Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Hartwig Anzt
@article{DBLP:journals/corr/abs-2403-06218, author = {Andr{\'{e}}s E. Tom{\'{a}}s and Enrique S. Quintana{-}Ort{\'{\i}} and Hartwig Anzt}, title = {Fast Truncated {SVD} of Sparse and Dense Matrices on Graphics Processors}, journal = {CoRR}, volume = {abs/2403.06218}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.06218}, doi = {10.48550/ARXIV.2403.06218}, eprinttype = {arXiv}, eprint = {2403.06218}, timestamp = {Fri, 05 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-06218.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/TsaiCA23, author = {Yu{-}Hsiang Tsai and Terry Cojean and Hartwig Anzt}, title = {Providing performance portable numerics for Intel GPUs}, journal = {Concurr. Comput. Pract. Exp.}, volume = {35}, number = {20}, year = {2023}, url = {https://doi.org/10.1002/cpe.7400}, doi = {10.1002/CPE.7400}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/concurrency/TsaiCA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/AliagaAQT23, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, title = {Sparse matrix-vector and matrix-multivector products for the truncated {SVD} on graphics processors}, journal = {Concurr. Comput. Pract. Exp.}, volume = {35}, number = {28}, year = {2023}, url = {https://doi.org/10.1002/cpe.7871}, doi = {10.1002/CPE.7871}, timestamp = {Wed, 24 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/concurrency/AliagaAQT23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cse/HoeflerSPBSSTKMFKGAFZKKSFL23, author = {Torsten Hoefler and Bjorn Stevens and Andreas F. Prein and Johanna Baehr and Thomas C. Schulthess and Thomas F. Stocker and John A. Taylor and Daniel Klocke and Pekka Manninen and Piers M. Forster and Tobias K{\"{o}}lling and Nicolas Gruber and Hartwig Anzt and Claudia Frauen and Florian Ziemen and Milan Kl{\"{o}}wer and Karthik Kashinath and Christoph M. Sch{\"{a}}r and Oliver Fuhrer and Bryan N. Lawrence}, title = {Earth Virtualization Engines: {A} Technical Perspective}, journal = {Comput. Sci. Eng.}, volume = {25}, number = {3}, pages = {50--59}, year = {2023}, url = {https://doi.org/10.1109/MCSE.2023.3311148}, doi = {10.1109/MCSE.2023.3311148}, timestamp = {Thu, 09 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/cse/HoeflerSPBSSTKMFKGAFZKKSFL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/fgcs/TsaiBA23, author = {Yu{-}Hsiang Mike Tsai and Natalie Beams and Hartwig Anzt}, title = {Three-precision algebraic multigrid on GPUs}, journal = {Future Gener. Comput. Syst.}, volume = {149}, pages = {280--293}, year = {2023}, url = {https://doi.org/10.1016/j.future.2023.07.024}, doi = {10.1016/J.FUTURE.2023.07.024}, timestamp = {Sat, 28 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/fgcs/TsaiBA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AliagaAGQT23, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Thomas Gr{\"{u}}tzmacher and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, title = {Compressed basis {GMRES} on high-performance graphics processing units}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {37}, number = {2}, pages = {82--100}, year = {2023}, url = {https://doi.org/10.1177/10943420221115140}, doi = {10.1177/10943420221115140}, timestamp = {Sat, 28 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/AliagaAGQT23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/TomasQA23, author = {Andr{\'{e}}s E. Tom{\'{a}}s and Enrique S. Quintana{-}Ort{\'{\i}} and Hartwig Anzt}, title = {Fast truncated {SVD} of sparse and dense matrices on graphics processors}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {37}, number = {3-4}, pages = {380--393}, year = {2023}, url = {https://doi.org/10.1177/10943420231179699}, doi = {10.1177/10943420231179699}, timestamp = {Fri, 18 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/TomasQA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jpdc/KashiNKSLA23, author = {Aditya Kashi and Pratik Nayak and Dhruva Kulkarni and Aaron Scheinberg and Paul Lin and Hartwig Anzt}, title = {Integrating batched sparse iterative solvers for the collision operator in fusion plasma simulations on GPUs}, journal = {J. Parallel Distributed Comput.}, volume = {178}, pages = {69--81}, year = {2023}, url = {https://doi.org/10.1016/j.jpdc.2023.03.012}, doi = {10.1016/J.JPDC.2023.03.012}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jpdc/KashiNKSLA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spe/GrutzmacherAQ23, author = {Thomas Gr{\"{u}}tzmacher and Hartwig Anzt and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Using Ginkgo's memory accessor for improving the accuracy of memory-bound low precision {BLAS}}, journal = {Softw. Pract. Exp.}, volume = {53}, number = {1}, pages = {81--98}, year = {2023}, url = {https://doi.org/10.1002/spe.3041}, doi = {10.1002/SPE.3041}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/spe/GrutzmacherAQ23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/SidLakhdarCBALGTJWDDA23, author = {Wissam M. Sid{-}Lakhdar and S{\'{e}}bastien Cayrols and Daniel Bielich and Ahmad Abdelfattah and Piotr Luszczek and Mark Gates and Stanimire Tomov and Hans Johansen and David B. Williams{-}Young and Timothy A. Davis and Jack J. Dongarra and Hartwig Anzt}, title = {{PAQR:} Pivoting Avoiding {QR} factorization}, booktitle = {{IEEE} International Parallel and Distributed Processing Symposium, {IPDPS} 2023, St. Petersburg, FL, USA, May 15-19, 2023}, pages = {322--332}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IPDPS54959.2023.00040}, doi = {10.1109/IPDPS54959.2023.00040}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/SidLakhdarCBALGTJWDDA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/NayakA23, author = {Pratik Nayak and Hartwig Anzt}, title = {Utilizing batched solver ideas for efficient solution of non-batched linear systems}, booktitle = {{IEEE} International Parallel and Distributed Processing Symposium, {IPDPS} 2023 - Workshops, St. Petersburg, FL, USA, May 15-19, 2023}, pages = {662--665}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IPDPSW59300.2023.00113}, doi = {10.1109/IPDPSW59300.2023.00113}, timestamp = {Wed, 09 Aug 2023 16:25:12 +0200}, biburl = {https://dblp.org/rec/conf/ipps/NayakA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/NguyenNA23, author = {Phuong Nguyen and Pratik Nayak and Hartwig Anzt}, title = {Porting Batched Iterative Solvers onto Intel GPUs with {SYCL}}, booktitle = {Proceedings of the {SC} '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, {SC-W} 2023, Denver, CO, USA, November 12-17, 2023}, pages = {1048--1058}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3624062.3624181}, doi = {10.1145/3624062.3624181}, timestamp = {Tue, 28 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/NguyenNA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AbdelfattahTLAD23, author = {Ahmad Abdelfattah and Stanimire Tomov and Piotr Luszczek and Hartwig Anzt and Jack J. Dongarra}, title = {GPU-based {LU} Factorization and Solve on Batches of Matrices with Band Structure}, booktitle = {Proceedings of the {SC} '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, {SC-W} 2023, Denver, CO, USA, November 12-17, 2023}, pages = {1670--1679}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3624062.3624247}, doi = {10.1145/3624062.3624247}, timestamp = {Tue, 28 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/AbdelfattahTLAD23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/SukkariGFAD23, author = {Dalal Sukkari and Mark Gates and Mohammed A. Al Farhan and Hartwig Anzt and Jack J. Dongarra}, title = {Task-Based Polar Decomposition Using {SLATE} on Massively Parallel Systems with Hardware Accelerators}, booktitle = {Proceedings of the {SC} '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, {SC-W} 2023, Denver, CO, USA, November 12-17, 2023}, pages = {1680--1687}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3624062.3624248}, doi = {10.1145/3624062.3624248}, timestamp = {Tue, 28 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/SukkariGFAD23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/RibizelA23, author = {Tobias Ribizel and Hartwig Anzt}, title = {Parallel Symbolic Cholesky Factorization}, booktitle = {Proceedings of the {SC} '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, {SC-W} 2023, Denver, CO, USA, November 12-17, 2023}, pages = {1721--1727}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3624062.3624253}, doi = {10.1145/3624062.3624253}, timestamp = {Tue, 28 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/RibizelA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/supercomputer/GeorgiouBDA23, author = {Vasileios Georgiou and Christos Boutsikas and Petros Drineas and Hartwig Anzt}, editor = {Abhinav Bhatele and Jeff R. Hammond and Marc Baboulin and Carola Kruse}, title = {A Mixed Precision Randomized Preconditioner for the {LSQR} Solver on GPUs}, booktitle = {High Performance Computing - 38th International Conference, {ISC} High Performance 2023, Hamburg, Germany, May 21-25, 2023, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {13948}, pages = {164--181}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/978-3-031-32041-5\_9}, doi = {10.1007/978-3-031-32041-5\_9}, timestamp = {Wed, 17 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/supercomputer/GeorgiouBDA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-14337, author = {Kasia Swirydowicz and Nicholson Koukpaizan and Tobias Ribizel and Fritz G{\"{o}}bel and Shrirang Abhyankar and Hartwig Anzt and Slaven Peles}, title = {GPU-Resident Sparse Direct Linear Solvers for Alternating Current Optimal Power Flow Analysis}, journal = {CoRR}, volume = {abs/2306.14337}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.14337}, doi = {10.48550/ARXIV.2306.14337}, eprinttype = {arXiv}, eprint = {2306.14337}, timestamp = {Tue, 27 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-14337.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-08417, author = {Phuong Nguyen and Pratik Nayak and Hartwig Anzt}, title = {Porting Batched Iterative Solvers onto Intel GPUs with {SYCL}}, journal = {CoRR}, volume = {abs/2308.08417}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.08417}, doi = {10.48550/ARXIV.2308.08417}, eprinttype = {arXiv}, eprint = {2308.08417}, timestamp = {Thu, 24 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-08417.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-09002, author = {Torsten Hoefler and Bjorn Stevens and Andreas F. Prein and Johanna Baehr and Thomas C. Schulthess and Thomas F. Stocker and John A. Taylor and Daniel Klocke and Pekka Manninen and Piers M. Forster and Tobias K{\"{o}}lling and Nicolas Gruber and Hartwig Anzt and Claudia Frauen and Florian Ziemen and Milan Kl{\"{o}}wer and Karthik Kashinath and Christoph M. Sch{\"{a}}r and Oliver Fuhrer and Bryan N. Lawrence}, title = {Earth Virtualization Engines - {A} Technical Perspective}, journal = {CoRR}, volume = {abs/2309.09002}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.09002}, doi = {10.48550/ARXIV.2309.09002}, eprinttype = {arXiv}, eprint = {2309.09002}, timestamp = {Wed, 08 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-09002.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/AliagaAGQT22, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Thomas Gr{\"{u}}tzmacher and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, title = {Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing units}, journal = {Concurr. Comput. Pract. Exp.}, volume = {34}, number = {14}, year = {2022}, url = {https://doi.org/10.1002/cpe.6515}, doi = {10.1002/CPE.6515}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/concurrency/AliagaAGQT22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AgulloAABBBBCCD22, author = {Emmanuel Agullo and Mirco Altenbernd and Hartwig Anzt and Leonardo Bautista{-}Gomez and Tommaso Benacchio and Luca Bonaventura and Hans{-}Joachim Bungartz and Sanjay Chatterjee and Florina M. Ciorba and Nathan DeBardeleben and Daniel Drzisga and Sebastian Eibl and Christian Engelmann and Wilfried N. Gansterer and Luc Giraud and Dominik G{\"{o}}ddeke and Marco Heisig and Fabienne J{\'{e}}z{\'{e}}quel and Nils Kohl and Xiaoye Sherry Li and Romain Lion and Miriam Mehl and Paul Mycek and Michael Obersteiner and Enrique S. Quintana{-}Ort{\'{\i}} and Francesco Rizzi and Ulrich R{\"{u}}de and Martin Schulz and Fred Fung and Robert Speck and Linda Stals and Keita Teranishi and Samuel Thibault and Dominik Th{\"{o}}nnes and Andreas Wagner and Barbara I. Wohlmuth}, title = {Resiliency in numerical algorithm design for extreme scale simulations}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {36}, number = {2}, pages = {251--285}, year = {2022}, url = {https://doi.org/10.1177/10943420211055188}, doi = {10.1177/10943420211055188}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/AgulloAABBBBCCD22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/CojeanTA22, author = {Terry Cojean and Yu{-}Hsiang Mike Tsai and Hartwig Anzt}, title = {Ginkgo - {A} math library designed for platform portability}, journal = {Parallel Comput.}, volume = {111}, pages = {102902}, year = {2022}, url = {https://doi.org/10.1016/j.parco.2022.102902}, doi = {10.1016/J.PARCO.2022.102902}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pc/CojeanTA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/toms/AnztCFGGNRTQ22, author = {Hartwig Anzt and Terry Cojean and Goran Flegar and Fritz G{\"{o}}bel and Thomas Gr{\"{u}}tzmacher and Pratik Nayak and Tobias Ribizel and Yuhsiang Mike Tsai and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Ginkgo: {A} Modern Linear Operator Algebra Framework for High Performance Computing}, journal = {{ACM} Trans. Math. Softw.}, volume = {48}, number = {1}, pages = {2:1--2:33}, year = {2022}, url = {https://doi.org/10.1145/3480935}, doi = {10.1145/3480935}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/toms/AnztCFGGNRTQ22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eduhpc/QasemAACCCFGJKKLMMNOOPPRSSSSST22, author = {Apan Qasem and Hartwig Anzt and Eduard Ayguad{\'{e}} and Katharine Cahill and Ramon Canal and Jany Chan and Eric Fosler{-}Lussier and Fritz G{\"{o}}bel and Arpan Jain and Marcel Koch and Mateusz Kuzak and Josep Llosa and Raghu Machiraju and Xavier Martorell and Pratik Nayak and Shameema Oottikkal and Marcin Ostasz and Dhabaleswar K. Panda and Dirk Pleiter and Rajiv Ramnath and Maria{-}Ribera Sancho and Alessio Sclocco and Aamir Shafi and Hanno Spreeuw and Hari Subramoni and Karen Tomko}, title = {Lightning Talks of EduHPC 2022}, booktitle = {{IEEE/ACM} International Workshop on Education for High Performance Computing, EduHPC 2022, Dallas, TX, USA, November 13-18, 2022}, pages = {42--49}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/EduHPC56719.2022.00011}, doi = {10.1109/EDUHPC56719.2022.00011}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/eduhpc/QasemAACCCFGJKKLMMNOOPPRSSSSST22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/KashiNKSLA22, author = {Aditya Kashi and Pratik Nayak and Dhruva Kulkarni and Aaron Scheinberg and Paul Lin and Hartwig Anzt}, title = {Batched sparse iterative solvers on {GPU} for the collision operator for fusion plasma simulations}, booktitle = {2022 {IEEE} International Parallel and Distributed Processing Symposium, {IPDPS} 2022, Lyon, France, May 30 - June 3, 2022}, pages = {157--167}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IPDPS53621.2022.00024}, doi = {10.1109/IPDPS53621.2022.00024}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/KashiNKSLA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppam/TsaiBA22, author = {Yu{-}Hsiang Mike Tsai and Natalie Beams and Hartwig Anzt}, editor = {Roman Wyrzykowski and Jack J. Dongarra and Ewa Deelman and Konrad Karczewski}, title = {Mixed Precision Algebraic Multigrid on GPUs}, booktitle = {Parallel Processing and Applied Mathematics - 14th International Conference, {PPAM} 2022, Gdansk, Poland, September 11-14, 2022, Revised Selected Papers, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {13826}, pages = {113--125}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-30442-2\_9}, doi = {10.1007/978-3-031-30442-2\_9}, timestamp = {Wed, 17 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ppam/TsaiBA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppsc/FunkGA22, author = {Yannick Funk and Markus G{\"{o}}tz and Hartwig Anzt}, editor = {Xiaoye S. Li and Keita Teranishi}, title = {Prediction of Optimal Solvers for Sparse Linear Systems Using Deep Learning}, booktitle = {Proceedings of the 2022 {SIAM} Conference on Parallel Processing for Scientific Computing, {PPSC} 2022, Seattle, WA, USA, February 23-26, 2022}, pages = {14--24}, publisher = {{SIAM}}, year = {2022}, url = {https://doi.org/10.1137/1.9781611977141.2}, doi = {10.1137/1.9781611977141.2}, timestamp = {Thu, 21 Apr 2022 15:52:13 +0200}, biburl = {https://dblp.org/rec/conf/ppsc/FunkGA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/TsaiNCA22, author = {Yu{-}Hsiang Mike Tsai and Pratik Nayak and Edmond Chow and Hartwig Anzt}, title = {Implementing Asynchronous Jacobi Iteration on GPUs}, booktitle = {{IEEE/ACM} Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems, ScalAH@SC 2022, Dallas, TX, USA, November 13-18, 2022}, pages = {1--9}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ScalAH56622.2022.00006}, doi = {10.1109/SCALAH56622.2022.00006}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/TsaiNCA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/smc2/AggarwalNKA22, author = {Isha Aggarwal and Pratik Nayak and Aditya Kashi and Hartwig Anzt}, editor = {Douglas B. Kothe and Al Geist and Swaroop Pophale and Hong Liu and Suzanne Parete{-}Koon}, title = {Preconditioners for Batched Iterative Linear Solvers on GPUs}, booktitle = {Accelerating Science and Engineering Discoveries Through Integrated Research Infrastructure for Experiment, Big Data, Modeling and Simulation - 22nd Smoky Mountains Computational Sciences and Engineering Conference, {SMC} 2022, Virtual Event, August 23-25, 2022, Revised Selected Papers}, series = {Communications in Computer and Information Science}, volume = {1690}, pages = {38--53}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-23606-8\_3}, doi = {10.1007/978-3-031-23606-8\_3}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/smc2/AggarwalNKA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/supercomputer/2022w, editor = {Hartwig Anzt and Amanda Bienz and Piotr Luszczek and Marc Baboulin}, title = {High Performance Computing. {ISC} High Performance 2022 International Workshops - Hamburg, Germany, May 29 - June 2, 2022, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {13387}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-23220-6}, doi = {10.1007/978-3-031-23220-6}, isbn = {978-3-031-23219-0}, timestamp = {Sat, 13 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/supercomputer/2022w.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/NayakCA21, author = {Pratik Nayak and Terry Cojean and Hartwig Anzt}, title = {Evaluating asynchronous Schwarz solvers on GPUs}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {35}, number = {3}, year = {2021}, url = {https://doi.org/10.1177/1094342020946814}, doi = {10.1177/1094342020946814}, timestamp = {Wed, 19 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/NayakCA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AbdelfattahABCC21, author = {Ahmad Abdelfattah and Hartwig Anzt and Erik G. Boman and Erin C. Carson and Terry Cojean and Jack J. Dongarra and Alyson Fox and Mark Gates and Nicholas J. Higham and Xiaoye S. Li and Jennifer A. Loe and Piotr Luszczek and Srikara Pranesh and Siva Rajamanickam and Tobias Ribizel and Barry F. Smith and Kasia Swirydowicz and Stephen J. Thomas and Stanimire Tomov and Yaohung M. Tsai and Ulrike Meier Yang}, title = {A survey of numerical linear algebra methods utilizing mixed-precision arithmetic}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {35}, number = {4}, year = {2021}, url = {https://doi.org/10.1177/10943420211003313}, doi = {10.1177/10943420211003313}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijhpca/AbdelfattahABCC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jocs/AnztKF21, author = {Hartwig Anzt and Eileen Kuehn and Goran Flegar}, title = {Crediting pull requests to open source research software as an academic contribution}, journal = {J. Comput. Sci.}, volume = {49}, pages = {101278}, year = {2021}, url = {https://doi.org/10.1016/j.jocs.2020.101278}, doi = {10.1016/J.JOCS.2020.101278}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jocs/AnztKF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/toms/FlegarACQ21, author = {Goran Flegar and Hartwig Anzt and Terry Cojean and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Adaptive Precision Block-Jacobi for High Performance Preconditioning in the Ginkgo Linear Algebra Software}, journal = {{ACM} Trans. Math. Softw.}, volume = {47}, number = {2}, pages = {14:1--14:28}, year = {2021}, url = {https://doi.org/10.1145/3441850}, doi = {10.1145/3441850}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/toms/FlegarACQ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/TsaiCA21, author = {Yuhsiang M. Tsai and Terry Cojean and Hartwig Anzt}, editor = {Ricardo Chaves and Dora B. Heras and Aleksandar Ilic and Didem Unat and Rosa M. Badia and Andrea Bracciali and Patrick Diehl and Anshu Dubey and Oh Sangyoon and Stephen L. Scott and Laura Ricci}, title = {Porting Sparse Linear Algebra to Intel GPUs}, booktitle = {Euro-Par 2021: Parallel Processing Workshops - Euro-Par 2021 International Workshops, Lisbon, Portugal, August 30-31, 2021, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {13098}, pages = {57--68}, publisher = {Springer}, year = {2021}, url = {https://doi.org/10.1007/978-3-031-06156-1\_5}, doi = {10.1007/978-3-031-06156-1\_5}, timestamp = {Tue, 14 Feb 2023 22:22:15 +0100}, biburl = {https://dblp.org/rec/conf/europar/TsaiCA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/GobelGRA21, author = {Fritz G{\"{o}}bel and Thomas Gr{\"{u}}tzmacher and Tobias Ribizel and Hartwig Anzt}, editor = {Leonel Sousa and Nuno Roma and Pedro Tom{\'{a}}s}, title = {Mixed Precision Incomplete and Factorized Sparse Approximate Inverse Preconditioning on GPUs}, 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 = {550--564}, publisher = {Springer}, year = {2021}, url = {https://doi.org/10.1007/978-3-030-85665-6\_34}, doi = {10.1007/978-3-030-85665-6\_34}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/europar/GobelGRA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccS/NayakGA21, author = {Pratik Nayak and Fritz G{\"{o}}bel and Hartwig Anzt}, editor = {Maciej Paszynski and Dieter Kranzlm{\"{u}}ller and Valeria V. Krzhizhanovskaya and Jack J. Dongarra and Peter M. A. Sloot}, title = {A Collaborative Peer Review Process for Grading Coding Assignments}, booktitle = {Computational Science - {ICCS} 2021 - 21st International Conference, Krakow, Poland, June 16-18, 2021, Proceedings, Part {VI}}, series = {Lecture Notes in Computer Science}, volume = {12747}, pages = {654--660}, publisher = {Springer}, year = {2021}, url = {https://doi.org/10.1007/978-3-030-77980-1\_49}, doi = {10.1007/978-3-030-77980-1\_49}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iccS/NayakGA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/scala-ws/AggarwalKNBWA21, author = {Isha Aggarwal and Aditya Kashi and Pratik Nayak and Cody J. Balos and Carol S. Woodward and Hartwig Anzt}, title = {Batched Sparse Iterative Solvers for Computational Chemistry Simulations on GPUs}, booktitle = {12th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2021, St. Louis, MN, USA, November 19, 2021}, pages = {35--43}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ScalA54577.2021.00010}, doi = {10.1109/SCALA54577.2021.00010}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/scala-ws/AggarwalKNBWA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/supercomputer/2021w, editor = {Heike Jagode and Hartwig Anzt and Hatem Ltaief and Piotr Luszczek}, title = {High Performance Computing - {ISC} High Performance Digital 2021 International Workshops, Frankfurt am Main, Germany, June 24 - July 2, 2021, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {12761}, publisher = {Springer}, year = {2021}, url = {https://doi.org/10.1007/978-3-030-90539-2}, doi = {10.1007/978-3-030-90539-2}, isbn = {978-3-030-90538-5}, timestamp = {Wed, 17 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/supercomputer/2021w.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-10883, author = {Daniel S. Katz and Morane Gruenpeter and Tom Honeyman and Lorraine J. Hwang and Mark D. Wilkinson and Vanessa V. Sochat and Hartwig Anzt and Carole A. Goble}, title = {A Fresh Look at {FAIR} for Research Software}, journal = {CoRR}, volume = {abs/2101.10883}, year = {2021}, url = {https://arxiv.org/abs/2101.10883}, eprinttype = {arXiv}, eprint = {2101.10883}, timestamp = {Tue, 27 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-10883.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-10116, author = {Yuhsiang M. Tsai and Terry Cojean and Hartwig Anzt}, title = {Porting a sparse linear algebra math library to Intel GPUs}, journal = {CoRR}, volume = {abs/2103.10116}, year = {2021}, url = {https://arxiv.org/abs/2103.10116}, eprinttype = {arXiv}, eprint = {2103.10116}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-10116.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/GrutzmacherCFGA20, author = {Thomas Gr{\"{u}}tzmacher and Terry Cojean and Goran Flegar and Fritz G{\"{o}}bel and Hartwig Anzt}, title = {A customized precision format based on mantissa segmentation for accelerating sparse linear algebra}, journal = {Concurr. Comput. Pract. Exp.}, volume = {32}, number = {15}, year = {2020}, url = {https://doi.org/10.1002/cpe.5418}, doi = {10.1002/CPE.5418}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/concurrency/GrutzmacherCFGA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jossw/AnztCCFGGNRT20, author = {Hartwig Anzt and Terry Cojean and Yen{-}Chen Chen and Goran Flegar and Fritz G{\"{o}}bel and Thomas Gr{\"{u}}tzmacher and Pratik Nayak and Tobias Ribizel and Yuhsiang M. Tsai}, title = {Ginkgo: {A} high performance numerical linear algebra library}, journal = {J. Open Source Softw.}, volume = {5}, number = {52}, pages = {2260}, year = {2020}, url = {https://doi.org/10.21105/joss.02260}, doi = {10.21105/JOSS.02260}, timestamp = {Tue, 16 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jossw/AnztCCFGGNRT20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/RibizelA20, author = {Tobias Ribizel and Hartwig Anzt}, title = {Parallel selection on GPUs}, journal = {Parallel Comput.}, volume = {91}, year = {2020}, url = {https://doi.org/10.1016/j.parco.2019.102588}, doi = {10.1016/J.PARCO.2019.102588}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pc/RibizelA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/topc/AnztCYDFNTTW20, author = {Hartwig Anzt and Terry Cojean and Chen Yen{-}Chen and Jack J. Dongarra and Goran Flegar and Pratik Nayak and Stanimire Tomov and Yuhsiang M. Tsai and Weichung Wang}, title = {Load-balancing Sparse Matrix Vector Product Kernels on GPUs}, journal = {{ACM} Trans. Parallel Comput.}, volume = {7}, number = {1}, pages = {2:1--2:26}, year = {2020}, url = {https://doi.org/10.1145/3380930}, doi = {10.1145/3380930}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/topc/AnztCYDFNTTW20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/topc/GrutzmacherCFAQ20, author = {Thomas Gr{\"{u}}tzmacher and Terry Cojean and Goran Flegar and Hartwig Anzt and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Acceleration of PageRank with Customized Precision Based on Mantissa Segmentation}, journal = {{ACM} Trans. Parallel Comput.}, volume = {7}, number = {1}, pages = {4:1--4:19}, year = {2020}, url = {https://doi.org/10.1145/3380934}, doi = {10.1145/3380934}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/topc/GrutzmacherCFAQ20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/AliagaAQTT20, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s and Yuhsiang M. Tsai}, editor = {Bartosz Balis and Dora B. Heras and Laura Antonelli and Andrea Bracciali and Thomas Gruber and Jin Hyun{-}Wook and Michael Kuhn and Stephen L. Scott and Didem Unat and Roman Wyrzykowski}, title = {Balanced and Compressed Coordinate Layout for the Sparse Matrix-Vector Product on GPUs}, booktitle = {Euro-Par 2020: Parallel Processing Workshops - Euro-Par 2020 International Workshops, Warsaw, Poland, August 24-25, 2020, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {12480}, pages = {83--95}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-71593-9\_7}, doi = {10.1007/978-3-030-71593-9\_7}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/europar/AliagaAQTT20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/TsaiCRA20, author = {Yuhsiang M. Tsai and Terry Cojean and Tobias Ribizel and Hartwig Anzt}, editor = {Bartosz Balis and Dora B. Heras and Laura Antonelli and Andrea Bracciali and Thomas Gruber and Jin Hyun{-}Wook and Michael Kuhn and Stephen L. Scott and Didem Unat and Roman Wyrzykowski}, title = {Preparing Ginkgo for {AMD} GPUs - {A} Testimonial on Porting {CUDA} Code to {HIP}}, booktitle = {Euro-Par 2020: Parallel Processing Workshops - Euro-Par 2020 International Workshops, Warsaw, Poland, August 24-25, 2020, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {12480}, pages = {109--121}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-71593-9\_9}, doi = {10.1007/978-3-030-71593-9\_9}, timestamp = {Tue, 23 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/europar/TsaiCRA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/GobelACFQ20, author = {Fritz G{\"{o}}bel and Hartwig Anzt and Terry Cojean and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Maciej Malawski and Krzysztof Rzadca}, title = {Multiprecision Block-Jacobi for Iterative Triangular Solves}, booktitle = {Euro-Par 2020: Parallel Processing - 26th International Conference on Parallel and Distributed Computing, Warsaw, Poland, August 24-28, 2020, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {12247}, pages = {546--560}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-57675-2\_34}, doi = {10.1007/978-3-030-57675-2\_34}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/europar/GobelACFQ20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpec/LuszczekTLAD20, author = {Piotr Luszczek and Yaohung M. Tsai and Neil Lindquist and Hartwig Anzt and Jack J. Dongarra}, title = {Scalable Data Generation for Evaluating Mixed-Precision Solvers}, booktitle = {2020 {IEEE} High Performance Extreme Computing Conference, {HPEC} 2020, Waltham, MA, USA, September 22-24, 2020}, pages = {1--6}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/HPEC43674.2020.9286145}, doi = {10.1109/HPEC43674.2020.9286145}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hpec/LuszczekTLAD20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pmbs-ws/AnztTACD20, author = {Hartwig Anzt and Yuhsiang M. Tsai and Ahmad Abdelfattah and Terry Cojean and Jack J. Dongarra}, title = {Evaluating the Performance of NVIDIA's {A100} Ampere {GPU} for Sparse and Batched Computations}, booktitle = {2020 {IEEE/ACM} Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, PMBS@SC 2020, Atlanta, GA, USA, November 12, 2020}, pages = {26--38}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/PMBS51919.2020.00009}, doi = {10.1109/PMBS51919.2020.00009}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/pmbs-ws/AnztTACD20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/scala-ws/NayakCA20, author = {Pratik Nayak and Terry Cojean and Hartwig Anzt}, title = {Two-stage Asynchronous Iterative Solvers for multi-GPU Clusters}, booktitle = {11th {IEEE/ACM} Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2020, Atlanta, GA, USA, November 13, 2020}, pages = {9--18}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ScalA51936.2020.00007}, doi = {10.1109/SCALA51936.2020.00007}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/scala-ws/NayakCA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/supercomputer/TsaiCA20, author = {Yuhsiang M. Tsai and Terry Cojean and Hartwig Anzt}, editor = {Ponnuswamy Sadayappan and Bradford L. Chamberlain and Guido Juckeland and Hatem Ltaief}, title = {Sparse Linear Algebra on {AMD} and {NVIDIA} GPUs - The Race Is On}, booktitle = {High Performance Computing - 35th International Conference, {ISC} High Performance 2020, Frankfurt/Main, Germany, June 22-25, 2020, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {12151}, pages = {309--327}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-50743-5\_16}, doi = {10.1007/978-3-030-50743-5\_16}, timestamp = {Fri, 14 May 2021 08:34:20 +0200}, biburl = {https://dblp.org/rec/conf/supercomputer/TsaiCA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/supercomputer/2020w, editor = {Heike Jagode and Hartwig Anzt and Guido Juckeland and Hatem Ltaief}, title = {High Performance Computing - {ISC} High Performance 2020 International Workshops, Frankfurt, Germany, June 21-25, 2020, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {12321}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-59851-8}, doi = {10.1007/978-3-030-59851-8}, isbn = {978-3-030-59850-1}, timestamp = {Tue, 20 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/supercomputer/2020w.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-05361, author = {Pratik Nayak and Terry Cojean and Hartwig Anzt}, title = {Evaluating Abstract Asynchronous Schwarz solvers}, journal = {CoRR}, volume = {abs/2003.05361}, year = {2020}, url = {https://arxiv.org/abs/2003.05361}, eprinttype = {arXiv}, eprint = {2003.05361}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-05361.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-01469, author = {Hartwig Anzt and Felix Bach and Stephan Druskat and Frank L{\"{o}}ffler and Axel Loewe and Bernhard Y. Renard and Gunnar Seemann and Alexander Struck and Elke Achhammer and Piush Aggarwal and Franziska Appel and Michael Bader and Lutz Brusch and Christian Busse and Gerasimos Chourdakis and Piotr Wojtek Dabrowski and Peter Ebert and Bernd Flemisch and Sven Friedl and Bernadette Fritzsch and Maximilian D. Funk and Volker Gast and Florian Goth and Jean{-}No{\"{e}}l Grad and Sibylle Hermann and Florian Hohmann and Stephan Janosch and Dominik Kutra and Jan Linxweiler and Thilo Muth and Wolfgang Peters{-}Kottig and Fabian Rack and Fabian H. C. Raters and Stephan Rave and Guido Reina and Malte Rei{\ss}ig and Timo Ropinski and J{\"{o}}rg Schaarschmidt and Heidi Seibold and Jan P. Thiele and Benjamin Uekermann and Stefan Unger and Rudolf Weeber}, title = {An Environment for Sustainable Research Software in Germany and Beyond: Current State, Open Challenges, and Call for Action}, journal = {CoRR}, volume = {abs/2005.01469}, year = {2020}, url = {https://arxiv.org/abs/2005.01469}, eprinttype = {arXiv}, eprint = {2005.01469}, timestamp = {Sun, 21 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-01469.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-14290, author = {Yuhsiang M. Tsai and Terry Cojean and Tobias Ribizel and Hartwig Anzt}, title = {Preparing Ginkgo for {AMD} GPUs - {A} Testimonial on Porting {CUDA} Code to {HIP}}, journal = {CoRR}, volume = {abs/2006.14290}, year = {2020}, url = {https://arxiv.org/abs/2006.14290}, eprinttype = {arXiv}, eprint = {2006.14290}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-14290.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-16852, author = {Hartwig Anzt and Terry Cojean and Goran Flegar and Fritz G{\"{o}}bel and Thomas Gr{\"{u}}tzmacher and Pratik Nayak and Tobias Ribizel and Yu{-}Hsiang Tsai and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Ginkgo: {A} Modern Linear Operator Algebra Framework for High Performance Computing}, journal = {CoRR}, volume = {abs/2006.16852}, year = {2020}, url = {https://arxiv.org/abs/2006.16852}, eprinttype = {arXiv}, eprint = {2006.16852}, timestamp = {Sat, 23 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-16852.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2007-06674, author = {Ahmad Abdelfattah and Hartwig Anzt and Erik G. Boman and Erin C. Carson and Terry Cojean and Jack J. Dongarra and Mark Gates and Thomas Gr{\"{u}}tzmacher and Nicholas J. Higham and Xiaoye Sherry Li and Neil Lindquist and Yang Liu and Jennifer A. Loe and Piotr Luszczek and Pratik Nayak and Srikara Pranesh and Sivasankaran Rajamanickam and Tobias Ribizel and Barry Smith and Kasia Swirydowicz and Stephen J. Thomas and Stanimire Tomov and Yaohung M. Tsai and Ichitaro Yamazaki and Ulrike Meier Yang}, title = {A Survey of Numerical Methods Utilizing Mixed Precision Arithmetic}, journal = {CoRR}, volume = {abs/2007.06674}, year = {2020}, url = {https://arxiv.org/abs/2007.06674}, eprinttype = {arXiv}, eprint = {2007.06674}, timestamp = {Mon, 29 Mar 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2007-06674.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-08478, author = {Yuhsiang Mike Tsai and Terry Cojean and Hartwig Anzt}, title = {Evaluating the Performance of NVIDIA's {A100} Ampere {GPU} for Sparse Linear Algebra Computations}, journal = {CoRR}, volume = {abs/2008.08478}, year = {2020}, url = {https://arxiv.org/abs/2008.08478}, eprinttype = {arXiv}, eprint = {2008.08478}, timestamp = {Sat, 23 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-08478.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2009-12101, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Thomas Gr{\"{u}}tzmacher and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, title = {Compressed Basis {GMRES} on High Performance GPUs}, journal = {CoRR}, volume = {abs/2009.12101}, year = {2020}, url = {https://arxiv.org/abs/2009.12101}, eprinttype = {arXiv}, eprint = {2009.12101}, timestamp = {Wed, 30 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2009-12101.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-13342, author = {Emmanuel Agullo and Mirco Altenbernd and Hartwig Anzt and Leonardo Bautista{-}Gomez and Tommaso Benacchio and Luca Bonaventura and Hans{-}Joachim Bungartz and Sanjay Chatterjee and Florina M. Ciorba and Nathan DeBardeleben and Daniel Drzisga and Sebastian Eibl and Christian Engelmann and Wilfried N. Gansterer and Luc Giraud and Dominik G{\"{o}}ddeke and Marco Heisig and Fabienne J{\'{e}}z{\'{e}}quel and Nils Kohl and Xiaoye Sherry Li and Romain Lion and Miriam Mehl and Paul Mycek and Michael Obersteiner and Enrique S. Quintana{-}Ort{\'{\i}} and Francesco Rizzi and Ulrich R{\"{u}}de and Martin Schulz and Fred Fung and Robert Speck and Linda Stals and Keita Teranishi and Samuel Thibault and Dominik Th{\"{o}}nnes and Andreas Wagner and Barbara I. Wohlmuth}, title = {Resiliency in Numerical Algorithm Design for Extreme Scale Simulations}, journal = {CoRR}, volume = {abs/2010.13342}, year = {2020}, url = {https://arxiv.org/abs/2010.13342}, eprinttype = {arXiv}, eprint = {2010.13342}, timestamp = {Wed, 04 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-13342.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-08879, author = {Terry Cojean and Yu{-}Hsiang Mike Tsai and Hartwig Anzt}, title = {Ginkgo - {A} Math Library designed for Platform Portability}, journal = {CoRR}, volume = {abs/2011.08879}, year = {2020}, url = {https://arxiv.org/abs/2011.08879}, eprinttype = {arXiv}, eprint = {2011.08879}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-08879.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/f1000research/AnztBDLLRSSAAABBBCDEFFFFG20, author = {Hartwig Anzt and Felix Bach and Stephan Druskat and Frank L{\"{o}}ffler and Axel Loewe and Bernhard Y. Renard and Gunnar Seemann and Alexander Struck and Elke Achhammer and Piush Aggarwal and Franziska Appel and Michael Bader and Lutz Brusch and Christian Busse and Gerasimos Chourdakis and Piotr Wojciech Dabrowski and Peter Ebert and Bernd Flemisch and Sven Friedl and Bernadette Fritzsch and Maximilian D. Funk and Volker Gast and Florian Goth and Jean{-}No{\"{e}}l Grad and Sibylle Hermann and Florian Hohmann and Stephan Janosch and Dominik Kutra and Jan Linxweiler and Thilo Muth and Wolfgang Peters{-}Kottig and Fabian Rack and Fabian H. C. Raters and Stephan Rave and Guido Reina and Malte Rei{\ss}ig and Timo Ropinski and J{\"{o}}rg Schaarschmidt and Heidi Seibold and Jan P. Thiele and Benjamin Uekermann and Stefan Unger and Rudolf Weeber}, title = {An environment for sustainable research software in Germany and beyond: current state, open challenges, and call for action}, journal = {F1000Research}, volume = {9}, pages = {295}, year = {2020}, url = {https://doi.org/10.12688/f1000research.23224.1}, doi = {10.12688/F1000RESEARCH.23224.1}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/f1000research/AnztBDLLRSSAAABBBCDEFFFFG20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/AnztDFHQ19, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Nicholas J. Higham and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers}, journal = {Concurr. Comput. Pract. Exp.}, volume = {31}, number = {6}, year = {2019}, url = {https://doi.org/10.1002/cpe.4460}, doi = {10.1002/CPE.4460}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/concurrency/AnztDFHQ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AnztFGQ19, author = {Hartwig Anzt and Goran Flegar and Thomas Gr{\"{u}}tzmacher and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Toward a modular precision ecosystem for high-performance computing}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {33}, number = {6}, year = {2019}, url = {https://doi.org/10.1177/1094342019846547}, doi = {10.1177/1094342019846547}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/AnztFGQ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/JagodeDAD19, author = {Heike Jagode and Anthony Danalis and Hartwig Anzt and Jack J. Dongarra}, title = {{PAPI} software-defined events for in-depth performance analysis}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {33}, number = {6}, year = {2019}, url = {https://doi.org/10.1177/1094342019846287}, doi = {10.1177/1094342019846287}, timestamp = {Thu, 12 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijhpca/JagodeDAD19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jocs/AnztDQ19, author = {Hartwig Anzt and Jack J. Dongarra and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Fine-grained bit-flip protection for relaxation methods}, journal = {J. Comput. Sci.}, volume = {36}, year = {2019}, url = {https://doi.org/10.1016/j.jocs.2016.11.013}, doi = {10.1016/J.JOCS.2016.11.013}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jocs/AnztDQ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/AnztDFQ19, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Variable-size batched Gauss-Jordan elimination for block-Jacobi preconditioning on graphics processors}, journal = {Parallel Comput.}, volume = {81}, pages = {131--146}, year = {2019}, url = {https://doi.org/10.1016/j.parco.2017.12.006}, doi = {10.1016/J.PARCO.2017.12.006}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pc/AnztDFQ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztRFCD19, author = {Hartwig Anzt and Tobias Ribizel and Goran Flegar and Edmond Chow and Jack J. Dongarra}, title = {ParILUT - {A} Parallel Threshold {ILU} for GPUs}, booktitle = {2019 {IEEE} International Parallel and Distributed Processing Symposium, {IPDPS} 2019, Rio de Janeiro, Brazil, May 20-24, 2019}, pages = {231--241}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IPDPS.2019.00033}, doi = {10.1109/IPDPS.2019.00033}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/AnztRFCD19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/RibizelA19, author = {Tobias Ribizel and Hartwig Anzt}, title = {Approximate and Exact Selection on GPUs}, booktitle = {{IEEE} International Parallel and Distributed Processing Symposium Workshops, {IPDPSW} 2019, Rio de Janeiro, Brazil, May 20-24, 2019}, pages = {471--478}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IPDPSW.2019.00088}, doi = {10.1109/IPDPSW.2019.00088}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/RibizelA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztF19, author = {Hartwig Anzt and Goran Flegar}, title = {Are we Doing the Right Thing? - {A} Critical Analysis of the Academic {HPC} Community}, booktitle = {{IEEE} International Parallel and Distributed Processing Symposium Workshops, {IPDPSW} 2019, Rio de Janeiro, Brazil, May 20-24, 2019}, pages = {739--745}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IPDPSW.2019.00122}, doi = {10.1109/IPDPSW.2019.00122}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/AnztF19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pasc/AnztCCDFNQTW19, author = {Hartwig Anzt and Yen{-}Chen Chen and Terry Cojean and Jack J. Dongarra and Goran Flegar and Pratik Nayak and Enrique S. Quintana{-}Ort{\'{\i}} and Yuhsiang M. Tsai and Weichung Wang}, title = {Towards Continuous Benchmarking: An Automated Performance Evaluation Framework for High Performance Software}, booktitle = {Proceedings of the Platform for Advanced Scientific Computing Conference, {PASC} 2019, Zurich, Switzerland, June 12-14, 2019}, pages = {9:1--9:11}, publisher = {{ACM}}, year = {2019}, url = {https://doi.org/10.1145/3324989.3325719}, doi = {10.1145/3324989.3325719}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/pasc/AnztCCDFNQTW19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AnztKPPWD18, author = {Hartwig Anzt and Moritz Kreutzer and Eduardo Ponce and Gregory D. Peterson and Gerhard Wellein and Jack J. Dongarra}, title = {Optimization and performance evaluation of the {IDR} iterative Krylov solver on GPUs}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {32}, number = {2}, pages = {220--230}, year = {2018}, url = {https://doi.org/10.1177/1094342016646844}, doi = {10.1177/1094342016646844}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhpca/AnztKPPWD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jpdc/ChowASD18, author = {Edmond Chow and Hartwig Anzt and Jennifer A. Scott and Jack J. Dongarra}, title = {Using Jacobi iterations and blocking for solving sparse triangular systems in incomplete factorization preconditioning}, journal = {J. Parallel Distributed Comput.}, volume = {119}, pages = {219--230}, year = {2018}, url = {https://doi.org/10.1016/j.jpdc.2018.04.017}, doi = {10.1016/J.JPDC.2018.04.017}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jpdc/ChowASD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/AnztHBD18, author = {Hartwig Anzt and Thomas K. Huckle and J{\"{u}}rgen Br{\"{a}}ckle and Jack J. Dongarra}, title = {Incomplete Sparse Approximate Inverses for Parallel Preconditioning}, journal = {Parallel Comput.}, volume = {71}, pages = {1--22}, year = {2018}, url = {https://doi.org/10.1016/j.parco.2017.10.003}, doi = {10.1016/J.PARCO.2017.10.003}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pc/AnztHBD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/siamsc/AnztCD18, author = {Hartwig Anzt and Edmond Chow and Jack J. Dongarra}, title = {ParILUT - {A} New Parallel Threshold {ILU} Factorization}, journal = {{SIAM} J. Sci. Comput.}, volume = {40}, number = {4}, pages = {C503--C519}, year = {2018}, url = {https://doi.org/10.1137/16M1079506}, doi = {10.1137/16M1079506}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/siamsc/AnztCD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/GrutzmacherA18, author = {Thomas Gr{\"{u}}tzmacher and Hartwig Anzt}, editor = {Gabriele Mencagli and Dora B. Heras and Valeria Cardellini and Emiliano Casalicchio and Emmanuel Jeannot and Felix Wolf and Antonio Salis and Claudio Schifanella and Ravi Reddy Manumachu and Laura Ricci and Marco Beccuti and Laura Antonelli and Jos{\'{e}} Daniel Garc{\'{\i}}a S{\'{a}}nchez and Stephen L. Scott}, title = {A Modular Precision Format for Decoupling Arithmetic Format and Storage Format}, booktitle = {Euro-Par 2018: Parallel Processing Workshops - Euro-Par 2018 International Workshops, Turin, Italy, August 27-28, 2018, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {11339}, pages = {434--443}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-3-030-10549-5\_34}, doi = {10.1007/978-3-030-10549-5\_34}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/europar/GrutzmacherA18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sbac-pad/AnztDFG18, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Thomas Gr{\"{u}}tzmacher}, title = {Variable-Size Batched Condition Number Calculation on GPUs}, booktitle = {30th International Symposium on Computer Architecture and High Performance Computing, {SBAC-PAD} 2018, Lyon, France, September 24-27, 2018}, pages = {132--139}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/CAHPC.2018.8645907}, doi = {10.1109/CAHPC.2018.8645907}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/sbac-pad/AnztDFG18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sbac-pad/AnztD18, author = {Hartwig Anzt and Jack J. Dongarra}, title = {A Jaccard Weights Kernel Leveraging Independent Thread Scheduling on GPUs}, booktitle = {30th International Symposium on Computer Architecture and High Performance Computing, {SBAC-PAD} 2018, Lyon, France, September 24-27, 2018}, pages = {229--232}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/CAHPC.2018.8645946}, doi = {10.1109/CAHPC.2018.8645946}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sbac-pad/AnztD18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/GrutzmacherASQ18, author = {Thomas Gr{\"{u}}tzmacher and Hartwig Anzt and Florian Scheidegger and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {High-Performance {GPU} Implementation of PageRank with Reduced Precision Based on Mantissa Segmentation}, booktitle = {8th {IEEE/ACM} Workshop on Irregular Applications: Architectures and Algorithms, IA3@SC 2018, Dallas, TX, USA, November 12, 2018}, pages = {61--68}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/IA3.2018.00015}, doi = {10.1109/IA3.2018.00015}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/sc/GrutzmacherASQ18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/supercomputer/AnztFNQT18, author = {Hartwig Anzt and Goran Flegar and Vedran Novakovic and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, editor = {Rio Yokota and Mich{\`{e}}le Weiland and John Shalf and Sadaf R. Alam}, title = {Residual Replacement in Mixed-Precision Iterative Refinement for Sparse Linear Systems}, booktitle = {High Performance Computing - {ISC} High Performance 2018 International Workshops, Frankfurt/Main, Germany, June 28, 2018, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {11203}, pages = {554--561}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-3-030-02465-9\_39}, doi = {10.1007/978-3-030-02465-9\_39}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/supercomputer/AnztFNQT18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cse/DongarraTLKGYAH17, author = {Jack J. Dongarra and Stanimire Tomov and Piotr Luszczek and Jakub Kurzak and Mark Gates and Ichitaro Yamazaki and Hartwig Anzt and Azzam Haidar and Ahmad Abdelfattah}, title = {With Extreme Computing, the Rules Have Changed}, journal = {Comput. Sci. Eng.}, volume = {19}, number = {3}, pages = {52--62}, year = {2017}, url = {https://doi.org/10.1109/MCSE.2017.48}, doi = {10.1109/MCSE.2017.48}, timestamp = {Tue, 16 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/cse/DongarraTLKGYAH17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AnztTD17, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra}, title = {On the performance and energy efficiency of sparse linear algebra on GPUs}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {31}, number = {5}, pages = {375--390}, year = {2017}, url = {https://doi.org/10.1177/1094342016672081}, doi = {10.1177/1094342016672081}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijhpca/AnztTD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/AnztGDKWK17, author = {Hartwig Anzt and Mark Gates and Jack J. Dongarra and Moritz Kreutzer and Gerhard Wellein and Martin Koehler}, title = {Preconditioned Krylov solvers on GPUs}, journal = {Parallel Comput.}, volume = {68}, pages = {32--44}, year = {2017}, url = {https://doi.org/10.1016/j.parco.2017.05.006}, doi = {10.1016/J.PARCO.2017.05.006}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pc/AnztGDKWK17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccS/AnztDFQT17, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}} and Andr{\'{e}}s E. Tom{\'{a}}s}, editor = {Petros Koumoutsakos and Michael Lees and Valeria V. Krzhizhanovskaya and Jack J. Dongarra and Peter M. A. Sloot}, title = {Variable-Size Batched Gauss-Huard for Block-Jacobi Preconditioning}, booktitle = {International Conference on Computational Science, {ICCS} 2017, 12-14 June 2017, Zurich, Switzerland}, series = {Procedia Computer Science}, volume = {108}, pages = {1783--1792}, publisher = {Elsevier}, year = {2017}, url = {https://doi.org/10.1016/j.procs.2017.05.186}, doi = {10.1016/J.PROCS.2017.05.186}, timestamp = {Thu, 08 Jul 2021 16:04:01 +0200}, biburl = {https://dblp.org/rec/conf/iccS/AnztDFQT17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpp/AnztDFQ17, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Variable-Size Batched {LU} for Small Matrices and Its Integration into Block-Jacobi Preconditioning}, booktitle = {46th International Conference on Parallel Processing, {ICPP} 2017, Bristol, United Kingdom, August 14-17, 2017}, pages = {91--100}, publisher = {{IEEE} Computer Society}, year = {2017}, url = {https://doi.org/10.1109/ICPP.2017.18}, doi = {10.1109/ICPP.2017.18}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpp/AnztDFQ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppopp/AnztDFQ17, author = {Hartwig Anzt and Jack J. Dongarra and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Quan Chen and Zhiyi Huang}, title = {Batched Gauss-Jordan Elimination for Block-Jacobi Preconditioner Generation on GPUs}, booktitle = {Proceedings of the 8th International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM@PPoPP 2017, Austin, TX, USA, February 5, 2017}, pages = {1--10}, publisher = {{ACM}}, year = {2017}, url = {https://doi.org/10.1145/3026937.3026940}, doi = {10.1145/3026937.3026940}, timestamp = {Sun, 12 Jun 2022 19:46:08 +0200}, biburl = {https://dblp.org/rec/conf/ppopp/AnztDFQ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/FlegarA17, author = {Goran Flegar and Hartwig Anzt}, title = {Overcoming Load Imbalance for Irregular Sparse Matrices}, booktitle = {Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms, IA3@SC 2017, Denver, CO, USA, November 12 - 17, 2017}, pages = {2:1--2:8}, publisher = {{ACM}}, year = {2017}, url = {https://doi.org/10.1145/3149704.3149767}, doi = {10.1145/3149704.3149767}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/FlegarA17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AnztCDFQ17, author = {Hartwig Anzt and Gary Collins and Jack J. Dongarra and Goran Flegar and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Vassil Alexandrov and Al Geist and Jack J. Dongarra}, title = {Flexible batched sparse matrix-vector product on GPUs}, booktitle = {Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2017, Denver, CO, USA, November 13, 2017}, pages = {3:1--3:8}, publisher = {{ACM}}, year = {2017}, url = {https://doi.org/10.1145/3148226.3148230}, doi = {10.1145/3148226.3148230}, timestamp = {Wed, 12 Jul 2023 15:16:18 +0200}, biburl = {https://dblp.org/rec/conf/sc/AnztCDFQ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:books/sp/17/AnztDGKLTY17, author = {Hartwig Anzt and Jack J. Dongarra and Mark Gates and Jakub Kurzak and Piotr Luszczek and Stanimire Tomov and Ichitaro Yamazaki}, editor = {Albert Y. Zomaya and Sherif Sakr}, title = {Bringing High Performance Computing to Big Data Algorithms}, booktitle = {Handbook of Big Data Technologies}, pages = {777--806}, publisher = {Springer}, year = {2017}, url = {https://doi.org/10.1007/978-3-319-49340-4\_23}, doi = {10.1007/978-3-319-49340-4\_23}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/books/sp/17/AnztDGKLTY17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/actanum/AbdelfattahADGH16, author = {Ahmad Abdelfattah and Hartwig Anzt and Jack J. Dongarra and Mark Gates and Azzam Haidar and Jakub Kurzak and Piotr Luszczek and Stanimire Tomov and Ichitaro Yamazaki and Asim YarKhan}, title = {Linear algebra software for large-scale accelerated multicore computing}, journal = {Acta Numer.}, volume = {25}, pages = {1--160}, year = {2016}, url = {https://doi.org/10.1017/S0962492916000015}, doi = {10.1017/S0962492916000015}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/actanum/AbdelfattahADGH16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/na/AnztCSD16, author = {Hartwig Anzt and Edmond Chow and Jens Saak and Jack J. Dongarra}, title = {Updating incomplete factorization preconditioners for model order reduction}, journal = {Numer. Algorithms}, volume = {73}, number = {3}, pages = {611--630}, year = {2016}, url = {https://doi.org/10.1007/s11075-016-0110-2}, doi = {10.1007/S11075-016-0110-2}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/na/AnztCSD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tpds/KurzakAGD16, author = {Jakub Kurzak and Hartwig Anzt and Mark Gates and Jack J. Dongarra}, title = {Implementation and Tuning of Batched Cholesky Factorization and Solve for {NVIDIA} GPUs}, journal = {{IEEE} Trans. Parallel Distributed Syst.}, volume = {27}, number = {7}, pages = {2036--2048}, year = {2016}, url = {https://doi.org/10.1109/TPDS.2015.2481890}, doi = {10.1109/TPDS.2015.2481890}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tpds/KurzakAGD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/NewburnBWCPDSBL16, author = {Chris J. Newburn and Gaurav Bansal and Michael Wood and Luis Crivelli and Judit Planas and Alejandro Duran and Paulo Souza and Leonardo Borges and Piotr Luszczek and Stanimire Tomov and Jack J. Dongarra and Hartwig Anzt and Mark Gates and Azzam Haidar and Yulu Jia and Khairul Kabir and Ichitaro Yamazaki and Jes{\'{u}}s Labarta}, title = {Heterogeneous Streaming}, booktitle = {2016 {IEEE} International Parallel and Distributed Processing Symposium Workshops, {IPDPS} Workshops 2016, Chicago, IL, USA, May 23-27, 2016}, pages = {611--620}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/IPDPSW.2016.217}, doi = {10.1109/IPDPSW.2016.217}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/NewburnBWCPDSBL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztDKWK16, author = {Hartwig Anzt and Jack J. Dongarra and Moritz Kreutzer and Gerhard Wellein and Martin Koehler}, title = {Efficiency of General Krylov Methods on GPUs - An Experimental Study}, booktitle = {2016 {IEEE} International Parallel and Distributed Processing Symposium Workshops, {IPDPS} Workshops 2016, Chicago, IL, USA, May 23-27, 2016}, pages = {683--691}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/IPDPSW.2016.45}, doi = {10.1109/IPDPSW.2016.45}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ipps/AnztDKWK16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AnztCHD16, author = {Hartwig Anzt and Edmond Chow and Thomas Huckle and Jack J. Dongarra}, title = {Batched Generation of Incomplete Sparse Approximate Inverses on GPUs}, booktitle = {7th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2016, Salt Lake, UT, USA, November 14, 2016}, pages = {49--56}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/ScalA.2016.011}, doi = {10.1109/SCALA.2016.011}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/AnztCHD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/vecpar/AnztBDFHKW16, author = {Hartwig Anzt and Marc Baboulin and Jack J. Dongarra and Yvan Fournier and Frank H{\"{u}}lsemann and Amal Khabou and Yushan Wang}, editor = {In{\^{e}}s Dutra and Rui Camacho and Jorge G. Barbosa and Osni Marques}, title = {Accelerating the Conjugate Gradient Algorithm with GPUs in {CFD} Simulations}, booktitle = {High Performance Computing for Computational Science - {VECPAR} 2016 - 12th International Conference, Porto, Portugal, June 28-30, 2016, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {10150}, pages = {35--43}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-61982-8\_5}, doi = {10.1007/978-3-319-61982-8\_5}, timestamp = {Wed, 24 Mar 2021 17:11:59 +0100}, biburl = {https://dblp.org/rec/conf/vecpar/AnztBDFHKW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/lncse/AnztCSD16, author = {Hartwig Anzt and Edmond Chow and Daniel B. Szyld and Jack J. Dongarra}, editor = {Hans{-}Joachim Bungartz and Philipp Neumann and Wolfgang E. Nagel}, title = {Domain Overlap for Iterative Sparse Triangular Solves on GPUs}, booktitle = {Software for Exascale Computing - {SPPEXA} 2013-2015}, series = {Lecture Notes in Computational Science and Engineering}, volume = {113}, pages = {527--545}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-40528-5\_24}, doi = {10.1007/978-3-319-40528-5\_24}, timestamp = {Thu, 14 Oct 2021 08:45:21 +0200}, biburl = {https://dblp.org/rec/series/lncse/AnztCSD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/AliagaACFLPQ15, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Maribel Castillo and Juan Carlos Fern{\'{a}}ndez and Germ{\'{a}}n Le{\'{o}}n and Joaqu{\'{\i}}n P{\'{e}}rez and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Unveiling the performance-energy trade-off in iterative linear system solvers for multithreaded processors}, journal = {Concurr. Comput. Pract. Exp.}, volume = {27}, number = {4}, pages = {885--904}, year = {2015}, url = {https://doi.org/10.1002/cpe.3341}, doi = {10.1002/CPE.3341}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/concurrency/AliagaACFLPQ15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/concurrency/AnztHKLD15, author = {Hartwig Anzt and Blake Haugen and Jakub Kurzak and Piotr Luszczek and Jack J. Dongarra}, title = {Experiences in autotuning matrix multiplication for energy minimization on GPUs}, journal = {Concurr. Comput. Pract. Exp.}, volume = {27}, number = {17}, pages = {5096--5113}, year = {2015}, url = {https://doi.org/10.1002/cpe.3516}, doi = {10.1002/CPE.3516}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/concurrency/AnztHKLD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/AnztTLSD15, author = {Hartwig Anzt and Stanimire Tomov and Piotr Luszczek and William B. Sawyer and Jack J. Dongarra}, title = {Acceleration of GPU-based Krylov solvers via data transfer reduction}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {29}, number = {3}, pages = {366--383}, year = {2015}, url = {https://doi.org/10.1177/1094342015580139}, doi = {10.1177/1094342015580139}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijhpca/AnztTLSD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/bigdataconf/GatesAKD15, author = {Mark Gates and Hartwig Anzt and Jakub Kurzak and Jack J. Dongarra}, title = {Accelerating collaborative filtering using concepts from high performance computing}, booktitle = {2015 {IEEE} International Conference on Big Data {(IEEE} BigData 2015), Santa Clara, CA, USA, October 29 - November 1, 2015}, pages = {667--676}, publisher = {{IEEE} Computer Society}, year = {2015}, url = {https://doi.org/10.1109/BigData.2015.7363811}, doi = {10.1109/BIGDATA.2015.7363811}, timestamp = {Fri, 19 Nov 2021 16:08:20 +0100}, biburl = {https://dblp.org/rec/conf/bigdataconf/GatesAKD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/AnztCD15, author = {Hartwig Anzt and Edmond Chow and Jack J. Dongarra}, editor = {Jesper Larsson Tr{\"{a}}ff and Sascha Hunold and Francesco Versaci}, title = {Iterative Sparse Triangular Solves for Preconditioning}, 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 = {650--661}, publisher = {Springer}, year = {2015}, url = {https://doi.org/10.1007/978-3-662-48096-0\_50}, doi = {10.1007/978-3-662-48096-0\_50}, timestamp = {Sun, 12 Nov 2023 02:07:45 +0100}, biburl = {https://dblp.org/rec/conf/europar/AnztCD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppopp/AnztTD15, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra}, editor = {Pavan Balaji and Minyi Guo and Zhiyi Huang}, title = {Energy efficiency and performance frontiers for sparse computations on {GPU} supercomputers}, booktitle = {Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM@PPoPP 2015, San Francisco, CA, USA, February 7-8, 2015}, pages = {1--10}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2712386.2712387}, doi = {10.1145/2712386.2712387}, timestamp = {Sun, 12 Jun 2022 19:46:08 +0200}, biburl = {https://dblp.org/rec/conf/ppopp/AnztTD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AnztDQ15a, author = {Hartwig Anzt and Jack J. Dongarra and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Vassil Alexandrov and Al Geist and Jack J. Dongarra}, title = {Tuning stationary iterative solvers for fault resilience}, booktitle = {Proceedings of the 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2015, Austin, Texas, USA, November 15, 2015}, pages = {1:1--1:8}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2832080.2832081}, doi = {10.1145/2832080.2832081}, timestamp = {Mon, 10 Jul 2023 13:10:57 +0200}, biburl = {https://dblp.org/rec/conf/sc/AnztDQ15a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AnztDQ15, author = {Hartwig Anzt and Jack J. Dongarra and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Kirk W. Cameron and Adolfy Hoisie and Darren J. Kerbyson and David K. Lowenthal and Dimitrios S. Nikolopoulos and Sudha Yalamanchili and Laura Carrington and Joseph B. Manzano}, title = {Adaptive precision solvers for sparse linear systems}, booktitle = {Proceedings of the 3rd International Workshop on Energy Efficient Supercomputing, {E2SC} 2015, Austin, Texas, USA, November 15, 2015}, pages = {2:1--2:10}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2834800.2834802}, doi = {10.1145/2834800.2834802}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/AnztDQ15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/AnztPPD15, author = {Hartwig Anzt and Eduardo Ponce and Gregory D. Peterson and Jack J. Dongarra}, title = {GPU-accelerated co-design of induced dimension reduction: algorithmic fusion and kernel overlap}, booktitle = {Proceedings of the 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2015, Austin, Texas, USA, November 15, 2015}, pages = {5:1--5:8}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2834899.2834907}, doi = {10.1145/2834899.2834907}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/AnztPPD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/springsim/AnztTD15, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra}, editor = {Layne T. Watson and Josef Weinbub and Masha Sosonkina and William I. Thacker}, title = {Accelerating the {LOBPCG} method on GPUs using a blocked sparse matrix vector product}, booktitle = {Proceedings of the Symposium on High Performance Computing, {HPC} 2015, part of the 2015 Spring Simulation Multiconference, SpringSim '15, Alexandria, VA, USA, April 12-15, 2015}, pages = {75--82}, publisher = {{SCS/ACM}}, year = {2015}, url = {http://dl.acm.org/citation.cfm?id=2872609}, timestamp = {Mon, 21 Aug 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/springsim/AnztTD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/supercomputer/ChowAD15, author = {Edmond Chow and Hartwig Anzt and Jack J. Dongarra}, editor = {Julian M. Kunkel and Thomas Ludwig}, title = {Asynchronous Iterative Algorithm for Computing Incomplete Factorizations on GPUs}, booktitle = {High Performance Computing - 30th International Conference, {ISC} High Performance 2015, Frankfurt, Germany, July 12-16, 2015, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {9137}, pages = {1--16}, publisher = {Springer}, year = {2015}, url = {https://doi.org/10.1007/978-3-319-20119-1\_1}, doi = {10.1007/978-3-319-20119-1\_1}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/supercomputer/ChowAD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ife/AnztBCFHK14, author = {Hartwig Anzt and Armen Beglarian and Suren Chilingaryan and Andrew Ferrone and Vincent Heuveline and Andreas Kopmann}, title = {A unified energy footprint for simulation software}, journal = {Comput. Sci. Res. Dev.}, volume = {29}, number = {2}, pages = {131--138}, year = {2014}, url = {https://doi.org/10.1007/s00450-012-0225-1}, doi = {10.1007/S00450-012-0225-1}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ife/AnztBCFHK14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/LukarskiATD14, author = {Dimitar Lukarski and Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra}, title = {Hybrid Multi-elimination {ILU} Preconditioners on GPUs}, booktitle = {2014 {IEEE} International Parallel {\&} Distributed Processing Symposium Workshops, Phoenix, AZ, USA, May 19-23, 2014}, pages = {7--16}, publisher = {{IEEE} Computer Society}, year = {2014}, url = {https://doi.org/10.1109/IPDPSW.2014.7}, doi = {10.1109/IPDPSW.2014.7}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/LukarskiATD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/YamazakiATHD14, author = {Ichitaro Yamazaki and Hartwig Anzt and Stanimire Tomov and Mark Hoemmen and Jack J. Dongarra}, title = {Improving the Performance of {CA-GMRES} on Multicores with Multiple GPUs}, booktitle = {2014 {IEEE} 28th International Parallel and Distributed Processing Symposium, Phoenix, AZ, USA, May 19-23, 2014}, pages = {382--391}, publisher = {{IEEE} Computer Society}, year = {2014}, url = {https://doi.org/10.1109/IPDPS.2014.48}, doi = {10.1109/IPDPS.2014.48}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/YamazakiATHD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztSTLYD14, author = {Hartwig Anzt and William B. Sawyer and Stanimire Tomov and Piotr Luszczek and Ichitaro Yamazaki and Jack J. Dongarra}, title = {Optimizing Krylov Subspace Solvers on Graphics Processing Units}, booktitle = {2014 {IEEE} International Parallel {\&} Distributed Processing Symposium Workshops, Phoenix, AZ, USA, May 19-23, 2014}, pages = {941--949}, publisher = {{IEEE} Computer Society}, year = {2014}, url = {https://doi.org/10.1109/IPDPSW.2014.107}, doi = {10.1109/IPDPSW.2014.107}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/AnztSTLYD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/vecpar/AnztLTD14, author = {Hartwig Anzt and Dimitar Lukarski and Stanimire Tomov and Jack J. Dongarra}, editor = {Michel J. Dayd{\'{e}} and Osni Marques and Kengo Nakajima}, title = {Self-adaptive Multiprecision Preconditioners on Multicore and Manycore Architectures}, booktitle = {High Performance Computing for Computational Science - {VECPAR} 2014 - 11th International Conference, Eugene, OR, USA, June 30 - July 3, 2014, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {8969}, pages = {115--123}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-17353-5\_10}, doi = {10.1007/978-3-319-17353-5\_10}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/vecpar/AnztLTD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jpdc/AnztTDH13, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra and Vincent Heuveline}, title = {A block-asynchronous relaxation method for graphics processing units}, journal = {J. Parallel Distributed Comput.}, volume = {73}, number = {12}, pages = {1613--1626}, year = {2013}, url = {https://doi.org/10.1016/j.jpdc.2013.05.008}, doi = {10.1016/J.JPDC.2013.05.008}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jpdc/AnztTDH13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpp/AliagaPQA13, author = {Jos{\'{e}} Ignacio Aliaga and Joaqu{\'{\i}}n P{\'{e}}rez and Enrique S. Quintana{-}Ort{\'{\i}} and Hartwig Anzt}, title = {Reformulated Conjugate Gradient for the Energy-Aware Solution of Linear Systems on GPUs}, booktitle = {42nd International Conference on Parallel Processing, {ICPP} 2013, Lyon, France, October 1-4, 2013}, pages = {320--329}, publisher = {{IEEE} Computer Society}, year = {2013}, url = {https://doi.org/10.1109/ICPP.2013.41}, doi = {10.1109/ICPP.2013.41}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpp/AliagaPQA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppam/AliagaACFLPQ13, author = {Jos{\'{e}} Ignacio Aliaga and Hartwig Anzt and Maribel Castillo and Juan Carlos Fern{\'{a}}ndez and Germ{\'{a}}n Le{\'{o}}n and Joaqu{\'{\i}}n P{\'{e}}rez and Enrique S. Quintana{-}Ort{\'{\i}}}, editor = {Roman Wyrzykowski and Jack J. Dongarra and Konrad Karczewski and Jerzy Wasniewski}, title = {Performance and Energy Analysis of the Iterative Solution of Sparse Linear Systems on Multicore and Manycore Architectures}, booktitle = {Parallel Processing and Applied Mathematics - 10th International Conference, {PPAM} 2013, Warsaw, Poland, September 8-11, 2013, Revised Selected Papers, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {8384}, pages = {772--782}, publisher = {Springer}, year = {2013}, url = {https://doi.org/10.1007/978-3-642-55224-3\_72}, doi = {10.1007/978-3-642-55224-3\_72}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ppam/AliagaACFLPQ13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ife/AnztCFHIMQ12, author = {Hartwig Anzt and Maribel Castillo and Juan Carlos Fern{\'{a}}ndez and Vincent Heuveline and Francisco D. Igual and Rafael Mayo and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Optimization of power consumption in the iterative solution of sparse linear systems on graphics processors}, journal = {Comput. Sci. Res. Dev.}, volume = {27}, number = {4}, pages = {299--307}, year = {2012}, url = {https://doi.org/10.1007/s00450-011-0195-8}, doi = {10.1007/S00450-011-0195-8}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ife/AnztCFHIMQ12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/AnztTDH12, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra and Vincent Heuveline}, editor = {Ioannis Caragiannis and Michael Alexander and Rosa M. Badia and Mario Cannataro and Alexandru Costan and Marco Danelutto and Fr{\'{e}}d{\'{e}}ric Desprez and Bettina Krammer and Julio Sahuquillo and Stephen L. Scott and Josef Weidendorfer}, title = {Weighted Block-Asynchronous Iteration on GPU-Accelerated Systems}, booktitle = {Euro-Par 2012: Parallel Processing Workshops - BDMC, CGWS, HeteroPar, HiBB, OMHI, Paraphrase, PROPER, Resilience, UCHPC, VHPC, Rhodes Islands, Greece, August 27-31, 2012. Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {7640}, pages = {145--154}, publisher = {Springer}, year = {2012}, url = {https://doi.org/10.1007/978-3-642-36949-0\_17}, doi = {10.1007/978-3-642-36949-0\_17}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/europar/AnztTDH12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/AnztLDH12, author = {Hartwig Anzt and Piotr Luszczek and Jack J. Dongarra and Vincent Heuveline}, editor = {Christos Kaklamanis and Theodore S. Papatheodorou and Paul G. Spirakis}, title = {GPU-Accelerated Asynchronous Error Correction for Mixed Precision Iterative Refinement}, booktitle = {Euro-Par 2012 Parallel Processing - 18th International Conference, Euro-Par 2012, Rhodes Island, Greece, August 27-31, 2012. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {7484}, pages = {908--919}, publisher = {Springer}, year = {2012}, url = {https://doi.org/10.1007/978-3-642-32820-6\_89}, doi = {10.1007/978-3-642-32820-6\_89}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/europar/AnztLDH12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztTDH12, author = {Hartwig Anzt and Stanimire Tomov and Jack J. Dongarra and Vincent Heuveline}, title = {A Block-Asynchronous Relaxation Method for Graphics Processing Units}, booktitle = {26th {IEEE} International Parallel and Distributed Processing Symposium Workshops {\&} PhD Forum, {IPDPS} 2012, Shanghai, China, May 21-25, 2012}, pages = {113--124}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/IPDPSW.2012.11}, doi = {10.1109/IPDPSW.2012.11}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ipps/AnztTDH12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:journals/procedia/AnztTGDH12, author = {Hartwig Anzt and Stanimire Tomov and Mark Gates and Jack J. Dongarra and Vincent Heuveline}, editor = {Hesham H. Ali and Yong Shi and Deepak Khazanchi and Michael Lees and G. Dick van Albada and Jack J. Dongarra and Peter M. A. Sloot}, title = {Block-asynchronous Multigrid Smoothers for GPU-accelerated Systems}, booktitle = {Proceedings of the International Conference on Computational Science, {ICCS} 2012, Omaha, Nebraska, USA, 4-6 June, 2012}, series = {Procedia Computer Science}, volume = {9}, pages = {7--16}, publisher = {Elsevier}, year = {2012}, url = {https://doi.org/10.1016/j.procs.2012.04.002}, doi = {10.1016/J.PROCS.2012.04.002}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/procedia/AnztTGDH12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/green/AnztHACFMQ11, author = {Hartwig Anzt and Vincent Heuveline and Jos{\'{e}} Ignacio Aliaga and Maribel Castillo and Juan Carlos Fern{\'{a}}ndez and Rafael Mayo and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Analysis and optimization of power consumption in the iterative solution of sparse linear systems on multi-core and many-core platforms}, booktitle = {2011 International Green Computing Conference and Workshops, {IGCC} 2012, Orlando, FL, USA, July 25-28, 2011}, pages = {1--6}, publisher = {{IEEE} Computer Society}, year = {2011}, url = {https://doi.org/10.1109/IGCC.2011.6008594}, doi = {10.1109/IGCC.2011.6008594}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/green/AnztHACFMQ11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/AnztHRCFMQ11, author = {Hartwig Anzt and Vincent Heuveline and Bj{\"{o}}rn Rocker and Maribel Castillo and Juan Carlos Fern{\'{a}}ndez and Rafael Mayo and Enrique S. Quintana{-}Ort{\'{\i}}}, title = {Power Consumption of Mixed Precision in the Iterative Solution of Sparse Linear Systems}, booktitle = {25th {IEEE} International Symposium on Parallel and Distributed Processing, {IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May 2011 - Workshop Proceedings}, pages = {829--836}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IPDPS.2011.226}, doi = {10.1109/IPDPS.2011.226}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ipps/AnztHRCFMQ11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ptw/AnztABGHHHKLNRRSSSWWW11, author = {Hartwig Anzt and Werner Augustin and Martin Baumann and Thomas Gengenbach and Tobias Hahn and Andreas Helfrich{-}Schkarbanenko and Vincent Heuveline and Eva Ketelaer and Dimitar Lukarski and Andreas Nestler and Sebastian Ritterbusch and Staffan Ronnas and Michael Schick and Mareike Schmidtobreick and Chandramowli Subramanian and Jan{-}Philipp Weiss and Florian Wilhelm and Martin Wlotzka}, editor = {Holger Brunst and Matthias S. M{\"{u}}ller and Wolfgang E. Nagel and Michael M. Resch}, title = {HiFlow\({}^{\mbox{3}}\): {A} Hardware-Aware Parallel Finite Element Package}, booktitle = {Tools for High Performance Computing 2011 - Proceedings of the 5th International Workshop on Parallel Tools for High Performance Computing, ZIH, Dresden, September 2011}, pages = {139--151}, publisher = {Springer}, year = {2011}, url = {https://doi.org/10.1007/978-3-642-31476-6\_12}, doi = {10.1007/978-3-642-31476-6\_12}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ptw/AnztABGHHHKLNRRSSSWWW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ife/AnztRH10, author = {Hartwig Anzt and Bj{\"{o}}rn Rocker and Vincent Heuveline}, title = {Energy efficiency of mixed precision iterative refinement methods using hybrid hardware platforms - An evaluation of different solver and hardware configurations}, journal = {Comput. Sci. Res. Dev.}, volume = {25}, number = {3-4}, pages = {141--148}, year = {2010}, url = {https://doi.org/10.1007/s00450-010-0124-2}, doi = {10.1007/S00450-010-0124-2}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ife/AnztRH10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/para/AnztHR10, author = {Hartwig Anzt and Vincent Heuveline and Bj{\"{o}}rn Rocker}, editor = {Kristj{\'{a}}n J{\'{o}}nasson}, title = {Mixed Precision Iterative Refinement Methods for Linear Systems: Convergence Analysis Based on Krylov Subspace Methods}, 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 = {237--247}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-28145-7\_24}, doi = {10.1007/978-3-642-28145-7\_24}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/para/AnztHR10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/vecpar/AnztHR10, author = {Hartwig Anzt and Vincent Heuveline and Bj{\"{o}}rn Rocker}, editor = {Jos{\'{e}} M. Laginha M. Palma and Michel J. Dayd{\'{e}} and Osni Marques and Jo{\~{a}}o Correia Lopes}, title = {An Error Correction Solver for Linear Systems: Evaluation of Mixed Precision Implementations}, booktitle = {High Performance Computing for Computational Science - {VECPAR} 2010 - 9th International conference, Berkeley, CA, USA, June 22-25, 2010, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {6449}, pages = {58--70}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-19328-6\_8}, doi = {10.1007/978-3-642-19328-6\_8}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/vecpar/AnztHR10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.