Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Torsten Hoefler
@article{DBLP:journals/csur/BestaGPFPBAH24,
author = {Maciej Besta and
Robert Gerstenberger and
Emanuel Peter and
Marc Fischer and
Michal Podstawski and
Claude Barthels and
Gustavo Alonso and
Torsten Hoefler},
title = {Demystifying Graph Databases: Analysis and Taxonomy of Data Organization,
System Designs, and Graph Queries},
journal = {{ACM} Comput. Surv.},
volume = {56},
number = {2},
pages = {31:1--31:40},
year = {2024},
url = {https://doi.org/10.1145/3604932},
doi = {10.1145/3604932},
timestamp = {Fri, 27 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/csur/BestaGPFPBAH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/SensiMGVH24,
author = {Daniele De Sensi and
Edgar Costa Molero and
Salvatore Di Girolamo and
Laurent Vanbever and
Torsten Hoefler},
title = {Canary: Congestion-aware in-network allreduce using dynamic trees},
journal = {Future Gener. Comput. Syst.},
volume = {152},
pages = {70--82},
year = {2024},
url = {https://doi.org/10.1016/j.future.2023.10.010},
doi = {10.1016/J.FUTURE.2023.10.010},
timestamp = {Fri, 26 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/fgcs/SensiMGVH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ncs/BauerHSH24,
author = {Peter Bauer and
Torsten Hoefler and
Bjorn Stevens and
Wilco Hazeleger},
title = {Digital twins of Earth and the computing challenge of human interaction},
journal = {Nat. Comput. Sci.},
volume = {4},
number = {3},
pages = {154--157},
year = {2024},
url = {https://doi.org/10.1038/s43588-024-00599-3},
doi = {10.1038/S43588-024-00599-3},
timestamp = {Mon, 15 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ncs/BauerHSH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/BestaH24,
author = {Maciej Besta and
Torsten Hoefler},
title = {Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency
Analysis},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {46},
number = {5},
pages = {2584--2606},
year = {2024},
url = {https://doi.org/10.1109/TPAMI.2023.3303431},
doi = {10.1109/TPAMI.2023.3303431},
timestamp = {Mon, 15 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/BestaH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/BenzRSROKHB24,
author = {Thomas Benz and
Michael Rogenmoser and
Paul Scheffler and
Samuel Riedel and
Alessandro Ottaviano and
Andreas Kurth and
Torsten Hoefler and
Luca Benini},
title = {A High-Performance, Energy-Efficient Modular {DMA} Engine Architecture},
journal = {{IEEE} Trans. Computers},
volume = {73},
number = {1},
pages = {263--277},
year = {2024},
url = {https://doi.org/10.1109/TC.2023.3329930},
doi = {10.1109/TC.2023.3329930},
timestamp = {Sat, 13 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tc/BenzRSROKHB24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BestaBKGPGGLNNH24,
author = {Maciej Besta and
Nils Blach and
Ales Kubicek and
Robert Gerstenberger and
Michal Podstawski and
Lukas Gianinazzi and
Joanna Gajda and
Tomasz Lehmann and
Hubert Niewiadomski and
Piotr Nyczyk and
Torsten Hoefler},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {Graph of Thoughts: Solving Elaborate Problems with Large Language
Models},
booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},
pages = {17682--17690},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i16.29720},
doi = {10.1609/AAAI.V38I16.29720},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BestaBKGPGGLNNH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nsdi/BlachBSDH0IKLKF24,
author = {Nils Blach and
Maciej Besta and
Daniele De Sensi and
Jens Domke and
Hussein Harake and
Shigang Li and
Patrick Iff and
Marek Konieczny and
Kartik Lakhotia and
Ales Kubicek and
Marcel Ferrari and
Fabrizio Petrini and
Torsten Hoefler},
editor = {Laurent Vanbever and
Irene Zhang},
title = {A High-Performance Design, Implementation, Deployment, and Evaluation
of The Slim Fly Network},
booktitle = {21st {USENIX} Symposium on Networked Systems Design and Implementation,
{NSDI} 2024, Santa Clara, CA, April 15-17, 2024},
publisher = {{USENIX} Association},
year = {2024},
url = {https://www.usenix.org/conference/nsdi24/presentation/blach},
timestamp = {Fri, 19 Apr 2024 11:29:16 +0200},
biburl = {https://dblp.org/rec/conf/nsdi/BlachBSDH0IKLKF24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nsdi/SensiBSH24,
author = {Daniele De Sensi and
Tommaso Bonato and
David Saam and
Torsten Hoefler},
editor = {Laurent Vanbever and
Irene Zhang},
title = {Swing: Short-cutting Rings for Higher Bandwidth Allreduce},
booktitle = {21st {USENIX} Symposium on Networked Systems Design and Implementation,
{NSDI} 2024, Santa Clara, CA, April 15-17, 2024},
publisher = {{USENIX} Association},
year = {2024},
url = {https://www.usenix.org/conference/nsdi24/presentation/de-sensi},
timestamp = {Fri, 19 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nsdi/SensiBSH24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@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-2401-04552,
author = {Torsten Hoefler and
Marcin Copik and
Pete Beckman and
Andrew Jones and
Ian T. Foster and
Manish Parashar and
Daniel A. Reed and
Matthias Troyer and
Thomas C. Schulthess and
Dan Ernst and
Jack J. Dongarra},
title = {XaaS: Acceleration as a Service to Enable Productive High-Performance
Cloud Computing},
journal = {CoRR},
volume = {abs/2401.04552},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.04552},
doi = {10.48550/ARXIV.2401.04552},
eprinttype = {arXiv},
eprint = {2401.04552},
timestamp = {Wed, 24 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-04552.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-05932,
author = {Langwen Huang and
Lukas Gianinazzi and
Yuejiang Yu and
Peter D. D{\"{u}}ben and
Torsten Hoefler},
title = {DiffDA: a diffusion model for weather-scale data assimilation},
journal = {CoRR},
volume = {abs/2401.05932},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.05932},
doi = {10.48550/ARXIV.2401.05932},
eprinttype = {arXiv},
eprint = {2401.05932},
timestamp = {Thu, 25 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-05932.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-09356,
author = {Daniele De Sensi and
Tommaso Bonato and
David Saam and
Torsten Hoefler},
title = {Swing: Short-cutting Rings for Higher Bandwidth Allreduce},
journal = {CoRR},
volume = {abs/2401.09356},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.09356},
doi = {10.48550/ARXIV.2401.09356},
eprinttype = {arXiv},
eprint = {2401.09356},
timestamp = {Thu, 01 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-09356.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-09359,
author = {Samuel Riedel and
Marc Gantenbein and
Alessandro Ottaviano and
Torsten Hoefler and
Luca Benini},
title = {LRSCwait: Enabling Scalable and Efficient Synchronization in Manycore
Systems through Polling-Free and Retry-Free Operation},
journal = {CoRR},
volume = {abs/2401.09359},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.09359},
doi = {10.48550/ARXIV.2401.09359},
eprinttype = {arXiv},
eprint = {2401.09359},
timestamp = {Thu, 01 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-09359.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-10834,
author = {Lukas M{\"{o}}ller and
Marcin Copik and
Alexandru Calotoiu and
Torsten Hoefler},
title = {Cppless: Productive and Performant Serverless Programming in {C++}},
journal = {CoRR},
volume = {abs/2401.10834},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.10834},
doi = {10.48550/ARXIV.2401.10834},
eprinttype = {arXiv},
eprint = {2401.10834},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-10834.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-10852,
author = {Marcin Copik and
Marcin Chrapek and
Larissa Schmid and
Alexandru Calotoiu and
Torsten Hoefler},
title = {Software Resource Disaggregation for {HPC} with Serverless Computing},
journal = {CoRR},
volume = {abs/2401.10852},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.10852},
doi = {10.48550/ARXIV.2401.10852},
eprinttype = {arXiv},
eprint = {2401.10852},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-10852.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-14295,
author = {Maciej Besta and
Florim Memedi and
Zhenyu Zhang and
Robert Gerstenberger and
Nils Blach and
Piotr Nyczyk and
Marcin Copik and
Grzegorz Kwasniewski and
J{\"{u}}rgen M{\"{u}}ller and
Lukas Gianinazzi and
Ales Kubicek and
Hubert Niewiadomski and
Onur Mutlu and
Torsten Hoefler},
title = {Topologies of Reasoning: Demystifying Chains, Trees, and Graphs of
Thoughts},
journal = {CoRR},
volume = {abs/2401.14295},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.14295},
doi = {10.48550/ARXIV.2401.14295},
eprinttype = {arXiv},
eprint = {2401.14295},
timestamp = {Tue, 06 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-14295.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-15024,
author = {Saleh Ashkboos and
Maximilian L. Croci and
Marcelo Gennari Do Nascimento and
Torsten Hoefler and
James Hensman},
title = {SliceGPT: Compress Large Language Models by Deleting Rows and Columns},
journal = {CoRR},
volume = {abs/2401.15024},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.15024},
doi = {10.48550/ARXIV.2401.15024},
eprinttype = {arXiv},
eprint = {2401.15024},
timestamp = {Tue, 06 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-15024.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/cacm/HoeflerHT23,
author = {Torsten Hoefler and
Thomas H{\"{a}}ner and
Matthias Troyer},
title = {Disentangling Hype from Practicality: On Realistically Achieving Quantum
Advantage},
journal = {Commun. {ACM}},
volume = {66},
number = {5},
pages = {82--87},
year = {2023},
url = {https://doi.org/10.1145/3571725},
doi = {10.1145/3571725},
timestamp = {Thu, 18 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cacm/HoeflerHT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computer/HoeflerRUAGTKAS23,
author = {Torsten Hoefler and
Duncan Roweth and
Keith D. Underwood and
Robert Alverson and
Mark Griswold and
Vahid Tabatabaee and
Mohan Kalkunte and
Surendra Anubolu and
Siyuan Shen and
Moray McLaren and
Abdul Kabbani and
Steve Scott},
title = {Data Center Ethernet and Remote Direct Memory Access: Issues at Hyperscale},
journal = {Computer},
volume = {56},
number = {7},
pages = {67--77},
year = {2023},
url = {https://doi.org/10.1109/MC.2023.3261184},
doi = {10.1109/MC.2023.3261184},
timestamp = {Fri, 07 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computer/HoeflerRUAGTKAS23.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/ijhpca/MatsuokaDWDH23,
author = {Satoshi Matsuoka and
Jens Domke and
Mohamed Wahib and
Aleksandr Drozd and
Torsten Hoefler},
title = {Myths and legends in high-performance computing},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {37},
number = {3-4},
pages = {245--259},
year = {2023},
url = {https://doi.org/10.1177/10943420231166608},
doi = {10.1177/10943420231166608},
timestamp = {Sat, 05 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/MatsuokaDWDH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/BestaFKKH23,
author = {Maciej Besta and
Marc Fischer and
Vasiliki Kalavri and
Michael Kapralov and
Torsten Hoefler},
title = {Practice of Streaming Processing of Dynamic Graphs: Concepts, Models,
and Systems},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {34},
number = {6},
pages = {1860--1876},
year = {2023},
url = {https://doi.org/10.1109/TPDS.2021.3131677},
doi = {10.1109/TPDS.2021.3131677},
timestamp = {Fri, 02 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/BestaFKKH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/SchefflerZSHB23,
author = {Paul Scheffler and
Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Sparse Stream Semantic Registers: {A} Lightweight {ISA} Extension
Accelerating General Sparse Linear Algebra},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {34},
number = {12},
pages = {3147--3161},
year = {2023},
url = {https://doi.org/10.1109/TPDS.2023.3322029},
doi = {10.1109/TPDS.2023.3322029},
timestamp = {Sun, 10 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tpds/SchefflerZSHB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bigdataconf/QiuCWCH23,
author = {Wei Qiu and
Marcin Copik and
Yun Wang and
Alexandru Calotoiu and
Torsten Hoefler},
editor = {Jingrui He and
Themis Palpanas and
Xiaohua Hu and
Alfredo Cuzzocrea and
Dejing Dou and
Dominik Slezak and
Wei Wang and
Aleksandra Gruca and
Jerry Chun{-}Wei Lin and
Rakesh Agrawal},
title = {User-guided Page Merging for Memory Deduplication in Serverless Systems},
booktitle = {{IEEE} International Conference on Big Data, BigData 2023, Sorrento,
Italy, December 15-18, 2023},
pages = {159--169},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/BigData59044.2023.10386487},
doi = {10.1109/BIGDATA59044.2023.10386487},
timestamp = {Fri, 02 Feb 2024 12:00:39 +0100},
biburl = {https://dblp.org/rec/conf/bigdataconf/QiuCWCH23.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/dac/IffBCFBH23,
author = {Patrick Iff and
Maciej Besta and
Matheus A. Cavalcante and
Tim Fischer and
Luca Benini and
Torsten Hoefler},
title = {Sparse Hamming Graph: {A} Customizable Network-on-Chip Topology},
booktitle = {60th {ACM/IEEE} Design Automation Conference, {DAC} 2023, San Francisco,
CA, USA, July 9-13, 2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/DAC56929.2023.10247754},
doi = {10.1109/DAC56929.2023.10247754},
timestamp = {Sun, 24 Sep 2023 13:31:06 +0200},
biburl = {https://dblp.org/rec/conf/dac/IffBCFBH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dac/IffBCFBH23a,
author = {Patrick Iff and
Maciej Besta and
Matheus A. Cavalcante and
Tim Fischer and
Luca Benini and
Torsten Hoefler},
title = {HexaMesh: Scaling to Hundreds of Chiplets with an Optimized Chiplet
Arrangement},
booktitle = {60th {ACM/IEEE} Design Automation Conference, {DAC} 2023, San Francisco,
CA, USA, July 9-13, 2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/DAC56929.2023.10248006},
doi = {10.1109/DAC56929.2023.10248006},
timestamp = {Sun, 24 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dac/IffBCFBH23a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/MatteisGLH23,
author = {Tiziano De Matteis and
Lukas Gianinazzi and
Johannes de Fine Licht and
Torsten Hoefler},
editor = {Ali Raza Butt and
Ningfang Mi and
Kyle Chard},
title = {Streaming Task Graph Scheduling for Dataflow Architectures},
booktitle = {Proceedings of the 32nd International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2023, Orlando, FL, USA,
June 16-23, 2023},
pages = {225--237},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3588195.3592999},
doi = {10.1145/3588195.3592999},
timestamp = {Thu, 31 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hpdc/MatteisGLH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccv/LiGHMEV23,
author = {Yunqiang Li and
Jan C. van Gemert and
Torsten Hoefler and
Bert Moons and
Evangelos Eleftheriou and
Bram{-}Ernst Verhoef},
title = {Differentiable Transportation Pruning},
booktitle = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2023,
Paris, France, October 1-6, 2023},
pages = {16911--16921},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICCV51070.2023.01555},
doi = {10.1109/ICCV51070.2023.01555},
timestamp = {Mon, 22 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iccv/LiGHMEV23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FrantarAHA23,
author = {Elias Frantar and
Saleh Ashkboos and
Torsten Hoefler and
Dan Alistarh},
title = {{OPTQ:} Accurate Quantization for Generative Pre-trained Transformers},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=tcbBPnfwxS},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FrantarAHA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HuangH23,
author = {Langwen Huang and
Torsten Hoefler},
title = {Compressing multidimensional weather and climate data into neural
networks},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=Y5SEe3dfniJ},
timestamp = {Fri, 30 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HuangH23.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/ics/CopikBCH23,
author = {Marcin Copik and
Roman B{\"{o}}hringer and
Alexandru Calotoiu and
Torsten Hoefler},
editor = {Kyle A. Gallivan and
Efstratios Gallopoulos and
Dimitrios S. Nikolopoulos and
Ram{\'{o}}n Beivide},
title = {{FMI:} Fast and Cheap Message Passing for Serverless Functions},
booktitle = {Proceedings of the 37th International Conference on Supercomputing,
{ICS} 2023, Orlando, FL, USA, June 21-23, 2023},
pages = {373--385},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3577193.3593718},
doi = {10.1145/3577193.3593718},
timestamp = {Fri, 07 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/CopikBCH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/CopikTCH23,
author = {Marcin Copik and
Konstantin Taranov and
Alexandru Calotoiu and
Torsten Hoefler},
title = {rFaaS: Enabling High Performance Serverless with {RDMA} and Leases},
booktitle = {{IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2023, St. Petersburg, FL, USA, May 15-19, 2023},
pages = {897--907},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/IPDPS54959.2023.00094},
doi = {10.1109/IPDPS54959.2023.00094},
timestamp = {Tue, 25 Jul 2023 16:27:14 +0200},
biburl = {https://dblp.org/rec/conf/ipps/CopikTCH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/qce/NguyenSSSWRHL23,
author = {Tommy Nguyen and
Yue Shi and
Samuel Alexander Stein and
Tim Stavenger and
Marvin Warner and
Martin Roetteler and
Torsten Hoefler and
Ang Li},
editor = {Brian La Cour and
Lia Yeh and
Marek Osinski},
title = {A Reference Implementation for a Quantum Message Passing Interface},
booktitle = {{IEEE} International Conference on Quantum Computing and Engineering,
{QCE} 2023, Bellevue, WA, USA, September 17-22, 2023},
pages = {292--293},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/QCE57702.2023.10248},
doi = {10.1109/QCE57702.2023.10248},
timestamp = {Fri, 15 Dec 2023 20:24:40 +0100},
biburl = {https://dblp.org/rec/conf/qce/NguyenSSSWRHL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaGFPBEMCMNM23,
author = {Maciej Besta and
Robert Gerstenberger and
Marc Fischer and
Michal Podstawski and
Nils Blach and
Berke Egeli and
George Mitenkov and
Wojciech Chlapek and
Marek T. Michalewicz and
Hubert Niewiadomski and
J{\"{u}}rgen M{\"{u}}ller and
Torsten Hoefler},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {The Graph Database Interface: Scaling Online Transactional and Analytical
Graph Workloads to Hundreds of Thousands of 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 = {22:1--22:18},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3607068},
doi = {10.1145/3581784.3607068},
timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/BestaGFPBEMCMNM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ChrapekKH23,
author = {Marcin Chrapek and
Mikhail Khalilov and
Torsten Hoefler},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {{HEAR:} Homomorphically Encrypted Allreduce},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2023, Denver, CO, USA, November
12-17, 2023},
pages = {36:1--36:17},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3607099},
doi = {10.1145/3581784.3607099},
timestamp = {Tue, 28 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/ChrapekKH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaRGLZCGSSCI23,
author = {Maciej Besta and
Pawel Renc and
Robert Gerstenberger and
Paolo Sylos Labini and
Alexandros Nikolaos Ziogas and
Tiancheng Chen and
Lukas Gianinazzi and
Florian Scheidl and
Kalman Szenes and
Armon Carigiet and
Patrick Iff and
Grzegorz Kwasniewski and
Raghavendra Kanakagiri and
Chio Ge and
Sammy Jaeger and
Jaroslaw Was and
Flavio Vella and
Torsten Hoefler},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {High-Performance and Programmable Attentional Graph Neural Networks
with Global Tensor Formulations},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2023, Denver, CO, USA, November
12-17, 2023},
pages = {66:1--66:16},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3607067},
doi = {10.1145/3581784.3607067},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/BestaRGLZCGSSCI23.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/JiangLZLHSRZRHA23,
author = {Wenqi Jiang and
Shigang Li and
Yu Zhu and
Johannes de Fine Licht and
Zhenhao He and
Runbin Shi and
C{\'{e}}dric Renggli and
Shuai Zhang and
Theodoros Rekatsinas and
Torsten Hoefler and
Gustavo Alonso},
editor = {Dorian Arnold and
Rosa M. Badia and
Kathryn M. Mohror},
title = {Co-design Hardware and Algorithm for Vector Search},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2023, Denver, CO, USA, November
12-17, 2023},
pages = {87:1--87:15},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3581784.3607045},
doi = {10.1145/3581784.3607045},
timestamp = {Fri, 24 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/JiangLZLHSRZRHA23.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}
}
@inproceedings{DBLP:conf/sc/ShiNSSWRHL23,
author = {Yue Shi and
Tommy Nguyen and
Samuel Alexander Stein and
Tim Stavenger and
Marvin Warner and
Martin Roetteler and
Torsten Hoefler and
Ang Li},
title = {A Reference Implementation for a Quantum Message Passing Interface},
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 = {1420--1425},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3624062.3624212},
doi = {10.1145/3624062.3624212},
timestamp = {Thu, 30 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/ShiNSSWRHL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmetrics/SensiMTGRH23,
author = {Daniele De Sensi and
Tiziano De Matteis and
Konstantin Taranov and
Salvatore Di Girolamo and
Tobias Rahn and
Torsten Hoefler},
editor = {Evgenia Smirni and
Konstantin Avrachenkov and
Phillipa Gill and
Bhuvan Urgaonkar},
title = {Noise in the Clouds: Influence of Network Performance Variability
on Application Scalability},
booktitle = {Abstract Proceedings of the 2023 {ACM} {SIGMETRICS} International
Conference on Measurement and Modeling of Computer Systems, {SIGMETRICS}
2023, Orlando, FL, USA, June 19-23, 2023},
pages = {17--18},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3578338.3593555},
doi = {10.1145/3578338.3593555},
timestamp = {Fri, 07 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigmetrics/SensiMTGRH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/LakhotiaIMBHP23,
author = {Kartik Lakhotia and
Kelly Isham and
Laura Monroe and
Maciej Besta and
Torsten Hoefler and
Fabrizio Petrini},
editor = {Kunal Agrawal and
Julian Shun},
title = {In-network Allreduce with Multiple Spanning Trees on PolarFly},
booktitle = {Proceedings of the 35th {ACM} Symposium on Parallelism in Algorithms
and Architectures, {SPAA} 2023, Orlando, FL, USA, June 17-19, 2023},
pages = {165--176},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3558481.3591073},
doi = {10.1145/3558481.3591073},
timestamp = {Thu, 15 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/LakhotiaIMBHP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usenix/IvanovRDCHP23,
author = {Andrei Ivanov and
Benjamin Rothenberger and
Arnaud Dethise and
Marco Canini and
Torsten Hoefler and
Adrian Perrig},
editor = {Julia Lawall and
Dan Williams},
title = {{SAGE:} Software-based Attestation for {GPU} Execution},
booktitle = {2023 {USENIX} Annual Technical Conference, {USENIX} {ATC} 2023, Boston,
MA, USA, July 10-12, 2023},
pages = {485--499},
publisher = {{USENIX} Association},
year = {2023},
url = {https://www.usenix.org/conference/atc23/presentation/ivanov},
timestamp = {Sat, 15 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/usenix/IvanovRDCHP23.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-2301-02432,
author = {Satoshi Matsuoka and
Jens Domke and
Mohamed Wahib and
Aleksandr Drozd and
Torsten Hoefler},
title = {Myths and Legends in High-Performance Computing},
journal = {CoRR},
volume = {abs/2301.02432},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.02432},
doi = {10.48550/ARXIV.2301.02432},
eprinttype = {arXiv},
eprint = {2301.02432},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-02432.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-06813,
author = {Jinfan Chen and
Shigang Li and
Ran Guo and
Jinhui Yuan and
Torsten Hoefler},
title = {AutoDDL: Automatic Distributed Deep Learning with Asymptotically Optimal
Communication},
journal = {CoRR},
volume = {abs/2301.06813},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.06813},
doi = {10.48550/ARXIV.2301.06813},
eprinttype = {arXiv},
eprint = {2301.06813},
timestamp = {Thu, 19 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-06813.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-01066,
author = {Niels Gleinig and
Tobias Rohner and
Torsten Hoefler},
title = {Approximate Reversible Circuits for NISQ-Era Quantum Computers},
journal = {CoRR},
volume = {abs/2302.01066},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.01066},
doi = {10.48550/ARXIV.2302.01066},
eprinttype = {arXiv},
eprint = {2302.01066},
timestamp = {Thu, 09 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-01066.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-03337,
author = {Torsten Hoefler and
Duncan Roweth and
Keith D. Underwood and
Bob Alverson and
Mark Griswold and
Vahid Tabatabaee and
Mohan Kalkunte and
Surendra Anubolu and
Siyuan Shen and
Abdul Kabbani and
Moray McLaren and
Steve Scott},
title = {Datacenter Ethernet and {RDMA:} Issues at Hyperscale},
journal = {CoRR},
volume = {abs/2302.03337},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.03337},
doi = {10.48550/ARXIV.2302.03337},
eprinttype = {arXiv},
eprint = {2302.03337},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-03337.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-07217,
author = {Kartik Lakhotia and
Laura Monroe and
Kelly Isham and
Maciej Besta and
Nils Blach and
Torsten Hoefler and
Fabrizio Petrini},
title = {PolarStar: Expanding the Scalability Horizon of Diameter-3 Networks},
journal = {CoRR},
volume = {abs/2302.07217},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.07217},
doi = {10.48550/ARXIV.2302.07217},
eprinttype = {arXiv},
eprint = {2302.07217},
timestamp = {Mon, 20 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-07217.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-2305-04684,
author = {Kazuki Osawa and
Satoki Ishikawa and
Rio Yokota and
Shigang Li and
Torsten Hoefler},
title = {{ASDL:} {A} Unified Interface for Gradient Preconditioning in PyTorch},
journal = {CoRR},
volume = {abs/2305.04684},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.04684},
doi = {10.48550/ARXIV.2305.04684},
eprinttype = {arXiv},
eprint = {2305.04684},
timestamp = {Fri, 12 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-04684.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-05240,
author = {Thomas Benz and
Michael Rogenmoser and
Paul Scheffler and
Samuel Riedel and
Alessandro Ottaviano and
Andreas Kurth and
Torsten Hoefler and
Luca Benini},
title = {A High-performance, Energy-efficient Modular {DMA} Engine Architecture},
journal = {CoRR},
volume = {abs/2305.05240},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.05240},
doi = {10.48550/ARXIV.2305.05240},
eprinttype = {arXiv},
eprint = {2305.05240},
timestamp = {Fri, 12 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-05240.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-05559,
author = {Paul Scheffler and
Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Sparse Stream Semantic Registers: {A} Lightweight {ISA} Extension
Accelerating General Sparse Linear Algebra},
journal = {CoRR},
volume = {abs/2305.05559},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.05559},
doi = {10.48550/ARXIV.2305.05559},
eprinttype = {arXiv},
eprint = {2305.05559},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-05559.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-08763,
author = {Marcin Copik and
Roman B{\"{o}}hringer and
Alexandru Calotoiu and
Torsten Hoefler},
title = {{FMI:} Fast and Cheap Message Passing for Serverless Functions},
journal = {CoRR},
volume = {abs/2305.08763},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.08763},
doi = {10.48550/ARXIV.2305.08763},
eprinttype = {arXiv},
eprint = {2305.08763},
timestamp = {Wed, 17 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-08763.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-11162,
author = {Maciej Besta and
Robert Gerstenberger and
Marc Fischer and
Michal Podstawski and
J{\"{u}}rgen M{\"{u}}ller and
Nils Blach and
Berke Egeli and
George Mitenkov and
Wojciech Chlapek and
Marek T. Michalewicz and
Torsten Hoefler},
title = {High-Performance Graph Databases That Are Portable, Programmable,
and Scale to Hundreds of Thousands of Cores},
journal = {CoRR},
volume = {abs/2305.11162},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.11162},
doi = {10.48550/ARXIV.2305.11162},
eprinttype = {arXiv},
eprint = {2305.11162},
timestamp = {Sun, 30 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-11162.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-2306-02730,
author = {Tiziano De Matteis and
Lukas Gianinazzi and
Johannes de Fine Licht and
Torsten Hoefler},
title = {Streaming Task Graph Scheduling for Dataflow Architectures},
journal = {CoRR},
volume = {abs/2306.02730},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.02730},
doi = {10.48550/ARXIV.2306.02730},
eprinttype = {arXiv},
eprint = {2306.02730},
timestamp = {Tue, 13 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-02730.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-03078,
author = {Tim Dettmers and
Ruslan Svirschevski and
Vage Egiazarian and
Denis Kuznedelev and
Elias Frantar and
Saleh Ashkboos and
Alexander Borzunov and
Torsten Hoefler and
Dan Alistarh},
title = {SpQR: {A} Sparse-Quantized Representation for Near-Lossless {LLM}
Weight Compression},
journal = {CoRR},
volume = {abs/2306.03078},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.03078},
doi = {10.48550/ARXIV.2306.03078},
eprinttype = {arXiv},
eprint = {2306.03078},
timestamp = {Tue, 13 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-03078.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-11182,
author = {Wenqi Jiang and
Shigang Li and
Yu Zhu and
Johannes de Fine Licht and
Zhenhao He and
Runbin Shi and
C{\'{e}}dric Renggli and
Shuai Zhang and
Theodoros Rekatsinas and
Torsten Hoefler and
Gustavo Alonso},
title = {Co-design Hardware and Algorithm for Vector Search},
journal = {CoRR},
volume = {abs/2306.11182},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.11182},
doi = {10.48550/ARXIV.2306.11182},
eprinttype = {arXiv},
eprint = {2306.11182},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-11182.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-2307-00523,
author = {Torsten Hoefler and
Thomas H{\"{a}}ner and
Matthias Troyer},
title = {Disentangling Hype from Practicality: On Realistically Achieving Quantum
Advantage},
journal = {CoRR},
volume = {abs/2307.00523},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.00523},
doi = {10.48550/ARXIV.2307.00523},
eprinttype = {arXiv},
eprint = {2307.00523},
timestamp = {Mon, 10 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-00523.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-2307-08483,
author = {Yunqiang Li and
Jan C. van Gemert and
Torsten Hoefler and
Bert Moons and
Evangelos Eleftheriou and
Bram{-}Ernst Verhoef},
title = {Differentiable Transportation Pruning},
journal = {CoRR},
volume = {abs/2307.08483},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.08483},
doi = {10.48550/ARXIV.2307.08483},
eprinttype = {arXiv},
eprint = {2307.08483},
timestamp = {Tue, 25 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-08483.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-09687,
author = {Maciej Besta and
Nils Blach and
Ales Kubicek and
Robert Gerstenberger and
Lukas Gianinazzi and
Joanna Gajda and
Tomasz Lehmann and
Michal Podstawski and
Hubert Niewiadomski and
Piotr Nyczyk and
Torsten Hoefler},
title = {Graph of Thoughts: Solving Elaborate Problems with Large Language
Models},
journal = {CoRR},
volume = {abs/2308.09687},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.09687},
doi = {10.48550/ARXIV.2308.09687},
eprinttype = {arXiv},
eprint = {2308.09687},
timestamp = {Fri, 25 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-09687.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-2309-03628,
author = {Mikhail Khalilov and
Marcin Chrapek and
Siyuan Shen and
Alessandro Vezzu and
Thomas Benz and
Salvatore Di Girolamo and
Timo Schneider and
Daniele De Sensi and
Luca Benini and
Torsten Hoefler},
title = {{OSMOSIS:} Enabling Multi-Tenancy in Datacenter SmartNICs},
journal = {CoRR},
volume = {abs/2309.03628},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.03628},
doi = {10.48550/ARXIV.2309.03628},
eprinttype = {arXiv},
eprint = {2309.03628},
timestamp = {Tue, 12 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-03628.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/corr/abs-2309-16214,
author = {Daniele De Sensi and
Edgar Costa Molero and
Salvatore Di Girolamo and
Laurent Vanbever and
Torsten Hoefler},
title = {Canary: Congestion-Aware In-Network Allreduce Using Dynamic Trees},
journal = {CoRR},
volume = {abs/2309.16214},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.16214},
doi = {10.48550/ARXIV.2309.16214},
eprinttype = {arXiv},
eprint = {2309.16214},
timestamp = {Tue, 17 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-16214.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}
}
@article{DBLP:journals/corr/abs-2310-03742,
author = {Nils Blach and
Maciej Besta and
Daniele De Sensi and
Jens Domke and
Hussein Harake and
Shigang Li and
Patrick Iff and
Marek Konieczny and
Kartik Lakhotia and
Ales Kubicek and
Marcel Ferrari and
Fabrizio Petrini and
Torsten Hoefler},
title = {A High-Performance Design, Implementation, Deployment, and Evaluation
of The Slim Fly Network},
journal = {CoRR},
volume = {abs/2310.03742},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.03742},
doi = {10.48550/ARXIV.2310.03742},
eprinttype = {arXiv},
eprint = {2310.03742},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-03742.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-09259,
author = {Saleh Ashkboos and
Ilia Markov and
Elias Frantar and
Tingxuan Zhong and
Xincheng Wang and
Jie Ren and
Torsten Hoefler and
Dan Alistarh},
title = {Towards End-to-end 4-Bit Inference on Generative Large Language Models},
journal = {CoRR},
volume = {abs/2310.09259},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.09259},
doi = {10.48550/ARXIV.2310.09259},
eprinttype = {arXiv},
eprint = {2310.09259},
timestamp = {Wed, 25 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-09259.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-09949,
author = {Wenqi Jiang and
Marco Zeller and
Roger Waleffe and
Torsten Hoefler and
Gustavo Alonso},
title = {Chameleon: a Heterogeneous and Disaggregated Accelerator System for
Retrieval-Augmented Language Models},
journal = {CoRR},
volume = {abs/2310.09949},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.09949},
doi = {10.48550/ARXIV.2310.09949},
eprinttype = {arXiv},
eprint = {2310.09949},
timestamp = {Wed, 25 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-09949.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-06081,
author = {Patrick Iff and
Benigna Bruggmann and
Maciej Besta and
Luca Benini and
Torsten Hoefler},
title = {RapidChiplet: {A} Toolchain for Rapid Design Space Exploration of
Chiplet Architectures},
journal = {CoRR},
volume = {abs/2311.06081},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.06081},
doi = {10.48550/ARXIV.2311.06081},
eprinttype = {arXiv},
eprint = {2311.06081},
timestamp = {Wed, 15 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-06081.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-13588,
author = {Wei Qiu and
Marcin Copik and
Yun Wang and
Alexandru Calotoiu and
Torsten Hoefler},
title = {User-guided Page Merging for Memory Deduplication in Serverless Systems},
journal = {CoRR},
volume = {abs/2311.13588},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.13588},
doi = {10.48550/ARXIV.2311.13588},
eprinttype = {arXiv},
eprint = {2311.13588},
timestamp = {Thu, 30 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-13588.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-18526,
author = {Maciej Besta and
Afonso Claudino Catarino and
Lukas Gianinazzi and
Nils Blach and
Piotr Nyczyk and
Hubert Niewiadomski and
Torsten Hoefler},
title = {{HOT:} Higher-Order Dynamic Graph Representation Learning with Efficient
Transformers},
journal = {CoRR},
volume = {abs/2311.18526},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.18526},
doi = {10.48550/ARXIV.2311.18526},
eprinttype = {arXiv},
eprint = {2311.18526},
timestamp = {Tue, 05 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-18526.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-13547,
author = {Eldar Kurtic and
Torsten Hoefler and
Dan Alistarh},
title = {How to Prune Your Language Model: Recovering Accuracy on the "Sparsity
May Cry" Benchmark},
journal = {CoRR},
volume = {abs/2312.13547},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.13547},
doi = {10.48550/ARXIV.2312.13547},
eprinttype = {arXiv},
eprint = {2312.13547},
timestamp = {Wed, 17 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-13547.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computer/HoeflerHR22,
author = {Torsten Hoefler and
Ariel Hendel and
Duncan Roweth},
title = {The Convergence of Hyperscale Data Center and High-Performance Computing
Networks},
journal = {Computer},
volume = {55},
number = {7},
pages = {29--37},
year = {2022},
url = {https://doi.org/10.1109/MC.2022.3158437},
doi = {10.1109/MC.2022.3158437},
timestamp = {Wed, 06 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computer/HoeflerHR22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computer/Hoefler22,
author = {Torsten Hoefler},
title = {Benchmarking Data Science: 12 Ways to Lie With Statistics and Performance
on Parallel Computers},
journal = {Computer},
volume = {55},
number = {8},
pages = {49--56},
year = {2022},
url = {https://doi.org/10.1109/MC.2022.3152681},
doi = {10.1109/MC.2022.3152681},
timestamp = {Tue, 09 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computer/Hoefler22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/CopikGHBB22,
author = {Marcin Copik and
Tobias Grosser and
Torsten Hoefler and
Paolo Bientinesi and
Benjamin Berkels},
title = {Work-Stealing Prefix Scan: Addressing Load Imbalance in Large-Scale
Image Registration},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {33},
number = {3},
pages = {523--535},
year = {2022},
url = {https://doi.org/10.1109/TPDS.2021.3095230},
doi = {10.1109/TPDS.2021.3095230},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/CopikGHBB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccs/TaranovRSPH22,
author = {Konstantin Taranov and
Benjamin Rothenberger and
Daniele De Sensi and
Adrian Perrig and
Torsten Hoefler},
editor = {Heng Yin and
Angelos Stavrou and
Cas Cremers and
Elaine Shi},
title = {NeVerMore: Exploiting {RDMA} Mistakes in NVMe-oF Storage Applications},
booktitle = {Proceedings of the 2022 {ACM} {SIGSAC} Conference on Computer and
Communications Security, {CCS} 2022, Los Angeles, CA, USA, November
7-11, 2022},
pages = {2765--2778},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3548606.3560568},
doi = {10.1145/3548606.3560568},
timestamp = {Sat, 17 Dec 2022 01:15:29 +0100},
biburl = {https://dblp.org/rec/conf/ccs/TaranovRSPH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/date/CossettiniTVMHB22,
author = {Andrea Cossettini and
Konstantin Taranov and
Christian Vogt and
Michele Magno and
Torsten Hoefler and
Luca Benini},
editor = {Cristiana Bolchini and
Ingrid Verbauwhede and
Ioana Vatajelu},
title = {A {RDMA} Interface for Ultra-Fast Ultrasound Data-Streaming over an
Optical Link},
booktitle = {2022 Design, Automation {\&} Test in Europe Conference {\&}
Exhibition, {DATE} 2022, Antwerp, Belgium, March 14-23, 2022},
pages = {80--83},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.23919/DATE54114.2022.9774599},
doi = {10.23919/DATE54114.2022.9774599},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/date/CossettiniTVMHB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/date/GleinigH22,
author = {Niels Gleinig and
Torsten Hoefler},
editor = {Cristiana Bolchini and
Ingrid Verbauwhede and
Ioana Vatajelu},
title = {Circuits for Measurement Based Quantum State Preparation},
booktitle = {2022 Design, Automation {\&} Test in Europe Conference {\&}
Exhibition, {DATE} 2022, Antwerp, Belgium, March 14-23, 2022},
pages = {328--333},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.23919/DATE54114.2022.9774680},
doi = {10.23919/DATE54114.2022.9774680},
timestamp = {Wed, 25 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/date/GleinigH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsd/BiagioniCFCLMPP22,
author = {Andrea Biagioni and
Paolo Cretaro and
Ottorino Frezza and
Francesca Lo Cicero and
Alessandro Lonardo and
Michele Martinelli and
Pier Stanislao Paolucci and
Elena Pastorelli and
Francesco Simula and
Matteo Turisini and
Piero Vicini and
Roberto Ammendola and
Pascale Bernier{-}Bruna and
Claire Chen and
Said Derradji and
St{\'{e}}phane Guez and
Pierre{-}Axel Lagadec and
Gregoire Pichon and
Etienne Walter and
Gaetan De Gassowski and
Matthieu Hautreaux and
Stephane Mathieu and
Gilles Moreau and
Marc P{\'{e}}rache and
Hugo Taboada and
Torsten Hoefler and
Timo Schneider and
Matteo Barnaba and
Giuseppe Piero Brandino and
Francesco De Giorgi and
Matteo Poggi and
Iakovos Mavroidis and
Yannis Papaefstathiou and
Nikolaos Tampouratzis and
Benjamin Kalisch and
Ulrich Krackhardt and
Mondrian Nuessle and
Pantelis Xirouchakis and
Vangelis Mageiropoulos and
Michalis Gianioudis and
Harisis Loukas and
Aggelos Ioannou and
Nikos Kallimanis and
Nikos Chrysos and
Manolis Katevenis and
Wolfang Frings and
Dominik Gottwald and
Felime Guimaraes and
Max Holicki and
Volker Marx and
Yannik Muller and
Carsten Clauss and
Hugo Falter and
Xu Huang and
Jennifer Lopez Barillao and
Thomas Moschny and
Simon Pickartz and
Francisco J. Alfaro and
Jes{\'{u}}s Escudero{-}Sahuquillo and
Pedro Javier Garc{\'{\i}}a and
Francisco J. Quiles and
Jos{\'{e}} L. S{\'{a}}nchez and
Adri{\'{a}}n Castell{\'{o}} and
Jose Duro and
Mar{\'{\i}}a Engracia G{\'{o}}mez and
Enrique S. Quintana{-}Ort{\'{\i}} and
Julio Sahuquillo and
Eugenio Stabile},
title = {{RED-SEA:} Network Solution for Exascale Architectures},
booktitle = {25th Euromicro Conference on Digital System Design, {DSD} 2022, Maspalomas,
Spain, August 31 - Sept. 2, 2022},
pages = {712--719},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/DSD57027.2022.00100},
doi = {10.1109/DSD57027.2022.00100},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsd/BiagioniCFCLMPP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/exampi/CaoGH22,
author = {Shiyi Cao and
Salvatore Di Girolamo and
Torsten Hoefler},
title = {Accelerating Data Serialization/Deserialization Protocols with In-Network
Compute},
booktitle = {{IEEE/ACM} International Workshop on Exascale MPI, ExaMPI@SC 2022,
Dallas, TX, USA, November 13-18, 2022},
pages = {22--30},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ExaMPI56604.2022.00008},
doi = {10.1109/EXAMPI56604.2022.00008},
timestamp = {Mon, 13 Feb 2023 21:53:09 +0100},
biburl = {https://dblp.org/rec/conf/exampi/CaoGH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fccm/LichtPZSH22,
author = {Johannes de Fine Licht and
Christopher A. Pattison and
Alexandros Nikolaos Ziogas and
David Simmons{-}Duffin and
Torsten Hoefler},
title = {Fast Arbitrary Precision Floating Point on {FPGA}},
booktitle = {30th {IEEE} Annual International Symposium on Field-Programmable Custom
Computing Machines, {FCCM} 2022, New York City, NY, USA, May 15-18,
2022},
pages = {1--9},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/FCCM53951.2022.9786219},
doi = {10.1109/FCCM53951.2022.9786219},
timestamp = {Mon, 13 Jun 2022 16:53:36 +0200},
biburl = {https://dblp.org/rec/conf/fccm/LichtPZSH22.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/iclr/PlummerDFHS22,
author = {Bryan A. Plummer and
Nikoli Dryden and
Julius Frost and
Torsten Hoefler and
Kate Saenko},
title = {Neural Parameter Allocation Search},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=srtIXtySfT4},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/PlummerDFHS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/SchmidCCWRSKH22,
author = {Larissa Schmid and
Marcin Copik and
Alexandru Calotoiu and
Dominik Werle and
Andreas Reiter and
Michael Selzer and
Anne Koziolek and
Torsten Hoefler},
editor = {Lawrence Rauchwerger and
Kirk W. Cameron and
Dimitrios S. Nikolopoulos and
Dionisios N. Pnevmatikatos},
title = {Performance-detective: automatic deduction of cheap and accurate performance
models},
booktitle = {{ICS} '22: 2022 International Conference on Supercomputing, Virtual
Event, June 28 - 30, 2022},
pages = {3:1--3:13},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3524059.3532391},
doi = {10.1145/3524059.3532391},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/SchmidCCWRSKH22.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/icst/LascuDGH22,
author = {Andrei Lascu and
Alastair F. Donaldson and
Tobias Grosser and
Torsten Hoefler},
title = {Metamorphic Fuzzing of {C++} Libraries},
booktitle = {15th {IEEE} Conference on Software Testing, Verification and Validation,
{ICST} 2022, Valencia, Spain, April 4-14, 2022},
pages = {35--46},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICST53961.2022.00015},
doi = {10.1109/ICST53961.2022.00015},
timestamp = {Mon, 13 Jun 2022 16:53:36 +0200},
biburl = {https://dblp.org/rec/conf/icst/LascuDGH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/GleinigBH22,
author = {Niels Gleinig and
Maciej Besta and
Torsten Hoefler},
title = {I/O-Optimal Cache-Oblivious Sparse Matrix-Sparse Matrix Multiplication},
booktitle = {2022 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2022, Lyon, France, May 30 - June 3, 2022},
pages = {36--46},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IPDPS53621.2022.00013},
doi = {10.1109/IPDPS53621.2022.00013},
timestamp = {Fri, 22 Jul 2022 11:14:30 +0200},
biburl = {https://dblp.org/rec/conf/ipps/GleinigBH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/StrauszVGBH22,
author = {Andr{\'{a}}s Strausz and
Flavio Vella and
Salvatore Di Girolamo and
Maciej Besta and
Torsten Hoefler},
title = {Asynchronous Distributed-Memory Triangle Counting and {LCC} with {RMA}
Caching},
booktitle = {2022 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2022, Lyon, France, May 30 - June 3, 2022},
pages = {291--301},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IPDPS53621.2022.00036},
doi = {10.1109/IPDPS53621.2022.00036},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/StrauszVGBH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/BestaGMBKGKAGDH22,
author = {Maciej Besta and
Raphael Grob and
Cesare Miglioli and
Nicola Bernold and
Grzegorz Kwasniewski and
Gabriel Gjini and
Raghavendra Kanakagiri and
Saleh Ashkboos and
Lukas Gianinazzi and
Nikoli Dryden and
Torsten Hoefler},
editor = {Aidong Zhang and
Huzefa Rangwala},
title = {Motif Prediction with Graph Neural Networks},
booktitle = {{KDD} '22: The 28th {ACM} {SIGKDD} Conference on Knowledge Discovery
and Data Mining, Washington, DC, USA, August 14 - 18, 2022},
pages = {35--45},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3534678.3539343},
doi = {10.1145/3534678.3539343},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/kdd/BestaGMBKGKAGDH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/log/BestaISODPCH22,
author = {Maciej Besta and
Patrick Iff and
Florian Scheidl and
Kazuki Osawa and
Nikoli Dryden and
Michal Podstawski and
Tiancheng Chen and
Torsten Hoefler},
editor = {Bastian Rieck and
Razvan Pascanu},
title = {Neural Graph Databases},
booktitle = {Learning on Graphs Conference, LoG 2022, 9-12 December 2022, Virtual
Event},
series = {Proceedings of Machine Learning Research},
volume = {198},
pages = {31},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v198/besta22a.html},
timestamp = {Fri, 17 Feb 2023 16:29:10 +0100},
biburl = {https://dblp.org/rec/conf/log/BestaISODPCH22.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/nips/DrydenH22,
author = {Nikoli Dryden and
Torsten Hoefler},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Spatial Mixture-of-Experts},
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/4c5e2bcbf21bdf40d75fddad0bd43dc9-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/DrydenH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/0002H22,
author = {Shigang Li and
Torsten Hoefler},
editor = {Jaejin Lee and
Kunal Agrawal and
Michael F. Spear},
title = {Near-optimal sparse allreduce for distributed deep learning},
booktitle = {PPoPP '22: 27th {ACM} {SIGPLAN} Symposium on Principles and Practice
of Parallel Programming, Seoul, Republic of Korea, April 2 - 6, 2022},
pages = {135--149},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3503221.3508399},
doi = {10.1145/3503221.3508399},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/0002H22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/GirolamoSTMBSKH22,
author = {Salvatore Di Girolamo and
Daniele De Sensi and
Konstantin Taranov and
Milos Malesevic and
Maciej Besta and
Timo Schneider and
Severin Kistler and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {Building Blocks for Network-Accelerated Distributed File Systems},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {10:1--10:14},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00015},
doi = {10.1109/SC41404.2022.00015},
timestamp = {Wed, 24 May 2023 16:17:06 +0200},
biburl = {https://dblp.org/rec/conf/sc/GirolamoSTMBSKH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerBSGLHBGCS22,
author = {Torsten Hoefler and
Tommaso Bonato and
Daniele De Sensi and
Salvatore Di Girolamo and
Shigang Li and
Marco Heddes and
Jon Belk and
Deepak Goel and
Miguel Castro and
Steve Scott},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {HammingMesh: {A} Network Topology for Large-Scale Deep Learning},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {11:1--11:18},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00016},
doi = {10.1109/SC41404.2022.00016},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/HoeflerBSGLHBGCS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LakhotiaBMIIHP22,
author = {Kartik Lakhotia and
Maciej Besta and
Laura Monroe and
Kelly Isham and
Patrick Iff and
Torsten Hoefler and
Fabrizio Petrini},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {PolarFly: {A} Cost-Effective and Flexible Low-Diameter Topology},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {12:1--12:15},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00017},
doi = {10.1109/SC41404.2022.00017},
timestamp = {Wed, 24 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/LakhotiaBMIIHP22.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 = {Wed, 24 May 2023 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/LiOH22,
author = {Shigang Li and
Kazuki Osawa and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {Efficient Quantized Sparse Matrix Operations on Tensor Cores},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {37:1--37:15},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00042},
doi = {10.1109/SC41404.2022.00042},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/LiOH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaMLTIKAJPKGVMH22,
author = {Maciej Besta and
Cesare Miglioli and
Paolo Sylos Labini and
Jakub Tetek and
Patrick Iff and
Raghavendra Kanakagiri and
Saleh Ashkboos and
Kacper Janda and
Michal Podstawski and
Grzegorz Kwasniewski and
Niels Gleinig and
Flavio Vella and
Onur Mutlu and
Torsten Hoefler},
editor = {Felix Wolf and
Sameer Shende and
Candace Culhane and
Sadaf R. Alam and
Heike Jagode},
title = {ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic
Set Representations},
booktitle = {{SC22:} International Conference for High Performance Computing, Networking,
Storage and Analysis, Dallas, TX, USA, November 13-18, 2022},
pages = {43:1--43:17},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SC41404.2022.00048},
doi = {10.1109/SC41404.2022.00048},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/BestaMLTIKAJPKGVMH22.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}
}
@inproceedings{DBLP:conf/sigmod/TaranovBMH22,
author = {Konstantin Taranov and
Steve Byan and
Virendra J. Marathe and
Torsten Hoefler},
editor = {Zachary G. Ives and
Angela Bonifati and
Amr El Abbadi},
title = {KafkaDirect: Zero-copy Data Access for Apache Kafka over {RDMA} Networks},
booktitle = {{SIGMOD} '22: International Conference on Management of Data, Philadelphia,
PA, USA, June 12 - 17, 2022},
pages = {2191--2204},
publisher = {{ACM}},
year = {2022},
url = {https://doi.org/10.1145/3514221.3526056},
doi = {10.1145/3514221.3526056},
timestamp = {Thu, 16 Mar 2023 09:51:25 +0100},
biburl = {https://dblp.org/rec/conf/sigmod/TaranovBMH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sirocco/GleinigH22,
author = {Niels Gleinig and
Torsten Hoefler},
editor = {Merav Parter},
title = {The Red-Blue Pebble Game on Trees and DAGs with Large Input},
booktitle = {Structural Information and Communication Complexity - 29th International
Colloquium, {SIROCCO} 2022, Paderborn, Germany, June 27-29, 2022,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {13298},
pages = {135--153},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-09993-9\_8},
doi = {10.1007/978-3-031-09993-9\_8},
timestamp = {Tue, 28 Jun 2022 16:23:40 +0200},
biburl = {https://dblp.org/rec/conf/sirocco/GleinigH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-07598,
author = {Shigang Li and
Torsten Hoefler},
title = {Near-Optimal Sparse Allreduce for Distributed Deep Learning},
journal = {CoRR},
volume = {abs/2201.07598},
year = {2022},
url = {https://arxiv.org/abs/2201.07598},
eprinttype = {arXiv},
eprint = {2201.07598},
timestamp = {Fri, 21 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-07598.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-08080,
author = {Konstantin Taranov and
Benjamin Rothenberger and
Daniele De Sensi and
Adrian Perrig and
Torsten Hoefler},
title = {NeVerMore: Exploiting {RDMA} Mistakes in NVMe-oF Storage Applications},
journal = {CoRR},
volume = {abs/2202.08080},
year = {2022},
url = {https://arxiv.org/abs/2202.08080},
eprinttype = {arXiv},
eprint = {2202.08080},
timestamp = {Tue, 01 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-08080.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-13976,
author = {Andr{\'{a}}s Strausz and
Flavio Vella and
Salvatore Di Girolamo and
Maciej Besta and
Torsten Hoefler},
title = {Asynchronous Distributed-Memory Triangle Counting and {LCC} with {RMA}
Caching},
journal = {CoRR},
volume = {abs/2202.13976},
year = {2022},
url = {https://arxiv.org/abs/2202.13976},
eprinttype = {arXiv},
eprint = {2202.13976},
timestamp = {Thu, 03 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-13976.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-14859,
author = {Marcin Copik and
Alexandru Calotoiu and
Konstantin Taranov and
Torsten Hoefler},
title = {FaasKeeper: a Blueprint for Serverless Services},
journal = {CoRR},
volume = {abs/2203.14859},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.14859},
doi = {10.48550/ARXIV.2203.14859},
eprinttype = {arXiv},
eprint = {2203.14859},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-14859.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-06256,
author = {Johannes de Fine Licht and
Christopher A. Pattison and
Alexandros Nikolaos Ziogas and
David Simmons{-}Duffin and
Torsten Hoefler},
title = {Fast Arbitrary Precision Floating Point on {FPGA}},
journal = {CoRR},
volume = {abs/2204.06256},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.06256},
doi = {10.48550/ARXIV.2204.06256},
eprinttype = {arXiv},
eprint = {2204.06256},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-06256.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-2205-09702,
author = {Maciej Besta and
Torsten Hoefler},
title = {Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency
Analysis},
journal = {CoRR},
volume = {abs/2205.09702},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.09702},
doi = {10.48550/ARXIV.2205.09702},
eprinttype = {arXiv},
eprint = {2205.09702},
timestamp = {Mon, 23 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-09702.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-2206-10007,
author = {Salvatore Di Girolamo and
Daniele De Sensi and
Konstantin Taranov and
Milos Malesevic and
Maciej Besta and
Timo Schneider and
Severin Kistler and
Torsten Hoefler},
title = {Building Blocks for Network-Accelerated Distributed File Systems},
journal = {CoRR},
volume = {abs/2206.10007},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.10007},
doi = {10.48550/ARXIV.2206.10007},
eprinttype = {arXiv},
eprint = {2206.10007},
timestamp = {Mon, 27 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-10007.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-2208-01695,
author = {Kartik Lakhotia and
Maciej Besta and
Laura Monroe and
Kelly Isham and
Patrick Iff and
Torsten Hoefler and
Fabrizio Petrini},
title = {PolarFly: {A} Cost-Effective and Flexible Low-Diameter Topology},
journal = {CoRR},
volume = {abs/2208.01695},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2208.01695},
doi = {10.48550/ARXIV.2208.01695},
eprinttype = {arXiv},
eprint = {2208.01695},
timestamp = {Tue, 09 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2208-01695.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-11469,
author = {Maciej Besta and
Cesare Miglioli and
Paolo Sylos Labini and
Jakub Tetek and
Patrick Iff and
Raghavendra Kanakagiri and
Saleh Ashkboos and
Kacper Janda and
Michal Podstawski and
Grzegorz Kwasniewski and
Niels Gleinig and
Flavio Vella and
Onur Mutlu and
Torsten Hoefler},
title = {ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic
Set Representations},
journal = {CoRR},
volume = {abs/2208.11469},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2208.11469},
doi = {10.48550/ARXIV.2208.11469},
eprinttype = {arXiv},
eprint = {2208.11469},
timestamp = {Tue, 30 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2208-11469.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-01346,
author = {Torsten Hoefler and
Tommaso Bonato and
Daniele De Sensi and
Salvatore Di Girolamo and
Shigang Li and
Marco Heddes and
Jon Belk and
Deepak Goel and
Miguel Castro and
Steve Scott},
title = {HammingMesh: {A} Network Topology for Large-Scale Deep Learning},
journal = {CoRR},
volume = {abs/2209.01346},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.01346},
doi = {10.48550/ARXIV.2209.01346},
eprinttype = {arXiv},
eprint = {2209.01346},
timestamp = {Thu, 09 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-01346.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-03125,
author = {Andrei Ivanov and
Benjamin Rothenberger and
Arnaud Dethise and
Marco Canini and
Torsten Hoefler and
Adrian Perrig},
title = {{SAGE:} Software-based Attestation for {GPU} Execution},
journal = {CoRR},
volume = {abs/2209.03125},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.03125},
doi = {10.48550/ARXIV.2209.03125},
eprinttype = {arXiv},
eprint = {2209.03125},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-03125.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-06979,
author = {Shigang Li and
Kazuki Osawa and
Torsten Hoefler},
title = {Efficient Quantized Sparse Matrix Operations on Tensor Cores},
journal = {CoRR},
volume = {abs/2209.06979},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.06979},
doi = {10.48550/ARXIV.2209.06979},
eprinttype = {arXiv},
eprint = {2209.06979},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-06979.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-09732,
author = {Maciej Besta and
Patrick Iff and
Florian Scheidl and
Kazuki Osawa and
Nikoli Dryden and
Michal Podstawski and
Tiancheng Chen and
Torsten Hoefler},
title = {Neural Graph Databases},
journal = {CoRR},
volume = {abs/2209.09732},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.09732},
doi = {10.48550/ARXIV.2209.09732},
eprinttype = {arXiv},
eprint = {2209.09732},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-09732.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-2210-12538,
author = {Langwen Huang and
Torsten Hoefler},
title = {Compressing multidimensional weather and climate data into neural
networks},
journal = {CoRR},
volume = {abs/2210.12538},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.12538},
doi = {10.48550/ARXIV.2210.12538},
eprinttype = {arXiv},
eprint = {2210.12538},
timestamp = {Fri, 28 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-12538.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-15315,
author = {Daniele De Sensi and
Tiziano De Matteis and
Konstantin Taranov and
Salvatore Di Girolamo and
Tobias Rahn and
Torsten Hoefler},
title = {Noise in the Clouds: Influence of Network Performance Variability
on Application Scalability},
journal = {CoRR},
volume = {abs/2210.15315},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.15315},
doi = {10.48550/ARXIV.2210.15315},
eprinttype = {arXiv},
eprint = {2210.15315},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-15315.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-17323,
author = {Elias Frantar and
Saleh Ashkboos and
Torsten Hoefler and
Dan Alistarh},
title = {{GPTQ:} Accurate Post-Training Quantization for Generative Pre-trained
Transformers},
journal = {CoRR},
volume = {abs/2210.17323},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.17323},
doi = {10.48550/ARXIV.2210.17323},
eprinttype = {arXiv},
eprint = {2210.17323},
timestamp = {Thu, 03 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-17323.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-07629,
author = {Michael E. Beverland and
Prakash Murali and
Matthias Troyer and
Krysta M. Svore and
Torsten Hoefler and
Vadym Kliuchnikov and
Guang Hao Low and
Mathias Soeken and
Aarthi Sundaram and
Alexander Vaschillo},
title = {Assessing requirements to scale to practical quantum advantage},
journal = {CoRR},
volume = {abs/2211.07629},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.07629},
doi = {10.48550/ARXIV.2211.07629},
eprinttype = {arXiv},
eprint = {2211.07629},
timestamp = {Wed, 16 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-07629.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-13491,
author = {Nikoli Dryden and
Torsten Hoefler},
title = {Spatial Mixture-of-Experts},
journal = {CoRR},
volume = {abs/2211.13491},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.13491},
doi = {10.48550/ARXIV.2211.13491},
eprinttype = {arXiv},
eprint = {2211.13491},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-13491.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-13980,
author = {Patrick Iff and
Maciej Besta and
Matheus A. Cavalcante and
Tim Fischer and
Luca Benini and
Torsten Hoefler},
title = {Sparse Hamming Graph: {A} Customizable Network-on-Chip Topology},
journal = {CoRR},
volume = {abs/2211.13980},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.13980},
doi = {10.48550/ARXIV.2211.13980},
eprinttype = {arXiv},
eprint = {2211.13980},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-13980.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-13989,
author = {Patrick Iff and
Maciej Besta and
Matheus A. Cavalcante and
Tim Fischer and
Luca Benini and
Torsten Hoefler},
title = {HexaMesh: Scaling to Hundreds of Chiplets with an Optimized Chiplet
Arrangement},
journal = {CoRR},
volume = {abs/2211.13989},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.13989},
doi = {10.48550/ARXIV.2211.13989},
eprinttype = {arXiv},
eprint = {2211.13989},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-13989.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-14133,
author = {Kazuki Osawa and
Shigang Li and
Torsten Hoefler},
title = {PipeFisher: Efficient Training of Large Language Models Using Pipelining
and Fisher Information Matrices},
journal = {CoRR},
volume = {abs/2211.14133},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.14133},
doi = {10.48550/ARXIV.2211.14133},
eprinttype = {arXiv},
eprint = {2211.14133},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-14133.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-09134,
author = {Konstantin Taranov and
Fabian Fischer and
Torsten Hoefler},
title = {Efficient {RDMA} Communication Protocols},
journal = {CoRR},
volume = {abs/2212.09134},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.09134},
doi = {10.48550/ARXIV.2212.09134},
eprinttype = {arXiv},
eprint = {2212.09134},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-09134.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, 21 Mar 2023 00:00:00 +0100},
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/ncs/BauerDHQSW21,
author = {Peter Bauer and
Peter D. D{\"{u}}ben and
Torsten Hoefler and
Tiago Quintino and
Thomas C. Schulthess and
Nils P. Wedi},
title = {The digital revolution of Earth-system science},
journal = {Nat. Comput. Sci.},
volume = {1},
number = {2},
pages = {104--113},
year = {2021},
url = {https://doi.org/10.1038/s43588-021-00023-0},
doi = {10.1038/S43588-021-00023-0},
timestamp = {Mon, 15 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ncs/BauerDHQSW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pacmpl/PitchanathanUWH21,
author = {Arjun Pitchanathan and
Christian Ulmann and
Michel Weber and
Torsten Hoefler and
Tobias Grosser},
title = {{FPL:} fast Presburger arithmetic through transprecision},
journal = {Proc. {ACM} Program. Lang.},
volume = {5},
number = {{OOPSLA}},
pages = {1--26},
year = {2021},
url = {https://doi.org/10.1145/3485539},
doi = {10.1145/3485539},
timestamp = {Wed, 25 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pacmpl/PitchanathanUWH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pomacs/SensiMTGRH21,
author = {Daniele De Sensi and
Tiziano De Matteis and
Konstantin Taranov and
Salvatore Di Girolamo and
Tobias Rahn and
Torsten Hoefler},
title = {Noise in the Clouds: Influence of Network Performance Variability
on Application Scalability},
journal = {Proc. {ACM} Meas. Anal. Comput. Syst.},
volume = {6},
number = {3},
pages = {49:1--49:27},
year = {2021},
url = {https://doi.org/10.1145/3570609},
doi = {10.1145/3570609},
timestamp = {Sun, 15 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pomacs/SensiMTGRH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pvldb/BestaVSSKGBJHLT21,
author = {Maciej Besta and
Zur Vonarburg{-}Shmaria and
Yannick Schaffner and
Leonardo Schwarz and
Grzegorz Kwasniewski and
Lukas Gianinazzi and
Jakub Ber{\'{a}}nek and
Kacper Janda and
Tobias Holenstein and
Sebastian Leisinger and
Peter Tatkowski and
Esref {\"{O}}zdemir and
Adrian Balla and
Marcin Copik and
Philipp Lindenberger and
Marek Konieczny and
Onur Mutlu and
Torsten Hoefler},
title = {GraphMineSuite: Enabling High-Performance and Programmable Graph Mining
Algorithms with Set Algebra},
journal = {Proc. {VLDB} Endow.},
volume = {14},
number = {11},
pages = {1922--1936},
year = {2021},
url = {http://www.vldb.org/pvldb/vol14/p1922-besta.pdf},
doi = {10.14778/3476249.3476252},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pvldb/BestaVSSKGBJHLT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/siamsc/SolomonikDH21,
author = {Edgar Solomonik and
James Demmel and
Torsten Hoefler},
title = {Communication Lower Bounds of Bilinear Algorithms for Symmetric Tensor
Contractions},
journal = {{SIAM} J. Sci. Comput.},
volume = {43},
number = {5},
pages = {A3328--A3356},
year = {2021},
url = {https://doi.org/10.1137/20M1338599},
doi = {10.1137/20M1338599},
timestamp = {Fri, 03 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/siamsc/SolomonikDH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taco/GysiMZHDWFHG21,
author = {Tobias Gysi and
Christoph M{\"{u}}ller and
Oleksandr Zinenko and
Stephan Herhut and
Eddie Davis and
Tobias Wicky and
Oliver Fuhrer and
Torsten Hoefler and
Tobias Grosser},
title = {Domain-Specific Multi-Level {IR} Rewriting for {GPU:} The Open Earth
Compiler for GPU-accelerated Climate Simulation},
journal = {{ACM} Trans. Archit. Code Optim.},
volume = {18},
number = {4},
pages = {51:1--51:23},
year = {2021},
url = {https://doi.org/10.1145/3469030},
doi = {10.1145/3469030},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taco/GysiMZHDWFHG21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/SchuikiZHB21,
author = {Fabian Schuiki and
Florian Zaruba and
Torsten Hoefler and
Luca Benini},
title = {Stream Semantic Registers: {A} Lightweight {RISC-V} {ISA} Extension
Achieving Full Compute Utilization in Single-Issue Cores},
journal = {{IEEE} Trans. Computers},
volume = {70},
number = {2},
pages = {212--227},
year = {2021},
url = {https://doi.org/10.1109/TC.2020.2987314},
doi = {10.1109/TC.2020.2987314},
timestamp = {Tue, 26 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tc/SchuikiZHB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tc/ZarubaSHB21,
author = {Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Snitch: {A} Tiny Pseudo Dual-Issue Processor for Area and Energy Efficient
Execution of Floating-Point Intensive Workloads},
journal = {{IEEE} Trans. Computers},
volume = {70},
number = {11},
pages = {1845--1860},
year = {2021},
url = {https://doi.org/10.1109/TC.2020.3027900},
doi = {10.1109/TC.2020.3027900},
timestamp = {Wed, 03 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tc/ZarubaSHB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/BestaDSKGSSH21,
author = {Maciej Besta and
Jens Domke and
Marcel Schneider and
Marek Konieczny and
Salvatore Di Girolamo and
Timo Schneider and
Ankit Singla and
Torsten Hoefler},
title = {High-Performance Routing With Multipathing and Path Diversity in Ethernet
and {HPC} Networks},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {32},
number = {4},
pages = {943--959},
year = {2021},
url = {https://doi.org/10.1109/TPDS.2020.3035761},
doi = {10.1109/TPDS.2020.3035761},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/BestaDSKGSSH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/LichtBMH21,
author = {Johannes de Fine Licht and
Maciej Besta and
Simon Meierhans and
Torsten Hoefler},
title = {Transformations of High-Level Synthesis Codes for High-Performance
Computing},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {32},
number = {5},
pages = {1014--1029},
year = {2021},
url = {https://doi.org/10.1109/TPDS.2020.3039409},
doi = {10.1109/TPDS.2020.3039409},
timestamp = {Tue, 26 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tpds/LichtBMH21.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/ant/GraurBBRSHA21,
author = {Dan Graur and
Rodrigo Bruno and
Joschka Bischoff and
Marcel Rieser and
Wolfgang Scherr and
Torsten Hoefler and
Gustavo Alonso},
editor = {Elhadi M. Shakshuki and
Ansar{-}Ul{-}Haque Yasar},
title = {Hermes: Enabling efficient large-scale simulation in MATSim},
booktitle = {The 12th International Conference on Ambient Systems, Networks and
Technologies {(ANT} 2021) / The 4th International Conference on Emerging
Data and Industry 4.0 {(EDI40} 2021) / Affiliated Workshops, March
23-26, 2021, Warsaw, Poland},
series = {Procedia Computer Science},
volume = {184},
pages = {635--641},
publisher = {Elsevier},
year = {2021},
url = {https://doi.org/10.1016/j.procs.2021.03.079},
doi = {10.1016/J.PROCS.2021.03.079},
timestamp = {Wed, 27 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ant/GraurBBRSHA21.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/dac/GleinigH21,
author = {Niels Gleinig and
Torsten Hoefler},
title = {An Efficient Algorithm for Sparse Quantum State Preparation},
booktitle = {58th {ACM/IEEE} Design Automation Conference, {DAC} 2021, San Francisco,
CA, USA, December 5-9, 2021},
pages = {433--438},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/DAC18074.2021.9586240},
doi = {10.1109/DAC18074.2021.9586240},
timestamp = {Fri, 12 Nov 2021 12:31:50 +0100},
biburl = {https://dblp.org/rec/conf/dac/GleinigH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/date/SchefflerZSHB21,
author = {Paul Scheffler and
Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Indirection Stream Semantic Register Architecture for Efficient Sparse-Dense
Linear Algebra},
booktitle = {Design, Automation {\&} Test in Europe Conference {\&} Exhibition,
{DATE} 2021, Grenoble, France, February 1-5, 2021},
pages = {1787--1792},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.23919/DATE51398.2021.9474230},
doi = {10.23919/DATE51398.2021.9474230},
timestamp = {Wed, 21 Jul 2021 10:04:34 +0200},
biburl = {https://dblp.org/rec/conf/date/SchefflerZSHB21.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 = {Wed, 09 Jun 2021 15:33:33 +0200},
biburl = {https://dblp.org/rec/conf/ics/ZiogasBSH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/RitterGWCRH021,
author = {Marcus Ritter and
Alexander Gei{\ss} and
Johannes Wehrstein and
Alexandru Calotoiu and
Thorsten Reimann and
Torsten Hoefler and
Felix Wolf},
title = {Noise-Resilient Empirical Performance Modeling with Deep Neural Networks},
booktitle = {35th {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2021, Portland, OR, USA, May 17-21, 2021},
pages = {23--34},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/IPDPS49936.2021.00012},
doi = {10.1109/IPDPS49936.2021.00012},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ipps/RitterGWCRH021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isca/GirolamoKCBSBBH21,
author = {Salvatore Di Girolamo and
Andreas Kurth and
Alexandru Calotoiu and
Thomas Benz and
Timo Schneider and
Jakub Ber{\'{a}}nek and
Luca Benini and
Torsten Hoefler},
title = {A {RISC-V} in-network accelerator for flexible high-performance low-power
packet processing},
booktitle = {48th {ACM/IEEE} Annual International Symposium on Computer Architecture,
{ISCA} 2021, Virtual Event / Valencia, Spain, June 14-18, 2021},
pages = {958--971},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ISCA52012.2021.00079},
doi = {10.1109/ISCA52012.2021.00079},
timestamp = {Mon, 19 Feb 2024 07:32:07 +0100},
biburl = {https://dblp.org/rec/conf/isca/GirolamoKCBSBBH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/micro/BestaKKABKJVGSG21,
author = {Maciej Besta and
Raghavendra Kanakagiri and
Grzegorz Kwasniewski and
Rachata Ausavarungnirun and
Jakub Ber{\'{a}}nek and
Konstantinos Kanellopoulos and
Kacper Janda and
Zur Vonarburg{-}Shmaria and
Lukas Gianinazzi and
Ioana Stefan and
Juan G{\'{o}}mez{-}Luna and
Jakub Golinowski and
Marcin Copik and
Lukas Kapp{-}Schwoerer and
Salvatore Di Girolamo and
Nils Blach and
Marek Konieczny and
Onur Mutlu and
Torsten Hoefler},
title = {{SISA:} Set-Centric Instruction Set Architecture for Graph Mining
on Processing-in-Memory Systems},
booktitle = {{MICRO} '21: 54th Annual {IEEE/ACM} International Symposium on Microarchitecture,
Virtual Event, Greece, October 18-22, 2021},
pages = {282--297},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3466752.3480133},
doi = {10.1145/3466752.3480133},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/micro/BestaKKABKJVGSG21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/middleware/CopikKBPH21,
author = {Marcin Copik and
Grzegorz Kwasniewski and
Maciej Besta and
Michal Podstawski and
Torsten Hoefler},
editor = {Kaiwen Zhang and
Abdelouahed Gherbi and
Nalini Venkatasubramanian and
Lu{\'{\i}}s Veiga},
title = {SeBS: a serverless benchmark suite for function-as-a-service computing},
booktitle = {Middleware '21: 22nd International Middleware Conference, Qu{\'{e}}bec
City, Canada, December 6 - 10, 2021},
pages = {64--78},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3464298.3476133},
doi = {10.1145/3464298.3476133},
timestamp = {Sat, 09 Apr 2022 12:40:10 +0200},
biburl = {https://dblp.org/rec/conf/middleware/CopikKBPH21.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/2021/hash/c9e1074f5b3f9fc8ea15d152add07294-Abstract.html},
timestamp = {Mon, 23 May 2022 11:55:02 +0200},
biburl = {https://dblp.org/rec/conf/mlsys/IvanovDB0H21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/CopikCGW0H21,
author = {Marcin Copik and
Alexandru Calotoiu and
Tobias Grosser and
Nicolas Wicki and
Felix Wolf and
Torsten Hoefler},
editor = {Jaejin Lee and
Erez Petrank},
title = {Extracting clean performance models from tainted programs},
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 = {403--417},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3437801.3441613},
doi = {10.1145/3437801.3441613},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/CopikCGW0H21.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 = {Sun, 12 Jun 2022 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/HanerSHT21,
author = {Thomas H{\"{a}}ner and
Damian S. Steiger and
Torsten Hoefler and
Matthias Troyer},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {Distributed quantum computing with {QMPI}},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {16},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476172},
doi = {10.1145/3458817.3476172},
timestamp = {Tue, 08 Nov 2022 16:03:02 +0100},
biburl = {https://dblp.org/rec/conf/sc/HanerSHT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/0002H21,
author = {Shigang Li and
Torsten Hoefler},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {Chimera: efficiently training large-scale neural networks with bidirectional
pipelines},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {27},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476145},
doi = {10.1145/3458817.3476145},
timestamp = {Tue, 08 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/0002H21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SensiGA0H21,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Saleh Ashkboos and
Shigang Li and
Torsten Hoefler},
editor = {Bronis R. de Supinski and
Mary W. Hall and
Todd Gamblin},
title = {Flare: flexible in-network allreduce},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2021, St. Louis, Missouri, USA, November
14-19, 2021},
pages = {35},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3458817.3476178},
doi = {10.1145/3458817.3476178},
timestamp = {Tue, 08 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/SensiGA0H21.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, 08 Nov 2022 00:00:00 +0100},
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, 08 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/ZiogasSBCMLLH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmod/TaranovGH21,
author = {Konstantin Taranov and
Salvatore Di Girolamo and
Torsten Hoefler},
editor = {Guoliang Li and
Zhanhuai Li and
Stratos Idreos and
Divesh Srivastava},
title = {CoRM: Compactable Remote Memory over {RDMA}},
booktitle = {{SIGMOD} '21: International Conference on Management of Data, Virtual
Event, China, June 20-25, 2021},
pages = {1811--1824},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3448016.3452817},
doi = {10.1145/3448016.3452817},
timestamp = {Mon, 21 Jun 2021 11:48:16 +0200},
biburl = {https://dblp.org/rec/conf/sigmod/TaranovGH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/GianinazziBSH21,
author = {Lukas Gianinazzi and
Maciej Besta and
Yannick Schaffner and
Torsten Hoefler},
editor = {Kunal Agrawal and
Yossi Azar},
title = {Parallel Algorithms for Finding Large Cliques in Sparse Graphs},
booktitle = {{SPAA} '21: 33rd {ACM} Symposium on Parallelism in Algorithms and
Architectures, Virtual Event, USA, 6-8 July, 2021},
pages = {243--253},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3409964.3461800},
doi = {10.1145/3409964.3461800},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/GianinazziBSH21.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 = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/KwasniewskiBGCS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usenix/TaranovBAH21,
author = {Konstantin Taranov and
Rodrigo Bruno and
Gustavo Alonso and
Torsten Hoefler},
editor = {Irina Calciu and
Geoff Kuenning},
title = {Naos: Serialization-free {RDMA} networking in Java},
booktitle = {2021 {USENIX} Annual Technical Conference, {USENIX} {ATC} 2021, July
14-16, 2021},
pages = {1--14},
publisher = {{USENIX} Association},
year = {2021},
url = {https://www.usenix.org/conference/atc21/presentation/taranov},
timestamp = {Thu, 12 Aug 2021 18:08:26 +0200},
biburl = {https://dblp.org/rec/conf/usenix/TaranovBAH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usenix/PlanetaBAHH21,
author = {Maksym Planeta and
Jan Bierbaum and
Leo Sahaya Daphne Antony and
Torsten Hoefler and
Hermann H{\"{a}}rtig},
editor = {Irina Calciu and
Geoff Kuenning},
title = {MigrOS: Transparent Live-Migration Support for Containerised {RDMA}
Applications},
booktitle = {2021 {USENIX} Annual Technical Conference, {USENIX} {ATC} 2021, July
14-16, 2021},
pages = {47--63},
publisher = {{USENIX} Association},
year = {2021},
url = {https://www.usenix.org/conference/atc21/presentation/planeta},
timestamp = {Thu, 12 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/usenix/PlanetaBAHH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uss/RothenbergerTPH21,
author = {Benjamin Rothenberger and
Konstantin Taranov and
Adrian Perrig and
Torsten Hoefler},
editor = {Michael D. Bailey and
Rachel Greenstadt},
title = {ReDMArk: Bypassing {RDMA} Security Mechanisms},
booktitle = {30th {USENIX} Security Symposium, {USENIX} Security 2021, August 11-13,
2021},
pages = {4277--4292},
publisher = {{USENIX} Association},
year = {2021},
url = {https://www.usenix.org/conference/usenixsecurity21/presentation/rothenberger},
timestamp = {Mon, 20 Nov 2023 08:57:49 +0100},
biburl = {https://dblp.org/rec/conf/uss/RothenbergerTPH21.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-2101-11030,
author = {David Ittah and
Thomas H{\"{a}}ner and
Vadym Kliuchnikov and
Torsten Hoefler},
title = {Enabling Dataflow Optimization for Quantum Programs},
journal = {CoRR},
volume = {abs/2101.11030},
year = {2021},
url = {https://arxiv.org/abs/2101.11030},
eprinttype = {arXiv},
eprint = {2101.11030},
timestamp = {Sun, 31 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-11030.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-2103-03653,
author = {Maciej Besta and
Zur Vonarburg{-}Shmaria and
Yannick Schaffner and
Leonardo Schwarz and
Grzegorz Kwasniewski and
Lukas Gianinazzi and
Jakub Ber{\'{a}}nek and
Kacper Janda and
Tobias Holenstein and
Sebastian Leisinger and
Peter Tatkowski and
Esref {\"{O}}zdemir and
Adrian Balla and
Marcin Copik and
Philipp Lindenberger and
Pavel Kalvoda and
Marek Konieczny and
Onur Mutlu and
Torsten Hoefler},
title = {GraphMineSuite: Enabling High-Performance and Programmable Graph Mining
Algorithms with Set Algebra},
journal = {CoRR},
volume = {abs/2103.03653},
year = {2021},
url = {https://arxiv.org/abs/2103.03653},
eprinttype = {arXiv},
eprint = {2103.03653},
timestamp = {Fri, 27 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-03653.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-07582,
author = {Maciej Besta and
Raghavendra Kanakagiri and
Grzegorz Kwasniewski and
Rachata Ausavarungnirun and
Jakub Ber{\'{a}}nek and
Konstantinos Kanellopoulos and
Kacper Janda and
Zur Vonarburg{-}Shmaria and
Lukas Gianinazzi and
Ioana Stefan and
Juan G{\'{o}}mez{-}Luna and
Marcin Copik and
Lukas Kapp{-}Schwoerer and
Salvatore Di Girolamo and
Marek Konieczny and
Onur Mutlu and
Torsten Hoefler},
title = {{SISA:} Set-Centric Instruction Set Architecture for Graph Mining
on Processing-in-Memory Systems},
journal = {CoRR},
volume = {abs/2104.07582},
year = {2021},
url = {https://arxiv.org/abs/2104.07582},
eprinttype = {arXiv},
eprint = {2104.07582},
timestamp = {Tue, 20 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-07582.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-01109,
author = {Thomas H{\"{a}}ner and
Damian S. Steiger and
Torsten Hoefler and
Matthias Troyer},
title = {Distributed Quantum Computing with {QMPI}},
journal = {CoRR},
volume = {abs/2105.01109},
year = {2021},
url = {https://arxiv.org/abs/2105.01109},
eprinttype = {arXiv},
eprint = {2105.01109},
timestamp = {Fri, 14 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-01109.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-2105-12663,
author = {Maciej Besta and
Marcel Schneider and
Salvatore Di Girolamo and
Ankit Singla and
Torsten Hoefler},
title = {Towards Million-Server Network Simulations on Just a Laptop},
journal = {CoRR},
volume = {abs/2105.12663},
year = {2021},
url = {https://arxiv.org/abs/2105.12663},
eprinttype = {arXiv},
eprint = {2105.12663},
timestamp = {Tue, 01 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-12663.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-00761,
author = {Maciej Besta and
Raphael Grob and
Cesare Miglioli and
Nicola Bernold and
Grzegorz Kwasniewski and
Gabriel Gjini and
Raghavendra Kanakagiri and
Saleh Ashkboos and
Lukas Gianinazzi and
Nikoli Dryden and
Torsten Hoefler},
title = {Motif Prediction with Graph Neural Networks},
journal = {CoRR},
volume = {abs/2106.00761},
year = {2021},
url = {https://arxiv.org/abs/2106.00761},
eprinttype = {arXiv},
eprint = {2106.00761},
timestamp = {Wed, 09 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-00761.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-2106-13859,
author = {Marcin Copik and
Konstantin Taranov and
Alexandru Calotoiu and
Torsten Hoefler},
title = {RFaaS: RDMA-Enabled FaaS Platform for Serverless High-Performance
Computing},
journal = {CoRR},
volume = {abs/2106.13859},
year = {2021},
url = {https://arxiv.org/abs/2106.13859},
eprinttype = {arXiv},
eprint = {2106.13859},
timestamp = {Wed, 30 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-13859.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-15565,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Saleh Ashkboos and
Shigang Li and
Torsten Hoefler},
title = {Flare: Flexible In-Network Allreduce},
journal = {CoRR},
volume = {abs/2106.15565},
year = {2021},
url = {https://arxiv.org/abs/2106.15565},
eprinttype = {arXiv},
eprint = {2106.15565},
timestamp = {Mon, 05 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-15565.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-2107-06925,
author = {Shigang Li and
Torsten H{\"{o}}fler},
title = {Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional
Pipelines},
journal = {CoRR},
volume = {abs/2107.06925},
year = {2021},
url = {https://arxiv.org/abs/2107.06925},
eprinttype = {arXiv},
eprint = {2107.06925},
timestamp = {Wed, 21 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-06925.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-2109-09663,
author = {Lukas Gianinazzi and
Maciej Besta and
Yannick Schaffner and
Torsten Hoefler},
title = {Parallel Algorithms for Finding Large Cliques in Sparse Graphs},
journal = {CoRR},
volume = {abs/2109.09663},
year = {2021},
url = {https://arxiv.org/abs/2109.09663},
eprinttype = {arXiv},
eprint = {2109.09663},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-09663.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/pacmpl/HanerHT20,
author = {Thomas H{\"{a}}ner and
Torsten Hoefler and
Matthias Troyer},
title = {Assertion-based optimization of Quantum programs},
journal = {Proc. {ACM} Program. Lang.},
volume = {4},
number = {{OOPSLA}},
pages = {133:1--133:20},
year = {2020},
url = {https://doi.org/10.1145/3428201},
doi = {10.1145/3428201},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pacmpl/HanerHT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pacmpl/GrosserTFPKRSH20,
author = {Tobias Grosser and
Theodoros Theodoridis and
Maximilian Falkenstein and
Arjun Pitchanathan and
Michael Kruse and
Manuel Rigger and
Zhendong Su and
Torsten Hoefler},
title = {Fast linear programming through transprecision computing on small
and sparse data},
journal = {Proc. {ACM} Program. Lang.},
volume = {4},
number = {{OOPSLA}},
pages = {195:1--195:28},
year = {2020},
url = {https://doi.org/10.1145/3428263},
doi = {10.1145/3428263},
timestamp = {Tue, 30 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pacmpl/GrosserTFPKRSH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/TraffH20,
author = {Jesper Larsson Tr{\"{a}}ff and
Torsten Hoefler},
title = {Special issue: Selected papers from EuroMPI 2019},
journal = {Parallel Comput.},
volume = {99},
pages = {102695},
year = {2020},
url = {https://doi.org/10.1016/j.parco.2020.102695},
doi = {10.1016/J.PARCO.2020.102695},
timestamp = {Fri, 18 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pc/TraffH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/superfri/OsunaWTHF20,
author = {Carlos Osuna and
Tobias Wicky and
Fabian Thuering and
Torsten Hoefler and
Oliver Fuhrer},
title = {Dawn: a High-level Domain-Specific Language Compiler Toolchain for
Weather and Climate Applications},
journal = {Supercomput. Front. Innov.},
volume = {7},
number = {2},
pages = {79--97},
year = {2020},
url = {https://doi.org/10.14529/jsfi200205},
doi = {10.14529/JSFI200205},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/superfri/OsunaWTHF20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcad/KhanMGHC20,
author = {Asif Ali Khan and
Hauke Mewes and
Tobias Grosser and
Torsten Hoefler and
Jer{\'{o}}nimo Castrill{\'{o}}n},
title = {Polyhedral Compilation for Racetrack Memories},
journal = {{IEEE} Trans. Comput. Aided Des. Integr. Circuits Syst.},
volume = {39},
number = {11},
pages = {3968--3980},
year = {2020},
url = {https://doi.org/10.1109/TCAD.2020.3012266},
doi = {10.1109/TCAD.2020.3012266},
timestamp = {Thu, 17 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcad/KhanMGHC20.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/dac/KurthRZHB20,
author = {Andreas Kurth and
Samuel Riedel and
Florian Zaruba and
Torsten Hoefler and
Luca Benini},
title = {ATUNs: Modular and Scalable Support for Atomic Operations in a Shared
Memory Multiprocessor},
booktitle = {57th {ACM/IEEE} Design Automation Conference, {DAC} 2020, San Francisco,
CA, USA, July 20-24, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/DAC18072.2020.9218661},
doi = {10.1109/DAC18072.2020.9218661},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dac/KurthRZHB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fpga/LichtKH20,
author = {Johannes de Fine Licht and
Grzegorz Kwasniewski and
Torsten Hoefler},
editor = {Stephen Neuendorffer and
Lesley Shannon},
title = {Flexible Communication Avoiding Matrix Multiplication on {FPGA} with
High-Level Synthesis},
booktitle = {{FPGA} '20: The 2020 {ACM/SIGDA} International Symposium on Field-Programmable
Gate Arrays, Seaside, CA, USA, February 23-25, 2020},
pages = {244--254},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3373087.3375296},
doi = {10.1145/3373087.3375296},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/fpga/LichtKH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/RitterCRRH020,
author = {Marcus Ritter and
Alexandru Calotoiu and
Sebastian Rinke and
Thorsten Reimann and
Torsten Hoefler and
Felix Wolf},
title = {Learning Cost-Effective Sampling Strategies for Empirical Performance
Modeling},
booktitle = {2020 {IEEE} International Parallel and Distributed Processing Symposium
(IPDPS), New Orleans, LA, USA, May 18-22, 2020},
pages = {884--895},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/IPDPS47924.2020.00095},
doi = {10.1109/IPDPS47924.2020.00095},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ipps/RitterCRRH020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BestaKMKRHS20,
author = {Maciej Besta and
Raghavendra Kanakagiri and
Harun Mustafa and
Mikhail Karasikov and
Gunnar R{\"{a}}tsch and
Torsten Hoefler and
Edgar Solomonik},
title = {Communication-Efficient Jaccard similarity for High-Performance Distributed
Genome Comparisons},
booktitle = {2020 {IEEE} International Parallel and Distributed Processing Symposium
(IPDPS), New Orleans, LA, USA, May 18-22, 2020},
pages = {1122--1132},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/IPDPS47924.2020.00118},
doi = {10.1109/IPDPS47924.2020.00118},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ipps/BestaKMKRHS20.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/ppopp/JinWTHLZ20,
author = {Yuyang Jin and
Haojie Wang and
Xiongchao Tang and
Torsten Hoefler and
Xu Liu and
Jidong Zhai},
editor = {Rajiv Gupta and
Xipeng Shen},
title = {Identifying scalability bottlenecks for large-scale parallel programs
with graph analysis},
booktitle = {PPoPP '20: 25th {ACM} {SIGPLAN} Symposium on Principles and Practice
of Parallel Programming, San Diego, California, USA, February 22-26,
2020},
pages = {409--410},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3332466.3374518},
doi = {10.1145/3332466.3374518},
timestamp = {Sun, 12 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/JinWTHLZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/NigayMSH20,
author = {Alexandr Nigay and
Lukas Mosimann and
Timo Schneider and
Torsten Hoefler},
editor = {Wesley Bland and
Kathryn M. Mohror and
Toni Pena},
title = {Communication and Timing Issues with {MPI} Virtualization},
booktitle = {EuroMPI/USA '20: 27th European {MPI} Users' Group Meeting, Virtual
Meeting, Austin, TX, USA, September 21-24, 2020},
pages = {11--20},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3416315.3416317},
doi = {10.1145/3416315.3416317},
timestamp = {Tue, 25 Jul 2023 13:44:09 +0200},
biburl = {https://dblp.org/rec/conf/pvm/NigayMSH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaSKCHGSH20,
author = {Maciej Besta and
Marcel Schneider and
Marek Konieczny and
Karolina Cynk and
Erik Henriksson and
Salvatore Di Girolamo and
Ankit Singla and
Torsten Hoefler},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {FatPaths: routing in supercomputers and data centers when shortest
paths fall short},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {27},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00031},
doi = {10.1109/SC41405.2020.00031},
timestamp = {Wed, 04 May 2022 13:02:27 +0200},
biburl = {https://dblp.org/rec/conf/sc/BestaSKCHGSH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/JinWYTH0Z20,
author = {Yuyang Jin and
Haojie Wang and
Teng Yu and
Xiongchao Tang and
Torsten Hoefler and
Xu Liu and
Jidong Zhai},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {ScalAna: automating scaling loss detection with graph analysis},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {28},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00032},
doi = {10.1109/SC41405.2020.00032},
timestamp = {Mon, 01 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/JinWYTH0Z20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SensiGMRH20,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Kim H. McMahon and
Duncan Roweth and
Torsten Hoefler},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {An in-depth analysis of the slingshot interconnect},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {35},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00039},
doi = {10.1109/SC41405.2020.00039},
timestamp = {Mon, 01 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/SensiGMRH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/MatteisLH20,
author = {Tiziano De Matteis and
Johannes de Fine Licht and
Torsten Hoefler},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {fBLAS: streaming linear algebra on {FPGA}},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {59},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00063},
doi = {10.1109/SC41405.2020.00063},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/MatteisLH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/CalotoiuGKR0HO020,
author = {Alexandru Calotoiu and
Markus Geisenhofer and
Florian Kummer and
Marcus Ritter and
Jens Weber and
Torsten Hoefler and
Martin Oberlack and
Felix Wolf},
title = {Empirical Modeling of Spatially Diverging Performance},
booktitle = {{IEEE/ACM} International Workshop on {HPC} User Support Tools and
Workshop on Programming and Performance Visualization Tools, HUST/ProTools@SC
2020, Atlanta, GA, USA, November 18, 2020},
pages = {71--80},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/HUSTProtools51951.2020.00015},
doi = {10.1109/HUSTPROTOOLS51951.2020.00015},
timestamp = {Fri, 30 Apr 2021 12:35:39 +0200},
biburl = {https://dblp.org/rec/conf/sc/CalotoiuGKR0HO020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaCJVGH20,
author = {Maciej Besta and
Armon Carigiet and
Kacper Janda and
Zur Vonarburg{-}Shmaria and
Lukas Gianinazzi and
Torsten Hoefler},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {High-performance parallel graph coloring with strong guarantees on
work, depth, and quality},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {99},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00103},
doi = {10.1109/SC41405.2020.00103},
timestamp = {Mon, 01 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/BestaCJVGH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/GianinazziH20,
author = {Lukas Gianinazzi and
Torsten Hoefler},
editor = {Christian Scheideler and
Michael Spear},
title = {Parallel Planar Subgraph Isomorphism and Vertex Connectivity},
booktitle = {{SPAA} '20: 32nd {ACM} Symposium on Parallelism in Algorithms and
Architectures, Virtual Event, USA, July 15-17, 2020},
pages = {269--280},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3350755.3400259},
doi = {10.1145/3350755.3400259},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/GianinazziH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/usenix/TaranovRPH20,
author = {Konstantin Taranov and
Benjamin Rothenberger and
Adrian Perrig and
Torsten Hoefler},
editor = {Ada Gavrilovska and
Erez Zadok},
title = {sRDMA - Efficient NIC-based Authentication and Encryption for Remote
Direct Memory Access},
booktitle = {2020 {USENIX} Annual Technical Conference, {USENIX} {ATC} 2020, July
15-17, 2020},
pages = {691--704},
publisher = {{USENIX} Association},
year = {2020},
url = {https://www.usenix.org/conference/atc20/presentation/taranov},
timestamp = {Mon, 01 Feb 2021 08:43:25 +0100},
biburl = {https://dblp.org/rec/conf/usenix/TaranovRPH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncse/CalotoiuCHRS020,
author = {Alexandru Calotoiu and
Marcin Copik and
Torsten Hoefler and
Marcus Ritter and
Sergei Shudler and
Felix Wolf},
editor = {Hans{-}Joachim Bungartz and
Severin Reiz and
Benjamin Uekermann and
Philipp Neumann and
Wolfgang E. Nagel},
title = {ExtraPeak: Advanced Automatic Performance Modeling for {HPC} Applications},
booktitle = {Software for Exascale Computing - {SPPEXA} 2016-2019},
series = {Lecture Notes in Computational Science and Engineering},
volume = {136},
pages = {453--482},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-47956-5\_15},
doi = {10.1007/978-3-030-47956-5\_15},
timestamp = {Thu, 14 Oct 2021 08:45:21 +0200},
biburl = {https://dblp.org/rec/series/lncse/CalotoiuCHRS020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-01653,
author = {Tobias Gysi and
Tobias Grosser and
Laurin Brandner and
Torsten Hoefler},
title = {A Fast Analytical Model of Fully Associative Caches},
journal = {CoRR},
volume = {abs/2001.01653},
year = {2020},
url = {http://arxiv.org/abs/2001.01653},
eprinttype = {arXiv},
eprint = {2001.01653},
timestamp = {Fri, 10 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-01653.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2001-07747,
author = {Robert Gerstenberger and
Maciej Besta and
Torsten Hoefler},
title = {Enabling Highly-Scalable Remote Memory Access Programming with {MPI-3}
One Sided},
journal = {CoRR},
volume = {abs/2001.07747},
year = {2020},
url = {https://arxiv.org/abs/2001.07747},
eprinttype = {arXiv},
eprint = {2001.07747},
timestamp = {Fri, 24 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-07747.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-10143,
author = {Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Snitch: {A} 10 kGE Pseudo Dual-Issue Processor for Area and Energy
Efficient Execution of Floating-Point Intensive Workloads},
journal = {CoRR},
volume = {abs/2002.10143},
year = {2020},
url = {https://arxiv.org/abs/2002.10143},
eprinttype = {arXiv},
eprint = {2002.10143},
timestamp = {Tue, 03 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-10143.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-2005-13014,
author = {Tobias Gysi and
Christoph M{\"{u}}ller and
Oleksandr Zinenko and
Stephan Herhut and
Eddie Davis and
Tobias Wicky and
Oliver Fuhrer and
Torsten Hoefler and
Tobias Grosser},
title = {Domain-Specific Multi-Level {IR} Rewriting for {GPU}},
journal = {CoRR},
volume = {abs/2005.13014},
year = {2020},
url = {https://arxiv.org/abs/2005.13014},
eprinttype = {arXiv},
eprint = {2005.13014},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-13014.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-10598,
author = {Bryan A. Plummer and
Nikoli Dryden and
Julius Frost and
Torsten Hoefler and
Kate Saenko},
title = {Shapeshifter Networks: Cross-layer Parameter Sharing for Scalable
and Effective Deep Learning},
journal = {CoRR},
volume = {abs/2006.10598},
year = {2020},
url = {https://arxiv.org/abs/2006.10598},
eprinttype = {arXiv},
eprint = {2006.10598},
timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-10598.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-2007-01199,
author = {Lukas Gianinazzi and
Torsten Hoefler},
title = {Parallel Planar Subgraph Isomorphism and Vertex Connectivity},
journal = {CoRR},
volume = {abs/2007.01199},
year = {2020},
url = {https://arxiv.org/abs/2007.01199},
eprinttype = {arXiv},
eprint = {2007.01199},
timestamp = {Mon, 06 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-01199.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-03776,
author = {Maciej Besta and
Jens Domke and
Marcel Schneider and
Marek Konieczny and
Salvatore Di Girolamo and
Timo Schneider and
Ankit Singla and
Torsten Hoefler},
title = {High-Performance Routing with Multipathing and Path Diversity in Supercomputers
and Data Centers},
journal = {CoRR},
volume = {abs/2007.03776},
year = {2020},
url = {https://arxiv.org/abs/2007.03776},
eprinttype = {arXiv},
eprint = {2007.03776},
timestamp = {Mon, 20 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-03776.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-08886,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Kim H. McMahon and
Duncan Roweth and
Torsten Hoefler},
title = {An In-Depth Analysis of the Slingshot Interconnect},
journal = {CoRR},
volume = {abs/2008.08886},
year = {2020},
url = {https://arxiv.org/abs/2008.08886},
eprinttype = {arXiv},
eprint = {2008.08886},
timestamp = {Fri, 21 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-08886.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-11321,
author = {Maciej Besta and
Armon Carigiet and
Zur Vonarburg{-}Shmaria and
Kacper Janda and
Lukas Gianinazzi and
Torsten Hoefler},
title = {High-Performance Parallel Graph Coloring with Strong Guarantees on
Work, Depth, and Quality},
journal = {CoRR},
volume = {abs/2008.11321},
year = {2020},
url = {https://arxiv.org/abs/2008.11321},
eprinttype = {arXiv},
eprint = {2008.11321},
timestamp = {Fri, 28 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-11321.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-01692,
author = {Yuyang Jin and
Haojie Wang and
Teng Yu and
Xiongchao Tang and
Torsten Hoefler and
Xu Liu and
Jidong Zhai},
title = {ScalAna: Automating Scaling Loss Detection with Graph Analysis},
journal = {CoRR},
volume = {abs/2009.01692},
year = {2020},
url = {https://arxiv.org/abs/2009.01692},
eprinttype = {arXiv},
eprint = {2009.01692},
timestamp = {Wed, 16 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-01692.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-06988,
author = {Maksym Planeta and
Jan Bierbaum and
Leo Sahaya Daphne Antony and
Torsten Hoefler and
Hermann H{\"{a}}rtig},
title = {TardiS: Migrating Containers with {RDMA} Networks},
journal = {CoRR},
volume = {abs/2009.06988},
year = {2020},
url = {https://arxiv.org/abs/2009.06988},
eprinttype = {arXiv},
eprint = {2009.06988},
timestamp = {Fri, 18 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-06988.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-03536,
author = {Salvatore Di Girolamo and
Andreas Kurth and
Alexandru Calotoiu and
Thomas Benz and
Timo Schneider and
Jakub Ber{\'{a}}nek and
Luca Benini and
Torsten Hoefler},
title = {PsPIN: {A} high-performance low-power architecture for flexible in-network
compute},
journal = {CoRR},
volume = {abs/2010.03536},
year = {2020},
url = {https://arxiv.org/abs/2010.03536},
eprinttype = {arXiv},
eprint = {2010.03536},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-03536.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-2010-09025,
author = {Maciej Besta and
Torsten Hoefler},
title = {Fault Tolerance for Remote Memory Access Programming Models},
journal = {CoRR},
volume = {abs/2010.09025},
year = {2020},
url = {https://arxiv.org/abs/2010.09025},
eprinttype = {arXiv},
eprint = {2010.09025},
timestamp = {Wed, 21 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09025.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09135,
author = {Maciej Besta and
Torsten Hoefler},
title = {Accelerating Irregular Computations with Hardware Transactional Memory
and Active Messages},
journal = {CoRR},
volume = {abs/2010.09135},
year = {2020},
url = {https://arxiv.org/abs/2010.09135},
eprinttype = {arXiv},
eprint = {2010.09135},
timestamp = {Wed, 21 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09135.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09852,
author = {Hermann Schweizer and
Maciej Besta and
Torsten Hoefler},
title = {Evaluating the Cost of Atomic Operations on Modern Architectures},
journal = {CoRR},
volume = {abs/2010.09852},
year = {2020},
url = {https://arxiv.org/abs/2010.09852},
eprinttype = {arXiv},
eprint = {2010.09852},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09852.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09854,
author = {Patrick Schmid and
Maciej Besta and
Torsten Hoefler},
title = {High-Performance Distributed {RMA} Locks},
journal = {CoRR},
volume = {abs/2010.09854},
year = {2020},
url = {https://arxiv.org/abs/2010.09854},
eprinttype = {arXiv},
eprint = {2010.09854},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09854.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09913,
author = {Maciej Besta and
Florian Marending and
Edgar Solomonik and
Torsten Hoefler},
title = {SlimSell: {A} Vectorizable Graph Representation for Breadth-First
Search},
journal = {CoRR},
volume = {abs/2010.09913},
year = {2020},
url = {https://arxiv.org/abs/2010.09913},
eprinttype = {arXiv},
eprint = {2010.09913},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09913.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-10683,
author = {Maciej Besta and
Syed Minhaj Hassan and
Sudhakar Yalamanchili and
Rachata Ausavarungnirun and
Onur Mutlu and
Torsten Hoefler},
title = {Slim NoC: {A} Low-Diameter On-Chip Network Topology for High Energy
Efficiency and Scalability},
journal = {CoRR},
volume = {abs/2010.10683},
year = {2020},
url = {https://arxiv.org/abs/2010.10683},
eprinttype = {arXiv},
eprint = {2010.10683},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-10683.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-12478,
author = {Marcin Copik and
Tobias Grosser and
Torsten Hoefler and
Paolo Bientinesi and
Benjamin Berkels},
title = {Work-stealing prefix scan: Addressing load imbalance in large-scale
image registration},
journal = {CoRR},
volume = {abs/2010.12478},
year = {2020},
url = {https://arxiv.org/abs/2010.12478},
eprinttype = {arXiv},
eprint = {2010.12478},
timestamp = {Tue, 27 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-12478.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-2010-15879,
author = {Maciej Besta and
Dimitri Stanojevic and
Tijana Zivic and
Jagpreet Singh and
Maurice Hoerold and
Torsten Hoefler},
title = {Log(Graph): {A} Near-Optimal High-Performance Graph Representation},
journal = {CoRR},
volume = {abs/2010.15879},
year = {2020},
url = {https://arxiv.org/abs/2010.15879},
eprinttype = {arXiv},
eprint = {2010.15879},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-15879.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-16012,
author = {Maciej Besta and
Michal Podstawski and
Linus Groner and
Edgar Solomonik and
Torsten Hoefler},
title = {To Push or To Pull: On Reducing Communication and Synchronization
in Graph Computations},
journal = {CoRR},
volume = {abs/2010.16012},
year = {2020},
url = {https://arxiv.org/abs/2010.16012},
eprinttype = {arXiv},
eprint = {2010.16012},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-16012.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-2011-08070,
author = {Paul Scheffler and
Florian Zaruba and
Fabian Schuiki and
Torsten Hoefler and
Luca Benini},
title = {Indirection Stream Semantic Register Architecture for Efficient Sparse-Dense
Linear Algebra},
journal = {CoRR},
volume = {abs/2011.08070},
year = {2020},
url = {https://arxiv.org/abs/2011.08070},
eprinttype = {arXiv},
eprint = {2011.08070},
timestamp = {Wed, 18 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-08070.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/corr/abs-2012-14132,
author = {Marcin Copik and
Grzegorz Kwasniewski and
Maciej Besta and
Michal Podstawski and
Torsten Hoefler},
title = {SeBS: {A} Serverless Benchmark Suite for Function-as-a-Service Computing},
journal = {CoRR},
volume = {abs/2012.14132},
year = {2020},
url = {https://arxiv.org/abs/2012.14132},
eprinttype = {arXiv},
eprint = {2012.14132},
timestamp = {Tue, 05 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-14132.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-15592,
author = {Marcin Copik and
Alexandru Calotoiu and
Tobias Grosser and
Nicolas Wicki and
Felix Wolf and
Torsten Hoefler},
title = {Extracting Clean Performance Models from Tainted Programs},
journal = {CoRR},
volume = {abs/2012.15592},
year = {2020},
url = {https://arxiv.org/abs/2012.15592},
eprinttype = {arXiv},
eprint = {2012.15592},
timestamp = {Fri, 08 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-15592.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/YebenesEGQH19,
author = {Pedro Y{\'{e}}benes and
Jes{\'{u}}s Escudero{-}Sahuquillo and
Pedro Javier Garc{\'{\i}}a and
Francisco J. Quiles and
Torsten Hoefler},
title = {Head-of-line blocking avoidance in Slim Fly networks using deadlock-free
non-minimal and adaptive routing},
journal = {Concurr. Comput. Pract. Exp.},
volume = {31},
number = {2},
year = {2019},
url = {https://doi.org/10.1002/cpe.4441},
doi = {10.1002/CPE.4441},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/concurrency/YebenesEGQH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cse/SchulthessBWFHS19,
author = {Thomas C. Schulthess and
Peter Bauer and
Nils Wedi and
Oliver Fuhrer and
Torsten Hoefler and
Christoph M. Sch{\"{a}}r},
title = {Reflecting on the Goal and Baseline for Exascale Computing: {A} Roadmap
Based on Weather and Climate Simulations},
journal = {Comput. Sci. Eng.},
volume = {21},
number = {1},
pages = {30--41},
year = {2019},
url = {https://doi.org/10.1109/MCSE.2018.2888788},
doi = {10.1109/MCSE.2018.2888788},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cse/SchulthessBWFHS19.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}
}
@article{DBLP:journals/pvldb/BarthelsMTAH19,
author = {Claude Barthels and
Ingo M{\"{u}}ller and
Konstantin Taranov and
Gustavo Alonso and
Torsten Hoefler},
title = {Strong consistency is not hard to get: Two-Phase Locking and Two-Phase
Commit on Thousands of Cores},
journal = {Proc. {VLDB} Endow.},
volume = {12},
number = {13},
pages = {2325--2338},
year = {2019},
url = {http://www.vldb.org/pvldb/vol12/p2325-barthels.pdf},
doi = {10.14778/3358701.3358702},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pvldb/BarthelsMTAH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/ShudlerBCHSW19,
author = {Sergei Shudler and
Yannick Berens and
Alexandru Calotoiu and
Torsten Hoefler and
Alexandre Strube and
Felix Wolf},
title = {Engineering Algorithms for Scalability through Continuous Validation
of Performance Expectations},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {30},
number = {8},
pages = {1768--1785},
year = {2019},
url = {https://doi.org/10.1109/TPDS.2019.2896993},
doi = {10.1109/TPDS.2019.2896993},
timestamp = {Fri, 02 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/ShudlerBCHSW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/GysiGH19,
author = {Tobias Gysi and
Tobias Grosser and
Torsten Hoefler},
title = {Absinthe: Learning an Analytical Performance Model to Fuse and Tile
Stencil Codes in One Shot},
booktitle = {28th International Conference on Parallel Architectures and Compilation
Techniques, {PACT} 2019, Seattle, WA, USA, September 23-26, 2019},
pages = {370--382},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/PACT.2019.00036},
doi = {10.1109/PACT.2019.00036},
timestamp = {Wed, 13 Nov 2019 18:02:12 +0100},
biburl = {https://dblp.org/rec/conf/IEEEpact/GysiGH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dac/GleinigHH19,
author = {Niels Gleinig and
Frances Ann Hubis and
Torsten Hoefler},
title = {Embedding Functions Into Reversible Circuits: {A} Probabilistic Approach
to the Number of Lines},
booktitle = {Proceedings of the 56th Annual Design Automation Conference 2019,
{DAC} 2019, Las Vegas, NV, USA, June 02-06, 2019},
pages = {72},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3316781.3317814},
doi = {10.1145/3316781.3317814},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/dac/GleinigHH19.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/ics/EllerHG19,
author = {Paul R. Eller and
Torsten Hoefler and
William Gropp},
editor = {Rudolf Eigenmann and
Chen Ding and
Sally A. McKee},
title = {Using performance models to understand scalable Krylov solver performance
at scale for structured grid problems},
booktitle = {Proceedings of the {ACM} International Conference on Supercomputing,
{ICS} 2019, Phoenix, AZ, USA, June 26-28, 2019},
pages = {138--149},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3330345.3330358},
doi = {10.1145/3330345.3330358},
timestamp = {Tue, 28 Jul 2020 07:46:43 +0200},
biburl = {https://dblp.org/rec/conf/ics/EllerHG19.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 = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/ipps/Ben-NunBHZPH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Hoefler19,
author = {Torsten Hoefler},
title = {Invited Talk 2},
booktitle = {{IEEE} International Parallel and Distributed Processing Symposium
Workshops, {IPDPSW} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
pages = {392},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/IPDPSW.2019.00074},
doi = {10.1109/IPDPSW.2019.00074},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/ipps/Hoefler19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/GirolamoSSH19,
author = {Salvatore Di Girolamo and
Pirmin Schmid and
Thomas C. Schulthess and
Torsten Hoefler},
title = {SimFS: {A} Simulation Data Virtualizing File System Interface},
booktitle = {2019 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
pages = {621--630},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/IPDPS.2019.00071},
doi = {10.1109/IPDPS.2019.00071},
timestamp = {Mon, 09 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ipps/GirolamoSSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pasc/ThalerMOBVAMFSH19,
author = {Felix Thaler and
Stefan Moosbrugger and
Carlos Osuna and
Mauro Bianco and
Hannes Vogt and
Anton Afanasyev and
Lukas Mosimann and
Oliver Fuhrer and
Thomas C. Schulthess and
Torsten Hoefler},
title = {Porting the {COSMO} Weather Model to Manycore CPUs},
booktitle = {Proceedings of the Platform for Advanced Scientific Computing Conference,
{PASC} 2019, Zurich, Switzerland, June 12-14, 2019},
pages = {13:1--13:11},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3324989.3325723},
doi = {10.1145/3324989.3325723},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pasc/ThalerMOBVAMFSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pldi/GysiGBH19,
author = {Tobias Gysi and
Tobias Grosser and
Laurin Brandner and
Torsten Hoefler},
editor = {Kathryn S. McKinley and
Kathleen Fisher},
title = {A fast analytical model of fully associative caches},
booktitle = {Proceedings of the 40th {ACM} {SIGPLAN} Conference on Programming
Language Design and Implementation, {PLDI} 2019, Phoenix, AZ, USA,
June 22-26, 2019},
pages = {816--829},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3314221.3314606},
doi = {10.1145/3314221.3314606},
timestamp = {Sun, 09 Jun 2019 18:52:19 +0200},
biburl = {https://dblp.org/rec/conf/pldi/GysiGBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/KuttlerPBWHBH19,
author = {Martin K{\"{u}}ttler and
Maksym Planeta and
Jan Bierbaum and
Carsten Weinhold and
Hermann H{\"{a}}rtig and
Amnon Barak and
Torsten Hoefler},
editor = {Jeffrey K. Hollingsworth and
Idit Keidar},
title = {Corrected trees for reliable group communication},
booktitle = {Proceedings of the 24th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA,
February 16-20, 2019},
pages = {287--299},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3293883.3295721},
doi = {10.1145/3293883.3295721},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/KuttlerPBWHBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/TraffH19,
author = {Jesper Larsson Tr{\"{a}}ff and
Torsten Hoefler},
editor = {Torsten Hoefler and
Jesper Larsson Tr{\"{a}}ff},
title = {Foreword EuroMPI 2019},
booktitle = {Proceedings of the 26th European {MPI} Users' Group Meeting, EuroMPI
2019, Z{\"{u}}rich, Switzerland, September 11-13, 2019},
pages = {1:1--1:2},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3343211.3343212},
doi = {10.1145/3343211.3343212},
timestamp = {Wed, 11 Sep 2019 12:26:40 +0200},
biburl = {https://dblp.org/rec/conf/pvm/TraffH19.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 = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/ZiogasBFSLH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/RenggliAAAH19,
author = {C{\'{e}}dric Renggli and
Saleh Ashkboos and
Mehdi Aghagolzadeh and
Dan Alistarh and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {SparCML: high-performance sparse communication for machine learning},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {11:1--11:15},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356222},
doi = {10.1145/3295500.3356222},
timestamp = {Sat, 09 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/RenggliAAAH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SensiGH19,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Mitigating network noise on Dragonfly networks through application-aware
routing},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {16:1--16:32},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356196},
doi = {10.1145/3295500.3356196},
timestamp = {Sat, 09 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/SensiGH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KwasniewskiKBVS19,
author = {Grzegorz Kwasniewski and
Marko Kabic and
Maciej Besta and
Joost VandeVondele and
Raffaele Solc{\`{a}} and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplication},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {24:1--24:22},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356181},
doi = {10.1145/3295500.3356181},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/KwasniewskiKBVS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaWGGIOH19,
author = {Maciej Besta and
Simon Weber and
Lukas Gianinazzi and
Robert Gerstenberger and
Andrey Ivanov and
Yishai Oltchik and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Slim graph: practical lossy graph compression for approximate graph
processing, storage, and analytics},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {35:1--35:25},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356182},
doi = {10.1145/3295500.3356182},
timestamp = {Wed, 10 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/BestaWGGIOH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/GirolamoTKSSBBB19,
author = {Salvatore Di Girolamo and
Konstantin Taranov and
Andreas Kurth and
Michael Schaffner and
Timo Schneider and
Jakub Ber{\'{a}}nek and
Maciej Besta and
Luca Benini and
Duncan Roweth and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Network-accelerated non-contiguous memory transfers},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {56:1--56:14},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356189},
doi = {10.1145/3295500.3356189},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/GirolamoTKSSBBB19.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 = {Sat, 09 Nov 2019 00:00:00 +0100},
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 = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/Ben-NunLZSH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/MatteisLBH19,
author = {Tiziano De Matteis and
Johannes de Fine Licht and
Jakub Ber{\'{a}}nek and
Torsten Hoefler},
editor = {Michela Taufer and
Pavan Balaji and
Antonio J. Pe{\~{n}}a},
title = {Streaming message interface: high-performance distributed memory programming
on reconfigurable hardware},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
November 17-19, 2019},
pages = {82:1--82:33},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3295500.3356201},
doi = {10.1145/3295500.3356201},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/MatteisLBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/pvm/2019,
editor = {Torsten Hoefler and
Jesper Larsson Tr{\"{a}}ff},
title = {Proceedings of the 26th European {MPI} Users' Group Meeting, EuroMPI
2019, Z{\"{u}}rich, Switzerland, September 11-13, 2019},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3343211},
doi = {10.1145/3343211},
isbn = {978-1-4503-7175-9},
timestamp = {Wed, 11 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/2019.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-1902-03154,
author = {Salvatore Di Girolamo and
Pirmin Schmid and
Thomas C. Schulthess and
Torsten Hoefler},
title = {SimFS: {A} Simulation Data Virtualizing File System Interface},
journal = {CoRR},
volume = {abs/1902.03154},
year = {2019},
url = {http://arxiv.org/abs/1902.03154},
eprinttype = {arXiv},
eprint = {1902.03154},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-03154.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-1906-10885,
author = {Maciej Besta and
Marcel Schneider and
Karolina Cynk and
Marek Konieczny and
Erik Henriksson and
Salvatore Di Girolamo and
Ankit Singla and
Torsten Hoefler},
title = {FatPaths: Routing in Supercomputers, Data Centers, and Clouds with
Low-Diameter Networks when Shortest Paths Fall Short},
journal = {CoRR},
volume = {abs/1906.10885},
year = {2019},
url = {http://arxiv.org/abs/1906.10885},
eprinttype = {arXiv},
eprint = {1906.10885},
timestamp = {Thu, 27 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-10885.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-07929,
author = {Tiziano De Matteis and
Johannes de Fine Licht and
Torsten Hoefler},
title = {{FBLAS:} Streaming Linear Algebra on {FPGA}},
journal = {CoRR},
volume = {abs/1907.07929},
year = {2019},
url = {http://arxiv.org/abs/1907.07929},
eprinttype = {arXiv},
eprint = {1907.07929},
timestamp = {Tue, 23 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-07929.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-1908-08590,
author = {Salvatore Di Girolamo and
Konstantin Taranov and
Andreas Kurth and
Michael Schaffner and
Timo Schneider and
Jakub Ber{\'{a}}nek and
Maciej Besta and
Luca Benini and
Duncan Roweth and
Torsten Hoefler},
title = {Network-Accelerated Non-Contiguous Memory Transfers},
journal = {CoRR},
volume = {abs/1908.08590},
year = {2019},
url = {http://arxiv.org/abs/1908.08590},
eprinttype = {arXiv},
eprint = {1908.08590},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-08590.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-1908-09606,
author = {Grzegorz Kwasniewski and
Marko Kabic and
Maciej Besta and
Joost VandeVondele and
Raffaele Solc{\`{a}} and
Torsten Hoefler},
title = {Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplication},
journal = {CoRR},
volume = {abs/1908.09606},
year = {2019},
url = {http://arxiv.org/abs/1908.09606},
eprinttype = {arXiv},
eprint = {1908.09606},
timestamp = {Thu, 29 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-09606.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-03231,
author = {Tiziano De Matteis and
Johannes de Fine Licht and
Jakub Ber{\'{a}}nek and
Torsten Hoefler},
title = {Streaming Message Interface: High-Performance Distributed Memory Programming
on Reconfigurable Hardware},
journal = {CoRR},
volume = {abs/1909.03231},
year = {2019},
url = {http://arxiv.org/abs/1909.03231},
eprinttype = {arXiv},
eprint = {1909.03231},
timestamp = {Tue, 17 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-03231.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-07865,
author = {Daniele De Sensi and
Salvatore Di Girolamo and
Torsten Hoefler},
title = {Mitigating Network Noise on Dragonfly Networks through Application-Aware
Routing},
journal = {CoRR},
volume = {abs/1909.07865},
year = {2019},
url = {http://arxiv.org/abs/1909.07865},
eprinttype = {arXiv},
eprint = {1909.07865},
timestamp = {Tue, 24 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-07865.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-04436,
author = {Johannes de Fine Licht and
Torsten Hoefler},
title = {hlslib: Software Engineering for Hardware Design},
journal = {CoRR},
volume = {abs/1910.04436},
year = {2019},
url = {http://arxiv.org/abs/1910.04436},
eprinttype = {arXiv},
eprint = {1910.04436},
timestamp = {Wed, 16 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-04436.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-09017,
author = {Maciej Besta and
Emanuel Peter and
Robert Gerstenberger and
Marc Fischer and
Michal Podstawski and
Claude Barthels and
Gustavo Alonso and
Torsten Hoefler},
title = {Demystifying Graph Databases: Analysis and Taxonomy of Data Organization,
System Designs, and Graph Queries},
journal = {CoRR},
volume = {abs/1910.09017},
year = {2019},
url = {http://arxiv.org/abs/1910.09017},
eprinttype = {arXiv},
eprint = {1910.09017},
timestamp = {Tue, 22 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-09017.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-12897,
author = {Maciej Besta and
Torsten Hoefler},
title = {Active Access: {A} Mechanism for High-Performance Distributed Data-Centric
Computations},
journal = {CoRR},
volume = {abs/1910.12897},
year = {2019},
url = {http://arxiv.org/abs/1910.12897},
eprinttype = {arXiv},
eprint = {1910.12897},
timestamp = {Thu, 31 Oct 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-12897.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-1911-04200,
author = {Maciej Besta and
Raghavendra Kanakagiri and
Harun Mustafa and
Mikhail Karasikov and
Gunnar R{\"{a}}tsch and
Torsten Hoefler and
Edgar Solomonik},
title = {Communication-Efficient Jaccard Similarity for High-Performance Distributed
Genome Comparisons},
journal = {CoRR},
volume = {abs/1911.04200},
year = {2019},
url = {http://arxiv.org/abs/1911.04200},
eprinttype = {arXiv},
eprint = {1911.04200},
timestamp = {Sun, 01 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-04200.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-08356,
author = {Fabian Schuiki and
Florian Zaruba and
Torsten Hoefler and
Luca Benini},
title = {Stream Semantic Registers: {A} Lightweight {RISC-V} {ISA} Extension
Achieving Full Compute Utilization in Single-Issue Cores},
journal = {CoRR},
volume = {abs/1911.08356},
year = {2019},
url = {http://arxiv.org/abs/1911.08356},
eprinttype = {arXiv},
eprint = {1911.08356},
timestamp = {Mon, 02 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-08356.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-06526,
author = {Johannes de Fine Licht and
Grzegorz Kwasniewski and
Torsten Hoefler},
title = {Flexible Communication Avoiding Matrix Multiplication on {FPGA} with
High-Level Synthesis},
journal = {CoRR},
volume = {abs/1912.06526},
year = {2019},
url = {http://arxiv.org/abs/1912.06526},
eprinttype = {arXiv},
eprint = {1912.06526},
timestamp = {Thu, 02 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-06526.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-1912-08950,
author = {Maciej Besta and
Simon Weber and
Lukas Gianinazzi and
Robert Gerstenberger and
Andrey Ivanov and
Yishai Oltchik and
Torsten Hoefler},
title = {Slim Graph: Practical Lossy Graph Compression for Approximate Graph
Processing, Storage, and Analytics},
journal = {CoRR},
volume = {abs/1912.08950},
year = {2019},
url = {http://arxiv.org/abs/1912.08950},
eprinttype = {arXiv},
eprint = {1912.08950},
timestamp = {Wed, 10 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-08950.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-08968,
author = {Maciej Besta and
Torsten Hoefler},
title = {Slim Fly: {A} Cost Effective Low-Diameter Network Topology},
journal = {CoRR},
volume = {abs/1912.08968},
year = {2019},
url = {http://arxiv.org/abs/1912.08968},
eprinttype = {arXiv},
eprint = {1912.08968},
timestamp = {Fri, 03 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-08968.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}
}
@article{DBLP:journals/corr/abs-1912-12740,
author = {Maciej Besta and
Marc Fischer and
Vasiliki Kalavri and
Michael Kapralov and
Torsten Hoefler},
title = {Practice of Streaming and Dynamic Graphs: Concepts, Models, Systems,
and Parallelism},
journal = {CoRR},
volume = {abs/1912.12740},
year = {2019},
url = {http://arxiv.org/abs/1912.12740},
eprinttype = {arXiv},
eprint = {1912.12740},
timestamp = {Sat, 04 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-12740.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cacm/GerstenbergerBH18,
author = {Robert Gerstenberger and
Maciej Besta and
Torsten Hoefler},
title = {Enabling highly scalable remote memory access programming with {MPI-3}
one sided},
journal = {Commun. {ACM}},
volume = {61},
number = {10},
pages = {106--113},
year = {2018},
url = {https://doi.org/10.1145/3264413},
doi = {10.1145/3264413},
timestamp = {Wed, 21 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cacm/GerstenbergerBH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/LiZH18,
author = {Shigang Li and
Yunquan Zhang and
Torsten Hoefler},
title = {Cache-Oblivious {MPI} All-to-All Communications Based on Morton Order},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {29},
number = {3},
pages = {542--555},
year = {2018},
url = {https://doi.org/10.1109/TPDS.2017.2768413},
doi = {10.1109/TPDS.2017.2768413},
timestamp = {Fri, 02 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/LiZH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/BestaSZSHH18,
author = {Maciej Besta and
Dimitri Stanojevic and
Tijana Zivic and
Jagpreet Singh and
Maurice Hoerold and
Torsten Hoefler},
editor = {Skevos Evripidou and
Per Stenstr{\"{o}}m and
Michael F. P. O'Boyle},
title = {Log(graph): a near-optimal high-performance graph representation},
booktitle = {Proceedings of the 27th International Conference on Parallel Architectures
and Compilation Techniques, {PACT} 2018, Limassol, Cyprus, November
01-04, 2018},
pages = {7:1--7:13},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3243176.3243198},
doi = {10.1145/3243176.3243198},
timestamp = {Wed, 21 Nov 2018 12:44:10 +0100},
biburl = {https://dblp.org/rec/conf/IEEEpact/BestaSZSHH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asplos/BestaHYAMH18,
author = {Maciej Besta and
Syed Minhaj Hassan and
Sudhakar Yalamanchili and
Rachata Ausavarungnirun and
Onur Mutlu and
Torsten Hoefler},
editor = {Xipeng Shen and
James Tuck and
Ricardo Bianchini and
Vivek Sarkar},
title = {Slim NoC: {A} Low-Diameter On-Chip Network Topology for High Energy
Efficiency and Scalability},
booktitle = {Proceedings of the Twenty-Third International Conference on Architectural
Support for Programming Languages and Operating Systems, {ASPLOS}
2018, Williamsburg, VA, USA, March 24-28, 2018},
pages = {43--55},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3173162.3177158},
doi = {10.1145/3173162.3177158},
timestamp = {Tue, 23 Jan 2024 20:31:22 +0100},
biburl = {https://dblp.org/rec/conf/asplos/BestaHYAMH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/CalotoiuGHLR018,
author = {Alexandru Calotoiu and
Alexander Graf and
Torsten Hoefler and
Daniel Lorenz and
Sebastian Rinke and
Felix Wolf},
title = {Lightweight Requirements Engineering for Exascale Co-design},
booktitle = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2018,
Belfast, UK, September 10-13, 2018},
pages = {201--211},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/CLUSTER.2018.00038},
doi = {10.1109/CLUSTER.2018.00038},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/CalotoiuGHLR018.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/eurosys/TaranovAH18,
author = {Konstantin Taranov and
Gustavo Alonso and
Torsten Hoefler},
editor = {Rui Oliveira and
Pascal Felber and
Y. Charlie Hu},
title = {Fast and strongly-consistent per-item resilience in key-value stores},
booktitle = {Proceedings of the Thirteenth EuroSys Conference, EuroSys 2018, Porto,
Portugal, April 23-26, 2018},
pages = {39:1--39:14},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3190508.3190536},
doi = {10.1145/3190508.3190536},
timestamp = {Thu, 23 Jun 2022 19:57:07 +0200},
biburl = {https://dblp.org/rec/conf/eurosys/TaranovAH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icde/0002AHA18,
author = {Ingo M{\"{u}}ller and
Andrea Arteaga and
Torsten Hoefler and
Gustavo Alonso},
title = {Reproducible Floating-Point Aggregation in RDBMSs},
booktitle = {34th {IEEE} International Conference on Data Engineering, {ICDE} 2018,
Paris, France, April 16-19, 2018},
pages = {1049--1060},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/ICDE.2018.00098},
doi = {10.1109/ICDE.2018.00098},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icde/0002AHA18.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}
}
@inproceedings{DBLP:conf/nips/AlistarhH0KKR18,
author = {Dan Alistarh and
Torsten Hoefler and
Mikael Johansson and
Nikola Konstantinov and
Sarit Khirirat and
C{\'{e}}dric Renggli},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {The Convergence of Sparsified Gradient Methods},
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 = {5977--5987},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/314450613369e0ee72d0da7f6fee773c-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/AlistarhH0KKR18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/GianinazziKPBH18,
author = {Lukas Gianinazzi and
Pavel Kalvoda and
Alessandro De Palma and
Maciej Besta and
Torsten Hoefler},
editor = {Andreas Krall and
Thomas R. Gross},
title = {Communication-avoiding parallel minimum cuts and connected components},
booktitle = {Proceedings of the 23rd {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, PPoPP 2018, Vienna, Austria, February
24-28, 2018},
pages = {219--232},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3178487.3178504},
doi = {10.1145/3178487.3178504},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/GianinazziKPBH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/LichtBH18,
author = {Johannes de Fine Licht and
Michaela Blott and
Torsten Hoefler},
editor = {Andreas Krall and
Thomas R. Gross},
title = {Designing scalable {FPGA} architectures using high-level synthesis},
booktitle = {Proceedings of the 23rd {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, PPoPP 2018, Vienna, Austria, February
24-28, 2018},
pages = {403--404},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3178487.3178527},
doi = {10.1145/3178487.3178527},
timestamp = {Sun, 12 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/LichtBH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LinZYTXCZHMLZX18,
author = {Heng Lin and
Xiaowei Zhu and
Bowen Yu and
Xiongchao Tang and
Wei Xue and
Wenguang Chen and
Lufei Zhang and
Torsten Hoefler and
Xiaosong Ma and
Xin Liu and
Weimin Zheng and
Jingfang Xu},
title = {ShenTu: processing multi-trillion edge graphs on millions of cores
in seconds},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage, and Analysis, {SC} 2018, Dallas, TX, USA, November
11-16, 2018},
pages = {56:1--56:11},
publisher = {{IEEE} / {ACM}},
year = {2018},
url = {http://dl.acm.org/citation.cfm?id=3291731},
timestamp = {Mon, 24 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/LinZYTXCZHMLZX18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/vmcai/BaumannDMHV18,
author = {Cedric Baumann and
Andrei Marian Dan and
Yuri Meshman and
Torsten Hoefler and
Martin T. Vechev},
editor = {Isil Dillig and
Jens Palsberg},
title = {Automatic Verification of {RMA} Programs via Abstraction Extrapolation},
booktitle = {Verification, Model Checking, and Abstract Interpretation - 19th International
Conference, {VMCAI} 2018, Los Angeles, CA, USA, January 7-9, 2018,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10747},
pages = {47--70},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-319-73721-8\_3},
doi = {10.1007/978-3-319-73721-8\_3},
timestamp = {Tue, 14 May 2019 10:00:43 +0200},
biburl = {https://dblp.org/rec/conf/vmcai/BaumannDMHV18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-08021,
author = {C{\'{e}}dric Renggli and
Dan Alistarh and
Torsten Hoefler},
title = {SparCML: High-Performance Sparse Communication for Machine Learning},
journal = {CoRR},
volume = {abs/1802.08021},
year = {2018},
url = {http://arxiv.org/abs/1802.08021},
eprinttype = {arXiv},
eprint = {1802.08021},
timestamp = {Sun, 16 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-08021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-09883,
author = {Ingo M{\"{u}}ller and
Andrea Arteaga and
Torsten Hoefler and
Gustavo Alonso},
title = {Reproducible Floating-Point Aggregation in RDBMSs},
journal = {CoRR},
volume = {abs/1802.09883},
year = {2018},
url = {http://arxiv.org/abs/1802.09883},
eprinttype = {arXiv},
eprint = {1802.09883},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-09883.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-1805-08288,
author = {Johannes de Fine Licht and
Maciej Besta and
Simon Meierhans and
Torsten Hoefler},
title = {Transformations of High-Level Synthesis Codes for High-Performance
Computing},
journal = {CoRR},
volume = {abs/1805.08288},
year = {2018},
url = {http://arxiv.org/abs/1805.08288},
eprinttype = {arXiv},
eprint = {1805.08288},
timestamp = {Wed, 16 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-08288.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-01799,
author = {Maciej Besta and
Torsten Hoefler},
title = {Survey and Taxonomy of Lossless Graph Compression and Space-Efficient
Graph Representations},
journal = {CoRR},
volume = {abs/1806.01799},
year = {2018},
url = {http://arxiv.org/abs/1806.01799},
eprinttype = {arXiv},
eprint = {1806.01799},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-01799.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}
}
@article{DBLP:journals/corr/abs-1809-10505,
author = {Dan Alistarh and
Torsten Hoefler and
Mikael Johansson and
Sarit Khirirat and
Nikola Konstantinov and
C{\'{e}}dric Renggli},
title = {The Convergence of Sparsified Gradient Methods},
journal = {CoRR},
volume = {abs/1809.10505},
year = {2018},
url = {http://arxiv.org/abs/1809.10505},
eprinttype = {arXiv},
eprint = {1809.10505},
timestamp = {Sun, 16 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-10505.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-00375,
author = {Thomas H{\"{a}}ner and
Torsten Hoefler and
Matthias Troyer},
title = {Using Hoare logic for quantum circuit optimization},
journal = {CoRR},
volume = {abs/1810.00375},
year = {2018},
url = {http://arxiv.org/abs/1810.00375},
eprinttype = {arXiv},
eprint = {1810.00375},
timestamp = {Thu, 01 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-00375.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/debu/BarthelsAH17,
author = {Claude Barthels and
Gustavo Alonso and
Torsten Hoefler},
title = {Designing Databases for Future High-Performance Networks},
journal = {{IEEE} Data Eng. Bull.},
volume = {40},
number = {1},
pages = {15--26},
year = {2017},
url = {http://sites.computer.org/debull/A17mar/p15.pdf},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/debu/BarthelsAH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pvldb/BarthelsAHSM17,
author = {Claude Barthels and
Gustavo Alonso and
Torsten Hoefler and
Timo Schneider and
Ingo M{\"{u}}ller},
title = {Distributed Join Algorithms on Thousands of Cores},
journal = {Proc. {VLDB} Endow.},
volume = {10},
number = {5},
pages = {517--528},
year = {2017},
url = {http://www.vldb.org/pvldb/vol10/p517-barthels.pdf},
doi = {10.14778/3055540.3055545},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pvldb/BarthelsAHSM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/UnatDHSABCCEFFH17,
author = {Didem Unat and
Anshu Dubey and
Torsten Hoefler and
John Shalf and
Mark James Abraham and
Mauro Bianco and
Bradford L. Chamberlain and
Romain Cledat and
H. Carter Edwards and
Hal Finkel and
Karl Fuerlinger and
Frank Hannig and
Emmanuel Jeannot and
Amir Kamil and
Jeff Keasler and
Paul H. J. Kelly and
Vitus J. Leung and
Hatem Ltaief and
Naoya Maruyama and
Chris J. Newburn and
Miquel Peric{\`{a}}s},
title = {Trends in Data Locality Abstractions for {HPC} Systems},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {28},
number = {10},
pages = {3007--3020},
year = {2017},
url = {https://doi.org/10.1109/TPDS.2017.2703149},
doi = {10.1109/TPDS.2017.2703149},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tpds/UnatDHSABCCEFFH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ciac/FoersterGHKSW17,
author = {Klaus{-}Tycho Foerster and
Linus Groner and
Torsten Hoefler and
Michael K{\"{o}}nig and
Sascha Schmid and
Roger Wattenhofer},
editor = {Dimitris Fotakis and
Aris Pagourtzis and
Vangelis Th. Paschos},
title = {Multi-agent Pathfinding with n Agents on Graphs with n Vertices: Combinatorial
Classification and Tight Algorithmic Bounds},
booktitle = {Algorithms and Complexity - 10th International Conference, {CIAC}
2017, Athens, Greece, May 24-26, 2017, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10236},
pages = {247--259},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-57586-5\_21},
doi = {10.1007/978-3-319-57586-5\_21},
timestamp = {Mon, 30 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ciac/FoersterGHKSW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/YebenesEG0H17,
author = {Pedro Y{\'{e}}benes and
Jes{\'{u}}s Escudero{-}Sahuquillo and
Pedro Javier Garc{\'{\i}}a and
Francisco J. Quiles and
Torsten Hoefler},
title = {Improving Non-minimal and Adaptive Routing Algorithms in Slim Fly
Networks},
booktitle = {25th {IEEE} Annual Symposium on High-Performance Interconnects, {HOTI}
2017, Santa Clara, CA, USA, August 28-30, 2017},
pages = {1--8},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/HOTI.2017.11},
doi = {10.1109/HOTI.2017.11},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/YebenesEG0H17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/SchneiderDFUH17,
author = {Timo Schneider and
James Dinan and
Mario Flajslik and
Keith D. Underwood and
Torsten Hoefler},
title = {Fast Networks and Slow Memories: {A} Mechanism for Mitigating Bandwidth
Mismatches},
booktitle = {25th {IEEE} Annual Symposium on High-Performance Interconnects, {HOTI}
2017, Santa Clara, CA, USA, August 28-30, 2017},
pages = {17--24},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/HOTI.2017.17},
doi = {10.1109/HOTI.2017.17},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/SchneiderDFUH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpca/YebenesEG0H17,
author = {Pedro Y{\'{e}}benes and
Jes{\'{u}}s Escudero{-}Sahuquillo and
Pedro Javier Garc{\'{\i}}a and
Francisco J. Quiles and
Torsten Hoefler},
editor = {Jes{\'{u}}s Escudero{-}Sahuquillo and
Pedro Javier Garc{\'{\i}}a},
title = {An Effective Queuing Scheme to Provide Slim Fly Topologies with HoL
Blocking Reduction and Deadlock Freedom for Minimal-Path Routing},
booktitle = {3rd {IEEE} International Workshop on High-Performance Interconnection
Networks in the Exascale and Big-Data Era, HiPINEB@HPCA 2017, Austin,
TX, USA, February 5, 2017},
pages = {25--32},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/HiPINEB.2017.9},
doi = {10.1109/HIPINEB.2017.9},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpca/YebenesEG0H17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/BestaPGSH17,
author = {Maciej Besta and
Michal Podstawski and
Linus Groner and
Edgar Solomonik and
Torsten Hoefler},
editor = {H. Howie Huang and
Jon B. Weissman and
Adriana Iamnitchi and
Alexandru Iosup},
title = {To Push or To Pull: On Reducing Communication and Synchronization
in Graph Computations},
booktitle = {Proceedings of the 26th International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2017, Washington, DC, USA,
June 26-30, 2017},
pages = {93--104},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3078597.3078616},
doi = {10.1145/3078597.3078616},
timestamp = {Tue, 06 Nov 2018 11:07:20 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/BestaPGSH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/PokeHG17,
author = {Marius Poke and
Torsten Hoefler and
Colin W. Glass},
editor = {H. Howie Huang and
Jon B. Weissman and
Adriana Iamnitchi and
Alexandru Iosup},
title = {AllConcur: Leaderless Concurrent Atomic Broadcast},
booktitle = {Proceedings of the 26th International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2017, Washington, DC, USA,
June 26-30, 2017},
pages = {205--218},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3078597.3078598},
doi = {10.1145/3078597.3078598},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/PokeHG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/ArteagaFHS17,
author = {Andrea Arteaga and
Oliver Fuhrer and
Torsten Hoefler and
Thomas C. Schulthess},
editor = {Petros Koumoutsakos and
Michael Lees and
Valeria V. Krzhizhanovskaya and
Jack J. Dongarra and
Peter M. A. Sloot},
title = {Model-Driven Choice of Numerical Methods for the Solution of the Linear
Advection Equation},
booktitle = {International Conference on Computational Science, {ICCS} 2017, 12-14
June 2017, Zurich, Switzerland},
series = {Procedia Computer Science},
volume = {108},
pages = {1542--1551},
publisher = {Elsevier},
year = {2017},
url = {https://doi.org/10.1016/j.procs.2017.05.208},
doi = {10.1016/J.PROCS.2017.05.208},
timestamp = {Thu, 08 Jul 2021 16:04:01 +0200},
biburl = {https://dblp.org/rec/conf/iccS/ArteagaFHS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BestaMSH17,
author = {Maciej Besta and
Florian Marending and
Edgar Solomonik and
Torsten Hoefler},
title = {SlimSell: {A} Vectorizable Graph Representation for Breadth-First
Search},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
pages = {32--41},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPS.2017.93},
doi = {10.1109/IPDPS.2017.93},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/BestaMSH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/RamosH17,
author = {Sabela Ramos and
Torsten Hoefler},
title = {Capability Models for Manycore Memory Systems: {A} Case-Study with
Xeon Phi {KNL}},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
pages = {297--306},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPS.2017.30},
doi = {10.1109/IPDPS.2017.30},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/RamosH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerBSD17,
author = {Torsten Hoefler and
Amnon Barak and
Amnon Shiloh and
Zvi Drezner},
title = {Corrected Gossip Algorithms for Fast Reliable Broadcast on Unreliable
Systems},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
pages = {357--366},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPS.2017.36},
doi = {10.1109/IPDPS.2017.36},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerBSD17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/WickySH17,
author = {Tobias Wicky and
Edgar Solomonik and
Torsten Hoefler},
title = {Communication-Avoiding Parallel Algorithms for Solving Triangular
Systems of Linear Equations},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
pages = {678--687},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPS.2017.104},
doi = {10.1109/IPDPS.2017.104},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/WickySH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/GirolamoVH17,
author = {Salvatore Di Girolamo and
Flavio Vella and
Torsten Hoefler},
title = {Transparent Caching for {RMA} Systems},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2017, Orlando, FL, USA, May 29 - June 2, 2017},
pages = {1018--1027},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPS.2017.92},
doi = {10.1109/IPDPS.2017.92},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/GirolamoVH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/SongH17,
author = {Shuaiwen Leon Song and
Torsten Hoefler},
title = {{IPDRM} Workshop Introduction},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium
Workshops, {IPDPS} Workshops 2017, Orlando / Buena Vista, FL, USA,
May 29 - June 2, 2017},
pages = {1284},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPSW.2017.184},
doi = {10.1109/IPDPSW.2017.184},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/SongH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Hoefler17,
author = {Torsten Hoefler},
title = {{EMBRACE} Keynote},
booktitle = {2017 {IEEE} International Parallel and Distributed Processing Symposium
Workshops, {IPDPS} Workshops 2017, Orlando / Buena Vista, FL, USA,
May 29 - June 2, 2017},
pages = {1558},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/IPDPSW.2017.220},
doi = {10.1109/IPDPSW.2017.220},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/Hoefler17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/ShudlerCHW17,
author = {Sergei Shudler and
Alexandru Calotoiu and
Torsten Hoefler and
Felix Wolf},
editor = {Vivek Sarkar and
Lawrence Rauchwerger},
title = {Isoefficiency in Practice: Configuring and Understanding the Performance
of Task-based Applications},
booktitle = {Proceedings of the 22nd {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, Austin, TX, USA, February 4-8, 2017},
pages = {131--143},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3018743.3018770},
doi = {10.1145/3018743.3018770},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/ShudlerCHW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/0002ZH17,
author = {Shigang Li and
Yunquan Zhang and
Torsten Hoefler},
editor = {Vivek Sarkar and
Lawrence Rauchwerger},
title = {{POSTER:} Cache-Oblivious {MPI} All-to-All Communications on Many-Core
Architectures},
booktitle = {Proceedings of the 22nd {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, Austin, TX, USA, February 4-8, 2017},
pages = {445--446},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3018743.3019025},
doi = {10.1145/3018743.3019025},
timestamp = {Sun, 12 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/0002ZH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SolomonikBVH17,
author = {Edgar Solomonik and
Maciej Besta and
Flavio Vella and
Torsten Hoefler},
editor = {Bernd Mohr and
Padma Raghavan},
title = {Scaling betweenness centrality using communication-efficient sparse
matrix multiplication},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2017, Denver, CO, USA, November
12 - 17, 2017},
pages = {47},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3126908.3126971},
doi = {10.1145/3126908.3126971},
timestamp = {Tue, 08 Nov 2022 16:03:02 +0100},
biburl = {https://dblp.org/rec/conf/sc/SolomonikBVH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerGTGB17,
author = {Torsten Hoefler and
Salvatore Di Girolamo and
Konstantin Taranov and
Ryan E. Grant and
Ron Brightwell},
editor = {Bernd Mohr and
Padma Raghavan},
title = {sPIN: high-performance streaming processing in the network},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2017, Denver, CO, USA, November
12 - 17, 2017},
pages = {59},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3126908.3126970},
doi = {10.1145/3126908.3126970},
timestamp = {Tue, 08 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/HoeflerGTGB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/SolomonikBDH17,
author = {Edgar Solomonik and
Grey Ballard and
James Demmel and
Torsten Hoefler},
editor = {Christian Scheideler and
Mohammad Taghi Hajiaghayi},
title = {A Communication-Avoiding Parallel Algorithm for the Symmetric Eigenvalue
Problem},
booktitle = {Proceedings of the 29th {ACM} Symposium on Parallelism in Algorithms
and Architectures, {SPAA} 2017, Washington DC, USA, July 24-26, 2017},
pages = {111--121},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3087556.3087561},
doi = {10.1145/3087556.3087561},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spaa/SolomonikBDH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/hpdc/2017ross,
editor = {Torsten Hoefler and
Kamil Iskra},
title = {Proceedings of the 7th International Workshop on Runtime and Operating
Systems for Supercomputers, ROSS@HPDC 2017, Washingon, DC, DC, USA,
June 27 - 27, 2017},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3095770},
doi = {10.1145/3095770},
isbn = {978-1-4503-5086-0},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/2017ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SolomonikDH17,
author = {Edgar Solomonik and
James Demmel and
Torsten Hoefler},
title = {Communication Lower Bounds of Bilinear Algorithms for Symmetric Tensor
Contractions},
journal = {CoRR},
volume = {abs/1707.04618},
year = {2017},
url = {http://arxiv.org/abs/1707.04618},
eprinttype = {arXiv},
eprint = {1707.04618},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SolomonikDH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-05483,
author = {Torsten Hoefler and
Salvatore Di Girolamo and
Konstantin Taranov and
Ryan E. Grant and
Ron Brightwell},
title = {sPIN: High-performance streaming Processing in the Network},
journal = {CoRR},
volume = {abs/1709.05483},
year = {2017},
url = {http://arxiv.org/abs/1709.05483},
eprinttype = {arXiv},
eprint = {1709.05483},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-05483.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/WidenerLFH16,
author = {Patrick M. Widener and
Scott Levy and
Kurt B. Ferreira and
Torsten Hoefler},
title = {On noise and the performance benefit of nonblocking collectives},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {30},
number = {1},
pages = {121--133},
year = {2016},
url = {https://doi.org/10.1177/1094342015611952},
doi = {10.1177/1094342015611952},
timestamp = {Sun, 12 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijhpca/WidenerLFH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/micro/GirolamoJUH16,
author = {Salvatore Di Girolamo and
Pierre Jolivet and
Keith D. Underwood and
Torsten Hoefler},
title = {Exploiting Offload-Enabled Network Interfaces},
journal = {{IEEE} Micro},
volume = {36},
number = {4},
pages = {6--17},
year = {2016},
url = {https://doi.org/10.1109/MM.2016.56},
doi = {10.1109/MM.2016.56},
timestamp = {Sat, 20 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/micro/GirolamoJUH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/RamosH16,
author = {Sabela Ramos and
Torsten Hoefler},
title = {Cache Line Aware Algorithm Design for Cache-Coherent Architectures},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {27},
number = {10},
pages = {2824--2837},
year = {2016},
url = {https://doi.org/10.1109/TPDS.2016.2516540},
doi = {10.1109/TPDS.2016.2516540},
timestamp = {Fri, 02 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/RamosH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/CalotoiuBEHKSW16,
author = {Alexandru Calotoiu and
David Beckingsale and
Christopher W. Earl and
Torsten Hoefler and
Ian Karlin and
Martin Schulz and
Felix Wolf},
title = {Fast Multi-parameter Performance Modeling},
booktitle = {2016 {IEEE} International Conference on Cluster Computing, {CLUSTER}
2016, Taipei, Taiwan, September 12-16, 2016},
pages = {172--181},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/CLUSTER.2016.57},
doi = {10.1109/CLUSTER.2016.57},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/CalotoiuBEHKSW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/SchneiderBH16,
author = {Timo Schneider and
Otto Bibartiu and
Torsten Hoefler},
title = {Ensuring Deadlock-Freedom in Low-Diameter InfiniBand Networks},
booktitle = {24th {IEEE} Annual Symposium on High-Performance Interconnects, {HOTI}
2016, Santa Clara, CA, USA, August 24-26, 2016},
pages = {1--8},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/HOTI.2016.015},
doi = {10.1109/HOTI.2016.015},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/SchneiderBH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/DomkeHM16,
author = {Jens Domke and
Torsten Hoefler and
Satoshi Matsuoka},
editor = {Hiroshi Nakashima and
Kenjiro Taura and
Jack Lange},
title = {Routing on the Dependency Graph: {A} New Approach to Deadlock-Free
High-Performance Routing},
booktitle = {Proceedings of the 25th {ACM} International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2016, Kyoto, Japan, May
31 - June 04, 2016},
pages = {3--14},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2907294.2907313},
doi = {10.1145/2907294.2907313},
timestamp = {Tue, 06 Nov 2018 11:07:21 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/DomkeHM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/SchmidBH16,
author = {Patrick Schmid and
Maciej Besta and
Torsten Hoefler},
editor = {Hiroshi Nakashima and
Kenjiro Taura and
Jack Lange},
title = {High-Performance Distributed {RMA} Locks},
booktitle = {Proceedings of the 25th {ACM} International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2016, Kyoto, Japan, May
31 - June 04, 2016},
pages = {19--30},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2907294.2907323},
doi = {10.1145/2907294.2907323},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/SchmidBH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icccn/SasakiPLHP16,
author = {Takayuki Sasaki and
Christos Pappas and
Taeho Lee and
Torsten Hoefler and
Adrian Perrig},
title = {SDNsec: Forwarding Accountability for the {SDN} Data Plane},
booktitle = {25th International Conference on Computer Communication and Networks,
{ICCCN} 2016, Waikoloa, HI, USA, August 1-4, 2016},
pages = {1--10},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICCCN.2016.7568569},
doi = {10.1109/ICCCN.2016.7568569},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icccn/SasakiPLHP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/GrosserH16,
author = {Tobias Grosser and
Torsten Hoefler},
editor = {Ozcan Ozturk and
Kemal Ebcioglu and
Mahmut T. Kandemir and
Onur Mutlu},
title = {Polly-ACC Transparent compilation to heterogeneous hardware},
booktitle = {Proceedings of the 2016 International Conference on Supercomputing,
{ICS} 2016, Istanbul, Turkey, June 1-3, 2016},
pages = {1:1--1:13},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2925426.2926286},
doi = {10.1145/2925426.2926286},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/GrosserH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/oopsla/DanLHV16,
author = {Andrei Marian Dan and
Patrick Lam and
Torsten Hoefler and
Martin T. Vechev},
editor = {Eelco Visser and
Yannis Smaragdakis},
title = {Modeling and analysis of remote memory access programming},
booktitle = {Proceedings of the 2016 {ACM} {SIGPLAN} International Conference on
Object-Oriented Programming, Systems, Languages, and Applications,
{OOPSLA} 2016, part of {SPLASH} 2016, Amsterdam, The Netherlands,
October 30 - November 4, 2016},
pages = {129--144},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2983990.2984033},
doi = {10.1145/2983990.2984033},
timestamp = {Wed, 23 Jun 2021 15:34:31 +0200},
biburl = {https://dblp.org/rec/conf/oopsla/DanLHV16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pasc/Hoefler16,
author = {Torsten Hoefler},
editor = {Torsten Hoefler and
David E. Keyes and
Timothy Robinson},
title = {Selecting Technical Papers for an Interdisciplinary Conference: The
{PASC} Review Process},
booktitle = {Proceedings of the Platform for Advanced Scientific Computing Conference,
{PASC} 2016, Lausanne, Switzerland, June 8-10, 2016},
pages = {13},
publisher = {{ACM}},
year = {2016},
url = {http://dl.acm.org/citation.cfm?id=2970926},
timestamp = {Tue, 06 Nov 2018 11:07:28 +0100},
biburl = {https://dblp.org/rec/conf/pasc/Hoefler16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DomkeH16,
author = {Jens Domke and
Torsten Hoefler},
editor = {John West and
Cherri M. Pancake},
title = {Scheduling-aware routing for supercomputers},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
November 13-18, 2016},
pages = {142--153},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/SC.2016.12},
doi = {10.1109/SC.2016.12},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/DomkeH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/TangWEKHIMWORW16,
author = {William M. Tang and
Bei Wang and
St{\'{e}}phane Ethier and
Grzegorz Kwasniewski and
Torsten Hoefler and
Khaled Z. Ibrahim and
Kamesh Madduri and
Samuel Williams and
Leonid Oliker and
Carlos Rosales{-}Fernandez and
Timothy J. Williams},
editor = {John West and
Cherri M. Pancake},
title = {Extreme scale plasma turbulence simulations on top supercomputers
worldwide},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
November 13-18, 2016},
pages = {502--513},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/SC.2016.42},
doi = {10.1109/SC.2016.42},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/TangWEKHIMWORW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/GysiBH16,
author = {Tobias Gysi and
Jeremia B{\"{a}}r and
Torsten Hoefler},
editor = {John West and
Cherri M. Pancake},
title = {dCUDA: hardware supported overlap of computation and communication},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
November 13-18, 2016},
pages = {609--620},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/SC.2016.51},
doi = {10.1109/SC.2016.51},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/GysiBH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/MartinassoKASH16,
author = {Maxime Martinasso and
Grzegorz Kwasniewski and
Sadaf R. Alam and
Thomas C. Schulthess and
Torsten Hoefler},
editor = {John West and
Cherri M. Pancake},
title = {A PCIe congestion-aware performance model for densely populated accelerator
servers},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
November 13-18, 2016},
pages = {739--749},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/SC.2016.62},
doi = {10.1109/SC.2016.62},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/MartinassoKASH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncse/WolfBCHIKMSSVW16,
author = {Felix Wolf and
Christian H. Bischof and
Alexandru Calotoiu and
Torsten Hoefler and
Christian Iwainsky and
Grzegorz Kwasniewski and
Bernd Mohr and
Sergei Shudler and
Alexandre Strube and
Andreas Vogel and
Gabriel Wittum},
editor = {Hans{-}Joachim Bungartz and
Philipp Neumann and
Wolfgang E. Nagel},
title = {Automatic Performance Modeling of {HPC} Applications},
booktitle = {Software for Exascale Computing - {SPPEXA} 2013-2015},
series = {Lecture Notes in Computational Science and Engineering},
volume = {113},
pages = {445--465},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-40528-5\_20},
doi = {10.1007/978-3-319-40528-5\_20},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/series/lncse/WolfBCHIKMSSVW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/hpdc/2016ross,
editor = {Kamil Iskra and
Torsten Hoefler},
title = {Proceedings of the 6th International Workshop on Runtime and Operating
Systems for Supercomputers, Kyoto, Japan, June 1, 2016},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2931088},
doi = {10.1145/2931088},
isbn = {978-1-4503-4387-9},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/2016ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/pasc/2016,
editor = {Torsten Hoefler and
David E. Keyes and
Timothy Robinson},
title = {Proceedings of the Platform for Advanced Scientific Computing Conference,
{PASC} 2016, Lausanne, Switzerland, June 8-10, 2016},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2929908},
doi = {10.1145/2929908},
isbn = {978-1-4503-4126-4},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pasc/2016.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SolomonikBDH16,
author = {Edgar Solomonik and
Grey Ballard and
James Demmel and
Torsten Hoefler},
title = {A communication-avoiding parallel algorithm for the symmetric eigenvalue
problem},
journal = {CoRR},
volume = {abs/1604.03703},
year = {2016},
url = {http://arxiv.org/abs/1604.03703},
eprinttype = {arXiv},
eprint = {1604.03703},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SolomonikBDH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SasakiPLHP16,
author = {Takayuki Sasaki and
Christos Pappas and
Taeho Lee and
Torsten Hoefler and
Adrian Perrig},
title = {SDNsec: Forwarding Accountability for the {SDN} Data Plane},
journal = {CoRR},
volume = {abs/1605.01944},
year = {2016},
url = {http://arxiv.org/abs/1605.01944},
eprinttype = {arXiv},
eprint = {1605.01944},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/SasakiPLHP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PokeHG16,
author = {Marius Poke and
Torsten Hoefler and
Colin W. Glass},
title = {AllConcur: Leaderless Concurrent Atomic Broadcast (Extended Version)},
journal = {CoRR},
volume = {abs/1608.05866},
year = {2016},
url = {http://arxiv.org/abs/1608.05866},
eprinttype = {arXiv},
eprint = {1608.05866},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PokeHG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SolomonikBVH16,
author = {Edgar Solomonik and
Maciej Besta and
Flavio Vella and
Torsten Hoefler},
title = {Betweenness Centrality is more Parallelizable than Dense Matrix Multiplication},
journal = {CoRR},
volume = {abs/1609.07008},
year = {2016},
url = {http://arxiv.org/abs/1609.07008},
eprinttype = {arXiv},
eprint = {1609.07008},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SolomonikBVH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WickySH16,
author = {Tobias Wicky and
Edgar Solomonik and
Torsten Hoefler},
title = {Communication-Avoiding Parallel Algorithms for Solving Triangular
Systems of Linear Equations},
journal = {CoRR},
volume = {abs/1612.01855},
year = {2016},
url = {http://arxiv.org/abs/1612.01855},
eprinttype = {arXiv},
eprint = {1612.01855},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WickySH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/IskraH15,
author = {Kamil Iskra and
Torsten Hoefler},
title = {Operating systems and runtime environments on supercomputers},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {29},
number = {1},
pages = {3--4},
year = {2015},
url = {https://doi.org/10.1177/1094342014560666},
doi = {10.1177/1094342014560666},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/IskraH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/HoeflerDTBBGU15,
author = {Torsten Hoefler and
James Dinan and
Rajeev Thakur and
Brian Barrett and
Pavan Balaji and
William Gropp and
Keith D. Underwood},
title = {Remote Memory Access Programming in {MPI-3}},
journal = {{ACM} Trans. Parallel Comput.},
volume = {2},
number = {2},
pages = {9:1--9:26},
year = {2015},
url = {https://doi.org/10.1145/2780584},
doi = {10.1145/2780584},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/topc/HoeflerDTBBGU15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/DinitzH15,
author = {Michael Dinitz and
Torsten Hoefler},
title = {Introduction to the Special Issue on {SPAA} 2013},
journal = {{ACM} Trans. Parallel Comput.},
volume = {2},
number = {3},
pages = {14e:1--14e:2},
year = {2015},
url = {https://doi.org/10.1145/2809923},
doi = {10.1145/2809923},
timestamp = {Sat, 25 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/topc/DinitzH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/SchweizerBH15,
author = {Hermann Schweizer and
Maciej Besta and
Torsten Hoefler},
title = {Evaluating the Cost of Atomic Operations on Modern Architectures},
booktitle = {2015 International Conference on Parallel Architectures and Compilation,
{PACT} 2015, San Francisco, CA, USA, October 18-21, 2015},
pages = {445--456},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/PACT.2015.24},
doi = {10.1109/PACT.2015.24},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEpact/SchweizerBH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/BhattacharyyaKH15,
author = {Arnamoy Bhattacharyya and
Grzegorz Kwasniewski and
Torsten Hoefler},
title = {Using Compiler Techniques to Improve Automatic Performance Modeling},
booktitle = {2015 International Conference on Parallel Architectures and Compilation,
{PACT} 2015, San Francisco, CA, USA, October 18-21, 2015},
pages = {468--479},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/PACT.2015.39},
doi = {10.1109/PACT.2015.39},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEpact/BhattacharyyaKH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cfi/LeePBHHP15,
author = {Taeho Lee and
Christos Pappas and
Cristina Basescu and
Jun Han and
Torsten Hoefler and
Adrian Perrig},
title = {Source-Based Path Selection: The Data Plane Perspective},
booktitle = {The 10th International Conference on Future Internet, {CFI} '15, Seoul,
Republic of Korea, June 8-10, 2015},
pages = {41--45},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2775088.2775090},
doi = {10.1145/2775088.2775090},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cfi/LeePBHHP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/GirolamoJUH15,
author = {Salvatore Di Girolamo and
Pierre Jolivet and
Keith D. Underwood and
Torsten Hoefler},
title = {Exploiting Offload Enabled Network Interfaces},
booktitle = {23rd {IEEE} Annual Symposium on High-Performance Interconnects, {HOTI}
2015, Santa Clara, CA, USA, August 26-28, 2015},
pages = {26--33},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/HOTI.2015.21},
doi = {10.1109/HOTI.2015.21},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/GirolamoJUH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hotos/HoeflerRR15,
author = {Torsten Hoefler and
Robert B. Ross and
Timothy Roscoe},
editor = {George Candea},
title = {Distributing the Data Plane for Remote Storage Access},
booktitle = {15th Workshop on Hot Topics in Operating Systems, HotOS XV, Kartause
Ittingen, Switzerland, May 18-20, 2015},
publisher = {{USENIX} Association},
year = {2015},
url = {https://www.usenix.org/conference/hotos15/workshop-program/presentation/hoefler},
timestamp = {Wed, 04 Jul 2018 13:06:34 +0200},
biburl = {https://dblp.org/rec/conf/hotos/HoeflerRR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/RamosH15,
author = {Sabela Ramos and
Torsten Hoefler},
editor = {Thilo Kielmann and
Dean Hildebrand and
Michela Taufer},
title = {Cache Line Aware Optimizations for ccNUMA Systems},
booktitle = {Proceedings of the 24th International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2015, Portland, OR, USA,
June 15-19, 2015},
pages = {85--88},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2749246.2749256},
doi = {10.1145/2749246.2749256},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/RamosH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/PokeH15,
author = {Marius Poke and
Torsten Hoefler},
editor = {Thilo Kielmann and
Dean Hildebrand and
Michela Taufer},
title = {{DARE:} High-Performance State Machine Replication on {RDMA} Networks},
booktitle = {Proceedings of the 24th International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2015, Portland, OR, USA,
June 15-19, 2015},
pages = {107--118},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2749246.2749267},
doi = {10.1145/2749246.2749267},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/PokeH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/BestaH15,
author = {Maciej Besta and
Torsten Hoefler},
editor = {Thilo Kielmann and
Dean Hildebrand and
Michela Taufer},
title = {Accelerating Irregular Computations with Hardware Transactional Memory
and Active Messages},
booktitle = {Proceedings of the 24th International Symposium on High-Performance
Parallel and Distributed Computing, {HPDC} 2015, Portland, OR, USA,
June 15-19, 2015},
pages = {161--172},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2749246.2749263},
doi = {10.1145/2749246.2749263},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/BestaH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/BestaH15,
author = {Maciej Besta and
Torsten Hoefler},
editor = {Laxmi N. Bhuyan and
Fred Chong and
Vivek Sarkar},
title = {Active Access: {A} Mechanism for High-Performance Distributed Data-Centric
Computations},
booktitle = {Proceedings of the 29th {ACM} on International Conference on Supercomputing,
ICS'15, Newport Beach/Irvine, CA, USA, June 08 - 11, 2015},
pages = {155--164},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2751205.2751219},
doi = {10.1145/2751205.2751219},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/BestaH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/ShudlerCHSW15,
author = {Sergei Shudler and
Alexandru Calotoiu and
Torsten Hoefler and
Alexandre Strube and
Felix Wolf},
editor = {Laxmi N. Bhuyan and
Fred Chong and
Vivek Sarkar},
title = {Exascaling Your Library: Will Your Implementation Meet Your Expectations?},
booktitle = {Proceedings of the 29th {ACM} on International Conference on Supercomputing,
ICS'15, Newport Beach/Irvine, CA, USA, June 08 - 11, 2015},
pages = {165--175},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2751205.2751216},
doi = {10.1145/2751205.2751216},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/ShudlerCHSW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/GysiGH15,
author = {Tobias Gysi and
Tobias Grosser and
Torsten Hoefler},
editor = {Laxmi N. Bhuyan and
Fred Chong and
Vivek Sarkar},
title = {{MODESTO:} Data-centric Analytic Optimization of Complex Stencil Programs
on Heterogeneous Architectures},
booktitle = {Proceedings of the 29th {ACM} on International Conference on Supercomputing,
ICS'15, Newport Beach/Irvine, CA, USA, June 08 - 11, 2015},
pages = {177--186},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2751205.2751223},
doi = {10.1145/2751205.2751223},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/GysiGH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerK15,
author = {Torsten Hoefler and
Laxmikant V. Kal{\'{e}}},
title = {{HIPS-LSPP} Keynotes},
booktitle = {2015 {IEEE} International Parallel and Distributed Processing Symposium
Workshop, {IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
pages = {204},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/IPDPSW.2015.173},
doi = {10.1109/IPDPSW.2015.173},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BelliH15,
author = {Roberto Belli and
Torsten Hoefler},
title = {Notified Access: Extending Remote Memory Access Programming Models
for Producer-Consumer Synchronization},
booktitle = {2015 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
pages = {871--881},
publisher = {{IEEE} Computer Society},
year = {2015},
url = {https://doi.org/10.1109/IPDPS.2015.30},
doi = {10.1109/IPDPS.2015.30},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/BelliH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KathareiosMPRH15,
author = {Georgios Kathareios and
Cyriel Minkenberg and
Bogdan Prisacari and
Germ{\'{a}}n Rodr{\'{\i}}guez and
Torsten Hoefler},
editor = {Jackie Kern and
Jeffrey S. Vetter},
title = {Cost-effective diameter-two topologies: analysis and evaluation},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2015, Austin, TX, USA, November
15-20, 2015},
pages = {36:1--36:11},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2807591.2807652},
doi = {10.1145/2807591.2807652},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/KathareiosMPRH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerB15,
author = {Torsten Hoefler and
Roberto Belli},
editor = {Jackie Kern and
Jeffrey S. Vetter},
title = {Scientific benchmarking of parallel computing systems: twelve ways
to tell the masses when reporting performance results},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2015, Austin, TX, USA, November
15-20, 2015},
pages = {73:1--73:12},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2807591.2807644},
doi = {10.1145/2807591.2807644},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/HoeflerB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/hpdc/2015ross,
editor = {Torsten Hoefler and
Kamil Iskra},
title = {Proceedings of the 5th International Workshop on Runtime and Operating
Systems for Supercomputers, {ROSS} 2015, Portland, OR, USA, June 16,
2015},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2768405},
doi = {10.1145/2768405},
isbn = {978-1-4503-3606-2},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/2015ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SolomonikH15,
author = {Edgar Solomonik and
Torsten Hoefler},
title = {Sparse Tensor Algebra as a Parallel Programming Model},
journal = {CoRR},
volume = {abs/1512.00066},
year = {2015},
url = {http://arxiv.org/abs/1512.00066},
eprinttype = {arXiv},
eprint = {1512.00066},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SolomonikH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cluster/0002HHS14,
author = {Shigang Li and
Torsten Hoefler and
Chungjin Hu and
Marc Snir},
title = {Improved {MPI} collectives for {MPI} processes in shared address spaces},
journal = {Clust. Comput.},
volume = {17},
number = {4},
pages = {1139--1155},
year = {2014},
url = {https://doi.org/10.1007/s10586-014-0361-4},
doi = {10.1007/S10586-014-0361-4},
timestamp = {Tue, 29 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cluster/0002HHS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computing/SchneiderGH14,
author = {Timo Schneider and
Robert Gerstenberger and
Torsten Hoefler},
title = {Application-oriented ping-pong benchmarking: how to assess the real
communication overheads},
journal = {Computing},
volume = {96},
number = {4},
pages = {279--292},
year = {2014},
url = {https://doi.org/10.1007/s00607-013-0330-4},
doi = {10.1007/S00607-013-0330-4},
timestamp = {Thu, 06 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computing/SchneiderGH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sp/GerstenbergerBH14,
author = {Robert Gerstenberger and
Maciej Besta and
Torsten Hoefler},
title = {Enabling highly-scalable remote memory access programming with {MPI-3}
One Sided},
journal = {Sci. Program.},
volume = {22},
number = {2},
pages = {75--91},
year = {2014},
url = {https://doi.org/10.3233/SPR-140383},
doi = {10.3233/SPR-140383},
timestamp = {Wed, 06 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sp/GerstenbergerBH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/superfri/HoeflerM14,
author = {Torsten Hoefler and
Dmitry Moor},
title = {Energy, Memory, and Runtime Tradeoffs for Implementing Collective
Communication Operations},
journal = {Supercomput. Front. Innov.},
volume = {1},
number = {2},
pages = {58--75},
year = {2014},
url = {https://doi.org/10.14529/jsfi140204},
doi = {10.14529/JSFI140204},
timestamp = {Wed, 16 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/superfri/HoeflerM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/BhattacharyyaH14,
author = {Arnamoy Bhattacharyya and
Torsten Hoefler},
editor = {Jos{\'{e}} Nelson Amaral and
Josep Torrellas},
title = {{PEMOGEN:} automatic adaptive performance modeling during program
runtime},
booktitle = {International Conference on Parallel Architectures and Compilation,
{PACT} '14, Edmonton, AB, Canada, August 24-27, 2014},
pages = {393--404},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2628071.2628100},
doi = {10.1145/2628071.2628100},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEpact/BhattacharyyaH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/WolfBHMWCISV14,
author = {Felix Wolf and
Christian H. Bischof and
Torsten Hoefler and
Bernd Mohr and
Gabriel Wittum and
Alexandru Calotoiu and
Christian Iwainsky and
Alexandre Strube and
Andreas Vogel},
editor = {Lu{\'{\i}}s M. B. Lopes and
Julius Zilinskas and
Alexandru Costan and
Roberto G. Cascella and
Gabor Kecskemeti and
Emmanuel Jeannot and
Mario Cannataro and
Laura Ricci and
Siegfried Benkner and
Salvador Petit and
Vittorio Scarano and
Jos{\'{e}} Gracia and
Sascha Hunold and
Stephen L. Scott and
Stefan Lankes and
Christian Lengauer and
Jes{\'{u}}s Carretero and
Jens Breitbart and
Michael Alexander},
title = {Catwalk: {A} Quick Development Path for Performance Models},
booktitle = {Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International
Workshops, Porto, Portugal, August 25-26, 2014, Revised Selected Papers,
Part {II}},
series = {Lecture Notes in Computer Science},
volume = {8806},
pages = {589--600},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-14313-2\_50},
doi = {10.1007/978-3-319-14313-2\_50},
timestamp = {Sun, 12 Nov 2023 02:07:45 +0100},
biburl = {https://dblp.org/rec/conf/europar/WolfBHMWCISV14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/BestaH14,
author = {Maciej Besta and
Torsten Hoefler},
editor = {Beth Plale and
Matei Ripeanu and
Franck Cappello and
Dongyan Xu},
title = {Fault tolerance for remote memory access programming models},
booktitle = {The 23rd International Symposium on High-Performance Parallel and
Distributed Computing, HPDC'14, Vancouver, BC, Canada - June 23 -
27, 2014},
pages = {37--48},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2600212.2600224},
doi = {10.1145/2600212.2600224},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/BestaH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/PrisacariRHCMH14,
author = {Bogdan Prisacari and
Germ{\'{a}}n Rodr{\'{\i}}guez and
Philip Heidelberger and
Dong Chen and
Cyriel Minkenberg and
Torsten Hoefler},
editor = {Beth Plale and
Matei Ripeanu and
Franck Cappello and
Dongyan Xu},
title = {Efficient task placement and routing of nearest neighbor exchanges
in dragonfly networks},
booktitle = {The 23rd International Symposium on High-Performance Parallel and
Distributed Computing, HPDC'14, Vancouver, BC, Canada - June 23 -
27, 2014},
pages = {129--140},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2600212.2600225},
doi = {10.1145/2600212.2600225},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/PrisacariRHCMH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/ArteagaFH14,
author = {Andrea Arteaga and
Oliver Fuhrer and
Torsten Hoefler},
title = {Designing Bit-Reproducible Portable High-Performance Applications},
booktitle = {2014 {IEEE} 28th International Parallel and Distributed Processing
Symposium, Phoenix, AZ, USA, May 19-23, 2014},
pages = {1235--1244},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/IPDPS.2014.127},
doi = {10.1109/IPDPS.2014.127},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/ArteagaFH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/WidenerFLH14,
author = {Patrick M. Widener and
Kurt B. Ferreira and
Scott Levy and
Torsten Hoefler},
editor = {Jack J. Dongarra and
Yutaka Ishikawa and
Atsushi Hori},
title = {Exploring the effect of noise on the performance benefit of nonblocking
allreduce},
booktitle = {21st European {MPI} Users' Group Meeting, EuroMPI/ASIA '14, Kyoto,
Japan - September 09 - 12, 2014},
pages = {77},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2642769.2642786},
doi = {10.1145/2642769.2642786},
timestamp = {Sun, 12 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pvm/WidenerFLH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BestaH14,
author = {Maciej Besta and
Torsten Hoefler},
editor = {Trish Damkroger and
Jack J. Dongarra},
title = {Slim Fly: {A} Cost Effective Low-Diameter Network Topology},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2014, New Orleans, LA, USA, November 16-21,
2014},
pages = {348--359},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/SC.2014.34},
doi = {10.1109/SC.2014.34},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/BestaH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DomkeHM14,
author = {Jens Domke and
Torsten Hoefler and
Satoshi Matsuoka},
editor = {Trish Damkroger and
Jack J. Dongarra},
title = {Fail-in-Place Network Design: Interaction Between Topology, Routing
Algorithm and Failures},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2014, New Orleans, LA, USA, November 16-21,
2014},
pages = {597--608},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/SC.2014.54},
doi = {10.1109/SC.2014.54},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/DomkeHM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/FerreiraWLAH14,
author = {Kurt B. Ferreira and
Patrick M. Widener and
Scott Levy and
Dorian C. Arnold and
Torsten Hoefler},
editor = {Trish Damkroger and
Jack J. Dongarra},
title = {Understanding the Effects of Communication and Coordination on Checkpointing
at Scale},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, {SC} 2014, New Orleans, LA, USA, November 16-21,
2014},
pages = {883--894},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/SC.2014.77},
doi = {10.1109/SC.2014.77},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/FerreiraWLAH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/HoeflerK14,
author = {Torsten Hoefler and
Grzegorz Kwasniewski},
editor = {Guy E. Blelloch and
Peter Sanders},
title = {Automatic complexity analysis of explicitly parallel programs},
booktitle = {26th {ACM} Symposium on Parallelism in Algorithms and Architectures,
{SPAA} '14, Prague, Czech Republic - June 23 - 25, 2014},
pages = {226--235},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2612669.2612685},
doi = {10.1145/2612669.2612685},
timestamp = {Wed, 21 Nov 2018 11:18:43 +0100},
biburl = {https://dblp.org/rec/conf/spaa/HoeflerK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/ics/2014ross,
editor = {Kamil Iskra and
Torsten Hoefler},
title = {Proceedings of the 4th International Workshop on Runtime and Operating
Systems for Supercomputers, {ROSS} 2014, Munich, Germany, June 10,
2014},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2612262},
doi = {10.1145/2612262},
isbn = {978-1-4503-2950-7},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/2014ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computing/HoeflerDBBBBGKT13,
author = {Torsten Hoefler and
James Dinan and
Darius Buntinas and
Pavan Balaji and
Brian Barrett and
Ron Brightwell and
William Gropp and
Vivek Kale and
Rajeev Thakur},
title = {{MPI} + {MPI:} a new hybrid approach to parallel programming with
{MPI} plus shared memory},
journal = {Computing},
volume = {95},
number = {12},
pages = {1121--1136},
year = {2013},
url = {https://doi.org/10.1007/s00607-013-0324-2},
doi = {10.1007/S00607-013-0324-2},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computing/HoeflerDBBBBGKT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/HoeflerI13,
author = {Torsten Hoefler and
Kamil Iskra},
title = {Operating systems and runtime environments on supercomputers},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {27},
number = {2},
pages = {123},
year = {2013},
url = {https://doi.org/10.1177/1094342013481376},
doi = {10.1177/1094342013481376},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/HoeflerI13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taco/PrisacariRMH13,
author = {Bogdan Prisacari and
Germ{\'{a}}n Rodr{\'{\i}}guez and
Cyriel Minkenberg and
Torsten Hoefler},
title = {Fast pattern-specific routing for fat tree networks},
journal = {{ACM} Trans. Archit. Code Optim.},
volume = {10},
number = {4},
pages = {36:1--36:25},
year = {2013},
url = {https://doi.org/10.1145/2541228.2555293},
doi = {10.1145/2541228.2555293},
timestamp = {Wed, 17 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taco/PrisacariRMH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/LysneHLB13,
author = {Olav Lysne and
Torsten Hoefler and
Pedro L{\'{o}}pez and
Davide Bertozzi},
editor = {Felix Wolf and
Bernd Mohr and
Dieter an Mey},
title = {Topic 13: High-Performance Networks and Communication - (Introduction)},
booktitle = {Euro-Par 2013 Parallel Processing - 19th International Conference,
Aachen, Germany, August 26-30, 2013. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {8097},
pages = {684},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-40047-6\_68},
doi = {10.1007/978-3-642-40047-6\_68},
timestamp = {Tue, 14 May 2019 10:00:46 +0200},
biburl = {https://dblp.org/rec/conf/europar/LysneHLB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/LiHS13,
author = {Shigang Li and
Torsten Hoefler and
Marc Snir},
editor = {Manish Parashar and
Jon B. Weissman and
Dick H. J. Epema and
Renato J. O. Figueiredo},
title = {NUMA-aware shared-memory collective communication for {MPI}},
booktitle = {The 22nd International Symposium on High-Performance Parallel and
Distributed Computing, HPDC'13, New York, NY, {USA} - June 17 - 21,
2013},
pages = {85--96},
publisher = {{ACM}},
year = {2013},
url = {https://dl.acm.org/citation.cfm?id=2462903},
timestamp = {Mon, 26 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/LiHS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/RamosH13,
author = {Sabela Ramos and
Torsten Hoefler},
editor = {Manish Parashar and
Jon B. Weissman and
Dick H. J. Epema and
Renato J. O. Figueiredo},
title = {Modeling communication in cache-coherent {SMP} systems: a case-study
with Xeon Phi},
booktitle = {The 22nd International Symposium on High-Performance Parallel and
Distributed Computing, HPDC'13, New York, NY, {USA} - June 17 - 21,
2013},
pages = {97--108},
publisher = {{ACM}},
year = {2013},
url = {https://dl.acm.org/citation.cfm?id=2462916},
timestamp = {Mon, 26 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/RamosH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/SchneiderHGBB13,
author = {Timo Schneider and
Torsten Hoefler and
Ryan E. Grant and
Brian W. Barrett and
Ron Brightwell},
title = {Protocols for Fully Offloaded Collective Operations on Accelerated
Network Adapters},
booktitle = {42nd International Conference on Parallel Processing, {ICPP} 2013,
Lyon, France, October 1-4, 2013},
pages = {593--602},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/ICPP.2013.73},
doi = {10.1109/ICPP.2013.73},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpp/SchneiderHGBB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/PrisacariRMH13,
author = {Bogdan Prisacari and
Germ{\'{a}}n Rodr{\'{\i}}guez and
Cyriel Minkenberg and
Torsten Hoefler},
editor = {Allen D. Malony and
Mario Nemirovsky and
Samuel P. Midkiff},
title = {Bandwidth-optimal all-to-all exchanges in fat tree networks},
booktitle = {International Conference on Supercomputing, ICS'13, Eugene, OR, {USA}
- June 10 - 14, 2013},
pages = {139--148},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2464996.2465434},
doi = {10.1145/2464996.2465434},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/PrisacariRMH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lcpc/SchneiderGH13,
author = {Timo Schneider and
Robert Gerstenberger and
Torsten Hoefler},
editor = {Calin Cascaval and
Pablo Montesinos},
title = {Compiler Optimizations for Non-contiguous Remote Data Movement},
booktitle = {Languages and Compilers for Parallel Computing - 26th International
Workshop, {LCPC} 2013, San Jose, CA, USA, September 25-27, 2013. Revised
Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {8664},
pages = {307--321},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-09967-5\_18},
doi = {10.1007/978-3-319-09967-5\_18},
timestamp = {Tue, 14 May 2019 10:00:47 +0200},
biburl = {https://dblp.org/rec/conf/lcpc/SchneiderGH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/FriedleyHBLM13,
author = {Andrew Friedley and
Torsten Hoefler and
Greg Bronevetsky and
Andrew Lumsdaine and
Ching{-}Chen Ma},
editor = {Alex Nicolau and
Xiaowei Shen and
Saman P. Amarasinghe and
Richard W. Vuduc},
title = {Ownership passing: efficient distributed memory programming on multi-core
systems},
booktitle = {{ACM} {SIGPLAN} Symposium on Principles and Practice of Parallel Programming,
PPoPP '13, Shenzhen, China, February 23-27, 2013},
pages = {177--186},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2442516.2442534},
doi = {10.1145/2442516.2442534},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/FriedleyHBLM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/SchneiderKH13,
author = {Timo Schneider and
Fredrik Kjolstad and
Torsten Hoefler},
editor = {Jack J. Dongarra and
Javier Garc{\'{\i}}a Blas and
Jes{\'{u}}s Carretero},
title = {{MPI} datatype processing using runtime compilation},
booktitle = {20th European {MPI} Users's Group Meeting, EuroMPI '13, Madrid, Spain
- September 15 - 18, 2013},
pages = {19--24},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2488551.2488552},
doi = {10.1145/2488551.2488552},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/SchneiderKH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/FriedleyBHL13,
author = {Andrew Friedley and
Greg Bronevetsky and
Torsten Hoefler and
Andrew Lumsdaine},
editor = {William Gropp and
Satoshi Matsuoka},
title = {Hybrid {MPI:} efficient message passing for multi-core systems},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, SC'13, Denver, CO, {USA} - November 17 - 21,
2013},
pages = {18:1--18:11},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2503210.2503294},
doi = {10.1145/2503210.2503294},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/FriedleyBHL13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/CalotoiuHPW13,
author = {Alexandru Calotoiu and
Torsten Hoefler and
Marius Poke and
Felix Wolf},
editor = {William Gropp and
Satoshi Matsuoka},
title = {Using automated performance modeling to find scalability bugs in complex
codes},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, SC'13, Denver, CO, {USA} - November 17 - 21,
2013},
pages = {45:1--45:12},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2503210.2503277},
doi = {10.1145/2503210.2503277},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/CalotoiuHPW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/GerstenbergerBH13,
author = {Robert Gerstenberger and
Maciej Besta and
Torsten Hoefler},
editor = {William Gropp and
Satoshi Matsuoka},
title = {Enabling highly-scalable remote memory access programming with {MPI-3}
one sided},
booktitle = {International Conference for High Performance Computing, Networking,
Storage and Analysis, SC'13, Denver, CO, {USA} - November 17 - 21,
2013},
pages = {53:1--53:12},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2503210.2503286},
doi = {10.1145/2503210.2503286},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/GerstenbergerBH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LevyTFAHW13,
author = {Scott Levy and
Bryan Topp and
Kurt B. Ferreira and
Dorian C. Arnold and
Torsten Hoefler and
Patrick M. Widener},
editor = {Stephen A. Jarvis and
Steven A. Wright and
Simon D. Hammond},
title = {Using Simulation to Evaluate the Performance of Resilience Strategies
at Scale},
booktitle = {High Performance Computing Systems. Performance Modeling, Benchmarking
and Simulation - 4th International Workshop, {PMBS} 2013, Denver,
CO, USA, November 18, 2013. Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {8551},
pages = {91--114},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-10214-6\_5},
doi = {10.1007/978-3-319-10214-6\_5},
timestamp = {Sun, 12 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/LevyTFAHW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/ics/2013ross,
editor = {Torsten Hoefler and
Kamil Iskra},
title = {Proceedings of the 3rd International Workshop on Runtime and Operating
Systems for Supercomputers, {ROSS} 2013, Eugene, Oregon, USA, June
10, 2013},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2491661},
doi = {10.1145/2491661},
isbn = {978-1-4503-2146-4},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/2013ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/HoeflerI12,
author = {Torsten Hoefler and
Kamil Iskra},
title = {Operating systems and runtime environments on supercomputers},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {26},
number = {2},
pages = {93--94},
year = {2012},
url = {https://doi.org/10.1177/1094342012442456},
doi = {10.1177/1094342012442456},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/HoeflerI12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/micro/HoeflerGPT12,
author = {Torsten Hoefler and
Patrick Geoffray and
Fabrizio Petrini and
Jesper Larsson Tr{\"{a}}ff},
title = {Top Picks from Hot Interconnects 2011: Petascale Network Architectures},
journal = {{IEEE} Micro},
volume = {32},
number = {1},
pages = {4--7},
year = {2012},
url = {https://doi.org/10.1109/MM.2012.11},
doi = {10.1109/MM.2012.11},
timestamp = {Wed, 11 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/micro/HoeflerGPT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/Hoefler12,
author = {Torsten Hoefler},
title = {Extensions for next-generation parallel programming models},
journal = {Parallel Comput.},
volume = {38},
number = {1-2},
pages = {1},
year = {2012},
url = {https://doi.org/10.1016/j.parco.2011.10.012},
doi = {10.1016/J.PARCO.2011.10.012},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pc/Hoefler12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/HoeflerS12,
author = {Torsten Hoefler and
Timo Schneider},
editor = {Pen{-}Chung Yew and
Sangyeun Cho and
Luiz DeRose and
David J. Lilja},
title = {Runtime detection and optimization of collective communication patterns},
booktitle = {International Conference on Parallel Architectures and Compilation
Techniques, {PACT} '12, Minneapolis, MN, {USA} - September 19 - 23,
2012},
pages = {263--272},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2370816.2370856},
doi = {10.1145/2370816.2370856},
timestamp = {Wed, 11 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/IEEEpact/HoeflerS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/GottschlingH12,
author = {Peter Gottschling and
Torsten Hoefler},
title = {Productive Parallel Linear Algebra Programming with Unstructured Topology
Adaption},
booktitle = {12th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
Computing, CCGrid 2012, Ottawa, Canada, May 13-16, 2012},
pages = {9--16},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/CCGrid.2012.51},
doi = {10.1109/CCGRID.2012.51},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ccgrid/GottschlingH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/BauerGH12,
author = {Greg Bauer and
Steven Gottlieb and
Torsten Hoefler},
title = {Performance Modeling and Comparative Analysis of the {MILC} Lattice
{QCD} Application su3{\_}rmd},
booktitle = {12th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
Computing, CCGrid 2012, Ottawa, Canada, May 13-16, 2012},
pages = {652--659},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/CCGrid.2012.123},
doi = {10.1109/CCGRID.2012.123},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ccgrid/BauerGH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/PellegriniHF12,
author = {Simone Pellegrini and
Torsten Hoefler and
Thomas Fahringer},
title = {On the Effects of {CPU} Caches on {MPI} Point-to-Point Communications},
booktitle = {2012 {IEEE} International Conference on Cluster Computing, {CLUSTER}
2012, Beijing, China, September 24-28, 2012},
pages = {495--503},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/CLUSTER.2012.22},
doi = {10.1109/CLUSTER.2012.22},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/PellegriniHF12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/KharbasKHM12,
author = {Kishor Kharbas and
Donghoon Kim and
Torsten Hoefler and
Frank Mueller},
editor = {Rainer Stotzka and
Michael Schiffers and
Yannis Cotronis},
title = {Assessing {HPC} Failure Detectors for {MPI} Jobs},
booktitle = {Proceedings of the 20th Euromicro International Conference on Parallel,
Distributed and Network-Based Processing, {PDP} 2012, Munich, Germany,
February 15-17, 2012},
pages = {81--88},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/PDP.2012.11},
doi = {10.1109/PDP.2012.11},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/KharbasKHM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/HoeflerS12,
author = {Torsten Hoefler and
Timo Schneider},
editor = {J. Ramanujam and
P. Sadayappan},
title = {Communication-centric optimizations by dynamically detecting collective
operations},
booktitle = {Proceedings of the 17th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, {PPOPP} 2012, New Orleans, LA, USA,
February 25-29, 2012},
pages = {305--306},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2145816.2145866},
doi = {10.1145/2145816.2145866},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/HoeflerS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/KjolstadHS12,
author = {Fredrik Kjolstad and
Torsten Hoefler and
Marc Snir},
editor = {J. Ramanujam and
P. Sadayappan},
title = {Automatic datatype generation and optimization},
booktitle = {Proceedings of the 17th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, {PPOPP} 2012, New Orleans, LA, USA,
February 25-29, 2012},
pages = {327--328},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2145816.2145878},
doi = {10.1145/2145816.2145878},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/KjolstadHS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/PellegriniHF12,
author = {Simone Pellegrini and
Torsten Hoefler and
Thomas Fahringer},
editor = {Jesper Larsson Tr{\"{a}}ff and
Siegfried Benkner and
Jack J. Dongarra},
title = {Exact Dependence Analysis for Increased Communication Overlap},
booktitle = {Recent Advances in the Message Passing Interface - 19th European {MPI}
Users' Group Meeting, EuroMPI 2012, Vienna, Austria, September 23-26,
2012. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7490},
pages = {89--99},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-33518-1\_14},
doi = {10.1007/978-3-642-33518-1\_14},
timestamp = {Sun, 25 Jul 2021 11:50:18 +0200},
biburl = {https://dblp.org/rec/conf/pvm/PellegriniHF12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/SchneiderGH12,
author = {Timo Schneider and
Robert Gerstenberger and
Torsten Hoefler},
editor = {Jesper Larsson Tr{\"{a}}ff and
Siegfried Benkner and
Jack J. Dongarra},
title = {Micro-applications for Communication Data Access Patterns and {MPI}
Datatypes},
booktitle = {Recent Advances in the Message Passing Interface - 19th European {MPI}
Users' Group Meeting, EuroMPI 2012, Vienna, Austria, September 23-26,
2012. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7490},
pages = {121--131},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-33518-1\_17},
doi = {10.1007/978-3-642-33518-1\_17},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/SchneiderGH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerDBBBBGKT12,
author = {Torsten Hoefler and
James Dinan and
Darius Buntinas and
Pavan Balaji and
Brian W. Barrett and
Ron Brightwell and
William Gropp and
Vivek Kale and
Rajeev Thakur},
editor = {Jesper Larsson Tr{\"{a}}ff and
Siegfried Benkner and
Jack J. Dongarra},
title = {Leveraging MPI's One-Sided Communication Interface for Shared-Memory
Programming},
booktitle = {Recent Advances in the Message Passing Interface - 19th European {MPI}
Users' Group Meeting, EuroMPI 2012, Vienna, Austria, September 23-26,
2012. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7490},
pages = {132--141},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-33518-1\_18},
doi = {10.1007/978-3-642-33518-1\_18},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerDBBBBGKT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerS12,
author = {Torsten Hoefler and
Timo Schneider},
editor = {Jeffrey K. Hollingsworth},
title = {Optimization principles for collective neighborhood communications},
booktitle = {{SC} Conference on High Performance Computing Networking, Storage
and Analysis, {SC} '12, Salt Lake City, UT, {USA} - November 11 -
15, 2012},
pages = {98},
publisher = {{IEEE/ACM}},
year = {2012},
url = {https://doi.org/10.1109/SC.2012.86},
doi = {10.1109/SC.2012.86},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/HoeflerS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KaleGHSG12,
author = {Vivek Kale and
Todd Gamblin and
Torsten Hoefler and
Bronis R. de Supinski and
William D. Gropp},
title = {Abstract: Slack-Conscious Lightweight Loop Scheduling for Improving
Scalability of Bulk-synchronous {MPI} Applications},
booktitle = {2012 {SC} Companion: High Performance Computing, Networking Storage
and Analysis, Salt Lake City, UT, USA, November 10-16, 2012},
pages = {1392},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/SC.Companion.2012.209},
doi = {10.1109/SC.COMPANION.2012.209},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/KaleGHSG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/ics/2012ross,
editor = {Torsten Hoefler and
Kamil Iskra},
title = {Proceedings of the 2nd International Workshop on Runtime and Operating
Systems for Supercomputers, {ROSS} '12, Venice, Italy, June 29, 2012},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2318916},
doi = {10.1145/2318916},
isbn = {978-1-4503-1460-2},
timestamp = {Wed, 12 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/2012ross.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/HoeflerRRSTT11,
author = {Torsten Hoefler and
Rolf Rabenseifner and
Hubert Ritzdorf and
Bronis R. de Supinski and
Rajeev Thakur and
Jesper Larsson Tr{\"{a}}ff},
title = {The scalable process topology interface of {MPI} 2.2},
journal = {Concurr. Comput. Pract. Exp.},
volume = {23},
number = {4},
pages = {293--310},
year = {2011},
url = {https://doi.org/10.1002/cpe.1643},
doi = {10.1002/CPE.1643},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/concurrency/HoeflerRRSTT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ppl/BalajiBGGHKLTT11,
author = {Pavan Balaji and
Darius Buntinas and
David Goodell and
William Gropp and
Torsten Hoefler and
Sameer Kumar and
Ewing L. Lusk and
Rajeev Thakur and
Jesper Larsson Tr{\"{a}}ff},
title = {Mpi on millions of Cores},
journal = {Parallel Process. Lett.},
volume = {21},
number = {1},
pages = {45--60},
year = {2011},
url = {https://doi.org/10.1142/S0129626411000060},
doi = {10.1142/S0129626411000060},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ppl/BalajiBGGHKLTT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/SchneiderEHR11,
author = {Timo Schneider and
Sven Eckelmann and
Torsten Hoefler and
Wolfgang Rehm},
editor = {Emmanuel Jeannot and
Raymond Namyst and
Jean Roman},
title = {Kernel-Based Offload of Collective Operations - Implementation, Evaluation
and Lessons Learned},
booktitle = {Euro-Par 2011 Parallel Processing - 17th International Conference,
Euro-Par 2011, Bordeaux, France, August 29 - September 2, 2011, Proceedings,
Part {II}},
series = {Lecture Notes in Computer Science},
volume = {6853},
pages = {264--275},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-23397-5\_26},
doi = {10.1007/978-3-642-23397-5\_26},
timestamp = {Tue, 14 May 2019 10:00:46 +0200},
biburl = {https://dblp.org/rec/conf/europar/SchneiderEHR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/HoeflerS11,
author = {Torsten Hoefler and
Marc Snir},
editor = {David K. Lowenthal and
Bronis R. de Supinski and
Sally A. McKee},
title = {Generic topology mapping strategies for large-scale parallel architectures},
booktitle = {Proceedings of the 25th International Conference on Supercomputing,
2011, Tucson, AZ, USA, May 31 - June 04, 2011},
pages = {75--84},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/1995896.1995909},
doi = {10.1145/1995896.1995909},
timestamp = {Tue, 06 Nov 2018 11:07:03 +0100},
biburl = {https://dblp.org/rec/conf/ics/HoeflerS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/WillcockHEL11,
author = {Jeremiah Willcock and
Torsten Hoefler and
Nicholas Gerard Edmonds and
Andrew Lumsdaine},
editor = {David K. Lowenthal and
Bronis R. de Supinski and
Sally A. McKee},
title = {Active pebbles: parallel programming for data-driven applications},
booktitle = {Proceedings of the 25th International Conference on Supercomputing,
2011, Tucson, AZ, USA, May 31 - June 04, 2011},
pages = {235--244},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/1995896.1995934},
doi = {10.1145/1995896.1995934},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ics/WillcockHEL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/DomkeHN11,
author = {Jens Domke and
Torsten Hoefler and
Wolfgang E. Nagel},
title = {Deadlock-Free Oblivious Routing for Arbitrary Topologies},
booktitle = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May, 2011 - Conference
Proceedings},
pages = {616--627},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/IPDPS.2011.65},
doi = {10.1109/IPDPS.2011.65},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/DomkeHN11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Hoefler11,
author = {Torsten Hoefler},
title = {{HIPS} Introduction},
booktitle = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May 2011 - Workshop Proceedings},
pages = {1139--1140},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/IPDPS.2011.405},
doi = {10.1109/IPDPS.2011.405},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/Hoefler11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/padl/HolkBWHCL11,
author = {Eric Holk and
William E. Byrd and
Jeremiah Willcock and
Torsten Hoefler and
Arun Chauhan and
Andrew Lumsdaine},
editor = {Ricardo Rocha and
John Launchbury},
title = {Kanor - {A} Declarative Language for Explicit Communication},
booktitle = {Practical Aspects of Declarative Languages - 13th International Symposium,
{PADL} 2011, Austin, TX, USA, January 24-25, 2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6539},
pages = {190--204},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-18378-2\_16},
doi = {10.1007/978-3-642-18378-2\_16},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/padl/HolkBWHCL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/WillcockHEL11,
author = {Jeremiah Willcock and
Torsten Hoefler and
Nicholas Gerard Edmonds and
Andrew Lumsdaine},
editor = {Calin Cascaval and
Pen{-}Chung Yew},
title = {Active pebbles: a programming model for highly parallel fine-grained
data-driven computations},
booktitle = {Proceedings of the 16th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, {PPOPP} 2011, San Antonio, TX, USA,
February 12-16, 2011},
pages = {305--306},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/1941553.1941601},
doi = {10.1145/1941553.1941601},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/WillcockHEL11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/VenkatesanCGH11,
author = {Vishwanath Venkatesan and
Mohamad Chaarawi and
Edgar Gabriel and
Torsten Hoefler},
editor = {Yiannis Cotronis and
Anthony Danalis and
Dimitrios S. Nikolopoulos and
Jack J. Dongarra},
title = {Design and Evaluation of Nonblocking Collective {I/O} Operations},
booktitle = {Recent Advances in the Message Passing Interface - 18th European {MPI}
Users' Group Meeting, EuroMPI 2011, Santorini, Greece, September 18-21,
2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6960},
pages = {90--98},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24449-0\_12},
doi = {10.1007/978-3-642-24449-0\_12},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/pvm/VenkatesanCGH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/GroppHTT11,
author = {William Gropp and
Torsten Hoefler and
Rajeev Thakur and
Jesper Larsson Tr{\"{a}}ff},
editor = {Yiannis Cotronis and
Anthony Danalis and
Dimitrios S. Nikolopoulos and
Jack J. Dongarra},
title = {Performance Expectations and Guidelines for {MPI} Derived Datatypes},
booktitle = {Recent Advances in the Message Passing Interface - 18th European {MPI}
Users' Group Meeting, EuroMPI 2011, Santorini, Greece, September 18-21,
2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6960},
pages = {150--159},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24449-0\_18},
doi = {10.1007/978-3-642-24449-0\_18},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/GroppHTT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerS11,
author = {Torsten Hoefler and
Marc Snir},
editor = {Yiannis Cotronis and
Anthony Danalis and
Dimitrios S. Nikolopoulos and
Jack J. Dongarra},
title = {Writing Parallel Libraries with {MPI} - Common Practice, Issues, and
Extensions},
booktitle = {Recent Advances in the Message Passing Interface - 18th European {MPI}
Users' Group Meeting, EuroMPI 2011, Santorini, Greece, September 18-21,
2011. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6960},
pages = {345--355},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24449-0\_45},
doi = {10.1007/978-3-642-24449-0\_45},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerGKS11,
author = {Torsten Hoefler and
William Gropp and
William Kramer and
Marc Snir},
editor = {Scott A. Lathrop and
Jim Costa and
William Kramer},
title = {Performance modeling for systematic performance tuning},
booktitle = {Conference on High Performance Computing Networking, Storage and Analysis
- State of the Practice Reports, {SC} 2011, Seattle, Washington, USA,
November 12-18, 2011},
pages = {6:1--6:12},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2063348.2063356},
doi = {10.1145/2063348.2063356},
timestamp = {Fri, 03 Jul 2020 08:57:23 +0200},
biburl = {https://dblp.org/rec/conf/sc/HoeflerGKS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tg/HarrellSSHLO11,
author = {Stephen Lien Harrell and
Preston M. Smith and
Doug Smith and
Torsten Hoefler and
Anna A. Labutina and
Trinity Overmyer},
editor = {John Towns and
Shawn Brown and
Daniel S. Katz},
title = {Methods of creating student cluster competition teams},
booktitle = {Proceedings of the 2011 TeraGrid Conference - Extreme Digital Discovery,
{TG} '11, Salt Lake City, Utah, USA, July 18-21, 2011},
pages = {50:1--50:6},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2016741.2016795},
doi = {10.1145/2016741.2016795},
timestamp = {Sat, 09 Apr 2022 12:46:56 +0200},
biburl = {https://dblp.org/rec/conf/tg/HarrellSSHLO11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cse/Hoefler10,
author = {Torsten Hoefler},
title = {Software and Hardware Techniques for Power-Efficient {HPC} Networking},
journal = {Comput. Sci. Eng.},
volume = {12},
number = {6},
pages = {30--37},
year = {2010},
url = {https://doi.org/10.1109/MCSE.2010.96},
doi = {10.1109/MCSE.2010.96},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cse/Hoefler10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/paapp/HoeflerSL10,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {Accurately measuring overhead, communication time and progression
of blocking and nonblocking collective operations at massive scale},
journal = {Int. J. Parallel Emergent Distributed Syst.},
volume = {25},
number = {4},
pages = {241--258},
year = {2010},
url = {https://doi.org/10.1080/17445760902894688},
doi = {10.1080/17445760902894688},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/paapp/HoeflerSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEpact/WillcockHEL10,
author = {Jeremiah Willcock and
Torsten Hoefler and
Nicholas Gerard Edmonds and
Andrew Lumsdaine},
editor = {Valentina Salapura and
Michael Gschwind and
Jens Knoop},
title = {{AM++:} a generalized active message framework},
booktitle = {19th International Conference on Parallel Architectures and Compilation
Techniques, {PACT} 2010, Vienna, Austria, September 11-15, 2010},
pages = {401--410},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1854273.1854323},
doi = {10.1145/1854273.1854323},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/IEEEpact/WillcockHEL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/Hoefler10,
author = {Torsten Hoefler},
editor = {Mario R. Guarracino and
Fr{\'{e}}d{\'{e}}ric Vivien and
Jesper Larsson Tr{\"{a}}ff and
Mario Cannataro and
Marco Danelutto and
Anders Hast and
Francesca Perla and
Andreas Kn{\"{u}}pfer and
Beniamino Di Martino and
Michael Alexander},
title = {Bridging Performance Analysis Tools and Analytic Performance Modeling
for {HPC}},
booktitle = {Euro-Par 2010 Parallel Processing Workshops - HeteroPar, HPCC, HiBB,
CoreGrid, UCHPC, HPCF, PROPER, CCPI, VHPC, Ischia, Italy, August 31-September
3, 2010, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {6586},
pages = {483--491},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-21878-1\_60},
doi = {10.1007/978-3-642-21878-1\_60},
timestamp = {Wed, 19 Feb 2020 14:52:57 +0100},
biburl = {https://dblp.org/rec/conf/europar/Hoefler10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/EdmondsHL10,
author = {Nick Edmonds and
Torsten Hoefler and
Andrew Lumsdaine},
title = {A space-efficient parallel algorithm for computing betweenness centrality
in distributed memory},
booktitle = {2010 International Conference on High Performance Computing, HiPC
2010, Dona Paula, Goa, India, December 19-22, 2010},
pages = {1--10},
publisher = {{IEEE} Computer Society},
year = {2010},
url = {https://doi.org/10.1109/HIPC.2010.5713180},
doi = {10.1109/HIPC.2010.5713180},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hipc/EdmondsHL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/ArimilliACCDDHJLLNR10,
author = {L. Baba Arimilli and
Ravi Arimilli and
Vicente Chung and
Scott Clark and
Wolfgang E. Denzel and
Ben C. Drerup and
Torsten Hoefler and
Jody B. Joyner and
Jerry Lewis and
Jian Li and
Nan Ni and
Ramakrishnan Rajamony},
editor = {Fabrizio Petrini and
Dennis Abts and
Ron Brightwell and
Pavan Balaji and
Cyriel Minkenberg},
title = {The {PERCS} High-Performance Interconnect},
booktitle = {{IEEE} 18th Annual Symposium on High Performance Interconnects, {HOTI}
2010, Google Campus, Mountain View, California, USA, August 18-20,
2010},
pages = {75--82},
publisher = {{IEEE} Computer Society},
year = {2010},
url = {https://doi.org/10.1109/HOTI.2010.16},
doi = {10.1109/HOTI.2010.16},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/ArimilliACCDDHJLLNR10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/HoeflerSL10,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
editor = {Salim Hariri and
Kate Keahey},
title = {LogGOPSim: simulating large-scale applications in the LogGOPS model},
booktitle = {Proceedings of the 19th {ACM} International Symposium on High Performance
Distributed Computing, {HPDC} 2010, Chicago, Illinois, USA, June 21-25,
2010},
pages = {597--604},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1851476.1851564},
doi = {10.1145/1851476.1851564},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hpdc/HoeflerSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/HoeflerSL10,
author = {Torsten Hoefler and
Christian Siebert and
Andrew Lumsdaine},
editor = {R. Govindarajan and
David A. Padua and
Mary W. Hall},
title = {Scalable communication protocols for dynamic sparse data exchange},
booktitle = {Proceedings of the 15th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, {PPOPP} 2010, Bangalore, India,
January 9-14, 2010},
pages = {159--168},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1693453.1693476},
doi = {10.1145/1693453.1693476},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/HoeflerSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerGTT10,
author = {Torsten Hoefler and
William Gropp and
Rajeev Thakur and
Jesper Larsson Tr{\"{a}}ff},
editor = {Rainer Keller and
Edgar Gabriel and
Michael M. Resch and
Jack J. Dongarra},
title = {Toward Performance Models of {MPI} Implementations for Understanding
Application Scaling Issues},
booktitle = {Recent Advances in the Message Passing Interface - 17th European {MPI}
Users' Group Meeting, EuroMPI 2010, Stuttgart, Germany, September
12-15, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6305},
pages = {21--30},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15646-5\_3},
doi = {10.1007/978-3-642-15646-5\_3},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerGTT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerBBSL10,
author = {Torsten Hoefler and
Greg Bronevetsky and
Brian Barrett and
Bronis R. de Supinski and
Andrew Lumsdaine},
editor = {Rainer Keller and
Edgar Gabriel and
Michael M. Resch and
Jack J. Dongarra},
title = {Efficient {MPI} Support for Advanced Hybrid Programming Models},
booktitle = {Recent Advances in the Message Passing Interface - 17th European {MPI}
Users' Group Meeting, EuroMPI 2010, Stuttgart, Germany, September
12-15, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6305},
pages = {50--61},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15646-5\_6},
doi = {10.1007/978-3-642-15646-5\_6},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerBBSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerG10,
author = {Torsten Hoefler and
Steven Gottlieb},
editor = {Rainer Keller and
Edgar Gabriel and
Michael M. Resch and
Jack J. Dongarra},
title = {Parallel Zero-Copy Algorithms for Fast Fourier Transform and Conjugate
Gradient Using {MPI} Datatypes},
booktitle = {Recent Advances in the Message Passing Interface - 17th European {MPI}
Users' Group Meeting, EuroMPI 2010, Stuttgart, Germany, September
12-15, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6305},
pages = {132--141},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15646-5\_14},
doi = {10.1007/978-3-642-15646-5\_14},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerSL10,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {Characterizing the Influence of System Noise on Large-Scale Applications
by Simulation},
booktitle = {Conference on High Performance Computing Networking, Storage and Analysis,
{SC} 2010, New Orleans, LA, USA, November 13-19, 2010},
pages = {1--11},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/SC.2010.12},
doi = {10.1109/SC.2010.12},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/HoeflerSL10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ppl/HoeflerSL09,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {The Effect of Network Noise on Large-Scale Collective Communications},
journal = {Parallel Process. Lett.},
volume = {19},
number = {4},
pages = {573--593},
year = {2009},
url = {https://doi.org/10.1142/S0129626409000420},
doi = {10.1142/S0129626409000420},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ppl/HoeflerSL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simpra/HoeflerSL09,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {LogGP in theory and practice - An in-depth analysis of modern interconnection
networks and benchmarking methods for collective operations},
journal = {Simul. Model. Pract. Theory},
volume = {17},
number = {9},
pages = {1511--1521},
year = {2009},
url = {https://doi.org/10.1016/j.simpat.2009.06.007},
doi = {10.1016/J.SIMPAT.2009.06.007},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simpra/HoeflerSL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/KambadurGHL09,
author = {Prabhanjan Kambadur and
Anshul Gupta and
Torsten Hoefler and
Andrew Lumsdaine},
editor = {Yuanyuan Yang and
Manish Parashar and
Rajeev Muralidhar and
Viktor K. Prasanna},
title = {Demand-driven execution of static directed acyclic graphs using task
parallelism},
booktitle = {16th International Conference on High Performance Computing, HiPC
2009, December 16-19, 2009, Kochi, India, Proceedings},
pages = {284--293},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/HIPC.2009.5433201},
doi = {10.1109/HIPC.2009.5433201},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hipc/KambadurGHL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/HoeflerSL09,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
editor = {Keren Bergman and
Ron Brightwell and
Fabrizio Petrini and
Head Bubba},
title = {Optimized Routing for Large-Scale InfiniBand Networks},
booktitle = {17th {IEEE} Symposium on High Performance Interconnects, {HOTI} 2009,
New York, New York, USA, August 25-27, 2009},
pages = {103--111},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/HOTI.2009.9},
doi = {10.1109/HOTI.2009.9},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/HoeflerSL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/HoeflerSL09,
author = {Torsten Hoefler and
Christian Siebert and
Andrew Lumsdaine},
title = {Group Operation Assembly Language - {A} Flexible Way to Express Collective
Communication},
booktitle = {{ICPP} 2009, International Conference on Parallel Processing, Vienna,
Austria, 22-25 September 2009},
pages = {574--581},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/ICPP.2009.70},
doi = {10.1109/ICPP.2009.70},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpp/HoeflerSL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerSL09,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {A power-aware, application-based performance study of modern commodity
cluster interconnection networks},
booktitle = {23rd {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2009, Rome, Italy, May 23-29, 2009},
pages = {1--7},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/IPDPS.2009.5160891},
doi = {10.1109/IPDPS.2009.5160891},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerSL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerSL09a,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {The impact of network noise at large-scale communication performance},
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.2009.5161095},
doi = {10.1109/IPDPS.2009.5161095},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerSL09a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerT09,
author = {Torsten Hoefler and
Jesper Larsson Tr{\"{a}}ff},
title = {Sparse collective operations for {MPI}},
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.2009.5160935},
doi = {10.1109/IPDPS.2009.5160935},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerT09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/KaiserHBB09,
author = {Christian Kaiser and
Torsten Hoefler and
Boris Bierbaum and
Thomas Bemmerl},
title = {Implementation and analysis of nonblocking collective operations on
{SCI} networks},
booktitle = {23rd {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2009, Rome, Italy, May 23-29, 2009},
pages = {1--7},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/IPDPS.2009.5160892},
doi = {10.1109/IPDPS.2009.5160892},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/KaiserHBB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerLD09,
author = {Torsten Hoefler and
Andrew Lumsdaine and
Jack J. Dongarra},
editor = {Matti Ropo and
Jan Westerholm and
Jack J. Dongarra},
title = {Towards Efficient MapReduce Using {MPI}},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
16th European {PVM/MPI} Users' Group Meeting, Espoo, Finland, September
7-10, 2009. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5759},
pages = {240--249},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-03770-2\_30},
doi = {10.1007/978-3-642-03770-2\_30},
timestamp = {Tue, 14 May 2019 10:00:52 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerLD09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/arcs/SchneiderHWMR08,
author = {Timo Schneider and
Torsten Hoefler and
Simon Wunderlich and
Torsten Mehlan and
Wolfgang Rehm},
editor = {Wolfgang E. Nagel and
Rolf Hoffmann and
Andreas Koch},
title = {An Optimized {ZGEMM} Implementation for the Cell {BE}},
booktitle = {9th Workshop on Parallel Systems and Algorithms {(PASA)} held at the
21st Conference on the Architecture of Computing Systems (ARCS), February
26th, 2008, in Dresden, Germany},
series = {{LNI}},
volume = {{P-124}},
pages = {113--122},
publisher = {{GI}},
year = {2008},
url = {https://dl.gi.de/handle/20.500.12116/22270},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/arcs/SchneiderHWMR08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/HoeflerL08,
author = {Torsten Hoefler and
Andrew Lumsdaine},
title = {Overlapping Communication and Computation with High Level Communication
Routines},
booktitle = {8th {IEEE} International Symposium on Cluster Computing and the Grid
(CCGrid 2008), 19-22 May 2008, Lyon, France},
pages = {572--577},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/CCGRID.2008.15},
doi = {10.1109/CCGRID.2008.15},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ccgrid/HoeflerL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/HoeflerSL08,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {Multistage switches are not crossbars: Effects of static routing in
high-performance networks},
booktitle = {Proceedings of the 2008 {IEEE} International Conference on Cluster
Computing, 29 September - 1 October 2008, Tsukuba, Japan},
pages = {116--125},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/CLUSTR.2008.4663762},
doi = {10.1109/CLUSTR.2008.4663762},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/HoeflerSL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/HoeflerL08,
author = {Torsten Hoefler and
Andrew Lumsdaine},
title = {Message progression in parallel computing - to thread or not to thread?},
booktitle = {Proceedings of the 2008 {IEEE} International Conference on Cluster
Computing, 29 September - 1 October 2008, Tsukuba, Japan},
pages = {213--222},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/CLUSTR.2008.4663774},
doi = {10.1109/CLUSTR.2008.4663774},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/HoeflerL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/GeoffrayH08,
author = {Patrick Geoffray and
Torsten Hoefler},
title = {Adaptive Routing Strategies for Modern High Performance Networks},
booktitle = {16th Annual {IEEE} Symposium on High Performance Interconnects {(HOTI}
2008), 26-28 August 2008, Stanford, CA, {USA}},
pages = {165--172},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/HOTI.2008.21},
doi = {10.1109/HOTI.2008.21},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hoti/GeoffrayH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerL08,
author = {Torsten Hoefler and
Andrew Lumsdaine},
title = {Optimizing non-blocking collective operations for infiniband},
booktitle = {22nd {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2008, Miami, Florida USA, April 14-18, 2008},
pages = {1--8},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/IPDPS.2008.4536138},
doi = {10.1109/IPDPS.2008.4536138},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerSL08,
author = {Torsten Hoefler and
Timo Schneider and
Andrew Lumsdaine},
title = {Accurately measuring collective operations at massive scale},
booktitle = {22nd {IEEE} International Symposium on Parallel and Distributed Processing,
{IPDPS} 2008, Miami, Florida USA, April 14-18, 2008},
pages = {1--8},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/IPDPS.2008.4536494},
doi = {10.1109/IPDPS.2008.4536494},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerSL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerLL08,
author = {Torsten Hoefler and
Florian Lorenzen and
Andrew Lumsdaine},
editor = {Alexey L. Lastovetsky and
M. Tahar Kechadi and
Jack J. Dongarra},
title = {Sparse Non-blocking Collectives in Quantum Mechanical Calculations},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
15th European {PVM/MPI} Users' Group Meeting, Dublin, Ireland, September
7-10, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5205},
pages = {55--63},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87475-1\_13},
doi = {10.1007/978-3-540-87475-1\_13},
timestamp = {Mon, 03 Jan 2022 22:32:15 +0100},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerLL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerSGL08,
author = {Torsten Hoefler and
Maraike Schellmann and
Sergei Gorlatch and
Andrew Lumsdaine},
editor = {Alexey L. Lastovetsky and
M. Tahar Kechadi and
Jack J. Dongarra},
title = {Communication Optimization for Medical Image Reconstruction Algorithms},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
15th European {PVM/MPI} Users' Group Meeting, Dublin, Ireland, September
7-10, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5205},
pages = {75--83},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-87475-1\_15},
doi = {10.1007/978-3-540-87475-1\_15},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerSGL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spaa/HoeflerGL08,
author = {Torsten Hoefler and
Peter Gottschling and
Andrew Lumsdaine},
editor = {Friedhelm Meyer auf der Heide and
Nir Shavit},
title = {Leveraging non-blocking collective communication in high-performance
applications},
booktitle = {{SPAA} 2008: Proceedings of the 20th Annual {ACM} Symposium on Parallelism
in Algorithms and Architectures, Munich, Germany, June 14-16, 2008},
pages = {113--115},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1378533.1378554},
doi = {10.1145/1378533.1378554},
timestamp = {Wed, 21 Nov 2018 11:14:43 +0100},
biburl = {https://dblp.org/rec/conf/spaa/HoeflerGL08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/HoeflerGLR07,
author = {Torsten Hoefler and
Peter Gottschling and
Andrew Lumsdaine and
Wolfgang Rehm},
title = {Optimizing a conjugate gradient solver with non-blocking collective
operations},
journal = {Parallel Comput.},
volume = {33},
number = {9},
pages = {624--633},
year = {2007},
url = {https://doi.org/10.1016/j.parco.2007.06.006},
doi = {10.1016/J.PARCO.2007.06.006},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pc/HoeflerGLR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcc/HoeflerMLR07,
author = {Torsten Hoefler and
Torsten Mehlan and
Andrew Lumsdaine and
Wolfgang Rehm},
editor = {Ronald H. Perrott and
Barbara M. Chapman and
Jaspal Subhlok and
Rodrigo Fernandes de Mello and
Laurence Tianruo Yang},
title = {Netgauge: {A} Network Performance Measurement Framework},
booktitle = {High Performance Computing and Communications, Third International
Conference, {HPCC} 2007, Houston, USA, September 26-28, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4782},
pages = {659--671},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-75444-2\_62},
doi = {10.1007/978-3-540-75444-2\_62},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/hpcc/HoeflerMLR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerLR07,
author = {Torsten Hoefler and
Andre Lichei and
Wolfgang Rehm},
title = {Low-Overhead LogGP Parameter Assessment for Modern Interconnection
Networks},
booktitle = {21th International Parallel and Distributed Processing Symposium {(IPDPS}
2007), Proceedings, 26-30 March 2007, Long Beach, California, {USA}},
pages = {1--8},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/IPDPS.2007.370593},
doi = {10.1109/IPDPS.2007.370593},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerLR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerSR07,
author = {Torsten Hoefler and
Christian Siebert and
Wolfgang Rehm},
title = {A practically constant-time {MPI} Broadcast Algorithm for large-scale
InfiniBand Clusters with Multicast},
booktitle = {21th International Parallel and Distributed Processing Symposium {(IPDPS}
2007), Proceedings, 26-30 March 2007, Long Beach, California, {USA}},
pages = {1--8},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/IPDPS.2007.370475},
doi = {10.1109/IPDPS.2007.370475},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerSR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerKGSL07,
author = {Torsten Hoefler and
Prabhanjan Kambadur and
Richard L. Graham and
Galen M. Shipman and
Andrew Lumsdaine},
editor = {Franck Cappello and
Thomas H{\'{e}}rault and
Jack J. Dongarra},
title = {A Case for Standard Non-blocking Collective Operations},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
14th European {PVM/MPI} User's Group Meeting, Paris, France, September
30 - October 3, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4757},
pages = {125--134},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-75416-9\_22},
doi = {10.1007/978-3-540-75416-9\_22},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerKGSL07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoeflerLR07,
author = {Torsten Hoefler and
Andrew Lumsdaine and
Wolfgang Rehm},
editor = {Becky Verastegui},
title = {Implementation and performance analysis of non-blocking collective
operations for {MPI}},
booktitle = {Proceedings of the {ACM/IEEE} Conference on High Performance Networking
and Computing, {SC} 2007, November 10-16, 2007, Reno, Nevada, {USA}},
pages = {52},
publisher = {{ACM} Press},
year = {2007},
url = {https://doi.org/10.1145/1362622.1362692},
doi = {10.1145/1362622.1362692},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/HoeflerLR07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/arcs/HoeflerMMR06,
author = {Torsten Hoefler and
Torsten Mehlan and
Frank Mietke and
Wolfgang Rehm},
editor = {Wolfgang Karl and
J{\"{u}}rgen Becker and
Karl{-}Erwin Gro{\ss}pietsch and
Christian Hochberger and
Erik Maehle},
title = {Adding Low-Cost Hardware Barrier Support to Small Commodity Clusters},
booktitle = {{ARCS} 2006 - 19th International Conference on Architecture of Computing
Systems, Workshops Proceedings, March 16, 2006, Frankfurt am Main,
Germany},
series = {{LNI}},
volume = {{P-81}},
pages = {343--350},
publisher = {{GI}},
year = {2006},
url = {https://dl.gi.de/handle/20.500.12116/29432},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/arcs/HoeflerMMR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/MietkeRBMHR06,
author = {Frank Mietke and
Robert Rex and
Robert Baumgartl and
Torsten Mehlan and
Torsten Hoefler and
Wolfgang Rehm},
editor = {Wolfgang E. Nagel and
Wolfgang V. Walter and
Wolfgang Lehner},
title = {Analysis of the Memory Registration Process in the Mellanox InfiniBand
Software Stack},
booktitle = {Euro-Par 2006, Parallel Processing, 12th International Euro-Par Conference,
Dresden, Germany, August 28 - September 1, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4128},
pages = {124--133},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11823285\_13},
doi = {10.1007/11823285\_13},
timestamp = {Tue, 14 May 2019 10:00:46 +0200},
biburl = {https://dblp.org/rec/conf/europar/MietkeRBMHR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerMMR06,
author = {Torsten Hoefler and
Torsten Mehlan and
Frank Mietke and
Wolfgang Rehm},
title = {Fast barrier synchronization for InfiniBand{\texttrademark}},
booktitle = {20th International Parallel and Distributed Processing Symposium {(IPDPS}
2006), Proceedings, 25-29 April 2006, Rhodes Island, Greece},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/IPDPS.2006.1639561},
doi = {10.1109/IPDPS.2006.1639561},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerMMR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HoeflerMMR06a,
author = {Torsten Hoefler and
Torsten Mehlan and
Frank Mietke and
Wolfgang Rehm},
title = {LogfP - a model for small messages in InfiniBand},
booktitle = {20th International Parallel and Distributed Processing Symposium {(IPDPS}
2006), Proceedings, 25-29 April 2006, Rhodes Island, Greece},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/IPDPS.2006.1639624},
doi = {10.1109/IPDPS.2006.1639624},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/HoeflerMMR06a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispa/HoeflerSRL06,
author = {Torsten Hoefler and
Jeffrey M. Squyres and
Wolfgang Rehm and
Andrew Lumsdaine},
editor = {Geyong Min and
Beniamino Di Martino and
Laurence Tianruo Yang and
Minyi Guo and
Gudula R{\"{u}}nger},
title = {A Case for Non-blocking Collective Operations},
booktitle = {Frontiers of High Performance Computing and Networking - {ISPA} 2006
Workshops, {ISPA} 2006 International Workshops, FHPCN, XHPC, S-GRACE,
GridGIS, HPC-GTP, PDCE, ParDMCom, WOMP, ISDF, and UPWN, Sorrento,
Italy, December 4-7, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4331},
pages = {155--164},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11942634\_17},
doi = {10.1007/11942634\_17},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ispa/HoeflerSRL06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/parelec/MehlanSHMR06,
author = {Torsten Mehlan and
Jochen Strunk and
Torsten Hoefler and
Frank Mietke and
Wolfgang Rehm},
title = {{IRS} - {A} Portable Interface for Reconfigurable Systems},
booktitle = {Fifth International Conference on Parallel Computing in Electrical
Engineering {(PARELEC} 2006), 13-17 September 2006, Bialystok, Poland},
pages = {187--191},
publisher = {{IEEE} Computer Society},
year = {2006},
url = {https://doi.org/10.1109/PARELEC.2006.50},
doi = {10.1109/PARELEC.2006.50},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/parelec/MehlanSHMR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/parelec/HoeflerVMMR06,
author = {Torsten Hoefler and
Carsten Viertel and
Torsten Mehlan and
Frank Mietke and
Wolfgang Rehm},
title = {Assessing Single-Message and Multi-Node Communication Performance
of InfiniBand},
booktitle = {Fifth International Conference on Parallel Computing in Electrical
Engineering {(PARELEC} 2006), 13-17 September 2006, Bialystok, Poland},
pages = {227--232},
publisher = {{IEEE} Computer Society},
year = {2006},
url = {https://doi.org/10.1109/PARELEC.2006.16},
doi = {10.1109/PARELEC.2006.16},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/parelec/HoeflerVMMR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoeflerGRL06,
author = {Torsten Hoefler and
Peter Gottschling and
Wolfgang Rehm and
Andrew Lumsdaine},
editor = {Bernd Mohr and
Jesper Larsson Tr{\"{a}}ff and
Joachim Worringen and
Jack J. Dongarra},
title = {Optimizing a Conjugate Gradient Solver with Non-Blocking Collective
Operations},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
13th European {PVM/MPI} User's Group Meeting, Bonn, Germany, September
17-20, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4192},
pages = {374--382},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11846802\_52},
doi = {10.1007/11846802\_52},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/HoeflerGRL06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icppw/HoeflerCMMR05,
author = {Torsten Hoefler and
Lavinio Cerquetti and
Torsten Mehlan and
Frank Mietke and
Wolfgang Rehm},
title = {A Practical Approach to the Rating of Barrier Algorithms Using the
LogP Model and Open {MPI}},
booktitle = {34th International Conference on Parallel Processing Workshops {(ICPP}
2005 Workshops), 14-17 June 2005, Oslo, Norway},
pages = {562--569},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/ICPPW.2005.14},
doi = {10.1109/ICPPW.2005.14},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icppw/HoeflerCMMR05.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 2024-04-25 05:55 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:
