Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Tor M. Aamodt
@inproceedings{DBLP:conf/iclr/ShahA23, author = {Deval Shah and Tor M. Aamodt}, title = {Learning Label Encodings for Deep Regression}, 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=k60XE\_b0Ix6}, timestamp = {Fri, 30 Jun 2023 14:38:38 +0200}, biburl = {https://dblp.org/rec/conf/iclr/ShahA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iiswc/LiuSCGNA23, author = {Lufei Liu and Mohammadreza Saed and Yuan{-}Hsi Chou and Davit Grigoryan and Tyler Nowicki and Tor M. Aamodt}, title = {LumiBench: {A} Benchmark Suite for Hardware Ray Tracing}, booktitle = {{IEEE} International Symposium on Workload Characterization, {IISWC} 2023, Ghent, Belgium, October 1-3, 2023}, pages = {1--14}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IISWC59245.2023.00011}, doi = {10.1109/IISWC59245.2023.00011}, timestamp = {Sat, 11 Nov 2023 13:55:39 +0100}, biburl = {https://dblp.org/rec/conf/iiswc/LiuSCGNA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/ShahYA23, author = {Deval Shah and Ningfeng Yang and Tor M. Aamodt}, editor = {Yan Solihin and Mark A. Heinrich}, title = {Energy-Efficient Realtime Motion Planning}, booktitle = {Proceedings of the 50th Annual International Symposium on Computer Architecture, {ISCA} 2023, Orlando, FL, USA, June 17-21, 2023}, pages = {57:1--57:17}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3579371.3589092}, doi = {10.1145/3579371.3589092}, timestamp = {Fri, 07 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isca/ShahYA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/ChouNA23, author = {Yuan{-}Hsi Chou and Tyler Nowicki and Tor M. Aamodt}, title = {Treelet Prefetching For Ray Tracing}, booktitle = {Proceedings of the 56th Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2023, Toronto, ON, Canada, 28 October 2023 - 1 November 2023}, pages = {742--755}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3613424.3614288}, doi = {10.1145/3613424.3614288}, timestamp = {Sun, 31 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/micro/ChouNA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/asplos/2023-2, editor = {Tor M. Aamodt and Natalie D. Enright Jerger and Michael M. Swift}, title = {Proceedings of the 28th {ACM} International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, {ASPLOS} 2023, Vancouver, BC, Canada, March 25-29, 2023}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3575693}, doi = {10.1145/3575693}, isbn = {978-1-4503-9916-6}, timestamp = {Thu, 02 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asplos/2023-2.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/asplos/2023-3, editor = {Tor M. Aamodt and Natalie D. Enright Jerger and Michael M. Swift}, title = {Proceedings of the 28th {ACM} International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3, {ASPLOS} 2023, Vancouver, BC, Canada, March 25-29, 2023}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3582016}, doi = {10.1145/3582016}, isbn = {978-1-4503-9918-0}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asplos/2023-3.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/asplos/2023-4, editor = {Tor M. Aamodt and Michael M. Swift and Natalie D. Enright Jerger}, title = {Proceedings of the 28th {ACM} International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4, {ASPLOS} 2023, Vancouver, BC, Canada, March 25-29, 2023}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3623278}, doi = {10.1145/3623278}, timestamp = {Thu, 08 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asplos/2023-4.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-02273, author = {Deval Shah and Tor M. Aamodt}, title = {Learning Label Encodings for Deep Regression}, journal = {CoRR}, volume = {abs/2303.02273}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.02273}, doi = {10.48550/ARXIV.2303.02273}, eprinttype = {arXiv}, eprint = {2303.02273}, timestamp = {Tue, 14 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-02273.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/ShahXA22, author = {Deval Shah and Zi Yu Xue and Tor M. Aamodt}, title = {Label Encoding for Regression Networks}, 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=8WawVDdKqlL}, timestamp = {Sat, 20 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/ShahXA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/LewLGGEA22, author = {Jonathan S. Lew and Yunpeng Liu and Wenyi Gong and Negar Goli and R. David Evans and Tor M. Aamodt}, editor = {Valentina Salapura and Mohamed Zahran and Fred Chong and Lingjia Tang}, title = {Anticipating and eliminating redundant computations in accelerated sparse training}, booktitle = {{ISCA} '22: The 49th Annual International Symposium on Computer Architecture, New York, New York, USA, June 18 - 22, 2022}, pages = {536--551}, publisher = {{ACM}}, year = {2022}, url = {https://doi.org/10.1145/3470496.3527404}, doi = {10.1145/3470496.3527404}, timestamp = {Tue, 25 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isca/LewLGGEA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/SaedCLNA22, author = {Mohammadreza Saed and Yuan{-}Hsi Chou and Lufei Liu and Tyler Nowicki and Tor M. Aamodt}, title = {Vulkan-Sim: {A} {GPU} Architecture Simulator for Ray Tracing}, booktitle = {55th {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2022, Chicago, IL, USA, October 1-5, 2022}, pages = {263--281}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/MICRO56248.2022.00027}, doi = {10.1109/MICRO56248.2022.00027}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/SaedCLNA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/asplos/2023-1, editor = {Tor M. Aamodt and Natalie D. Enright Jerger and Michael M. Swift}, title = {Proceedings of the 28th {ACM} International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1, {ASPLOS} 2023, Vancouver, BC, Canada, March 25-29, 2023}, publisher = {{ACM}}, year = {2022}, url = {https://doi.org/10.1145/3567955}, doi = {10.1145/3567955}, isbn = {978-1-4503-9915-9}, timestamp = {Thu, 22 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asplos/2023-1.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-01927, author = {Deval Shah and Zi Yu Xue and Tor M. Aamodt}, title = {Label Encoding for Regression Networks}, journal = {CoRR}, volume = {abs/2212.01927}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.01927}, doi = {10.48550/ARXIV.2212.01927}, eprinttype = {arXiv}, eprint = {2212.01927}, timestamp = {Thu, 08 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-01927.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/LiuCDCSPNA21, author = {Lufei Liu and Wesley Chang and Francois Demoullin and Yuan{-}Hsi Chou and Mohammadreza Saed and David Pankratz and Tyler Nowicki and Tor M. Aamodt}, title = {Intersection Prediction for Accelerated {GPU} Ray Tracing}, booktitle = {{MICRO} '21: 54th Annual {IEEE/ACM} International Symposium on Microarchitecture, Virtual Event, Greece, October 18-22, 2021}, pages = {709--723}, publisher = {{ACM}}, year = {2021}, url = {https://doi.org/10.1145/3466752.3480097}, doi = {10.1145/3466752.3480097}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/LiuCDCSPNA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/KandiahPKPMRAH21, author = {Vijay Kandiah and Scott Peverelle and Mahmoud Khairy and Junrui Pan and Amogh Manjunath and Timothy G. Rogers and Tor M. Aamodt and Nikos Hardavellas}, title = {AccelWattch: {A} Power Modeling Framework for Modern GPUs}, booktitle = {{MICRO} '21: 54th Annual {IEEE/ACM} International Symposium on Microarchitecture, Virtual Event, Greece, October 18-22, 2021}, pages = {738--753}, publisher = {{ACM}}, year = {2021}, url = {https://doi.org/10.1145/3466752.3480063}, doi = {10.1145/3466752.3480063}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/KandiahPKPMRAH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/EvansA21, author = {R. David Evans and Tor M. Aamodt}, editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan}, title = {{AC-GC:} Lossy Activation Compression with Guaranteed Convergence}, booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual}, pages = {27434--27448}, year = {2021}, url = {https://proceedings.neurips.cc/paper/2021/hash/e655c7716a4b3ea67f48c6322fc42ed6-Abstract.html}, timestamp = {Tue, 03 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/nips/EvansA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-08906, author = {Deval Shah and Zi Yu Xue and Karthik Pattabiraman and Tor M. Aamodt}, title = {Characterizing and Improving the Resilience of Accelerators in Autonomous Robots}, journal = {CoRR}, volume = {abs/2110.08906}, year = {2021}, url = {https://arxiv.org/abs/2110.08906}, eprinttype = {arXiv}, eprint = {2110.08906}, timestamp = {Fri, 22 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-08906.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tc/MohammadiHABAD20, author = {Milad Mohammadi and Song Han and Ehsan Atoofian and Amirali Baniasadi and Tor M. Aamodt and William J. Dally}, title = {Energy Efficient On-Demand Dynamic Branch Prediction Models}, journal = {{IEEE} Trans. Computers}, volume = {69}, number = {3}, pages = {453--465}, year = {2020}, url = {https://doi.org/10.1109/TC.2019.2956710}, doi = {10.1109/TC.2019.2956710}, timestamp = {Fri, 20 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tc/MohammadiHABAD20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEpact/KimCRBAK20, author = {Jiho Kim and Sanghun Cho and Minsoo Rhu and Ali Bakhoda and Tor M. Aamodt and John Kim}, editor = {Vivek Sarkar and Hyesoon Kim}, title = {Bandwidth Bottleneck in Network-on-Chip for High-Throughput Processors}, booktitle = {{PACT} '20: International Conference on Parallel Architectures and Compilation Techniques, Virtual Event, GA, USA, October 3-7, 2020}, pages = {157--158}, publisher = {{ACM}}, year = {2020}, url = {https://doi.org/10.1145/3410463.3414673}, doi = {10.1145/3410463.3414673}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/IEEEpact/KimCRBAK20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/GoliA20, author = {Negar Goli and Tor M. Aamodt}, title = {ReSprop: Reuse Sparsified Backpropagation}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, pages = {1545--1555}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2020}, url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Goli\_ReSprop\_Reuse\_Sparsified\_Backpropagation\_CVPR\_2020\_paper.html}, doi = {10.1109/CVPR42600.2020.00162}, timestamp = {Tue, 31 Aug 2021 14:00:04 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/GoliA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/KhairySAR20, author = {Mahmoud Khairy and Zhesheng Shen and Tor M. Aamodt and Timothy G. Rogers}, title = {Accel-Sim: An Extensible Simulation Framework for Validated {GPU} Modeling}, booktitle = {47th {ACM/IEEE} Annual International Symposium on Computer Architecture, {ISCA} 2020, Virtual Event / Valencia, Spain, May 30 - June 3, 2020}, pages = {473--486}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ISCA45697.2020.00047}, doi = {10.1109/ISCA45697.2020.00047}, timestamp = {Mon, 19 Feb 2024 07:32:24 +0100}, biburl = {https://dblp.org/rec/conf/isca/KhairySAR20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/EvansLA20, author = {R. David Evans and Lufei Liu and Tor M. Aamodt}, title = {{JPEG-ACT:} Accelerating Deep Learning via Transform-based Lossy Compression}, booktitle = {47th {ACM/IEEE} Annual International Symposium on Computer Architecture, {ISCA} 2020, Virtual Event / Valencia, Spain, May 30 - June 3, 2020}, pages = {860--873}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ISCA45697.2020.00075}, doi = {10.1109/ISCA45697.2020.00075}, timestamp = {Wed, 22 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isca/EvansLA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/ChouNCISDRA20, author = {Yuan{-}Hsi Chou and Christopher Ng and Shaylin Cattell and Jeremy Intan and Matthew D. Sinclair and Joseph Devietti and Timothy G. Rogers and Tor M. Aamodt}, title = {Deterministic Atomic Buffering}, booktitle = {53rd Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2020, Athens, Greece, October 17-21, 2020}, pages = {981--995}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/MICRO50266.2020.00083}, doi = {10.1109/MICRO50266.2020.00083}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/ChouNCISDRA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/RaihanA20, author = {Md Aamir Raihan and Tor M. Aamodt}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, title = {Sparse Weight Activation Training}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/b44182379bf9fae976e6ae5996e13cd8-Abstract.html}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/RaihanA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-01969, author = {Md Aamir Raihan and Tor M. Aamodt}, title = {Sparse Weight Activation Training}, journal = {CoRR}, volume = {abs/2001.01969}, year = {2020}, url = {http://arxiv.org/abs/2001.01969}, eprinttype = {arXiv}, eprint = {2001.01969}, timestamp = {Mon, 13 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-01969.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEpact/HetheringtonLSA19, author = {Tayler Hicklin Hetherington and Maria Lubeznov and Deval Shah and Tor M. Aamodt}, title = {{EDGE:} Event-Driven {GPU} Execution}, booktitle = {28th International Conference on Parallel Architectures and Compilation Techniques, {PACT} 2019, Seattle, WA, USA, September 23-26, 2019}, pages = {337--353}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/PACT.2019.00034}, doi = {10.1109/PACT.2019.00034}, timestamp = {Wed, 13 Nov 2019 18:02:12 +0100}, biburl = {https://dblp.org/rec/conf/IEEEpact/HetheringtonLSA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/GubranA19, author = {Ayub A. Gubran and Tor M. Aamodt}, editor = {Srilatha Bobbie Manne and Hillery C. Hunter and Erik R. Altman}, title = {Emerald: graphics modeling for SoC systems}, booktitle = {Proceedings of the 46th International Symposium on Computer Architecture, {ISCA} 2019, Phoenix, AZ, USA, June 22-26, 2019}, pages = {169--182}, publisher = {{ACM}}, year = {2019}, url = {https://doi.org/10.1145/3307650.3322221}, doi = {10.1145/3307650.3322221}, timestamp = {Fri, 09 Jul 2021 15:51:20 +0200}, biburl = {https://dblp.org/rec/conf/isca/GubranA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/RaihanGA19, author = {Md Aamir Raihan and Negar Goli and Tor M. Aamodt}, title = {Modeling Deep Learning Accelerator Enabled GPUs}, booktitle = {{IEEE} International Symposium on Performance Analysis of Systems and Software, {ISPASS} 2019, Madison, WI, USA, March 24-26, 2019}, pages = {79--92}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ISPASS.2019.00016}, doi = {10.1109/ISPASS.2019.00016}, timestamp = {Wed, 16 Oct 2019 14:14:56 +0200}, biburl = {https://dblp.org/rec/conf/ispass/RaihanGA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/KhairyJAR19, author = {Mahmoud Khairy and Akshay Jain and Tor M. Aamodt and Timothy G. Rogers}, title = {A Detailed Model for Contemporary {GPU} Memory Systems}, booktitle = {{IEEE} International Symposium on Performance Analysis of Systems and Software, {ISPASS} 2019, Madison, WI, USA, March 24-26, 2019}, pages = {141--142}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ISPASS.2019.00023}, doi = {10.1109/ISPASS.2019.00023}, timestamp = {Sat, 04 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ispass/KhairyJAR19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/LewSPCZSNGSRA19, author = {Jonathan S. Lew and Deval A. Shah and Suchita Pati and Shaylin Cattell and Mengchi Zhang and Amruth Sandhupatla and Christopher Ng and Negar Goli and Matthew D. Sinclair and Timothy G. Rogers and Tor M. Aamodt}, title = {Analyzing Machine Learning Workloads Using a Detailed {GPU} Simulator}, booktitle = {{IEEE} International Symposium on Performance Analysis of Systems and Software, {ISPASS} 2019, Madison, WI, USA, March 24-26, 2019}, pages = {151--152}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ISPASS.2019.00028}, doi = {10.1109/ISPASS.2019.00028}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ispass/LewSPCZSNGSRA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1903-06658, author = {Ayub A. Gubran and Felix Huang and Tor M. Aamodt}, title = {Surface Compression Using Dynamic Color Palettes}, journal = {CoRR}, volume = {abs/1903.06658}, year = {2019}, url = {http://arxiv.org/abs/1903.06658}, eprinttype = {arXiv}, eprint = {1903.06658}, timestamp = {Mon, 01 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1903-06658.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1910-01304, author = {Francois Demoullin and Ayub A. Gubran and Tor M. Aamodt}, title = {Hash-Based Ray Path Prediction: Skipping {BVH} Traversal Computation by Exploiting Ray Locality}, journal = {CoRR}, volume = {abs/1910.01304}, year = {2019}, url = {http://arxiv.org/abs/1910.01304}, eprinttype = {arXiv}, eprint = {1910.01304}, timestamp = {Fri, 04 Oct 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-01304.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@book{DBLP:series/synthesis/2018Aamodt, author = {Tor M. Aamodt and Wilson Wai Lun Fung and Timothy G. Rogers}, title = {General-Purpose Graphics Processor Architectures}, series = {Synthesis Lectures on Computer Architecture}, publisher = {Morgan {\&} Claypool Publishers}, year = {2018}, url = {https://doi.org/10.2200/S00848ED1V01Y201804CAC044}, doi = {10.2200/S00848ED1V01Y201804CAC044}, isbn = {978-3-031-00631-9}, timestamp = {Sat, 28 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/series/synthesis/2018Aamodt.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/computer/MoshovosAJLSPHA18, author = {Andreas Moshovos and Jorge Albericio and Patrick Judd and Alberto Delmas Lascorz and Sayeh Sharify and Zissis Poulos and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger}, title = {Exploiting Typical Values to Accelerate Deep Learning}, journal = {Computer}, volume = {51}, number = {5}, pages = {18--30}, year = {2018}, url = {https://doi.org/10.1109/MC.2018.2381114}, doi = {10.1109/MC.2018.2381114}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/computer/MoshovosAJLSPHA18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/micro/MoshovosAJLSHAJ18, author = {Andreas Moshovos and Jorge Albericio and Patrick Judd and Alberto Delmas Lascorz and Sayeh Sharify and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger}, title = {Value-Based Deep-Learning Acceleration}, journal = {{IEEE} Micro}, volume = {38}, number = {1}, pages = {41--55}, year = {2018}, url = {https://doi.org/10.1109/MM.2018.112130309}, doi = {10.1109/MM.2018.112130309}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/micro/MoshovosAJLSHAJ18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/JuddAHAJUM18, author = {Patrick Judd and Jorge Albericio and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger and Raquel Urtasun and Andreas Moshovos}, title = {Proteus: Exploiting precision variability in deep neural networks}, journal = {Parallel Comput.}, volume = {73}, pages = {40--51}, year = {2018}, url = {https://doi.org/10.1016/j.parco.2017.05.003}, doi = {10.1016/J.PARCO.2017.05.003}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pc/JuddAHAJUM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/ElTantawyA18, author = {Ahmed ElTantawy and Tor M. Aamodt}, title = {Warp Scheduling for Fine-Grained Synchronization}, booktitle = {{IEEE} International Symposium on High Performance Computer Architecture, {HPCA} 2018, Vienna, Austria, February 24-28, 2018}, pages = {375--388}, publisher = {{IEEE} Computer Society}, year = {2018}, url = {https://doi.org/10.1109/HPCA.2018.00040}, doi = {10.1109/HPCA.2018.00040}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/ElTantawyA18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/newcas/MoshovosAJDSMHN18, author = {Andreas Moshovos and Jorge Albericio and Patrick Judd and Alberto Delmas and Sayeh Sharify and Mostafa Mahmoud and Tayler H. Hetherington and Milos Nikolic and Dylan Malone Stuart and Kevin Siu and Zissis Poulos and Tor M. Aamodt and Natalie D. Enright Jerger}, title = {Identifying and Exploiting Ineffectual Computations to Enable Hardware Acceleration of Deep Learning}, booktitle = {16th {IEEE} International New Circuits and Systems Conference, {NEWCAS} 2018, Montr{\'{e}}al, QC, Canada, June 24-27, 2018}, pages = {356--360}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/NEWCAS.2018.8585656}, doi = {10.1109/NEWCAS.2018.8585656}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/newcas/MoshovosAJDSMHN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1810-07269, author = {Mahmoud Khairy and Akshay Jain and Tor M. Aamodt and Timothy G. Rogers}, title = {Exploring Modern {GPU} Memory System Design Challenges through Accurate Modeling}, journal = {CoRR}, volume = {abs/1810.07269}, year = {2018}, url = {http://arxiv.org/abs/1810.07269}, eprinttype = {arXiv}, eprint = {1810.07269}, timestamp = {Tue, 30 Oct 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-07269.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-08309, author = {Md Aamir Raihan and Negar Goli and Tor M. Aamodt}, title = {Modeling Deep Learning Accelerator Enabled GPUs}, journal = {CoRR}, volume = {abs/1811.08309}, year = {2018}, url = {http://arxiv.org/abs/1811.08309}, eprinttype = {arXiv}, eprint = {1811.08309}, timestamp = {Mon, 26 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-08309.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-08933, author = {Jonathan S. Lew and Deval Shah and Suchita Pati and Shaylin Cattell and Mengchi Zhang and Amruth Sandhupatla and Christopher Ng and Negar Goli and Matthew D. Sinclair and Timothy G. Rogers and Tor M. Aamodt}, title = {Analyzing Machine Learning Workloads Using a Detailed {GPU} Simulator}, journal = {CoRR}, volume = {abs/1811.08933}, year = {2018}, url = {http://arxiv.org/abs/1811.08933}, eprinttype = {arXiv}, eprint = {1811.08933}, timestamp = {Wed, 01 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-08933.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taco/MohammadiAD17, author = {Milad Mohammadi and Tor M. Aamodt and William J. Dally}, title = {CG-OoO: Energy-Efficient Coarse-Grain Out-of-Order Execution Near In-Order Energy with Near Out-of-Order Performance}, journal = {{ACM} Trans. Archit. Code Optim.}, volume = {14}, number = {4}, pages = {39:1--39:26}, year = {2017}, url = {https://doi.org/10.1145/3151034}, doi = {10.1145/3151034}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taco/MohammadiAD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fpt/AssadikhomamiOA17, author = {Shadi Assadikhomami and Jennifer Ongko and Tor M. Aamodt}, title = {A state machine block for high-level synthesis}, booktitle = {International Conference on Field Programmable Technology, {FPT} 2017, Melbourne, Australia, December 11-13, 2017}, pages = {80--87}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/FPT.2017.8280124}, doi = {10.1109/FPT.2017.8280124}, timestamp = {Mon, 17 Feb 2020 13:32:07 +0100}, biburl = {https://dblp.org/rec/conf/fpt/AssadikhomamiOA17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/TurakhiaDAD17, author = {Yatish Turakhia and Subhasis Das and Tor M. Aamodt and William J. Dally}, title = {HoLiSwap: Reducing Wire Energy in {L1} Caches}, journal = {CoRR}, volume = {abs/1701.03878}, year = {2017}, url = {http://arxiv.org/abs/1701.03878}, eprinttype = {arXiv}, eprint = {1701.03878}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/TurakhiaDAD17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cal/LiA16, author = {Dongdong Li and Tor M. Aamodt}, title = {Inter-Core Locality Aware Memory Scheduling}, journal = {{IEEE} Comput. Archit. Lett.}, volume = {15}, number = {1}, pages = {25--28}, year = {2016}, url = {https://doi.org/10.1109/LCA.2015.2435709}, doi = {10.1109/LCA.2015.2435709}, timestamp = {Sun, 15 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/cal/LiA16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taco/DasAD16, author = {Subhasis Das and Tor M. Aamodt and William J. Dally}, title = {Reuse Distance-Based Probabilistic Cache Replacement}, journal = {{ACM} Trans. Archit. Code Optim.}, volume = {12}, number = {4}, pages = {33:1--33:22}, year = {2016}, url = {https://doi.org/10.1145/2818374}, doi = {10.1145/2818374}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taco/DasAD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ics/JuddAHAJM16, author = {Patrick Judd and Jorge Albericio and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger and Andreas Moshovos}, editor = {Ozcan Ozturk and Kemal Ebcioglu and Mahmut T. Kandemir and Onur Mutlu}, title = {Proteus: Exploiting Numerical Precision Variability in Deep Neural Networks}, booktitle = {Proceedings of the 2016 International Conference on Supercomputing, {ICS} 2016, Istanbul, Turkey, June 1-3, 2016}, pages = {23:1--23:12}, publisher = {{ACM}}, year = {2016}, url = {https://doi.org/10.1145/2925426.2926294}, doi = {10.1145/2925426.2926294}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ics/JuddAHAJM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/AlbericioJHAJM16, author = {Jorge Albericio and Patrick Judd and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger and Andreas Moshovos}, title = {Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing}, booktitle = {43rd {ACM/IEEE} Annual International Symposium on Computer Architecture, {ISCA} 2016, Seoul, South Korea, June 18-22, 2016}, pages = {1--13}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/ISCA.2016.11}, doi = {10.1109/ISCA.2016.11}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isca/AlbericioJHAJM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/ElTantawyA16, author = {Ahmed ElTantawy and Tor M. Aamodt}, title = {{MIMD} synchronization on {SIMT} architectures}, booktitle = {49th Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2016, Taipei, Taiwan, October 15-19, 2016}, pages = {11:1--11:14}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/MICRO.2016.7783714}, doi = {10.1109/MICRO.2016.7783714}, timestamp = {Tue, 31 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/ElTantawyA16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/JuddAHAM16, author = {Patrick Judd and Jorge Albericio and Tayler H. Hetherington and Tor M. Aamodt and Andreas Moshovos}, title = {Stripes: Bit-serial deep neural network computing}, booktitle = {49th Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2016, Taipei, Taiwan, October 15-19, 2016}, pages = {19:1--19:12}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/MICRO.2016.7783722}, doi = {10.1109/MICRO.2016.7783722}, timestamp = {Tue, 31 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/JuddAHAM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MohammadiAD16, author = {Milad Mohammadi and Tor M. Aamodt and William J. Dally}, title = {CG-OoO: Energy-Efficient Coarse-Grain Out-of-Order Execution}, journal = {CoRR}, volume = {abs/1606.01607}, year = {2016}, url = {http://arxiv.org/abs/1606.01607}, eprinttype = {arXiv}, eprint = {1606.01607}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MohammadiAD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cal/MohammadiHAD15, author = {Milad Mohammadi and Song Han and Tor M. Aamodt and William J. Dally}, title = {On-Demand Dynamic Branch Prediction}, journal = {{IEEE} Comput. Archit. Lett.}, volume = {14}, number = {1}, pages = {50--53}, year = {2015}, url = {https://doi.org/10.1109/LCA.2014.2330820}, doi = {10.1109/LCA.2014.2330820}, timestamp = {Fri, 20 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/cal/MohammadiHAD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cloud/HetheringtonOA15, author = {Tayler H. Hetherington and Mike O'Connor and Tor M. Aamodt}, editor = {Shahram Ghandeharizadeh and Sumita Barahmand and Magdalena Balazinska and Michael J. Freedman}, title = {MemcachedGPU: scaling-up scale-out key-value stores}, booktitle = {Proceedings of the Sixth {ACM} Symposium on Cloud Computing, SoCC 2015, Kohala Coast, Hawaii, USA, August 27-29, 2015}, pages = {43--57}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2806777.2806836}, doi = {10.1145/2806777.2806836}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cloud/HetheringtonOA15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/DasAD15, author = {Subhasis Das and Tor M. Aamodt and William J. Dally}, editor = {Deborah T. Marr and David H. Albonesi}, title = {{SLIP:} reducing wire energy in the memory hierarchy}, booktitle = {Proceedings of the 42nd Annual International Symposium on Computer Architecture, Portland, OR, USA, June 13-17, 2015}, pages = {349--361}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2749469.2750398}, doi = {10.1145/2749469.2750398}, timestamp = {Fri, 09 Jul 2021 15:51:20 +0200}, biburl = {https://dblp.org/rec/conf/isca/DasAD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/JuddAHAJUM15, author = {Patrick Judd and Jorge Albericio and Tayler H. Hetherington and Tor M. Aamodt and Natalie D. Enright Jerger and Raquel Urtasun and Andreas Moshovos}, title = {Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets}, journal = {CoRR}, volume = {abs/1511.05236}, year = {2015}, url = {http://arxiv.org/abs/1511.05236}, eprinttype = {arXiv}, eprint = {1511.05236}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/JuddAHAJUM15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cacm/RogersOA14, author = {Timothy G. Rogers and Mike O'Connor and Tor M. Aamodt}, title = {Learning your limit: managing massively multithreaded caches through scheduling}, journal = {Commun. {ACM}}, volume = {57}, number = {12}, pages = {91--98}, year = {2014}, url = {https://doi.org/10.1145/2682583}, doi = {10.1145/2682583}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/cacm/RogersOA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/micro/SinghSFOA14, author = {Inderpreet Singh and Arrvindh Shriraman and Wilson W. L. Fung and Mike O'Connor and Tor M. Aamodt}, title = {Cache Coherence for {GPU} Architectures}, journal = {{IEEE} Micro}, volume = {34}, number = {3}, pages = {69--79}, year = {2014}, url = {https://doi.org/10.1109/MM.2014.4}, doi = {10.1109/MM.2014.4}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/micro/SinghSFOA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/ElTantawyMOA14, author = {Ahmed ElTantawy and Jessica Wenjie Ma and Mike O'Connor and Tor M. Aamodt}, title = {A scalable multi-path microarchitecture for efficient {GPU} control flow}, booktitle = {20th {IEEE} International Symposium on High Performance Computer Architecture, {HPCA} 2014, Orlando, FL, USA, February 15-19, 2014}, pages = {248--259}, publisher = {{IEEE} Computer Society}, year = {2014}, url = {https://doi.org/10.1109/HPCA.2014.6835936}, doi = {10.1109/HPCA.2014.6835936}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/ElTantawyMOA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/samos/Aamodt14, author = {Tor M. Aamodt}, title = {Scaling usable computing capability}, booktitle = {XIVth International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, {SAMOS} 2014, Agios Konstantinos, Samos, Greece, July 14-17, 2014}, pages = {i}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/SAMOS.2014.6893185}, doi = {10.1109/SAMOS.2014.6893185}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/samos/Aamodt14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/micro/RogersOA13, author = {Timothy G. Rogers and Mike O'Connor and Tor M. Aamodt}, title = {Cache-Conscious Thread Scheduling for Massively Multithreaded Processors}, journal = {{IEEE} Micro}, volume = {33}, number = {3}, pages = {78--85}, year = {2013}, url = {https://doi.org/10.1109/MM.2013.24}, doi = {10.1109/MM.2013.24}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/micro/RogersOA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taco/BakhodaKA13, author = {Ali Bakhoda and John Kim and Tor M. Aamodt}, title = {Designing on-chip networks for throughput accelerators}, journal = {{ACM} Trans. Archit. Code Optim.}, volume = {10}, number = {3}, pages = {21:1--21:35}, year = {2013}, url = {https://doi.org/10.1145/2512429}, doi = {10.1145/2512429}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taco/BakhodaKA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asplos/JooybarFODA13, author = {Hadi Jooybar and Wilson W. L. Fung and Mike O'Connor and Joseph Devietti and Tor M. Aamodt}, editor = {Vivek Sarkar and Rastislav Bod{\'{\i}}k}, title = {GPUDet: a deterministic {GPU} architecture}, booktitle = {Architectural Support for Programming Languages and Operating Systems, {ASPLOS} 2013, Houston, TX, USA, March 16-20, 2013}, pages = {1--12}, publisher = {{ACM}}, year = {2013}, url = {https://doi.org/10.1145/2451116.2451118}, doi = {10.1145/2451116.2451118}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asplos/JooybarFODA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/date/ZakharenkoAM13, author = {Vitaly Zakharenko and Tor M. Aamodt and Andreas Moshovos}, editor = {Enrico Macii}, title = {Characterizing the performance benefits of fused {CPU/GPU} systems using FusionSim}, booktitle = {Design, Automation and Test in Europe, {DATE} 13, Grenoble, France, March 18-22, 2013}, pages = {685--688}, publisher = {{EDA} Consortium San Jose, CA, {USA} / {ACM} {DL}}, year = {2013}, url = {https://doi.org/10.7873/DATE.2013.148}, doi = {10.7873/DATE.2013.148}, timestamp = {Wed, 16 Oct 2019 14:14:53 +0200}, biburl = {https://dblp.org/rec/conf/date/ZakharenkoAM13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/SinghSFOA13, author = {Inderpreet Singh and Arrvindh Shriraman and Wilson W. L. Fung and Mike O'Connor and Tor M. Aamodt}, title = {Cache coherence for {GPU} architectures}, booktitle = {19th {IEEE} International Symposium on High Performance Computer Architecture, {HPCA} 2013, Shenzhen, China, February 23-27, 2013}, pages = {578--590}, publisher = {{IEEE} Computer Society}, year = {2013}, url = {https://doi.org/10.1109/HPCA.2013.6522351}, doi = {10.1109/HPCA.2013.6522351}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/SinghSFOA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isca/LengHEGKAR13, author = {Jingwen Leng and Tayler H. Hetherington and Ahmed ElTantawy and Syed Zohaib Gilani and Nam Sung Kim and Tor M. Aamodt and Vijay Janapa Reddi}, editor = {Avi Mendelson}, title = {GPUWattch: enabling energy optimizations in GPGPUs}, booktitle = {The 40th Annual International Symposium on Computer Architecture, ISCA'13, Tel-Aviv, Israel, June 23-27, 2013}, pages = {487--498}, publisher = {{ACM}}, year = {2013}, url = {https://doi.org/10.1145/2485922.2485964}, doi = {10.1145/2485922.2485964}, timestamp = {Fri, 09 Jul 2021 15:51:20 +0200}, biburl = {https://dblp.org/rec/conf/isca/LengHEGKAR13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/RogersOA13, author = {Timothy G. Rogers and Mike O'Connor and Tor M. Aamodt}, editor = {Matthew K. Farrens and Christos Kozyrakis}, title = {Divergence-aware warp scheduling}, booktitle = {The 46th Annual {IEEE/ACM} International Symposium on Microarchitecture, MICRO-46, Davis, CA, USA, December 7-11, 2013}, pages = {99--110}, publisher = {{ACM}}, year = {2013}, url = {https://doi.org/10.1145/2540708.2540718}, doi = {10.1145/2540708.2540718}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/RogersOA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/FungA13, author = {Wilson W. L. Fung and Tor M. Aamodt}, editor = {Matthew K. Farrens and Christos Kozyrakis}, title = {Energy efficient {GPU} transactional memory via space-time optimizations}, booktitle = {The 46th Annual {IEEE/ACM} International Symposium on Microarchitecture, MICRO-46, Davis, CA, USA, December 7-11, 2013}, pages = {408--420}, publisher = {{ACM}}, year = {2013}, url = {https://doi.org/10.1145/2540708.2540743}, doi = {10.1145/2540708.2540743}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/FungA13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/micro/FungSBA12, author = {Wilson Wai Lun Fung and Inderpreet Singh and Andrew Brownsword and Tor M. Aamodt}, title = {Kilo {TM:} Hardware Transactional Memory for {GPU} Architectures}, journal = {{IEEE} Micro}, volume = {32}, number = {3}, pages = {7--16}, year = {2012}, url = {https://doi.org/10.1109/MM.2012.16}, doi = {10.1109/MM.2012.16}, timestamp = {Sat, 20 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/micro/FungSBA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tc/ChenA12, author = {Xi E. Chen and Tor M. Aamodt}, title = {Modeling Cache Contention and Throughput of Multiprogrammed Manycore Processors}, journal = {{IEEE} Trans. Computers}, volume = {61}, number = {7}, pages = {913--927}, year = {2012}, url = {https://doi.org/10.1109/TC.2011.141}, doi = {10.1109/TC.2011.141}, timestamp = {Sat, 20 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tc/ChenA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tvlsi/GortPKAHWY12, author = {Marcel Gort and Flavio M. de Paula and Johnny J. W. Kuan and Tor M. Aamodt and Alan J. Hu and Steven J. E. Wilton and Jin Yang}, title = {Formal-Analysis-Based Trace Computation for Post-Silicon Debug}, journal = {{IEEE} Trans. Very Large Scale Integr. Syst.}, volume = {20}, number = {11}, pages = {1997--2010}, year = {2012}, url = {https://doi.org/10.1109/TVLSI.2011.2166416}, doi = {10.1109/TVLSI.2011.2166416}, timestamp = {Mon, 17 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tvlsi/GortPKAHWY12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fpt/KwaA12, author = {Jimmy Kwa and Tor M. Aamodt}, title = {Small virtual channel routers on FPGAs through block {RAM} sharing}, booktitle = {2012 International Conference on Field-Programmable Technology, {FPT} 2012, Seoul, Korea (South), December 10-12, 2012}, pages = {71--79}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/FPT.2012.6412115}, doi = {10.1109/FPT.2012.6412115}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/fpt/KwaA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/HetheringtonRHOA12, author = {Tayler H. Hetherington and Timothy G. Rogers and Lisa Hsu and Mike O'Connor and Tor M. Aamodt}, editor = {Rajeev Balasubramonian and Vijayalakshmi Srinivasan}, title = {Characterizing and evaluating a key-value store application on heterogeneous {CPU-GPU} systems}, booktitle = {2012 {IEEE} International Symposium on Performance Analysis of Systems {\&} Software, New Brunswick, NJ, USA, April 1-3, 2012}, pages = {88--98}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/ISPASS.2012.6189209}, doi = {10.1109/ISPASS.2012.6189209}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ispass/HetheringtonRHOA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/RogersOA12, author = {Timothy G. Rogers and Mike O'Connor and Tor M. Aamodt}, title = {Cache-Conscious Wavefront Scheduling}, booktitle = {45th Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2012, Vancouver, BC, Canada, December 1-5, 2012}, pages = {72--83}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/MICRO.2012.16}, doi = {10.1109/MICRO.2012.16}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/RogersOA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mtv/KuanA12, author = {Johnny J. W. Kuan and Tor M. Aamodt}, title = {Progressive-BackSpace: Efficient Predecessor Computation for Post-Silicon Debug}, booktitle = {13th International Workshop on Microprocessor Test and Verification, {MTV} 2012, Austin, TX, USA, December 10-13, 2012}, pages = {70--75}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/MTV.2012.23}, doi = {10.1109/MTV.2012.23}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mtv/KuanA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taco/ChenA11, author = {Xi E. Chen and Tor M. Aamodt}, title = {Hybrid analytical modeling of pending cache hits, data prefetching, and MSHRs}, journal = {{ACM} Trans. Archit. Code Optim.}, volume = {8}, number = {3}, pages = {10:1--10:28}, year = {2011}, url = {https://doi.org/10.1145/2019608.2019609}, doi = {10.1145/2019608.2019609}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taco/ChenA11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/FungA11, author = {Wilson W. L. Fung and Tor M. Aamodt}, title = {Thread block compaction for efficient {SIMT} control flow}, booktitle = {17th International Conference on High-Performance Computer Architecture {(HPCA-17} 2011), February 12-16 2011, San Antonio, Texas, {USA}}, pages = {25--36}, publisher = {{IEEE} Computer Society}, year = {2011}, url = {https://doi.org/10.1109/HPCA.2011.5749714}, doi = {10.1109/HPCA.2011.5749714}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/FungA11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/FungSBA11, author = {Wilson W. L. Fung and Inderpreet Singh and Andrew Brownsword and Tor M. Aamodt}, editor = {Carlo Galuzzi and Luigi Carro and Andreas Moshovos and Milos Prvulovic}, title = {Hardware transactional memory for {GPU} architectures}, booktitle = {44rd Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2011, Porto Alegre, Brazil, December 3-7, 2011}, pages = {296--307}, publisher = {{ACM}}, year = {2011}, url = {https://doi.org/10.1145/2155620.2155655}, doi = {10.1145/2155620.2155655}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/FungSBA11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEpact/BakhodaKA10, author = {Ali Bakhoda and John Kim and Tor M. Aamodt}, editor = {Valentina Salapura and Michael Gschwind and Jens Knoop}, title = {On-chip network design considerations for compute accelerators}, booktitle = {19th International Conference on Parallel Architectures and Compilation Techniques, {PACT} 2010, Vienna, Austria, September 11-15, 2010}, pages = {535--536}, publisher = {{ACM}}, year = {2010}, url = {https://doi.org/10.1145/1854273.1854339}, doi = {10.1145/1854273.1854339}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/IEEEpact/BakhodaKA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/ArielFTA10, author = {Aaron Ariel and Wilson W. L. Fung and Andrew E. Turner and Tor M. Aamodt}, title = {Visualizing complex dynamics in many-core accelerator architectures}, booktitle = {{IEEE} International Symposium on Performance Analysis of Systems and Software, {ISPASS} 2010, 28-30 March 2010, White Plains, NY, {USA}}, pages = {164--174}, publisher = {{IEEE} Computer Society}, year = {2010}, url = {https://doi.org/10.1109/ISPASS.2010.5452029}, doi = {10.1109/ISPASS.2010.5452029}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ispass/ArielFTA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isqed/KuanWA10, author = {Johnny J. W. Kuan and Steven J. E. Wilton and Tor M. Aamodt}, title = {Accelerating trace computation in post-silicon debug}, booktitle = {11th International Symposium on Quality of Electronic Design {(ISQED} 2010), 22-24 March 2010, San Jose, CA, {USA}}, pages = {244--249}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ISQED.2010.5450450}, doi = {10.1109/ISQED.2010.5450450}, timestamp = {Wed, 16 Oct 2019 14:14:55 +0200}, biburl = {https://dblp.org/rec/conf/isqed/KuanWA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/BakhodaKA10, author = {Ali Bakhoda and John Kim and Tor M. Aamodt}, title = {Throughput-Effective On-Chip Networks for Manycore Accelerators}, booktitle = {43rd Annual {IEEE/ACM} International Symposium on Microarchitecture, {MICRO} 2010, 4-8 December 2010, Atlanta, Georgia, {USA}}, pages = {421--432}, publisher = {{IEEE} Computer Society}, year = {2010}, url = {https://doi.org/10.1109/MICRO.2010.50}, doi = {10.1109/MICRO.2010.50}, timestamp = {Tue, 31 May 2022 14:39:58 +0200}, biburl = {https://dblp.org/rec/conf/micro/BakhodaKA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taco/FungSYA09, author = {Wilson W. L. Fung and Ivan Sham and George L. Yuan and Tor M. Aamodt}, title = {Dynamic warp formation: Efficient {MIMD} control flow on {SIMD} graphics hardware}, journal = {{ACM} Trans. Archit. Code Optim.}, volume = {6}, number = {2}, pages = {7:1--7:37}, year = {2009}, url = {https://doi.org/10.1145/1543753.1543756}, doi = {10.1145/1543753.1543756}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taco/FungSYA09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/ChenA09, author = {Xi E. Chen and Tor M. Aamodt}, title = {A first-order fine-grained multithreaded throughput model}, booktitle = {15th International Conference on High-Performance Computer Architecture {(HPCA-15} 2009), 14-18 February 2009, Raleigh, North Carolina, {USA}}, pages = {329--340}, publisher = {{IEEE} Computer Society}, year = {2009}, url = {https://doi.org/10.1109/HPCA.2009.4798270}, doi = {10.1109/HPCA.2009.4798270}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/hpca/ChenA09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ispass/BakhodaYFWA09, author = {Ali Bakhoda and George L. Yuan and Wilson W. L. Fung and Henry Wong and Tor M. Aamodt}, title = {Analyzing {CUDA} workloads using a detailed {GPU} simulator}, booktitle = {{IEEE} International Symposium on Performance Analysis of Systems and Software, {ISPASS} 2009, April 26-28, 2009, Boston, Massachusetts, USA, Proceedings}, pages = {163--174}, publisher = {{IEEE} Computer Society}, year = {2009}, url = {https://doi.org/10.1109/ISPASS.2009.4919648}, doi = {10.1109/ISPASS.2009.4919648}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ispass/BakhodaYFWA09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/YuanBA09, author = {George L. Yuan and Ali Bakhoda and Tor M. Aamodt}, editor = {David H. Albonesi and Margaret Martonosi and David I. August and Jos{\'{e}} F. Mart{\'{\i}}nez}, title = {Complexity effective memory access scheduling for many-core accelerator architectures}, booktitle = {42st Annual {IEEE/ACM} International Symposium on Microarchitecture {(MICRO-42} 2009), December 12-16, 2009, New York, New York, {USA}}, pages = {34--44}, publisher = {{ACM}}, year = {2009}, url = {https://doi.org/10.1145/1669112.1669119}, doi = {10.1145/1669112.1669119}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/YuanBA09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tecs/AamodtC08, author = {Tor M. Aamodt and Paul Chow}, title = {Compile-time and instruction-set methods for improving floating- to fixed-point conversion accuracy}, journal = {{ACM} Trans. Embed. Comput. Syst.}, volume = {7}, number = {3}, pages = {26:1--26:27}, year = {2008}, url = {https://doi.org/10.1145/1347375.1347379}, doi = {10.1145/1347375.1347379}, timestamp = {Tue, 08 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tecs/AamodtC08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEpact/WongBSACWCGJW08, author = {Henry Wong and Anne Bracy and Ethan Schuchman and Tor M. Aamodt and Jamison D. Collins and Perry H. Wang and Gautham N. Chinya and Ankur Khandelwal Groen and Hong Jiang and Hong Wang}, editor = {Andreas Moshovos and David Tarditi and Kunle Olukotun}, title = {Pangaea: a tightly-coupled {IA32} heterogeneous chip multiprocessor}, booktitle = {17th International Conference on Parallel Architectures and Compilation Techniques, {PACT} 2008, Toronto, Ontario, Canada, October 25-29, 2008}, pages = {52--61}, publisher = {{ACM}}, year = {2008}, url = {https://doi.org/10.1145/1454115.1454125}, doi = {10.1145/1454115.1454125}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/IEEEpact/WongBSACWCGJW08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/ChenA08, author = {Xi E. Chen and Tor M. Aamodt}, title = {Hybrid analytical modeling of pending cache hits, data prefetching, and MSHRs}, booktitle = {41st Annual {IEEE/ACM} International Symposium on Microarchitecture {(MICRO-41} 2008), November 8-12, 2008, Lake Como, Italy}, pages = {59--70}, publisher = {{IEEE} Computer Society}, year = {2008}, url = {https://doi.org/10.1109/MICRO.2008.4771779}, doi = {10.1109/MICRO.2008.4771779}, timestamp = {Tue, 31 May 2022 14:39:58 +0200}, biburl = {https://dblp.org/rec/conf/micro/ChenA08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ics/AamodtC07, author = {Tor M. Aamodt and Paul Chow}, editor = {Burton J. Smith}, title = {Optimization of data prefetch helper threads with path-expression based statistical modeling}, booktitle = {Proceedings of the 21th Annual International Conference on Supercomputing, {ICS} 2007, Seattle, Washington, USA, June 17-21, 2007}, pages = {210--221}, publisher = {{ACM}}, year = {2007}, url = {https://doi.org/10.1145/1274971.1275001}, doi = {10.1145/1274971.1275001}, timestamp = {Tue, 06 Nov 2018 11:07:02 +0100}, biburl = {https://dblp.org/rec/conf/ics/AamodtC07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/FungSYA07, author = {Wilson W. L. Fung and Ivan Sham and George L. Yuan and Tor M. Aamodt}, title = {Dynamic Warp Formation and Scheduling for Efficient {GPU} Control Flow}, booktitle = {40th Annual {IEEE/ACM} International Symposium on Microarchitecture {(MICRO-40} 2007), 1-5 December 2007, Chicago, Illinois, {USA}}, pages = {407--420}, publisher = {{IEEE} Computer Society}, year = {2007}, url = {https://doi.org/10.1109/MICRO.2007.30}, doi = {10.1109/MICRO.2007.30}, timestamp = {Tue, 31 May 2022 14:39:58 +0200}, biburl = {https://dblp.org/rec/conf/micro/FungSYA07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/AamodtCHWS04, author = {Tor M. Aamodt and Paul Chow and Per Hammarlund and Hong Wang and John Paul Shen}, title = {Hardware Support for Prescient Instruction Prefetch}, booktitle = {10th International Conference on High-Performance Computer Architecture {(HPCA-10} 2004), 14-18 February 2004, Madrid, Spain}, pages = {84--95}, publisher = {{IEEE} Computer Society}, year = {2004}, url = {https://doi.org/10.1109/HPCA.2004.10028}, doi = {10.1109/HPCA.2004.10028}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/AamodtCHWS04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sigmetrics/AamodtMCGHWS03, author = {Tor M. Aamodt and Pedro Marcuello and Paul Chow and Antonio Gonz{\'{a}}lez and Per Hammarlund and Hong Wang and John Paul Shen}, editor = {Bill Cheng and Satish K. Tripathi and Jennifer Rexford and William H. Sanders}, title = {A framework for modeling and optimization of prescient instruction prefetch}, booktitle = {Proceedings of the International Conference on Measurements and Modeling of Computer Systems, {SIGMETRICS} 2003, June 9-14, 2003, San Diego, CA, {USA}}, pages = {13--24}, publisher = {{ACM}}, year = {2003}, url = {https://doi.org/10.1145/781027.781030}, doi = {10.1145/781027.781030}, timestamp = {Thu, 23 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/sigmetrics/AamodtMCGHWS03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cases/AamodtC00, author = {Tor M. Aamodt and Paul Chow}, title = {Embedded {ISA} support for enhanced floating-point to fixed-point {ANSI-C} compilation}, booktitle = {Proceedings of the 2000 International Conference on Compilers, Architectures and Synthesis for Embedded Systems, {CASES} 2000, San Jose, California, USA, November 7-18, 2000}, pages = {128--137}, publisher = {{ACM}}, year = {2000}, url = {https://doi.org/10.1145/354880.354899}, doi = {10.1145/354880.354899}, timestamp = {Tue, 06 Nov 2018 11:07:42 +0100}, biburl = {https://dblp.org/rec/conf/cases/AamodtC00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.