},
  pages        = {349--359},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/IPDPS.2014.45},
  doi          = {10.1109/IPDPS.2014.45},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/DavidsonBGO14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wacv/MakHROJ14,
  author       = {Jason Mak and
                  Mauricio Hess{-}Flores and
                  Shawn Recker and
                  John D. Owens and
                  Kenneth I. Joy},
  title        = {GPU-accelerated and efficient multi-view triangulation for scene reconstruction},
  booktitle    = {{IEEE} Winter Conference on Applications of Computer Vision, Steamboat
                  Springs, CO, USA, March 24-26, 2014},
  pages        = {61--68},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/WACV.2014.6836117},
  doi          = {10.1109/WACV.2014.6836117},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/wacv/MakHROJ14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PatneyTSO14,
  author       = {Anjul Patney and
                  Stanley Tzeng and
                  Kerry A. Seitz Jr. and
                  John D. Owens},
  title        = {Piko: {A} Design Framework for Programmable Graphics Pipelines},
  journal      = {CoRR},
  volume       = {abs/1404.6293},
  year         = {2014},
  url          = {http://arxiv.org/abs/1404.6293},
  eprinttype    = {arXiv},
  eprint       = {1404.6293},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/PatneyTSO14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/EbeidaMAMMRO13,
  author       = {Mohamed S. Ebeida and
                  Ahmed H. Mahmoud and
                  Muhammad A. Awad and
                  Mohammed A. Mohammed and
                  Scott A. Mitchell and
                  Alexander Rand and
                  John D. Owens},
  title        = {Sifted Disks},
  journal      = {Comput. Graph. Forum},
  volume       = {32},
  number       = {2},
  pages        = {509--518},
  year         = {2013},
  url          = {https://doi.org/10.1111/cgf.12071},
  doi          = {10.1111/CGF.12071},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/EbeidaMAMMRO13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1302-3917,
  author       = {Mohamed S. Ebeida and
                  Anjul Patney and
                  Scott A. Mitchell and
                  Keith R. Dalbey and
                  Andrew A. Davidson and
                  John D. Owens},
  title        = {k-d Darts: Sampling by k-Dimensional Flat Searches},
  journal      = {CoRR},
  volume       = {abs/1302.3917},
  year         = {2013},
  url          = {http://arxiv.org/abs/1302.3917},
  eprinttype    = {arXiv},
  eprint       = {1302.3917},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1302-3917.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SeitzKRYO13,
  author       = {Kerry A. Seitz Jr. and
                  Alex Kennedy and
                  Owen Ransom and
                  Bassam A. Younis and
                  John D. Owens},
  title        = {A {GPU} Implementation for Two-Dimensional Shallow Water Modeling},
  journal      = {CoRR},
  volume       = {abs/1309.1230},
  year         = {2013},
  url          = {http://arxiv.org/abs/1309.1230},
  eprinttype    = {arXiv},
  eprint       = {1309.1230},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/SeitzKRYO13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/EbeidaMPDO12,
  author       = {Mohamed S. Ebeida and
                  Scott A. Mitchell and
                  Anjul Patney and
                  Andrew A. Davidson and
                  John D. Owens},
  title        = {A Simple Algorithm for Maximal Poisson-Disk Sampling in High Dimensions},
  journal      = {Comput. Graph. Forum},
  volume       = {31},
  number       = {2pt4},
  pages        = {785--794},
  year         = {2012},
  url          = {https://doi.org/10.1111/j.1467-8659.2012.03059.x},
  doi          = {10.1111/J.1467-8659.2012.03059.X},
  timestamp    = {Fri, 29 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/EbeidaMPDO12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computer/TzengLO12,
  author       = {Stanley Tzeng and
                  Brandon Lloyd and
                  John D. Owens},
  title        = {A {GPU} Task-Parallel Model with Dependency Resolution},
  journal      = {Computer},
  volume       = {45},
  number       = {8},
  pages        = {34--41},
  year         = {2012},
  url          = {https://doi.org/10.1109/MC.2012.255},
  doi          = {10.1109/MC.2012.255},
  timestamp    = {Wed, 12 Aug 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/computer/TzengLO12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/TzengPDEMO12,
  author       = {Stanley Tzeng and
                  Anjul Patney and
                  Andrew A. Davidson and
                  Mohamed S. Ebeida and
                  Scott A. Mitchell and
                  John D. Owens},
  editor       = {Carsten Dachsbacher and
                  Jacob Munkberg and
                  Jacopo Pantaleoni},
  title        = {High-Quality Parallel Depth-of-Field Using Line Samples},
  booktitle    = {Proceedings of the {EUROGRAPHICS} Conference on High Performance Graphics
                  2012, Paris, France, June 25-27, 2012},
  pages        = {23--31},
  publisher    = {Eurographics Association},
  year         = {2012},
  url          = {https://doi.org/10.2312/EGGH/HPG12/023-031},
  doi          = {10.2312/EGGH/HPG12/023-031},
  timestamp    = {Wed, 24 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/TzengPDEMO12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/LiSPAOA12,
  author       = {Shengren Li and
                  Lance Simons and
                  Jagadeesh Bhaskar Pakaravoor and
                  Fatemeh Abbasinejad and
                  John D. Owens and
                  Nina Amenta},
  editor       = {Carsten Dachsbacher and
                  Jacob Munkberg and
                  Jacopo Pantaleoni},
  title        = {kANN on the {GPU} with Shifted Sorting},
  booktitle    = {Proceedings of the {EUROGRAPHICS} Conference on High Performance Graphics
                  2012, Paris, France, June 25-27, 2012},
  pages        = {39--47},
  publisher    = {Eurographics Association},
  year         = {2012},
  url          = {https://doi.org/10.2312/EGGH/HPG12/039-047},
  doi          = {10.2312/EGGH/HPG12/039-047},
  timestamp    = {Wed, 24 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/LiSPAOA12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipas/ZhangRUTO12,
  author       = {Yao Zhang and
                  John Recker and
                  Robert Ulichney and
                  Ingeborg Tastl and
                  John D. Owens},
  editor       = {Karen O. Egiazarian and
                  Sos S. Agaian and
                  Atanas P. Gotchev and
                  John Recker and
                  Guijin Wang},
  title        = {Plane-dependent error diffusion on a {GPU}},
  booktitle    = {Image Processing: Algorithms and Systems X; and Parallel Processing
                  for Imaging Applications II, Burlingame, California, USA, January
                  23-25, 2012},
  series       = {{SPIE} Proceedings},
  volume       = {8295},
  pages        = {829515},
  publisher    = {{SPIE}},
  year         = {2012},
  url          = {https://doi.org/10.1117/12.906966},
  doi          = {10.1117/12.906966},
  timestamp    = {Wed, 12 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ipas/ZhangRUTO12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1201-2936,
  author       = {Stanley Tzeng and
                  John D. Owens},
  title        = {Finding Convex Hulls Using Quickhull on the {GPU}},
  journal      = {CoRR},
  volume       = {abs/1201.2936},
  year         = {2012},
  url          = {http://arxiv.org/abs/1201.2936},
  eprinttype    = {arXiv},
  eprint       = {1201.2936},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1201-2936.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cad/EbeidaMDPKO11,
  author       = {Mohamed S. Ebeida and
                  Scott A. Mitchell and
                  Andrew A. Davidson and
                  Anjul Patney and
                  Patrick M. Knupp and
                  John D. Owens},
  title        = {Efficient and good Delaunay meshes from random points},
  journal      = {Comput. Aided Des.},
  volume       = {43},
  number       = {11},
  pages        = {1506--1515},
  year         = {2011},
  url          = {https://doi.org/10.1016/j.cad.2011.08.012},
  doi          = {10.1016/J.CAD.2011.08.012},
  timestamp    = {Thu, 13 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/cad/EbeidaMDPKO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jacic/PhillipsZDO11,
  author       = {Everett H. Phillips and
                  Yao Zhang and
                  Roger L. Davis and
                  John D. Owens},
  title        = {Acceleration of 2-D Compressible Flow Solvers with Graphics Processing
                  Unit Clusters},
  journal      = {J. Aerosp. Comput. Inf. Commun.},
  volume       = {8},
  number       = {8},
  pages        = {237--249},
  year         = {2011},
  url          = {https://doi.org/10.2514/1.44909},
  doi          = {10.2514/1.44909},
  timestamp    = {Sun, 17 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/jacic/PhillipsZDO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/EbeidaDPKMO11,
  author       = {Mohamed S. Ebeida and
                  Andrew A. Davidson and
                  Anjul Patney and
                  Patrick M. Knupp and
                  Scott A. Mitchell and
                  John D. Owens},
  title        = {Efficient maximal poisson-disk sampling},
  journal      = {{ACM} Trans. Graph.},
  volume       = {30},
  number       = {4},
  pages        = {49},
  year         = {2011},
  url          = {https://doi.org/10.1145/2010324.1964944},
  doi          = {10.1145/2010324.1964944},
  timestamp    = {Tue, 14 May 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/EbeidaDPKMO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asplos/DavidsonO11,
  author       = {Andrew A. Davidson and
                  John D. Owens},
  title        = {Register packing for cyclic reduction: a case study},
  booktitle    = {Proceedings of 4th Workshop on General Purpose Processing on Graphics
                  Processing Units, {GPGPU} 2011, Newport Beach, CA, USA, March 5, 2011},
  pages        = {4},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/1964179.1964185},
  doi          = {10.1145/1964179.1964185},
  timestamp    = {Wed, 07 Jul 2021 13:23:08 +0200},
  biburl       = {https://dblp.org/rec/conf/asplos/DavidsonO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/JenkinsAOCS11,
  author       = {John Jenkins and
                  Isha Arkatkar and
                  John D. Owens and
                  Alok N. Choudhary and
                  Nagiza F. Samatova},
  editor       = {Emmanuel Jeannot and
                  Raymond Namyst and
                  Jean Roman},
  title        = {Lessons Learned from Exploring the Backtracking Paradigm on the {GPU}},
  booktitle    = {Euro-Par 2011 Parallel Processing - 17th International Conference,
                  Euro-Par 2011, Bordeaux, France, August 29 - September 2, 2011, Proceedings,
                  Part {II}},
  series       = {Lecture Notes in Computer Science},
  volume       = {6853},
  pages        = {425--437},
  publisher    = {Springer},
  year         = {2011},
  url          = {https://doi.org/10.1007/978-3-642-23397-5\_42},
  doi          = {10.1007/978-3-642-23397-5\_42},
  timestamp    = {Tue, 14 May 2019 10:00:46 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/JenkinsAOCS11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/GuptaO11,
  author       = {Kshitij Gupta and
                  John D. Owens},
  title        = {Compute {\&} memory optimizations for high-quality speech recognition
                  on low-end {GPU} processors},
  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.2011.6152741},
  doi          = {10.1109/HIPC.2011.6152741},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/GuptaO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpca/ZhangO11,
  author       = {Yao Zhang and
                  John D. Owens},
  title        = {A quantitative performance analysis model for {GPU} architectures},
  booktitle    = {17th International Conference on High-Performance Computer Architecture
                  {(HPCA-17} 2011), February 12-16 2011, San Antonio, Texas, {USA}},
  pages        = {382--393},
  publisher    = {{IEEE} Computer Society},
  year         = {2011},
  url          = {https://doi.org/10.1109/HPCA.2011.5749745},
  doi          = {10.1109/HPCA.2011.5749745},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpca/ZhangO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/DavidsonZO11,
  author       = {Andrew A. Davidson and
                  Yao Zhang and
                  John D. Owens},
  title        = {An Auto-tuned Method for Solving Large Tridiagonal Systems on the
                  {GPU}},
  booktitle    = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May, 2011 - Conference
                  Proceedings},
  pages        = {956--965},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/IPDPS.2011.92},
  doi          = {10.1109/IPDPS.2011.92},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/DavidsonZO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/StuartO11,
  author       = {Jeff A. Stuart and
                  John D. Owens},
  title        = {Multi-GPU MapReduce on {GPU} Clusters},
  booktitle    = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May, 2011 - Conference
                  Proceedings},
  pages        = {1068--1079},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/IPDPS.2011.102},
  doi          = {10.1109/IPDPS.2011.102},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/StuartO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ivs/GlavtchevMOO11,
  author       = {Vladimir Glavtchev and
                  Pinar Muyan{-}{\"{O}}z{\c{c}}elik and
                  Jeffrey M. Ota and
                  John D. Owens},
  title        = {Feature-based speed limit sign detection using a graphics processing
                  unit},
  booktitle    = {{IEEE} Intelligent Vehicles Symposium (IV), 2011, Baden-Baden, Germany,
                  June 5-9, 2011},
  pages        = {195--200},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/IVS.2011.5940539},
  doi          = {10.1109/IVS.2011.5940539},
  timestamp    = {Wed, 16 Oct 2019 14:14:57 +0200},
  biburl       = {https://dblp.org/rec/conf/ivs/GlavtchevMOO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppia/ZhangRUBTLO11,
  author       = {Yao Zhang and
                  John Recker and
                  Robert Ulichney and
                  Giordano B. Beretta and
                  Ingeborg Tastl and
                  I{-}Jong Lin and
                  John D. Owens},
  editor       = {John D. Owens and
                  I{-}Jong Lin and
                  Yu{-}Jin Zhang and
                  Giordano B. Beretta},
  title        = {A parallel error diffusion implementation on a {GPU}},
  booktitle    = {Proceedings of the Conference on Parallel Processing for Imaging Applications
                  2011, San Francisco Airport, CA, USA, January 24-25, 2011},
  series       = {{SPIE} Proceedings},
  volume       = {7872},
  pages        = {78720K},
  publisher    = {{SPIE}},
  year         = {2011},
  url          = {https://doi.org/10.1117/12.872616},
  doi          = {10.1117/12.872616},
  timestamp    = {Wed, 12 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppia/ZhangRUBTLO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/si3d/TzengPO11,
  author       = {Stanley Tzeng and
                  Anjul Patney and
                  John D. Owens},
  editor       = {Michael Garland and
                  Rui Wang},
  title        = {Efficient adaptive tiling for programmable rendering},
  booktitle    = {Symposium on Interactive 3D Graphics and Games, {I3D} '11, San Francisco,
                  CA, USA, February 18-20, 2011},
  pages        = {201},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/1944745.1944781},
  doi          = {10.1145/1944745.1944781},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/si3d/TzengPO11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/ppia/2011,
  editor       = {John D. Owens and
                  I{-}Jong Lin and
                  Yu{-}Jin Zhang and
                  Giordano B. Beretta},
  title        = {Proceedings of the Conference on Parallel Processing for Imaging Applications
                  2011, San Francisco Airport, CA, USA, January 24-25, 2011},
  series       = {{SPIE} Proceedings},
  volume       = {7872},
  publisher    = {{SPIE}},
  year         = {2011},
  url          = {http://proceedings.spiedigitallibrary.org/volume.aspx?volume=7872},
  isbn         = {978-0-8194-8409-3},
  timestamp    = {Tue, 28 Jun 2016 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppia/2011.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1110-4623,
  author       = {Jeff A. Stuart and
                  John D. Owens},
  title        = {Efficient Synchronization Primitives for GPUs},
  journal      = {CoRR},
  volume       = {abs/1110.4623},
  year         = {2011},
  url          = {http://arxiv.org/abs/1110.4623},
  eprinttype    = {arXiv},
  eprint       = {1110.4623},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1110-4623.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/PatneyTO10,
  author       = {Anjul Patney and
                  Stanley Tzeng and
                  John D. Owens},
  title        = {Fragment-Parallel Composite and Filter},
  journal      = {Comput. Graph. Forum},
  volume       = {29},
  number       = {4},
  pages        = {1251--1258},
  year         = {2010},
  url          = {https://doi.org/10.1111/j.1467-8659.2010.01720.x},
  doi          = {10.1111/J.1467-8659.2010.01720.X},
  timestamp    = {Fri, 26 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/PatneyTO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dagm/Muyan-OzcelikGOO10,
  author       = {Pinar Muyan{-}{\"{O}}z{\c{c}}elik and
                  Vladimir Glavtchev and
                  Jeffrey M. Ota and
                  John D. Owens},
  editor       = {Michael Goesele and
                  Stefan Roth and
                  Arjan Kuijper and
                  Bernt Schiele and
                  Konrad Schindler},
  title        = {A Template-Based Approach for Real-Time Speed-Limit-Sign Recognition
                  on an Embedded System Using {GPU} Computing},
  booktitle    = {Pattern Recognition - 32nd {DAGM} Symposium, Darmstadt, Germany, September
                  22-24, 2010. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {6376},
  pages        = {162--171},
  publisher    = {Springer},
  year         = {2010},
  url          = {https://doi.org/10.1007/978-3-642-15986-2\_17},
  doi          = {10.1007/978-3-642-15986-2\_17},
  timestamp    = {Sat, 30 Sep 2023 09:38:32 +0200},
  biburl       = {https://dblp.org/rec/conf/dagm/Muyan-OzcelikGOO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/TzengPO10,
  author       = {Stanley Tzeng and
                  Anjul Patney and
                  John D. Owens},
  editor       = {Justin Hensley and
                  Philipp Slusallek and
                  David K. McAllister and
                  Christiaan P. Gribble},
  title        = {Task management for irregular-parallel workloads on the {GPU}},
  booktitle    = {Proceedings of the {ACM} {SIGGRAPH/EUROGRAPHICS} Conference on High
                  Performance Graphics 2010, Saarbr{\"{u}}cken, Germany, June 25-27,
                  2010},
  pages        = {29--37},
  publisher    = {Eurographics Association},
  year         = {2010},
  url          = {https://doi.org/10.2312/EGGH/HPG10/029-037},
  doi          = {10.2312/EGGH/HPG10/029-037},
  timestamp    = {Wed, 24 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/TzengPO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/StuartCO10,
  author       = {Jeff A. Stuart and
                  Michael Cox and
                  John D. Owens},
  editor       = {Mario R. Guarracino and
                  Fr{\'{e}}d{\'{e}}ric Vivien and
                  Jesper Larsson Tr{\"{a}}ff and
                  Mario Cannataro and
                  Marco Danelutto and
                  Anders Hast and
                  Francesca Perla and
                  Andreas Kn{\"{u}}pfer and
                  Beniamino Di Martino and
                  Michael Alexander},
  title        = {GPU-to-CPU Callbacks},
  booktitle    = {Euro-Par 2010 Parallel Processing Workshops - HeteroPar, HPCC, HiBB,
                  CoreGrid, UCHPC, HPCF, PROPER, CCPI, VHPC, Ischia, Italy, August 31-September
                  3, 2010, Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {6586},
  pages        = {365--372},
  publisher    = {Springer},
  year         = {2010},
  url          = {https://doi.org/10.1007/978-3-642-21878-1\_45},
  doi          = {10.1007/978-3-642-21878-1\_45},
  timestamp    = {Wed, 19 Feb 2020 14:52:57 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/StuartCO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/StuartCMO10,
  author       = {Jeff A. Stuart and
                  Cheng{-}Kai Chen and
                  Kwan{-}Liu Ma and
                  John D. Owens},
  editor       = {Salim Hariri and
                  Kate Keahey},
  title        = {Multi-GPU volume rendering using MapReduce},
  booktitle    = {Proceedings of the 19th {ACM} International Symposium on High Performance
                  Distributed Computing, {HPDC} 2010, Chicago, Illinois, USA, June 21-25,
                  2010},
  pages        = {841--848},
  publisher    = {{ACM}},
  year         = {2010},
  url          = {https://doi.org/10.1145/1851476.1851597},
  doi          = {10.1145/1851476.1851597},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpdc/StuartCMO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/para/DavidsonO10,
  author       = {Andrew A. Davidson and
                  John D. Owens},
  editor       = {Kristj{\'{a}}n J{\'{o}}nasson},
  title        = {Toward Techniques for Auto-tuning {GPU} Algorithms},
  booktitle    = {Applied Parallel and Scientific Computing - 10th International Conference,
                  {PARA} 2010, Reykjav{\'{\i}}k, Iceland, June 6-9, 2010, Revised
                  Selected Papers, Part {II}},
  series       = {Lecture Notes in Computer Science},
  volume       = {7134},
  pages        = {110--119},
  publisher    = {Springer},
  year         = {2010},
  url          = {https://doi.org/10.1007/978-3-642-28145-7\_11},
  doi          = {10.1007/978-3-642-28145-7\_11},
  timestamp    = {Tue, 14 May 2019 10:00:40 +0200},
  biburl       = {https://dblp.org/rec/conf/para/DavidsonO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/ZhangCO10,
  author       = {Yao Zhang and
                  Jonathan Cohen and
                  John D. Owens},
  editor       = {R. Govindarajan and
                  David A. Padua and
                  Mary W. Hall},
  title        = {Fast tridiagonal solvers on the {GPU}},
  booktitle    = {Proceedings of the 15th {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, {PPOPP} 2010, Bangalore, India,
                  January 9-14, 2010},
  pages        = {127--136},
  publisher    = {{ACM}},
  year         = {2010},
  url          = {https://doi.org/10.1145/1693453.1693472},
  doi          = {10.1145/1693453.1693472},
  timestamp    = {Sun, 12 Jun 2022 19:46:08 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/ZhangCO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/tf/10/SenguptaHGO10,
  author       = {Shubhabrata Sengupta and
                  Mark J. Harris and
                  Michael Garland and
                  John D. Owens},
  editor       = {Jakub Kurzak and
                  David A. Bader and
                  Jack J. Dongarra},
  title        = {Efficient Parallel Scan Algorithms for Manycore GPUs},
  booktitle    = {Scientific Computing with Multicore and Accelerators},
  series       = {Chapman and Hall / {CRC} computational science series},
  pages        = {413--442},
  publisher    = {{CRC} Press / Taylor {\&} Francis},
  year         = {2010},
  url          = {https://doi.org/10.1201/b10376-29},
  doi          = {10.1201/B10376-29},
  timestamp    = {Sat, 19 Oct 2019 19:02:58 +0200},
  biburl       = {https://dblp.org/rec/books/tf/10/SenguptaHGO10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/BudgeBSSJO09,
  author       = {Brian Budge and
                  Tony Bernardin and
                  Jeff A. Stuart and
                  Shubhabrata Sengupta and
                  Kenneth I. Joy and
                  John D. Owens},
  title        = {Out-of-core Data Management for Path Tracing on Hybrid Resources},
  journal      = {Comput. Graph. Forum},
  volume       = {28},
  number       = {2},
  pages        = {385--396},
  year         = {2009},
  url          = {https://doi.org/10.1111/j.1467-8659.2009.01378.x},
  doi          = {10.1111/J.1467-8659.2009.01378.X},
  timestamp    = {Fri, 26 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/BudgeBSSJO09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/AlcantaraSASMOA09,
  author       = {Dan A. Alcantara and
                  Andrei Sharf and
                  Fatemeh Abbasinejad and
                  Shubhabrata Sengupta and
                  Michael Mitzenmacher and
                  John D. Owens and
                  Nina Amenta},
  title        = {Real-time parallel hashing on the {GPU}},
  journal      = {{ACM} Trans. Graph.},
  volume       = {28},
  number       = {5},
  pages        = {154},
  year         = {2009},
  url          = {https://doi.org/10.1145/1618452.1618500},
  doi          = {10.1145/1618452.1618500},
  timestamp    = {Sat, 19 Oct 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/AlcantaraSASMOA09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/GuptaO09,
  author       = {Kshitij Gupta and
                  John D. Owens},
  title        = {Three-layer optimizations for fast {GMM} computations on GPU-like
                  parallel processors},
  booktitle    = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding,
                  {ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009},
  pages        = {146--151},
  publisher    = {{IEEE}},
  year         = {2009},
  url          = {https://doi.org/10.1109/ASRU.2009.5373410},
  doi          = {10.1109/ASRU.2009.5373410},
  timestamp    = {Wed, 01 Sep 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/asru/GuptaO09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/PatneyEO09,
  author       = {Anjul Patney and
                  Mohamed S. Ebeida and
                  John D. Owens},
  editor       = {Stephen N. Spencer and
                  David K. McAllister and
                  Matt Pharr and
                  Ingo Wald and
                  David P. Luebke and
                  Philipp Slusallek},
  title        = {Parallel view-dependent tessellation of Catmull-Clark subdivision
                  surfaces},
  booktitle    = {Proceedings of the {ACM} {SIGGRAPH/EUROGRAPHICS} Conference on High
                  Performance Graphics 2009, New Orleans, Louisiana, USA, August 1-3,
                  2009},
  pages        = {99--108},
  publisher    = {Eurographics Association},
  year         = {2009},
  url          = {https://doi.org/10.2312/EGGH/HPG09/099-108},
  doi          = {10.2312/EGGH/HPG09/099-108},
  timestamp    = {Tue, 06 Nov 2018 11:06:57 +0100},
  biburl       = {https://dblp.org/rec/conf/egh/PatneyEO09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Owens09,
  author       = {John D. Owens},
  title        = {{HCW} 2009 keynote talk: {GPU} computing: Heterogeneous computing
                  for future systems},
  booktitle    = {23rd {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2009, Rome, Italy, May 23-29, 2009},
  pages        = {1},
  publisher    = {{IEEE}},
  year         = {2009},
  url          = {https://doi.org/10.1109/IPDPS.2009.5160866},
  doi          = {10.1109/IPDPS.2009.5160866},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/Owens09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/StuartO09,
  author       = {Jeff A. Stuart and
                  John D. Owens},
  title        = {Message passing on data-parallel architectures},
  booktitle    = {23rd {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2009, Rome, Italy, May 23-29, 2009},
  pages        = {1--12},
  publisher    = {{IEEE}},
  year         = {2009},
  url          = {https://doi.org/10.1109/IPDPS.2009.5161065},
  doi          = {10.1109/IPDPS.2009.5161065},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/StuartO09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssdbm/GosinkWBOJ09,
  author       = {Luke J. Gosink and
                  Kesheng Wu and
                  E. Wes Bethel and
                  John D. Owens and
                  Kenneth I. Joy},
  editor       = {Marianne Winslett},
  title        = {Data Parallel Bin-Based Indexing for Answering Queries on Multi-core
                  Architectures},
  booktitle    = {Scientific and Statistical Database Management, 21st International
                  Conference, {SSDBM} 2009, New Orleans, LA, USA, June 2-4, 2009, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {5566},
  pages        = {110--129},
  publisher    = {Springer},
  year         = {2009},
  url          = {https://doi.org/10.1007/978-3-642-02279-1\_9},
  doi          = {10.1007/978-3-642-02279-1\_9},
  timestamp    = {Sun, 02 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ssdbm/GosinkWBOJ09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cgf/MoerschellO08,
  author       = {Adam Moerschell and
                  John D. Owens},
  title        = {Distributed Texture Memory in a Multi-GPU Environment},
  journal      = {Comput. Graph. Forum},
  volume       = {27},
  number       = {1},
  pages        = {130--151},
  year         = {2008},
  url          = {https://doi.org/10.1111/j.1467-8659.2007.01101.x},
  doi          = {10.1111/J.1467-8659.2007.01101.X},
  timestamp    = {Fri, 26 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/cgf/MoerschellO08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pieee/OwensHLGSP08,
  author       = {John D. Owens and
                  Mike Houston and
                  David Luebke and
                  Simon Green and
                  John E. Stone and
                  James C. Phillips},
  title        = {{GPU} Computing},
  journal      = {Proc. {IEEE}},
  volume       = {96},
  number       = {5},
  pages        = {879--899},
  year         = {2008},
  url          = {https://doi.org/10.1109/JPROC.2008.917757},
  doi          = {10.1109/JPROC.2008.917757},
  timestamp    = {Tue, 29 Dec 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pieee/OwensHLGSP08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/PatneyO08,
  author       = {Anjul Patney and
                  John D. Owens},
  title        = {Real-time Reyes-style adaptive surface subdivision},
  journal      = {{ACM} Trans. Graph.},
  volume       = {27},
  number       = {5},
  pages        = {143},
  year         = {2008},
  url          = {https://doi.org/10.1145/1409060.1409096},
  doi          = {10.1145/1409060.1409096},
  timestamp    = {Tue, 14 May 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tog/PatneyO08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccsa/Muyan-OzcelikOXS08,
  author       = {Pinar Muyan{-}{\"{O}}z{\c{c}}elik and
                  John D. Owens and
                  Junyi Xia and
                  Sanjiv S. Samant},
  editor       = {Marina L. Gavrilova and
                  Osvaldo Gervasi and
                  Antonio Lagan{\`{a}} and
                  Youngsong Mun and
                  Andr{\'{e}}s Iglesias},
  title        = {Fast Deformable Registration on the {GPU:} {A} {CUDA} Implementation
                  of Demons},
  booktitle    = {Selected Papers of the Sixth International Conference on Computational
                  Sciences and Its Applications, {ICCSA} '08, Perugia, Italy, June 30
                  - July 3, 2008},
  pages        = {223--233},
  publisher    = {{IEEE} Computer Society},
  year         = {2008},
  url          = {https://doi.org/10.1109/ICCSA.2008.22},
  doi          = {10.1109/ICCSA.2008.22},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iccsa/Muyan-OzcelikOXS08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/SilbersteinSGPO08,
  author       = {Mark Silberstein and
                  Assaf Schuster and
                  Dan Geiger and
                  Anjul Patney and
                  John D. Owens},
  editor       = {Pin Zhou},
  title        = {Efficient computation of sum-products on GPUs through software-managed
                  cache},
  booktitle    = {Proceedings of the 22nd Annual International Conference on Supercomputing,
                  {ICS} 2008, Island of Kos, Greece, June 7-12, 2008},
  pages        = {309--318},
  publisher    = {{ACM}},
  year         = {2008},
  url          = {https://doi.org/10.1145/1375527.1375572},
  doi          = {10.1145/1375527.1375572},
  timestamp    = {Wed, 14 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ics/SilbersteinSGPO08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/LefohnHBFFLO08,
  author       = {Aaron E. Lefohn and
                  Mike Houston and
                  Chas Boyd and
                  Kayvon Fatahalian and
                  Tom Forsyth and
                  David Luebke and
                  John D. Owens},
  title        = {Beyond programmable shading: fundamentals},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2008, Los Angeles, California, USA, August 11-15, 2008,
                  Classes},
  pages        = {9:1--9:21},
  publisher    = {{ACM}},
  year         = {2008},
  url          = {https://doi.org/10.1145/1401132.1401145},
  doi          = {10.1145/1401132.1401145},
  timestamp    = {Fri, 12 Mar 2021 10:04:42 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/LefohnHBFFLO08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/Owens08,
  author       = {John D. Owens},
  title        = {Parallel programming models overview},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2008, Los Angeles, California, USA, August 11-15, 2008,
                  Classes},
  pages        = {13:1--13:15},
  publisher    = {{ACM}},
  year         = {2008},
  url          = {https://doi.org/10.1145/1401132.1401149},
  doi          = {10.1145/1401132.1401149},
  timestamp    = {Wed, 15 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/Owens08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/egh/2008,
  editor       = {David P. Luebke and
                  John D. Owens},
  title        = {Proceedings of the {EUROGRAPHICS/ACM} {SIGGRAPH} Conference on Graphics
                  Hardware 2008, Sarajevo, Bosnia and Herzegovina, 2008},
  publisher    = {Eurographics Association},
  year         = {2008},
  url          = {http://diglib.eg.org/handle/10.2312/327},
  isbn         = {978-3-905674-09-5},
  timestamp    = {Thu, 26 Nov 2015 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/egh/2008.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/micro/OwensDHJKP07,
  author       = {John D. Owens and
                  William J. Dally and
                  Ron Ho and
                  Doddaballapur Narasimha{-}Murthy Jayasimha and
                  Stephen W. Keckler and
                  Li{-}Shiuan Peh},
  title        = {Research Challenges for On-Chip Interconnection Networks},
  journal      = {{IEEE} Micro},
  volume       = {27},
  number       = {5},
  pages        = {96--108},
  year         = {2007},
  url          = {http://doi.ieeecomputersociety.org/10.1109/MM.2007.91},
  doi          = {10.1109/MM.2007.91},
  timestamp    = {Sun, 03 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/micro/OwensDHJKP07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/LefohnSO07,
  author       = {Aaron E. Lefohn and
                  Shubhabrata Sengupta and
                  John D. Owens},
  title        = {Resolution-matched shadow maps},
  journal      = {{ACM} Trans. Graph.},
  volume       = {26},
  number       = {4},
  pages        = {20},
  year         = {2007},
  url          = {https://doi.org/10.1145/1289603.1289611},
  doi          = {10.1145/1289603.1289611},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tog/LefohnSO07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/SenguptaHZO07,
  author       = {Shubhabrata Sengupta and
                  Mark J. Harris and
                  Yao Zhang and
                  John D. Owens},
  editor       = {Mark Segal and
                  Timo Aila},
  title        = {Scan primitives for {GPU} computing},
  booktitle    = {Proceedings of the {ACM} {SIGGRAPH/EUROGRAPHICS} Conference on Graphics
                  Hardware 2007, San Diego, California, USA, August 4-5, 2007},
  pages        = {97--106},
  publisher    = {Eurographics Association},
  year         = {2007},
  url          = {https://doi.org/10.2312/EGGH/EGGH07/097-106},
  doi          = {10.2312/EGGH/EGGH07/097-106},
  timestamp    = {Wed, 12 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/SenguptaHZO07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/Owens07,
  author       = {John D. Owens},
  editor       = {Sara McMains and
                  Peter{-}Pike Sloan},
  title        = {{GPU} architecture overview},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2007, San Diego, California, USA, August 5-9, 2007, Courses},
  pages        = {2},
  publisher    = {{ACM}},
  year         = {2007},
  url          = {https://doi.org/10.1145/1281500.1281643},
  doi          = {10.1145/1281500.1281643},
  timestamp    = {Wed, 15 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/Owens07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/Owens07a,
  author       = {John D. Owens},
  editor       = {Sara McMains and
                  Peter{-}Pike Sloan},
  title        = {Data-parallel algorithms and data structures},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2007, San Diego, California, USA, August 5-9, 2007, Courses},
  pages        = {3},
  publisher    = {{ACM}},
  year         = {2007},
  url          = {https://doi.org/10.1145/1281500.1281644},
  doi          = {10.1145/1281500.1281644},
  timestamp    = {Wed, 15 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/Owens07a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tog/LefohnSKSO06,
  author       = {Aaron E. Lefohn and
                  Shubhabrata Sengupta and
                  Joe Kniss and
                  Robert Strzodka and
                  John D. Owens},
  title        = {Glift: Generic, efficient, random-access {GPU} data structures},
  journal      = {{ACM} Trans. Graph.},
  volume       = {25},
  number       = {1},
  pages        = {60--99},
  year         = {2006},
  url          = {https://doi.org/10.1145/1122501.1122505},
  doi          = {10.1145/1122501.1122505},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tog/LefohnSKSO06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tvcg/ParkLKOH06,
  author       = {Sung W. Park and
                  Lars Linsen and
                  Oliver Kreylos and
                  John D. Owens and
                  Bernd Hamann},
  title        = {Discrete Sibson Interpolation},
  journal      = {{IEEE} Trans. Vis. Comput. Graph.},
  volume       = {12},
  number       = {2},
  pages        = {243--253},
  year         = {2006},
  url          = {https://doi.org/10.1109/TVCG.2006.27},
  doi          = {10.1109/TVCG.2006.27},
  timestamp    = {Wed, 14 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tvcg/ParkLKOH06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dcoss/SzumelO06,
  author       = {Leo Szumel and
                  John D. Owens},
  editor       = {Phillip B. Gibbons and
                  Tarek F. Abdelzaher and
                  James Aspnes and
                  Ramesh R. Rao},
  title        = {The Virtual Pheromone Communication Primitive},
  booktitle    = {Distributed Computing in Sensor Systems, Second {IEEE} International
                  Conference, {DCOSS} 2006, San Francisco, CA, USA, June 18-20, 2006,
                  Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {4026},
  pages        = {135--149},
  publisher    = {Springer},
  year         = {2006},
  url          = {https://doi.org/10.1007/11776178\_9},
  doi          = {10.1007/11776178\_9},
  timestamp    = {Tue, 14 May 2019 10:00:38 +0200},
  biburl       = {https://dblp.org/rec/conf/dcoss/SzumelO06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/MoerschellO06,
  author       = {Adam Moerschell and
                  John D. Owens},
  editor       = {Michael C. Doggett and
                  Michael Wimmer},
  title        = {Distributed Texture Memory in a Multi-GPU Environment},
  booktitle    = {Proceedings of the 21st {ACM} {SIGGRAPH/EUROGRAPHICS} symposium on
                  Graphics hardware, Vienna, Austria, September 3-4, 2006},
  pages        = {31--38},
  publisher    = {The Eurographics Association},
  year         = {2006},
  url          = {https://doi.org/10.2312/EGGH/EGGH06/031-038},
  doi          = {10.2312/EGGH/EGGH06/031-038},
  timestamp    = {Wed, 26 May 2021 11:51:07 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/MoerschellO06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LuebkeHGLHOSPB06,
  author       = {David P. Luebke and
                  Mark J. Harris and
                  Naga K. Govindaraju and
                  Aaron E. Lefohn and
                  Mike Houston and
                  John D. Owens and
                  Mark Segal and
                  Matthew Papakipos and
                  Ian Buck},
  title        = {{S07} - {GPGPU:} general-purpose computation on graphics hardware},
  booktitle    = {Proceedings of the {ACM/IEEE} {SC2006} Conference on High Performance
                  Networking and Computing, November 11-17, 2006, Tampa, FL, {USA}},
  pages        = {208},
  publisher    = {{ACM} Press},
  year         = {2006},
  url          = {https://doi.org/10.1145/1188455.1188672},
  doi          = {10.1145/1188455.1188672},
  timestamp    = {Wed, 16 Oct 2019 14:14:57 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/LuebkeHGLHOSPB06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eurographics/OwensLGHKLP05,
  author       = {John D. Owens and
                  David Luebke and
                  Naga K. Govindaraju and
                  Mark J. Harris and
                  Jens H. Kr{\"{u}}ger and
                  Aaron E. Lefohn and
                  Timothy J. Purcell},
  editor       = {Yiorgos Chrysanthou and
                  Marcus A. Magnor},
  title        = {A Survey of General-Purpose Computation on Graphics Hardware},
  booktitle    = {26th Annual Conference of the European Association for Computer Graphics,
                  Eurographics 2005 - State of the Art Reports, Dublin, Ireland, August
                  29 - September 2, 2005},
  pages        = {21--51},
  publisher    = {Eurographics Association},
  year         = {2005},
  url          = {https://doi.org/10.2312/egst.20051043},
  doi          = {10.2312/EGST.20051043},
  timestamp    = {Fri, 03 Jul 2020 16:45:59 +0200},
  biburl       = {https://dblp.org/rec/conf/eurographics/OwensLGHKLP05.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/Owens05b,
  author       = {John D. Owens},
  editor       = {John Fujii},
  title        = {Streaming architectures and technology trends},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2005, Los Angeles, California, USA, July 31 - August 4,
                  2005, Courses},
  pages        = {9},
  publisher    = {{ACM}},
  year         = {2005},
  url          = {https://doi.org/10.1145/1198555.1198766},
  doi          = {10.1145/1198555.1198766},
  timestamp    = {Wed, 15 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/Owens05b.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/LefohnSKSO05,
  author       = {Aaron E. Lefohn and
                  Shubhabrata Sengupta and
                  Joe Kniss and
                  Robert Strzodka and
                  John D. Owens},
  editor       = {Juan Buhler},
  title        = {Dynamic adaptive shadow maps on graphics hardware},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2005, Los Angeles, California, USA, July 31 - August 4,
                  2005, Sketches},
  pages        = {13},
  publisher    = {{ACM}},
  year         = {2005},
  url          = {https://doi.org/10.1145/1187112.1187126},
  doi          = {10.1145/1187112.1187126},
  timestamp    = {Fri, 12 Mar 2021 11:32:36 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/LefohnSKSO05.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/KnissLSSO05,
  author       = {Joe Kniss and
                  Aaron E. Lefohn and
                  Robert Strzodka and
                  Shubhabrata Sengupta and
                  John D. Owens},
  editor       = {Juan Buhler},
  title        = {Octree textures on graphics hardware},
  booktitle    = {International Conference on Computer Graphics and Interactive Techniques,
                  {SIGGRAPH} 2005, Los Angeles, California, USA, July 31 - August 4,
                  2005, Sketches},
  pages        = {16},
  publisher    = {{ACM}},
  year         = {2005},
  url          = {https://doi.org/10.1145/1187112.1187129},
  doi          = {10.1145/1187112.1187129},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/siggraph/KnissLSSO05.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/visualization/LefohnBMOPS05,
  author       = {Aaron E. Lefohn and
                  Ian Buck and
                  Patrick S. McCormick and
                  John D. Owens and
                  Timothy J. Purcell and
                  Robert Strzodka},
  title        = {General Purpose Computation on Graphics Hardware},
  booktitle    = {16th {IEEE} Visualization Conference, {IEEE} Vis 2005, Minneapolis,
                  MN, USA, October 23-28, 2005, Proceedings},
  pages        = {121},
  publisher    = {{IEEE} Computer Society},
  year         = {2005},
  timestamp    = {Wed, 12 Aug 2020 09:23:06 +0200},
  biburl       = {https://dblp.org/rec/conf/visualization/LefohnBMOPS05.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/RiffelLVLO04,
  author       = {Andrew Riffel and
                  Aaron E. Lefohn and
                  Kiril Vidimce and
                  Mark Leone and
                  John D. Owens},
  editor       = {Michael D. McCool and
                  Tomas Akenine{-}M{\"{o}}ller},
  title        = {Mio: fast multipass partitioning via priority-based instruction scheduling},
  booktitle    = {Proceedings of the {ACM} {SIGGRAPH/EUROGRAPHICS} Symposium on Graphics
                  Hardware 2004, Grenoble, France, August 29-30, 2004},
  pages        = {35--44},
  publisher    = {Eurographics Association},
  year         = {2004},
  url          = {https://doi.org/10.2312/EGGH/EGGH04/035-044},
  doi          = {10.2312/EGGH/EGGH04/035-044},
  timestamp    = {Tue, 06 Nov 2018 11:06:57 +0100},
  biburl       = {https://dblp.org/rec/conf/egh/RiffelLVLO04.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computer/KapasiRDKAMO03,
  author       = {Ujval J. Kapasi and
                  Scott Rixner and
                  William J. Dally and
                  Brucek Khailany and
                  Jung Ho Ahn and
                  Peter R. Mattson and
                  John D. Owens},
  title        = {Programmable Stream Processors},
  journal      = {Computer},
  volume       = {36},
  number       = {8},
  pages        = {54--62},
  year         = {2003},
  url          = {https://doi.org/10.1109/MC.2003.1220582},
  doi          = {10.1109/MC.2003.1220582},
  timestamp    = {Wed, 12 Aug 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/computer/KapasiRDKAMO03.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpca/KhailanyDRKOT03,
  author       = {Brucek Khailany and
                  William J. Dally and
                  Scott Rixner and
                  Ujval J. Kapasi and
                  John D. Owens and
                  Brian Towles},
  title        = {Exploring the {VLSI} Scalability of Stream Processors},
  booktitle    = {Proceedings of the Ninth International Symposium on High-Performance
                  Computer Architecture (HPCA'03), Anaheim, California, USA, February
                  8-12, 2003},
  pages        = {153--164},
  publisher    = {{IEEE} Computer Society},
  year         = {2003},
  url          = {https://doi.org/10.1109/HPCA.2003.1183534},
  doi          = {10.1109/HPCA.2003.1183534},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpca/KhailanyDRKOT03.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/OwensKTD02,
  author       = {John D. Owens and
                  Brucek Khailany and
                  Brian Towles and
                  William J. Dally},
  editor       = {Thomas Ertl and
                  Wolfgang Heidrich and
                  Michael C. Doggett},
  title        = {Comparing Reyes and OpenGL on a Stream Architecture},
  booktitle    = {Proceedings of the 2002 {ACM} {SIGGRAPH/EUROGRAPHICS} Conference on
                  Graphics Hardware, Saarbr{\"{u}}cken, Germany, September 2-3,
                  2002},
  pages        = {47--56},
  publisher    = {The Eurographics Association},
  year         = {2002},
  url          = {https://doi.org/10.2312/EGGH/EGGH02/047-056},
  doi          = {10.2312/EGGH/EGGH02/047-056},
  timestamp    = {Wed, 24 May 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/OwensKTD02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccd/KapasiDROK02,
  author       = {Ujval J. Kapasi and
                  William J. Dally and
                  Scott Rixner and
                  John D. Owens and
                  Brucek Khailany},
  title        = {The Imagine Stream Processor},
  booktitle    = {20th International Conference on Computer Design {(ICCD} 2002), {VLSI}
                  in Computers and Processors, 16-18 September 2002, Freiburg, Germany,
                  Proceedings},
  pages        = {282--288},
  publisher    = {{IEEE} Computer Society},
  year         = {2002},
  url          = {https://doi.org/10.1109/ICCD.2002.1106783},
  doi          = {10.1109/ICCD.2002.1106783},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iccd/KapasiDROK02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccd/OwensRKMTSD02,
  author       = {John D. Owens and
                  Scott Rixner and
                  Ujval J. Kapasi and
                  Peter R. Mattson and
                  Brian Towles and
                  Ben Serebrin and
                  William J. Dally},
  title        = {Media Processing Applications on the Imagine Stream Processor},
  booktitle    = {20th International Conference on Computer Design {(ICCD} 2002), {VLSI}
                  in Computers and Processors, 16-18 September 2002, Freiburg, Germany,
                  Proceedings},
  pages        = {295--302},
  publisher    = {{IEEE} Computer Society},
  year         = {2002},
  url          = {https://doi.org/10.1109/ICCD.2002.1106785},
  doi          = {10.1109/ICCD.2002.1106785},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iccd/OwensRKMTSD02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccd/SerebrinOCCKMNRD02,
  author       = {Ben Serebrin and
                  John D. Owens and
                  Chen H. Chen and
                  Stephen P. Crago and
                  Ujval J. Kapasi and
                  Peter R. Mattson and
                  Jinyung Namkoong and
                  Scott Rixner and
                  William J. Dally},
  title        = {A Stream Processor Development Platform},
  booktitle    = {20th International Conference on Computer Design {(ICCD} 2002), {VLSI}
                  in Computers and Processors, 16-18 September 2002, Freiburg, Germany,
                  Proceedings},
  pages        = {303},
  publisher    = {{IEEE} Computer Society},
  year         = {2002},
  url          = {https://doi.org/10.1109/ICCD.2002.1106786},
  doi          = {10.1109/ICCD.2002.1106786},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iccd/SerebrinOCCKMNRD02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/micro/KhailanyDKMNOTCR01,
  author       = {Brucek Khailany and
                  William J. Dally and
                  Ujval J. Kapasi and
                  Peter R. Mattson and
                  Jinyung Namkoong and
                  John D. Owens and
                  Brian Towles and
                  Andrew Chang and
                  Scott Rixner},
  title        = {Imagine: Media Processing with Streams},
  journal      = {{IEEE} Micro},
  volume       = {21},
  number       = {2},
  pages        = {35--46},
  year         = {2001},
  url          = {https://doi.org/10.1109/40.918001},
  doi          = {10.1109/40.918001},
  timestamp    = {Thu, 16 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/micro/KhailanyDKMNOTCR01.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asplos/MattsonDRKO00,
  author       = {Peter R. Mattson and
                  William J. Dally and
                  Scott Rixner and
                  Ujval J. Kapasi and
                  John D. Owens},
  editor       = {Larry Rudolph and
                  Anoop Gupta},
  title        = {Communication Scheduling},
  booktitle    = {{ASPLOS-IX} Proceedings of the 9th International Conference on Architectural
                  Support for Programming Languages and Operating Systems, Cambridge,
                  MA, USA, November 12-15, 2000},
  pages        = {82--92},
  publisher    = {{ACM} Press},
  year         = {2000},
  url          = {https://doi.org/10.1145/378993.379005},
  doi          = {10.1145/378993.379005},
  timestamp    = {Wed, 07 Jul 2021 13:23:08 +0200},
  biburl       = {https://dblp.org/rec/conf/asplos/MattsonDRKO00.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/egh/OwensDKRMM00,
  author       = {John D. Owens and
                  William J. Dally and
                  Ujval J. Kapasi and
                  Scott Rixner and
                  Peter R. Mattson and
                  Ben Mowery},
  editor       = {Stephen N. Spencer},
  title        = {Polygon Rendering on a Stream Architecture},
  booktitle    = {Proceedings of the 2000 {ACM} {SIGGRAPH/EUROGRAPHICS} Workshop on
                  Graphics Hardware, Interlaken, Switzerland, August 21-22, 2000},
  pages        = {23--32},
  publisher    = {The Eurographics Association},
  year         = {2000},
  url          = {https://doi.org/10.2312/EGGH/EGGH00/023-032},
  doi          = {10.2312/EGGH/EGGH00/023-032},
  timestamp    = {Thu, 28 Sep 2023 09:26:09 +0200},
  biburl       = {https://dblp.org/rec/conf/egh/OwensDKRMM00.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpca/RixnerDKMKO00,
  author       = {Scott Rixner and
                  William J. Dally and
                  Brucek Khailany and
                  Peter R. Mattson and
                  Ujval J. Kapasi and
                  John D. Owens},
  title        = {Register Organization for Media Processing},
  booktitle    = {Proceedings of the Sixth International Symposium on High-Performance
                  Computer Architecture, Toulouse, France, January 8-12, 2000},
  pages        = {375--386},
  publisher    = {{IEEE} Computer Society},
  year         = {2000},
  url          = {https://doi.org/10.1109/HPCA.2000.824366},
  doi          = {10.1109/HPCA.2000.824366},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpca/RixnerDKMKO00.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isca/RixnerDKMO00,
  author       = {Scott Rixner and
                  William J. Dally and
                  Ujval J. Kapasi and
                  Peter R. Mattson and
                  John D. Owens},
  editor       = {Alan D. Berenbaum and
                  Joel S. Emer},
  title        = {Memory access scheduling},
  booktitle    = {27th International Symposium on Computer Architecture {(ISCA} 2000),
                  June 10-14, 2000, Vancouver, BC, Canada},
  pages        = {128--138},
  publisher    = {{IEEE} Computer Society},
  year         = {2000},
  url          = {https://doi.ieeecomputersociety.org/10.1109/ISCA.2000.854384},
  doi          = {10.1109/ISCA.2000.854384},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/isca/RixnerDKMO00.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/micro/KapasiDRMOK00,
  author       = {Ujval J. Kapasi and
                  William J. Dally and
                  Scott Rixner and
                  Peter R. Mattson and
                  John D. Owens and
                  Brucek Khailany},
  editor       = {Andrew Wolfe and
                  Michael S. Schlansker},
  title        = {Efficient conditional operations for data-parallel architectures},
  booktitle    = {Proceedings of the 33rd Annual {IEEE/ACM} International Symposium
                  on Microarchitecture, {MICRO} 33, Monterey, California, USA, December
                  10-13, 2000},
  pages        = {159--170},
  publisher    = {{ACM/IEEE} Computer Society},
  year         = {2000},
  url          = {https://doi.org/10.1109/MICRO.2000.898067},
  doi          = {10.1109/MICRO.2000.898067},
  timestamp    = {Tue, 31 May 2022 14:30:45 +0200},
  biburl       = {https://dblp.org/rec/conf/micro/KapasiDRMOK00.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/micro/RixnerDKKLMO98,
  author       = {Scott Rixner and
                  William J. Dally and
                  Ujval J. Kapasi and
                  Brucek Khailany and
                  Abelardo L{\'{o}}pez{-}Lagunas and
                  Peter R. Mattson and
                  John D. Owens},
  editor       = {James O. Bondi and
                  Jim Smith},
  title        = {A Bandwidth-efficient Architecture for Media Processing},
  booktitle    = {Proceedings of the 31st Annual {IEEE/ACM} International Symposium
                  on Microarchitecture, {MICRO} 31, Dallas, Texas, USA, November 30
                  - December 2, 1998},
  pages        = {3--13},
  publisher    = {{ACM/IEEE} Computer Society},
  year         = {1998},
  url          = {https://doi.org/10.1109/MICRO.1998.742118},
  doi          = {10.1109/MICRO.1998.742118},
  timestamp    = {Tue, 31 May 2022 14:39:58 +0200},
  biburl       = {https://dblp.org/rec/conf/micro/RixnerDKKLMO98.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}