Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Tal Ben-Nun
@inproceedings{DBLP:conf/ppopp/GianinazziZHLAS24,
author = {Lukas Gianinazzi and
Alexandros Nikolaos Ziogas and
Langwen Huang and
Piotr Luczynski and
Saleh Ashkboosh and
Florian Scheidl and
Armon Carigiet and
Chio Ge and
Nabil Abubaker and
Maciej Besta and
Tal Ben{-}Nun and
Torsten Hoefler},
editor = {Michel Steuwer and
I{-}Ting Angelina Lee and
Milind Chabbi},
title = {Arrow Matrix Decomposition: {A} Novel Approach for Communication-Efficient
Sparse Matrix Multiplication},
booktitle = {Proceedings of the 29th {ACM} {SIGPLAN} Annual Symposium on Principles
and Practice of Parallel Programming, PPoPP 2024, Edinburgh, United
Kingdom, March 2-6, 2024},
pages = {404--416},
publisher = {{ACM}},
year = {2024},
url = {https://doi.org/10.1145/3627535.3638496},
doi = {10.1145/3627535.3638496},
timestamp = {Mon, 01 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/GianinazziZHLAS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-19364,
author = {Lukas Gianinazzi and
Alexandros Nikolaos Ziogas and
Langwen Huang and
Piotr Luczynski and
Saleh Ashkboos and
Florian Scheidl and
Armon Carigiet and
Chio Ge and
Nabil Abubaker and
Maciej Besta and
Tal Ben{-}Nun and
Torsten Hoefler},
title = {Arrow Matrix Decomposition: {A} Novel Approach for Communication-Efficient
Sparse Matrix Multiplication},
journal = {CoRR},
volume = {abs/2402.19364},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.19364},
doi = {10.48550/ARXIV.2402.19364},
eprinttype = {arXiv},
eprint = {2402.19364},
timestamp = {Tue, 26 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-19364.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cse/DubeyBCSR23,
author = {Anshu Dubey and
Tal Ben{-}Nun and
Bradford L. Chamberlain and
Bronis R. de Supinski and
Damian W. I. Rouson},
title = {Performance on {HPC} Platforms Is Possible Without {C++}},
journal = {Comput. Sci. Eng.},
volume = {25},
number = {5},
pages = {48--52},
year = {2023},
url = {https://doi.org/10.1109/MCSE.2023.3329330},
doi = {10.1109/MCSE.2023.3329330},
timestamp = {Sat, 04 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cse/DubeyBCSR23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cgo/Ben-NunACH23,
author = {Tal Ben{-}Nun and
Berke Ates and
Alexandru Calotoiu and
Torsten Hoefler},
editor = {Christophe Dubach and
Derek Bruening and
Ben Hardekopf},
title = {Bridging Control-Centric and Data-Centric Optimization},
booktitle = {Proceedings of the 21st {ACM/IEEE} International Symposium on Code
Generation and Optimization, {CGO} 2023, Montr{\'{e}}al, QC,
Canada, 25 February 2023- 1 March 2023},
pages = {173--185},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3579990.3580018},
doi = {10.1145/3579990.3580018},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cgo/Ben-NunACH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ciac/BenNunGHO23,
author = {Tal Ben{-}Nun and
Lukas Gianinazzi and
Torsten Hoefler and
Yishai Oltchik},
editor = {Marios Mavronicolas},
title = {Maximum Flows in Parametric Graph Templates},
booktitle = {Algorithms and Complexity - 13th International Conference, {CIAC}
2023, Larnaca, Cyprus, June 13-16, 2023, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {13898},
pages = {97--111},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-30448-4\_8},
doi = {10.1007/978-3-031-30448-4\_8},
timestamp = {Wed, 17 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ciac/BenNunGHO23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/TrumperBSCH23,
author = {Lukas Tr{\"{u}}mper and
Tal Ben{-}Nun and
Philipp Schaad and
Alexandru Calotoiu and
Torsten Hoefler},
editor = {Kyle A. Gallivan and
Efstratios Gallopoulos and
Dimitrios S. Nikolopoulos and
Ram{\'{o}}n Beivide},
title = {Performance Embeddings: {A} Similarity-Based Transfer Tuning Approach
to Performance Optimization},
booktitle = {Proceedings of the 37th International Conference on Supercomputing,
{ICS} 2023, Orlando, FL, USA, June 21-23, 2023},
pages = {50--62},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3577193.3593714},
doi = {10.1145/3577193.3593714},
timestamp = {Fri, 07 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/TrumperBSCH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/CastroIABFH23,
author = {Roberto L. Castro and
Andrei Ivanov and
Diego Andrade and
Tal Ben{-}Nun and
Basilio B. Fraguela and
Torsten Hoefler},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {{VENOM:} {A} Vectorized {N:} {M} Format for Unleashing the Power of
Sparse Tensor Cores},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2023, Denver, CO, USA, November
12-17, 2023},
pages = {72:1--72:14},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3607087},
doi = {10.1145/3581784.3607087},
timestamp = {Tue, 28 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/CastroIABFH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SchaadSBCZH23,
author = {Philipp Schaad and
Timo Schneider and
Tal Ben{-}Nun and
Alexandru Calotoiu and
Alexandros Nikolaos Ziogas and
Torsten Hoefler},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {FuzzyFlow: Leveraging Dataflow To Find and Squash Program Optimization
Bugs},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2023, Denver, CO, USA, November
12-17, 2023},
pages = {88:1--88:15},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3613214},
doi = {10.1145/3581784.3613214},
timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/SchaadSBCZH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-01048,
author = {Niels Gleinig and
Tal Ben{-}Nun and
Torsten Hoefler},
title = {A Theory of I/O-Efficient Sparse Neural Network Inference},
journal = {CoRR},
volume = {abs/2301.01048},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.01048},
doi = {10.48550/ARXIV.2301.01048},
eprinttype = {arXiv},
eprint = {2301.01048},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-01048.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-08142,
author = {Lukas Tr{\"{u}}mper and
Tal Ben{-}Nun and
Philipp Schaad and
Alexandru Calotoiu and
Torsten Hoefler},
title = {Performance Embeddings: {A} Similarity-based Approach to Automatic
Performance Optimization},
journal = {CoRR},
volume = {abs/2303.08142},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.08142},
doi = {10.48550/ARXIV.2303.08142},
eprinttype = {arXiv},
eprint = {2303.08142},
timestamp = {Mon, 20 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-08142.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-07613,
author = {Andrei Ivanov and
Nikoli Dryden and
Tal Ben{-}Nun and
Saleh Ashkboos and
Torsten Hoefler},
title = {STen: Productive and Efficient Sparsity in PyTorch},
journal = {CoRR},
volume = {abs/2304.07613},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.07613},
doi = {10.48550/ARXIV.2304.07613},
eprinttype = {arXiv},
eprint = {2304.07613},
timestamp = {Fri, 21 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-07613.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-00366,
author = {Tal Ben{-}Nun and
Berke Ates and
Alexandru Calotoiu and
Torsten Hoefler},
title = {Bridging Control-Centric and Data-Centric Optimization},
journal = {CoRR},
volume = {abs/2306.00366},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.00366},
doi = {10.48550/ARXIV.2306.00366},
eprinttype = {arXiv},
eprint = {2306.00366},
timestamp = {Mon, 12 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-00366.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-16178,
author = {Philipp Schaad and
Timo Schneider and
Tal Ben{-}Nun and
Alexandru Calotoiu and
Alexandros Nikolaos Ziogas and
Torsten Hoefler},
title = {FuzzyFlow: Leveraging Dataflow To Find and Squash Program Optimization
Bugs},
journal = {CoRR},
volume = {abs/2306.16178},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.16178},
doi = {10.48550/ARXIV.2306.16178},
eprinttype = {arXiv},
eprint = {2306.16178},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-16178.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-08420,
author = {Tal Ben{-}Nun and
Lukas Gianinazzi and
Torsten Hoefler and
Yishai Oltchik},
title = {Maximum Flows in Parametric Graph Templates},
journal = {CoRR},
volume = {abs/2307.08420},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.08420},
doi = {10.48550/ARXIV.2307.08420},
eprinttype = {arXiv},
eprint = {2307.08420},
timestamp = {Tue, 25 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-08420.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-12093,
author = {Julia Bazinska and
Andrei Ivanov and
Tal Ben{-}Nun and
Nikoli Dryden and
Maciej Besta and
Siyuan Shen and
Torsten Hoefler},
title = {Cached Operator Reordering: {A} Unified View for Fast {GNN} Training},
journal = {CoRR},
volume = {abs/2308.12093},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.12093},
doi = {10.48550/ARXIV.2308.12093},
eprinttype = {arXiv},
eprint = {2308.12093},
timestamp = {Wed, 30 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-12093.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-15432,
author = {Aiden Grossman and
Ludger Paehler and
Konstantinos Parasyris and
Tal Ben{-}Nun and
Jacob Hegna and
William S. Moses and
Jose Manuel Monsalve Diaz and
Mircea Trofin and
Johannes Doerfert},
title = {ComPile: {A} Large {IR} Dataset from Production Sources},
journal = {CoRR},
volume = {abs/2309.15432},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.15432},
doi = {10.48550/ARXIV.2309.15432},
eprinttype = {arXiv},
eprint = {2309.15432},
timestamp = {Tue, 17 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-15432.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-02065,
author = {Roberto L. Castro and
Andrei Ivanov and
Diego Andrade and
Tal Ben{-}Nun and
Basilio B. Fraguela and
Torsten Hoefler},
title = {{VENOM:} {A} Vectorized {N:} {M} Format for Unleashing the Power of
Sparse Tensor Cores},
journal = {CoRR},
volume = {abs/2310.02065},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.02065},
doi = {10.48550/ARXIV.2310.02065},
eprinttype = {arXiv},
eprint = {2310.02065},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-02065.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccad/JohnsenMBLH22,
author = {Carl{-}Johannes Johnsen and
Tiziano De Matteis and
Tal Ben{-}Nun and
Johannes de Fine Licht and
Torsten Hoefler},
editor = {Tulika Mitra and
Evangeline F. Y. Young and
Jinjun Xiong},
title = {Temporal Vectorization: {A} Compiler Approach to Automatic Multi-Pumping},
booktitle = {Proceedings of the 41st {IEEE/ACM} International Conference on Computer-Aided
Design, {ICCAD} 2022, San Diego, California, USA, 30 October 2022
- 3 November 2022},
pages = {85:1--85:9},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3508352.3549374},
doi = {10.1145/3508352.3549374},
timestamp = {Tue, 06 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iccad/JohnsenMBLH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/CalotoiuBKLSSH22,
author = {Alexandru Calotoiu and
Tal Ben{-}Nun and
Grzegorz Kwasniewski and
Johannes de Fine Licht and
Timo Schneider and
Philipp Schaad and
Torsten Hoefler},
editor = {Lawrence Rauchwerger and
Kirk W. Cameron and
Dimitrios S. Nikolopoulos and
Dionisios N. Pnevmatikatos},
title = {Lifting {C} semantics for dataflow optimization},
booktitle = {{ICS} '22: 2022 International Conference on Supercomputing, Virtual
Event, June 28 - 30, 2022},
pages = {17:1--17:13},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3524059.3532389},
doi = {10.1145/3524059.3532389},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/CalotoiuBKLSSH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/RauschBDI0H22,
author = {Oliver Rausch and
Tal Ben{-}Nun and
Nikoli Dryden and
Andrei Ivanov and
Shigang Li and
Torsten Hoefler},
editor = {Lawrence Rauchwerger and
Kirk W. Cameron and
Dimitrios S. Nikolopoulos and
Dionisios N. Pnevmatikatos},
title = {A data-centric optimization framework for machine learning},
booktitle = {{ICS} '22: 2022 International Conference on Supercomputing, Virtual
Event, June 28 - 30, 2022},
pages = {36:1--36:13},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3524059.3532364},
doi = {10.1145/3524059.3532364},
timestamp = {Wed, 22 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/RauschBDI0H22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AshkboosHDBDGKH22,
author = {Saleh Ashkboos and
Langwen Huang and
Nikoli Dryden and
Tal Ben{-}Nun and
Peter Dueben and
Lukas Gianinazzi and
Luca Kummer and
Torsten Hoefler},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {{ENS-10:} {A} Dataset For Post-Processing Ensemble Weather Forecasts},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/89e44582fd28ddfea1ea4dcb0ebbf4b0-Abstract-Datasets\_and\_Benchmarks.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/AshkboosHDBDGKH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ZiogasKBSH22,
author = {Alexandros Nikolaos Ziogas and
Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Timo Schneider and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {Deinsum: Practically {I/O} Optimal Multi-Linear Algebra},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {25:1--25:15},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00030},
doi = {10.1109/SC41404.2022.00030},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/ZiogasKBSH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SchaadBH22,
author = {Philipp Schaad and
Tal Ben{-}Nun and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {Boosting Performance Optimization with Interactive Data Movement Visualization},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {64:1--64:16},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00069},
doi = {10.1109/SC41404.2022.00069},
timestamp = {Wed, 24 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/SchaadBH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BenNunGDWDDEGMTWFSH22,
author = {Tal Ben{-}Nun and
Linus Groner and
Florian Deconinck and
Tobias Wicky and
Eddie Davis and
Johann Dahm and
Oliver Elbert and
Rhea George and
Jeremy McGibbon and
Lukas Tr{\"{u}}mper and
Elynn Wu and
Oliver Fuhrer and
Thomas C. Schulthess and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {Productive Performance Engineering for Weather and Climate Modeling
with Python},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {73:1--73:14},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00078},
doi = {10.1109/SC41404.2022.00078},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/BenNunGDWDDEGMTWFSH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-04148,
author = {Tal Ben{-}Nun and
Linus Groner and
Florian Deconinck and
Tobias Wicky and
Eddie Davis and
Johann Dahm and
Oliver Elbert and
Rhea George and
Jeremy McGibbon and
Lukas Tr{\"{u}}mper and
Elynn Wu and
Oliver Fuhrer and
Thomas C. Schulthess and
Torsten Hoefler},
title = {Productive Performance Engineering for Weather and Climate Modeling
with Python},
journal = {CoRR},
volume = {abs/2205.04148},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.04148},
doi = {10.48550/ARXIV.2205.04148},
eprinttype = {arXiv},
eprint = {2205.04148},
timestamp = {Wed, 11 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-04148.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-04934,
author = {Lukas Gianinazzi and
Tal Ben{-}Nun and
Saleh Ashkboos and
Yves Baumann and
Piotr Luczynski and
Torsten Hoefler},
title = {The spatial computer: {A} model for energy-efficient parallel computation},
journal = {CoRR},
volume = {abs/2205.04934},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.04934},
doi = {10.48550/ARXIV.2205.04934},
eprinttype = {arXiv},
eprint = {2205.04934},
timestamp = {Wed, 11 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-04934.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-08301,
author = {Alexandros Nikolaos Ziogas and
Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Timo Schneider and
Torsten Hoefler},
title = {Deinsum: Practically {I/O} Optimal Multilinear Algebra},
journal = {CoRR},
volume = {abs/2206.08301},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.08301},
doi = {10.48550/ARXIV.2206.08301},
eprinttype = {arXiv},
eprint = {2206.08301},
timestamp = {Tue, 21 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-08301.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-14786,
author = {Saleh Ashkboos and
Langwen Huang and
Nikoli Dryden and
Tal Ben{-}Nun and
Peter Dueben and
Lukas Gianinazzi and
Luca Kummer and
Torsten Hoefler},
title = {{ENS-10:} {A} Dataset For Post-Processing Ensemble Weather Forecast},
journal = {CoRR},
volume = {abs/2206.14786},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.14786},
doi = {10.48550/ARXIV.2206.14786},
eprinttype = {arXiv},
eprint = {2206.14786},
timestamp = {Mon, 04 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-14786.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-07433,
author = {Philipp Schaad and
Tal Ben{-}Nun and
Torsten Hoefler},
title = {Boosting Performance Optimization with Interactive Data Movement Visualization},
journal = {CoRR},
volume = {abs/2207.07433},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.07433},
doi = {10.48550/ARXIV.2207.07433},
eprinttype = {arXiv},
eprint = {2207.07433},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-07433.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-04598,
author = {Carl{-}Johannes Johnsen and
Tiziano De Matteis and
Tal Ben{-}Nun and
Johannes de Fine Licht and
Torsten Hoefler},
title = {Temporal Vectorization: {A} Compiler Approach to Automatic Multi-Pumping},
journal = {CoRR},
volume = {abs/2210.04598},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.04598},
doi = {10.48550/ARXIV.2210.04598},
eprinttype = {arXiv},
eprint = {2210.04598},
timestamp = {Thu, 13 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-04598.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-13768,
author = {Johannes de Fine Licht and
Tiziano De Matteis and
Tal Ben{-}Nun and
Andreas Kuster and
Oliver Rausch and
Manuel Burger and
Carl{-}Johannes Johnsen and
Torsten Hoefler},
title = {Python {FPGA} Programming with Data-Centric Multi-Level Design},
journal = {CoRR},
volume = {abs/2212.13768},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.13768},
doi = {10.48550/ARXIV.2212.13768},
eprinttype = {arXiv},
eprint = {2212.13768},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-13768.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/HoeflerABDP21,
author = {Torsten Hoefler and
Dan Alistarh and
Tal Ben{-}Nun and
Nikoli Dryden and
Alexandra Peste},
title = {Sparsity in Deep Learning: Pruning and growth for efficient inference
and training in neural networks},
journal = {J. Mach. Learn. Res.},
volume = {22},
pages = {241:1--241:124},
year = {2021},
url = {http://jmlr.org/papers/v22/21-0366.html},
timestamp = {Mon, 31 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/HoeflerABDP21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/LiBNGDAH21,
author = {Shigang Li and
Tal Ben{-}Nun and
Giorgi Nadiradze and
Salvatore Di Girolamo and
Nikoli Dryden and
Dan Alistarh and
Torsten Hoefler},
title = {Breaking (Global) Barriers in Parallel Stochastic Optimization With
Wait-Avoiding Group Averaging},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {32},
number = {7},
pages = {1725--1739},
year = {2021},
url = {https://doi.org/10.1109/TPDS.2020.3040606},
doi = {10.1109/TPDS.2020.3040606},
timestamp = {Tue, 02 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tpds/LiBNGDAH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cgo/LichtKMBHH21,
author = {Johannes de Fine Licht and
Andreas Kuster and
Tiziano De Matteis and
Tal Ben{-}Nun and
Dominic Hofer and
Torsten Hoefler},
editor = {Jae W. Lee and
Mary Lou Soffa and
Ayal Zaks},
title = {StencilFlow: Mapping Large Stencil Programs to Distributed Spatial
Computing Systems},
booktitle = {{IEEE/ACM} International Symposium on Code Generation and Optimization,
{CGO} 2021, Seoul, South Korea, February 27 - March 3, 2021},
pages = {315--326},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/CGO51591.2021.9370315},
doi = {10.1109/CGO51591.2021.9370315},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cgo/LichtKMBHH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/CumminsFBHOL21,
author = {Chris Cummins and
Zacharias V. Fisches and
Tal Ben{-}Nun and
Torsten Hoefler and
Michael F. P. O'Boyle and
Hugh Leather},
editor = {Marina Meila and
Tong Zhang},
title = {ProGraML: {A} Graph-based Program Representation for Data Flow Analysis
and Compiler Optimizations},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {2244--2253},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/cummins21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/CumminsFBHOL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/ZiogasBSH21,
author = {Alexandros Nikolaos Ziogas and
Tal Ben{-}Nun and
Timo Schneider and
Torsten Hoefler},
editor = {Huiyang Zhou and
Jose Moreira and
Frank Mueller and
Yoav Etsion},
title = {NPBench: a benchmarking suite for high-performance NumPy},
booktitle = {{ICS} '21: 2021 International Conference on Supercomputing, Virtual
Event, USA, June 14-17, 2021},
pages = {63--74},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3447818.3460360},
doi = {10.1145/3447818.3460360},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/ZiogasBSH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlsys/IvanovDB0H21,
author = {Andrei Ivanov and
Nikoli Dryden and
Tal Ben{-}Nun and
Shigang Li and
Torsten Hoefler},
editor = {Alex Smola and
Alex Dimakis and
Ion Stoica},
title = {Data Movement Is All You Need: {A} Case Study on Optimizing Transformers},
booktitle = {Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual,
April 5-9, 2021},
publisher = {mlsys.org},
year = {2021},
url = {https://proceedings.mlsys.org/paper\_files/paper/2021/hash/bc86e95606a6392f51f95a8de106728d-Abstract.html},
timestamp = {Mon, 13 May 2024 16:08:52 +0200},
biburl = {https://dblp.org/rec/conf/mlsys/IvanovDB0H21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/KwasniewskiBZSB21,
author = {Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Alexandros Nikolaos Ziogas and
Timo Schneider and
Maciej Besta and
Torsten Hoefler},
editor = {Jaejin Lee and
Erez Petrank},
title = {On the parallel {I/O} optimality of linear algebra kernels: near-optimal
{LU} factorization},
booktitle = {PPoPP '21: 26th {ACM} {SIGPLAN} Symposium on Principles and Practice
of Parallel Programming, Virtual Event, Republic of Korea, February
27- March 3, 2021},
pages = {463--464},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3437801.3441590},
doi = {10.1145/3437801.3441590},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/KwasniewskiBZSB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KwasniewskiKBZS21,
author = {Grzegorz Kwasniewski and
Marko Kabic and
Tal Ben{-}Nun and
Alexandros Nikolaos Ziogas and
Jens Eirik Saethre and
Andr{\'{e}} Gaillard and
Timo Schneider and
Maciej Besta and
Anton Kozhevnikov and
Joost VandeVondele and
Torsten Hoefler},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {On the parallel {I/O} optimality of linear algebra kernels: near-optimal
matrix factorizations},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {70},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476167},
doi = {10.1145/3458817.3476167},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/KwasniewskiKBZS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DrydenBBH21,
author = {Nikoli Dryden and
Roman B{\"{o}}hringer and
Tal Ben{-}Nun and
Torsten Hoefler},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {Clairvoyant prefetching for distributed machine learning {I/O}},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {92},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476181},
doi = {10.1145/3458817.3476181},
timestamp = {Tue, 08 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/DrydenBBH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ZiogasSBCMLLH21,
author = {Alexandros Nikolaos Ziogas and
Timo Schneider and
Tal Ben{-}Nun and
Alexandru Calotoiu and
Tiziano De Matteis and
Johannes de Fine Licht and
Luca Lavarini and
Torsten Hoefler},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {Productivity, portability, performance: data-centric Python},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {95},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476176},
doi = {10.1145/3458817.3476176},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/ZiogasSBCMLLH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/KwasniewskiBGCS21,
author = {Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Lukas Gianinazzi and
Alexandru Calotoiu and
Timo Schneider and
Alexandros Nikolaos Ziogas and
Maciej Besta and
Torsten Hoefler},
editor = {Kunal Agrawal and
Yossi Azar},
title = {Pebbles, Graphs, and a Pinch of Combinatorics: Towards Tight {I/O}
Lower Bounds for Statically Analyzable Programs},
booktitle = {{SPAA} '21: 33rd {ACM} Symposium on Parallelism in Algorithms and
Architectures, Virtual Event, USA, 6-8 July, 2021},
pages = {328--339},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3409964.3461796},
doi = {10.1145/3409964.3461796},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/KwasniewskiBGCS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-08734,
author = {Roman B{\"{o}}hringer and
Nikoli Dryden and
Tal Ben{-}Nun and
Torsten Hoefler},
title = {Clairvoyant Prefetching for Distributed Machine Learning {I/O}},
journal = {CoRR},
volume = {abs/2101.08734},
year = {2021},
url = {https://arxiv.org/abs/2101.08734},
eprinttype = {arXiv},
eprint = {2101.08734},
timestamp = {Sat, 30 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-08734.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-00554,
author = {Torsten Hoefler and
Dan Alistarh and
Tal Ben{-}Nun and
Nikoli Dryden and
Alexandra Peste},
title = {Sparsity in Deep Learning: Pruning and growth for efficient inference
and training in neural networks},
journal = {CoRR},
volume = {abs/2102.00554},
year = {2021},
url = {https://arxiv.org/abs/2102.00554},
eprinttype = {arXiv},
eprint = {2102.00554},
timestamp = {Tue, 09 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-00554.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-07203,
author = {Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Lukas Gianinazzi and
Alexandru Calotoiu and
Timo Schneider and
Alexandros Nikolaos Ziogas and
Maciej Besta and
Torsten Hoefler},
title = {Pebbles, Graphs, and a Pinch of Combinatorics: Towards Tight {I/O}
Lower Bounds for Statically Analyzable Programs},
journal = {CoRR},
volume = {abs/2105.07203},
year = {2021},
url = {https://arxiv.org/abs/2105.07203},
eprinttype = {arXiv},
eprint = {2105.07203},
timestamp = {Tue, 18 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-07203.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-03594,
author = {Lukas Gianinazzi and
Maximilian Fries and
Nikoli Dryden and
Tal Ben{-}Nun and
Maciej Besta and
Torsten Hoefler},
title = {Learning Combinatorial Node Labeling Algorithms},
journal = {CoRR},
volume = {abs/2106.03594},
year = {2021},
url = {https://arxiv.org/abs/2106.03594},
eprinttype = {arXiv},
eprint = {2106.03594},
timestamp = {Thu, 15 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-03594.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-00555,
author = {Alexandros Nikolaos Ziogas and
Timo Schneider and
Tal Ben{-}Nun and
Alexandru Calotoiu and
Tiziano De Matteis and
Johannes de Fine Licht and
Luca Lavarini and
Torsten Hoefler},
title = {Productivity, Portability, Performance: Data-Centric Python},
journal = {CoRR},
volume = {abs/2107.00555},
year = {2021},
url = {https://arxiv.org/abs/2107.00555},
eprinttype = {arXiv},
eprint = {2107.00555},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-00555.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-09337,
author = {Grzegorz Kwasniewski and
Marko Kabic and
Tal Ben{-}Nun and
Alexandros Nikolaos Ziogas and
Jens Eirik Saethre and
Andr{\'{e}} Gaillard and
Timo Schneider and
Maciej Besta and
Anton Kozhevnikov and
Joost VandeVondele and
Torsten Hoefler},
title = {On the Parallel {I/O} Optimality of Linear Algebra Kernels: Near-Optimal
Matrix Factorizations},
journal = {CoRR},
volume = {abs/2108.09337},
year = {2021},
url = {https://arxiv.org/abs/2108.09337},
eprinttype = {arXiv},
eprint = {2108.09337},
timestamp = {Fri, 27 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-09337.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-10802,
author = {Oliver Rausch and
Tal Ben{-}Nun and
Nikoli Dryden and
Andrei Ivanov and
Shigang Li and
Torsten Hoefler},
title = {A Data-Centric Optimization Framework for Machine Learning},
journal = {CoRR},
volume = {abs/2110.10802},
year = {2021},
url = {https://arxiv.org/abs/2110.10802},
eprinttype = {arXiv},
eprint = {2110.10802},
timestamp = {Thu, 28 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-10802.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-11879,
author = {Alexandru Calotoiu and
Tal Ben{-}Nun and
Grzegorz Kwasniewski and
Johannes de Fine Licht and
Timo Schneider and
Philipp Schaad and
Torsten Hoefler},
title = {Lifting {C} Semantics for Dataflow Optimization},
journal = {CoRR},
volume = {abs/2112.11879},
year = {2021},
url = {https://arxiv.org/abs/2112.11879},
eprinttype = {arXiv},
eprint = {2112.11879},
timestamp = {Tue, 04 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-11879.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/Ben-NunSPP20,
author = {Tal Ben{-}Nun and
Michael Sutton and
Sreepathi Pai and
Keshav Pingali},
title = {Groute: Asynchronous Multi-GPU Programming Model with Applications
to Large-scale Graph Processing},
journal = {{ACM} Trans. Parallel Comput.},
volume = {7},
number = {3},
pages = {18:1--18:27},
year = {2020},
url = {https://doi.org/10.1145/3399730},
doi = {10.1145/3399730},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/topc/Ben-NunSPP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/trets/BestaFBSLH20,
author = {Maciej Besta and
Marc Fischer and
Tal Ben{-}Nun and
Dimitri Stanojevic and
Johannes de Fine Licht and
Torsten Hoefler},
title = {Substream-Centric Maximum Matchings on {FPGA}},
journal = {{ACM} Trans. Reconfigurable Technol. Syst.},
volume = {13},
number = {2},
pages = {8:1--8:33},
year = {2020},
url = {https://doi.org/10.1145/3377871},
doi = {10.1145/3377871},
timestamp = {Fri, 10 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/trets/BestaFBSLH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/HofferBHGHS20,
author = {Elad Hoffer and
Tal Ben{-}Nun and
Itay Hubara and
Niv Giladi and
Torsten Hoefler and
Daniel Soudry},
title = {Augment Your Batch: Improving Generalization Through Instance Repetition},
booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2020, Seattle, WA, USA, June 13-19, 2020},
pages = {8126--8135},
publisher = {Computer Vision Foundation / {IEEE}},
year = {2020},
url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Hoffer\_Augment\_Your\_Batch\_Improving\_Generalization\_Through\_Instance\_Repetition\_CVPR\_2020\_paper.html},
doi = {10.1109/CVPR42600.2020.00815},
timestamp = {Tue, 31 Aug 2021 14:00:04 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/HofferBHGHS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/LiBGAH20,
author = {Shigang Li and
Tal Ben{-}Nun and
Salvatore Di Girolamo and
Dan Alistarh and
Torsten Hoefler},
editor = {Rajiv Gupta and
Xipeng Shen},
title = {Taming unbalanced training workloads in deep learning with partial
collective operations},
booktitle = {PPoPP '20: 25th {ACM} {SIGPLAN} Symposium on Principles and Practice
of Parallel Programming, San Diego, California, USA, February 22-26,
2020},
pages = {45--61},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3332466.3374528},
doi = {10.1145/3332466.3374528},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/LiBGAH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/Ben-NunGHKN20,
author = {Tal Ben{-}Nun and
Todd Gamblin and
Daisy S. Hollman and
Hari Krishnan and
Chris J. Newburn},
title = {Workflows are the New Applications: Challenges in Performance, Portability,
and Productivity},
booktitle = {{IEEE/ACM} International Workshop on Performance, Portability and
Productivity in HPC, P3HPC@SC 2020, Atlanta, GA, USA, November 13,
2020},
pages = {57--69},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/P3HPC51967.2020.00011},
doi = {10.1109/P3HPC51967.2020.00011},
timestamp = {Wed, 20 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/Ben-NunGHKN20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-10536,
author = {Chris Cummins and
Zacharias V. Fisches and
Tal Ben{-}Nun and
Torsten Hoefler and
Hugh Leather},
title = {ProGraML: Graph-based Deep Learning for Program Optimization and Analysis},
journal = {CoRR},
volume = {abs/2003.10536},
year = {2020},
url = {https://arxiv.org/abs/2003.10536},
eprinttype = {arXiv},
eprint = {2003.10536},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-10536.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-00124,
author = {Shigang Li and
Tal Ben{-}Nun and
Dan Alistarh and
Salvatore Di Girolamo and
Nikoli Dryden and
Torsten Hoefler},
title = {Breaking (Global) Barriers in Parallel Stochastic Optimization with
Wait-Avoiding Group Averaging},
journal = {CoRR},
volume = {abs/2005.00124},
year = {2020},
url = {https://arxiv.org/abs/2005.00124},
eprinttype = {arXiv},
eprint = {2005.00124},
timestamp = {Fri, 08 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-00124.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-08748,
author = {Peter Gr{\"{o}}nquist and
Chengyuan Yao and
Tal Ben{-}Nun and
Nikoli Dryden and
Peter Dueben and
Shigang Li and
Torsten Hoefler},
title = {Deep Learning for Post-Processing Ensemble Weather Forecasts},
journal = {CoRR},
volume = {abs/2005.08748},
year = {2020},
url = {https://arxiv.org/abs/2005.08748},
eprinttype = {arXiv},
eprint = {2005.08748},
timestamp = {Fri, 22 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-08748.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-00072,
author = {Andrei Ivanov and
Nikoli Dryden and
Tal Ben{-}Nun and
Shigang Li and
Torsten Hoefler},
title = {Data Movement Is All You Need: {A} Case Study on Optimizing Transformers},
journal = {CoRR},
volume = {abs/2007.00072},
year = {2020},
url = {https://arxiv.org/abs/2007.00072},
eprinttype = {arXiv},
eprint = {2007.00072},
timestamp = {Mon, 06 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-00072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-05975,
author = {Grzegorz Kwasniewski and
Tal Ben{-}Nun and
Alexandros Nikolaos Ziogas and
Timo Schneider and
Maciej Besta and
Torsten Hoefler},
title = {On the Parallel {I/O} Optimality of Linear Algebra Kernels: Near-Optimal
{LU} Factorization},
journal = {CoRR},
volume = {abs/2010.05975},
year = {2020},
url = {https://arxiv.org/abs/2010.05975},
eprinttype = {arXiv},
eprint = {2010.05975},
timestamp = {Tue, 20 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-05975.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-14684,
author = {Maciej Besta and
Marc Fischer and
Tal Ben{-}Nun and
Dimitri Stanojevic and
Johannes de Fine Licht and
Torsten Hoefler},
title = {Substream-Centric Maximum Matchings on {FPGA}},
journal = {CoRR},
volume = {abs/2010.14684},
year = {2020},
url = {https://arxiv.org/abs/2010.14684},
eprinttype = {arXiv},
eprint = {2010.14684},
timestamp = {Mon, 02 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-14684.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-15218,
author = {Johannes de Fine Licht and
Andreas Kuster and
Tiziano De Matteis and
Tal Ben{-}Nun and
Dominic Hofer and
Torsten Hoefler},
title = {StencilFlow: Mapping Large Stencil Programs to Distributed Spatial
Computing Systems},
journal = {CoRR},
volume = {abs/2010.15218},
year = {2020},
url = {https://arxiv.org/abs/2010.15218},
eprinttype = {arXiv},
eprint = {2010.15218},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-15218.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-07001,
author = {Tal Ben{-}Nun and
Lukas Gianinazzi and
Torsten Hoefler and
Yishai Oltchik},
title = {Parametric Graph Templates: Properties and Algorithms},
journal = {CoRR},
volume = {abs/2011.07001},
year = {2020},
url = {https://arxiv.org/abs/2011.07001},
eprinttype = {arXiv},
eprint = {2011.07001},
timestamp = {Wed, 18 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-07001.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-01470,
author = {Chris Cummins and
Hugh Leather and
Zacharias V. Fisches and
Tal Ben{-}Nun and
Torsten Hoefler and
Michael F. P. O'Boyle},
title = {Deep Data Flow Analysis},
journal = {CoRR},
volume = {abs/2012.01470},
year = {2020},
url = {https://arxiv.org/abs/2012.01470},
eprinttype = {arXiv},
eprint = {2012.01470},
timestamp = {Fri, 04 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-01470.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csur/Ben-NunH19,
author = {Tal Ben{-}Nun and
Torsten Hoefler},
title = {Demystifying Parallel and Distributed Deep Learning: An In-depth Concurrency
Analysis},
journal = {{ACM} Comput. Surv.},
volume = {52},
number = {4},
pages = {65:1--65:43},
year = {2019},
url = {https://doi.org/10.1145/3320060},
doi = {10.1145/3320060},
timestamp = {Sat, 08 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csur/Ben-NunH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fpga/BestaFBLH19,
author = {Maciej Besta and
Marc Fischer and
Tal Ben{-}Nun and
Johannes de Fine Licht and
Torsten Hoefler},
editor = {Kia Bazargan and
Stephen Neuendorffer},
title = {Substream-Centric Maximum Matchings on {FPGA}},
booktitle = {Proceedings of the 2019 {ACM/SIGDA} International Symposium on Field-Programmable
Gate Arrays, {FPGA} 2019, Seaside, CA, USA, February 24-26, 2019},
pages = {152--161},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3289602.3293916},
doi = {10.1145/3289602.3293916},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/fpga/BestaFBLH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Ben-NunBHZPH19,
author = {Tal Ben{-}Nun and
Maciej Besta and
Simon Huber and
Alexandros Nikolaos Ziogas and
Daniel Peter and
Torsten Hoefler},
title = {A Modular Benchmarking Infrastructure for High-Performance and Reproducible
Deep Learning},
booktitle = {2019 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
pages = {66--77},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/IPDPS.2019.00018},
doi = {10.1109/IPDPS.2019.00018},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ipps/Ben-NunBHZPH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ZiogasBFSLH19,
author = {Alexandros Nikolaos Ziogas and
Tal Ben{-}Nun and
Guillermo Indalecio Fern{\'{a}}ndez and
Timo Schneider and
Mathieu Luisier and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {A data-centric approach to extreme-scale \emph{ab initio} dissipative
quantum transport simulations},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {1:1--1:13},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3357156},
doi = {10.1145/3295500.3357156},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/ZiogasBFSLH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ZiogasBFSLH19a,
author = {Alexandros Nikolaos Ziogas and
Tal Ben{-}Nun and
Guillermo Indalecio Fern{\'{a}}ndez and
Timo Schneider and
Mathieu Luisier and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Optimizing the data movement in quantum transport simulations via
data-centric parallel programming},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {78:1--78:17},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356200},
doi = {10.1145/3295500.3356200},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/ZiogasBFSLH19a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/Ben-NunLZSH19,
author = {Tal Ben{-}Nun and
Johannes de Fine Licht and
Alexandros Nikolaos Ziogas and
Timo Schneider and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Stateful dataflow multigraphs: a data-centric model for performance
portability on heterogeneous architectures},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {81:1--81:14},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356173},
doi = {10.1145/3295500.3356173},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/Ben-NunLZSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-09335,
author = {Elad Hoffer and
Tal Ben{-}Nun and
Itay Hubara and
Niv Giladi and
Torsten Hoefler and
Daniel Soudry},
title = {Augment your batch: better training with larger batches},
journal = {CoRR},
volume = {abs/1901.09335},
year = {2019},
url = {http://arxiv.org/abs/1901.09335},
eprinttype = {arXiv},
eprint = {1901.09335},
timestamp = {Sat, 02 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-09335.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-10183,
author = {Tal Ben{-}Nun and
Maciej Besta and
Simon Huber and
Alexandros Nikolaos Ziogas and
Daniel Peter and
Torsten Hoefler},
title = {A Modular Benchmarking Infrastructure for High-Performance and Reproducible
Deep Learning},
journal = {CoRR},
volume = {abs/1901.10183},
year = {2019},
url = {http://arxiv.org/abs/1901.10183},
eprinttype = {arXiv},
eprint = {1901.10183},
timestamp = {Sat, 02 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-10183.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-10345,
author = {Tal Ben{-}Nun and
Johannes de Fine Licht and
Alexandros Nikolaos Ziogas and
Timo Schneider and
Torsten Hoefler},
title = {Stateful Dataflow Multigraphs: {A} Data-Centric Model for High-Performance
Parallel Programs},
journal = {CoRR},
volume = {abs/1902.10345},
year = {2019},
url = {http://arxiv.org/abs/1902.10345},
eprinttype = {arXiv},
eprint = {1902.10345},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-10345.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-06697,
author = {Maciej Besta and
Dimitri Stanojevic and
Johannes de Fine Licht and
Tal Ben{-}Nun and
Torsten Hoefler},
title = {Graph Processing on FPGAs: Taxonomy, Survey, Challenges},
journal = {CoRR},
volume = {abs/1903.06697},
year = {2019},
url = {http://arxiv.org/abs/1903.06697},
eprinttype = {arXiv},
eprint = {1903.06697},
timestamp = {Mon, 01 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-06697.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-04207,
author = {Shigang Li and
Tal Ben{-}Nun and
Salvatore Di Girolamo and
Dan Alistarh and
Torsten Hoefler},
title = {Taming Unbalanced Training Workloads in Deep Learning with Partial
Collective Operations},
journal = {CoRR},
volume = {abs/1908.04207},
year = {2019},
url = {http://arxiv.org/abs/1908.04207},
eprinttype = {arXiv},
eprint = {1908.04207},
timestamp = {Mon, 19 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-04207.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-08986,
author = {Elad Hoffer and
Berry Weinstein and
Itay Hubara and
Tal Ben{-}Nun and
Torsten Hoefler and
Daniel Soudry},
title = {Mix {\&} Match: training convnets with mixed image sizes for improved
accuracy, speed and scale resiliency},
journal = {CoRR},
volume = {abs/1908.08986},
year = {2019},
url = {http://arxiv.org/abs/1908.08986},
eprinttype = {arXiv},
eprint = {1908.08986},
timestamp = {Thu, 29 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-08986.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-00630,
author = {Peter Gr{\"{o}}nquist and
Tal Ben{-}Nun and
Nikoli Dryden and
Peter Dueben and
Luca Lavarini and
Shigang Li and
Torsten Hoefler},
title = {Predicting Weather Uncertainty with Deep Convnets},
journal = {CoRR},
volume = {abs/1911.00630},
year = {2019},
url = {http://arxiv.org/abs/1911.00630},
eprinttype = {arXiv},
eprint = {1911.00630},
timestamp = {Mon, 11 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-00630.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-08810,
author = {Alexandros Nikolaos Ziogas and
Tal Ben{-}Nun and
Guillermo Indalecio Fern{\'{a}}ndez and
Timo Schneider and
Mathieu Luisier and
Torsten Hoefler},
title = {Optimizing the Data Movement in Quantum Transport Simulations via
Data-Centric Parallel Programming},
journal = {CoRR},
volume = {abs/1912.08810},
year = {2019},
url = {http://arxiv.org/abs/1912.08810},
eprinttype = {arXiv},
eprint = {1912.08810},
timestamp = {Fri, 03 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-08810.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-10024,
author = {Alexandros Nikolaos Ziogas and
Tal Ben{-}Nun and
Guillermo Indalecio Fern{\'{a}}ndez and
Timo Schneider and
Mathieu Luisier and
Torsten Hoefler},
title = {A Data-Centric Approach to Extreme-Scale Ab initio Dissipative Quantum
Transport Simulations},
journal = {CoRR},
volume = {abs/1912.10024},
year = {2019},
url = {http://arxiv.org/abs/1912.10024},
eprinttype = {arXiv},
eprint = {1912.10024},
timestamp = {Fri, 03 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-10024.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/OyamaBHM18,
author = {Yosuke Oyama and
Tal Ben{-}Nun and
Torsten Hoefler and
Satoshi Matsuoka},
title = {Accelerating Deep Learning Frameworks with Micro-Batches},
booktitle = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2018,
Belfast, UK, September 10-13, 2018},
pages = {402--412},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/CLUSTER.2018.00058},
doi = {10.1109/CLUSTER.2018.00058},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/OyamaBHM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/0001BB18,
author = {Michael Sutton and
Tal Ben{-}Nun and
Amnon Barak},
title = {Optimizing Parallel Graph Connectivity Computation via Subgraph Sampling},
booktitle = {2018 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2018, Vancouver, BC, Canada, May 21-25, 2018},
pages = {12--21},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/IPDPS.2018.00012},
doi = {10.1109/IPDPS.2018.00012},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/0001BB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Ben-NunJH18,
author = {Tal Ben{-}Nun and
Alice Shoshana Jakobovits and
Torsten Hoefler},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Neural Code Comprehension: {A} Learnable Representation of Code Semantics},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {3589--3601},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/17c3433fecc21b57000debdf7ad5c930-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Ben-NunJH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-09941,
author = {Tal Ben{-}Nun and
Torsten Hoefler},
title = {Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency
Analysis},
journal = {CoRR},
volume = {abs/1802.09941},
year = {2018},
url = {http://arxiv.org/abs/1802.09941},
eprinttype = {arXiv},
eprint = {1802.09941},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-09941.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-04806,
author = {Yosuke Oyama and
Tal Ben{-}Nun and
Torsten Hoefler and
Satoshi Matsuoka},
title = {{\(\mu\)}-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batching},
journal = {CoRR},
volume = {abs/1804.04806},
year = {2018},
url = {http://arxiv.org/abs/1804.04806},
eprinttype = {arXiv},
eprint = {1804.04806},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-04806.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-07336,
author = {Tal Ben{-}Nun and
Alice Shoshana Jakobovits and
Torsten Hoefler},
title = {Neural Code Comprehension: {A} Learnable Representation of Code Semantics},
journal = {CoRR},
volume = {abs/1806.07336},
year = {2018},
url = {http://arxiv.org/abs/1806.07336},
eprinttype = {arXiv},
eprint = {1806.07336},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-07336.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/damon/KarnagelBWHL17,
author = {Tomas Karnagel and
Tal Ben{-}Nun and
Matthias Werner and
Dirk Habich and
Wolfgang Lehner},
title = {Big data causing big {(TLB)} problems: taming random memory accesses
on the {GPU}},
booktitle = {Proceedings of the 13th International Workshop on Data Management
on New Hardware, DaMoN 2017, Chicago, IL, USA, May 15, 2017},
pages = {6:1--6:10},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3076113.3076115},
doi = {10.1145/3076113.3076115},
timestamp = {Tue, 06 Nov 2018 16:58:57 +0100},
biburl = {https://dblp.org/rec/conf/damon/KarnagelBWHL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/Ben-NunSPP17,
author = {Tal Ben{-}Nun and
Michael Sutton and
Sreepathi Pai and
Keshav Pingali},
editor = {Vivek Sarkar and
Lawrence Rauchwerger},
title = {Groute: An Asynchronous Multi-GPU Programming Model for Irregular
Computations},
booktitle = {Proceedings of the 22nd {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, Austin, TX, USA, February 4-8, 2017},
pages = {235--248},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3018743.3018756},
doi = {10.1145/3018743.3018756},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/Ben-NunSPP17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/il/Ben-Nun16,
author = {Tal Ben{-}Nun},
title = {Memory-Oriented Programming : {A} Data-Centric Programming Model for
Systems with Multiple Parallel Accelerators ({\unicode{1513}}{\unicode{1506}}{\unicode{1512}}
{\unicode{1504}}{\unicode{1493}}{\unicode{1505}}{\unicode{1507}} {\unicode{1489}}{\unicode{1506}}{\unicode{1489}}{\unicode{1512}}{\unicode{1497}}{\unicode{1514}}:
{\unicode{1514}}{\unicode{1499}}{\unicode{1504}}{\unicode{1493}}{\unicode{1514}}
{\unicode{1502}}{\unicode{1493}}{\unicode{1504}}{\unicode{1495}}{\unicode{1492}}
{\unicode{1494}}{\unicode{1497}}{\unicode{1499}}{\unicode{1512}}{\unicode{1493}}{\unicode{1503}}
: {\unicode{1502}}{\unicode{1493}}{\unicode{1491}}{\unicode{1500}}
{\unicode{1514}}{\unicode{1499}}{\unicode{1504}}{\unicode{1493}}{\unicode{1514}}
{\unicode{1506}}{\unicode{1489}}{\unicode{1493}}{\unicode{1512}} {\unicode{1502}}{\unicode{1506}}{\unicode{1512}}{\unicode{1499}}{\unicode{1493}}{\unicode{1514}}
{\unicode{1502}}{\unicode{1512}}{\unicode{1493}}{\unicode{1489}}{\unicode{1493}}{\unicode{1514}}
{\unicode{1502}}{\unicode{1488}}{\unicode{1497}}{\unicode{1510}}{\unicode{1497}}{\unicode{1501}}
{\unicode{1502}}{\unicode{1511}}{\unicode{1489}}{\unicode{1497}}{\unicode{1500}}{\unicode{1497}}{\unicode{1497}}{\unicode{1501}}.)},
school = {Hebrew University of Jerusalem, Israel},
year = {2016},
url = {https://huji-primo.hosted.exlibrisgroup.com/permalink/f/13ns5ae/972HUJI\_ALMA21220818810003701},
timestamp = {Wed, 14 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/phd/il/Ben-Nun16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jcisd/GinsburgBASRR16,
author = {Avi Ginsburg and
Tal Ben{-}Nun and
Roi Asor and
Asaf Shemesh and
Israel Ringel and
Uri Raviv},
title = {Reciprocal Grids: {A} Hierarchical Algorithm for Computing Solution
X-ray Scattering Curves from Supramolecular Complexes at High Resolution},
journal = {J. Chem. Inf. Model.},
volume = {56},
number = {8},
pages = {1518--1527},
year = {2016},
url = {https://doi.org/10.1021/acs.jcim.6b00159},
doi = {10.1021/ACS.JCIM.6B00159},
timestamp = {Fri, 06 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jcisd/GinsburgBASRR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jpdc/Ben-NunBR16,
author = {Tal Ben{-}Nun and
Amnon Barak and
Uri Raviv},
title = {Spline-based parallel nonlinear optimization of function sequences},
journal = {J. Parallel Distributed Comput.},
volume = {93-94},
pages = {132--145},
year = {2016},
url = {https://doi.org/10.1016/j.jpdc.2016.04.011},
doi = {10.1016/J.JPDC.2016.04.011},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jpdc/Ben-NunBR16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncse/WeinholdLBKPHSLBBSSFRLN16,
author = {Carsten Weinhold and
Adam Lackorzynski and
Jan Bierbaum and
Martin K{\"{u}}ttler and
Maksym Planeta and
Hermann H{\"{a}}rtig and
Amnon Shiloh and
Ely Levy and
Tal Ben{-}Nun and
Amnon Barak and
Thomas Steinke and
Thorsten Sch{\"{u}}tt and
Jan Fajerski and
Alexander Reinefeld and
Matthias Lieber and
Wolfgang E. Nagel},
editor = {Hans{-}Joachim Bungartz and
Philipp Neumann and
Wolfgang E. Nagel},
title = {{FFMK:} {A} Fast and Fault-Tolerant Microkernel-Based System for Exascale
Computing},
booktitle = {Software for Exascale Computing - {SPPEXA} 2013-2015},
series = {Lecture Notes in Computational Science and Engineering},
volume = {113},
pages = {405--426},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-40528-5\_18},
doi = {10.1007/978-3-319-40528-5\_18},
timestamp = {Thu, 14 Oct 2021 08:45:21 +0200},
biburl = {https://dblp.org/rec/series/lncse/WeinholdLBKPHSLBBSSFRLN16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SuttonBBPP16,
author = {Michael Sutton and
Tal Ben{-}Nun and
Amnon Barak and
Sreepathi Pai and
Keshav Pingali},
title = {Adaptive Work-Efficient Connected Components on the {GPU}},
journal = {CoRR},
volume = {abs/1612.01178},
year = {2016},
url = {http://arxiv.org/abs/1612.01178},
eprinttype = {arXiv},
eprint = {1612.01178},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SuttonBBPP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/Ben-NunLBR15,
author = {Tal Ben{-}Nun and
Ely Levy and
Amnon Barak and
Eri Rubin},
editor = {Jackie Kern and
Jeffrey S. Vetter},
title = {Memory access patterns: the missing piece of the multi-GPU puzzle},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2015, Austin, TX, USA, November
15-20, 2015},
pages = {19:1--19:12},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2807591.2807611},
doi = {10.1145/2807591.2807611},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/Ben-NunLBR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taco/RubinLBB14,
author = {Eri Rubin and
Ely Levy and
Amnon Barak and
Tal Ben{-}Nun},
title = {{MAPS:} Optimizing Massively Parallel Applications Using Device-Level
Memory Abstraction},
journal = {{ACM} Trans. Archit. Code Optim.},
volume = {11},
number = {4},
pages = {44:1--44:22},
year = {2014},
url = {https://doi.org/10.1145/2680544},
doi = {10.1145/2680544},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taco/RubinLBB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/systor/Ben-NunEF10,
author = {Tal Ben{-}Nun and
Yoav Etsion and
Dror G. Feitelson},
editor = {Gadi Haber and
Dilma Da Silva and
Ethan L. Miller},
title = {Design and implementation of a generic resource sharing virtual time
dispatcher},
booktitle = {Proceedings of of {SYSTOR} 2010: The 3rd Annual Haifa Experimental
Systems Conference, Haifa, Israel, May 24-26, 2010},
series = {{ACM} International Conference Proceeding Series},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1815695.1815700},
doi = {10.1145/1815695.1815700},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/systor/Ben-NunEF10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/EtsionBF09,
author = {Yoav Etsion and
Tal Ben{-}Nun and
Dror G. Feitelson},
title = {A global scheduling framework for virtualization environments},
booktitle = {23rd {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2009, Rome, Italy, May 23-29, 2009},
pages = {1--8},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/IPDPS.2009.5161228},
doi = {10.1109/IPDPS.2009.5161228},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/EtsionBF09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
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.
last updated on 2024-05-13 20:26 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
