default search action
BibTeX records: Rajib Nath
@inproceedings{DBLP:conf/hotchips/DitzelEABBBHIIJ21, author = {David R. Ditzel and Roger Espasa and Nivard Aymerich and Allen Baum and Tom Berg and Jim Burr and Eric Hao and Jayesh Iyer and Miquel Izquierdo and Shankar Jayaratnam and Darren Jones and Chris Klingner and Jin Kim and Stephen Lee and Marc Lupon and Grigorios Magklis and Bojan Maric and Rajib Nath and Mike Neilly and J. Duane Northcutt and Bill Orner and Jose Renau and Gerard Reves and Xavier Reves and Tom Riordan and Pedro Sanchez and Sridhar Samudrala and Guillem Sole and Raymond Tang and Tommy Thorn and Francisco Torres and Sebastia Tortella and Daniel Yau}, title = {Accelerating {ML} Recommendation with over a Thousand RISC-V/Tensor Processors on Esperanto's ET-SoC-1 Chip}, booktitle = {{IEEE} Hot Chips 33 Symposium, {HCS} 2021, Palo Alto, CA, USA, August 22-24, 2021}, pages = {1--23}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/HCS52781.2021.9566904}, doi = {10.1109/HCS52781.2021.9566904}, timestamp = {Mon, 25 Oct 2021 18:04:14 +0200}, biburl = {https://dblp.org/rec/conf/hotchips/DitzelEABBBHIIJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/micro/NathT15, author = {Rajib Nath and Dean M. Tullsen}, editor = {Milos Prvulovic}, title = {The {CRISP} performance model for dynamic voltage and frequency scaling in a {GPGPU}}, booktitle = {Proceedings of the 48th International Symposium on Microarchitecture, {MICRO} 2015, Waikiki, HI, USA, December 5-9, 2015}, pages = {281--293}, publisher = {{ACM}}, year = {2015}, url = {https://doi.org/10.1145/2830772.2830826}, doi = {10.1145/2830772.2830826}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/micro/NathT15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/todaes/AyoubNR13, author = {Raid Ayoub and Rajib Nath and Tajana Simunic Rosing}, title = {CoMETC: Coordinated management of energy/thermal/cooling in servers}, journal = {{ACM} Trans. Design Autom. Electr. Syst.}, volume = {19}, number = {1}, pages = {1:1--1:28}, year = {2013}, url = {https://doi.org/10.1145/2534381}, doi = {10.1145/2534381}, timestamp = {Tue, 06 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/todaes/AyoubNR13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dac/NathAR13, author = {Rajib Nath and Raid Zuhair Ayoub and Tajana Simunic Rosing}, title = {Temperature aware thread block scheduling in GPGPUs}, booktitle = {The 50th Annual Design Automation Conference 2013, {DAC} '13, Austin, TX, USA, May 29 - June 07, 2013}, pages = {177:1--177:6}, publisher = {{ACM}}, year = {2013}, url = {https://doi.org/10.1145/2463209.2488952}, doi = {10.1145/2463209.2488952}, timestamp = {Tue, 06 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dac/NathAR13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscc/NathCR13, author = {Rajib Nath and Douglas M. Carmean and Tajana Simunic Rosing}, title = {Power modeling and thermal management techniques for manycores}, booktitle = {2013 {IEEE} Symposium on Computers and Communications, {ISCC} 2013, Split, Croatia, 7-10 July, 2013}, pages = {740--746}, publisher = {{IEEE} Computer Society}, year = {2013}, url = {https://doi.org/10.1109/ISCC.2013.6755037}, doi = {10.1109/ISCC.2013.6755037}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscc/NathCR13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hpca/AyoubNR12, author = {Raid Zuhair Ayoub and Rajib Nath and Tajana Rosing}, title = {{JETC:} Joint energy thermal and cooling management for memory and {CPU} subsystems in servers}, booktitle = {18th {IEEE} International Symposium on High Performance Computer Architecture, {HPCA} 2012, New Orleans, LA, USA, 25-29 February, 2012}, pages = {299--310}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/HPCA.2012.6169035}, doi = {10.1109/HPCA.2012.6169035}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hpca/AyoubNR12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/europar/AgulloDNT11, author = {Emmanuel Agullo and Jack J. Dongarra and Rajib Nath and Stanimire Tomov}, editor = {Emmanuel Jeannot and Raymond Namyst and Jean Roman}, title = {A Fully Empirical Autotuned Dense {QR} Factorization for Multicore Architectures}, 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 = {194--205}, publisher = {Springer}, year = {2011}, url = {https://doi.org/10.1007/978-3-642-23397-5\_19}, doi = {10.1007/978-3-642-23397-5\_19}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/europar/AgulloDNT11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sc/NathTDD11, author = {Rajib Nath and Stanimire Tomov and Tingxing Dong and Jack J. Dongarra}, editor = {Scott A. Lathrop and Jim Costa and William Kramer}, title = {Optimizing symmetric dense matrix-vector multiplication on GPUs}, booktitle = {Conference on High Performance Computing Networking, Storage and Analysis, {SC} 2011, Seattle, WA, USA, November 12-18, 2011}, pages = {6:1--6:10}, publisher = {{ACM}}, year = {2011}, url = {https://doi.org/10.1145/2063384.2063392}, doi = {10.1145/2063384.2063392}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sc/NathTDD11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1102-5328, author = {Emmanuel Agullo and Jack J. Dongarra and Rajib Nath and Stanimire Tomov}, title = {Fully Empirical Autotuned {QR} Factorization For Multicore Architectures}, journal = {CoRR}, volume = {abs/1102.5328}, year = {2011}, url = {http://arxiv.org/abs/1102.5328}, eprinttype = {arXiv}, eprint = {1102.5328}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1102-5328.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhpca/NathTD10, author = {Rajib Nath and Stanimire Tomov and Jack J. Dongarra}, title = {An Improved Magma Gemm For Fermi Graphics Processing Units}, journal = {Int. J. High Perform. Comput. Appl.}, volume = {24}, number = {4}, pages = {511--515}, year = {2010}, url = {https://doi.org/10.1177/1094342010385729}, doi = {10.1177/1094342010385729}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijhpca/NathTD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pc/TomovND10, author = {Stanimire Tomov and Rajib Nath and Jack J. Dongarra}, title = {Accelerating the reduction to upper Hessenberg, tridiagonal, and bidiagonal forms through hybrid GPU-based computing}, journal = {Parallel Comput.}, volume = {36}, number = {12}, pages = {645--654}, year = {2010}, url = {https://doi.org/10.1016/j.parco.2010.06.001}, doi = {10.1016/J.PARCO.2010.06.001}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pc/TomovND10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ipps/TomovNLD10, author = {Stanimire Tomov and Rajib Nath and Hatem Ltaief and Jack J. Dongarra}, title = {Dense linear algebra solvers for multicore with {GPU} accelerators}, booktitle = {24th {IEEE} International Symposium on Parallel and Distributed Processing, {IPDPS} 2010, Atlanta, Georgia, USA, 19-23 April 2010 - Workshop Proceedings}, pages = {1--8}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/IPDPSW.2010.5470941}, doi = {10.1109/IPDPSW.2010.5470941}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ipps/TomovNLD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/para/KurzakNDD10, author = {Jakub Kurzak and Rajib Nath and Peng Du and Jack J. Dongarra}, editor = {Kristj{\'{a}}n J{\'{o}}nasson}, title = {An Implementation of the Tile {QR} Factorization for a {GPU} and Multiple CPUs}, booktitle = {Applied Parallel and Scientific Computing - 10th International Conference, {PARA} 2010, Reykjav{\'{\i}}k, Iceland, June 6-9, 2010, Revised Selected Papers, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {7134}, pages = {248--257}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-28145-7\_25}, doi = {10.1007/978-3-642-28145-7\_25}, timestamp = {Tue, 14 May 2019 10:00:40 +0200}, biburl = {https://dblp.org/rec/conf/para/KurzakNDD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/vecpar/NathTD10, author = {Rajib Nath and Stanimire Tomov and Jack J. Dongarra}, editor = {Jos{\'{e}} M. Laginha M. Palma and Michel J. Dayd{\'{e}} and Osni Marques and Jo{\~{a}}o Correia Lopes}, title = {Accelerating {GPU} Kernels for Dense Linear Algebra}, booktitle = {High Performance Computing for Computational Science - {VECPAR} 2010 - 9th International conference, Berkeley, CA, USA, June 22-25, 2010, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {6449}, pages = {83--92}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-19328-6\_10}, doi = {10.1007/978-3-642-19328-6\_10}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/vecpar/NathTD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/vecpar/LtaiefTNDD10, author = {Hatem Ltaief and Stanimire Tomov and Rajib Nath and Peng Du and Jack J. Dongarra}, editor = {Jos{\'{e}} M. Laginha M. Palma and Michel J. Dayd{\'{e}} and Osni Marques and Jo{\~{a}}o Correia Lopes}, title = {A Scalable High Performant Cholesky Factorization for Multicore with {GPU} Accelerators}, booktitle = {High Performance Computing for Computational Science - {VECPAR} 2010 - 9th International conference, Berkeley, CA, USA, June 22-25, 2010, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {6449}, pages = {93--101}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-19328-6\_11}, doi = {10.1007/978-3-642-19328-6\_11}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/vecpar/LtaiefTNDD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:books/tf/10/NathTD10, author = {Rajib Nath and Stanimire Tomov and Jack J. Dongarra}, editor = {Jakub Kurzak and David A. Bader and Jack J. Dongarra}, title = {{BLAS} for GPUs}, booktitle = {Scientific Computing with Multicore and Accelerators}, series = {Chapman and Hall / {CRC} computational science series}, pages = {57--80}, publisher = {{CRC} Press / Taylor {\&} Francis}, year = {2010}, url = {https://doi.org/10.1201/b10376-6}, doi = {10.1201/B10376-6}, timestamp = {Sat, 19 Oct 2019 19:02:58 +0200}, biburl = {https://dblp.org/rec/books/tf/10/NathTD10.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.