@book {, title = {Parallel Processing and Applied Mathematics: 13th International Conference, PPAM 2019, Bialystok, Poland, September 8{\textendash}11, 2019, Revised Selected Papers, Part II}, series = {Lecture Notes in Computer Science}, number = {12044}, year = {2020}, month = {2020-03}, pages = {503}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, isbn = {978-3-030-43222-5}, doi = {https://doi.org/10.1007/978-3-030-43222-5}, author = {Roman Wyrzykowski and Ewa Deelman and Jack Dongarra and Konrad Karczewski} } @book {, title = {Parallel Processing and Applied Mathematics: 13th International Conference, PPAM 2019, Bialystok, Poland, September 8{\textendash}11, 2019, Revised Selected Papers, Part I}, series = { Lecture Notes in Computer Science}, number = {12043}, year = {2020}, month = {2020-03}, pages = {581}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, edition = {1}, isbn = {978-3-030-43229-4}, doi = {https://doi.org/10.1007/978-3-030-43229-4}, author = {Roman Wyrzykowski and Ewa Deelman and Jack Dongarra and Konrad Karczewski} } @techreport {1398, title = {A Collection of Presentations from the BDEC2 Workshop in Kobe, Japan}, journal = {Innovative Computing Laboratory Technical Report}, number = {ICL-UT-19-09}, year = {2019}, month = {2019-02}, publisher = {University of Tennessee, Knoxville}, author = {Rosa M. Badia and Micah Beck and Fran{\c c}ois Bodin and Taisuke Boku and Franck Cappello and Alok Choudhary and Carlos Costa and Ewa Deelman and Nicola Ferrier and Katsuki Fujisawa and Kohei Fujita and Maria Girone and Geoffrey Fox and Shantenu Jha and Yoshinari Kameda and Christian Kniep and William Kramer and James Lin and Kengo Nakajima and Yiwei Qiu and Kishore Ramachandran and Glenn Ricart and Kim Serradell and Dan Stanzione and Lin Gan and Martin Swany and Christine Sweeney and Alex Szalay and Christine Kirkpatrick and Kenton McHenry and Alainna White and Steve Tuecke and Ian Foster and Joe Mambretti and William. M Tang and Michela Taufer and Miguel V{\'a}zquez} } @article {1211, title = {Big Data and Extreme-Scale Computing: Pathways to Convergence - Toward a Shaping Strategy for a Future Software and Data Ecosystem for Scientific Inquiry}, journal = {The International Journal of High Performance Computing Applications}, volume = {32}, year = {2018}, month = {2018-07}, pages = {435{\textendash}479}, abstract = {Over the past four years, the Big Data and Exascale Computing (BDEC) project organized a series of five international workshops that aimed to explore the ways in which the new forms of data-centric discovery introduced by the ongoing revolution in high-end data analysis (HDA) might be integrated with the established, simulation-centric paradigm of the high-performance computing (HPC) community. Based on those meetings, we argue that the rapid proliferation of digital data generators, the unprecedented growth in the volume and diversity of the data they generate, and the intense evolution of the methods for analyzing and using that data are radically reshaping the landscape of scientific computing. The most critical problems involve the logistics of wide-area, multistage workflows that will move back and forth across the computing continuum, between the multitude of distributed sensors, instruments and other devices at the networks edge, and the centralized resources of commercial clouds and HPC centers. We suggest that the prospects for the future integration of technological infrastructures and research ecosystems need to be considered at three different levels. First, we discuss the convergence of research applications and workflows that establish a research paradigm that combines both HPC and HDA, where ongoing progress is already motivating efforts at the other two levels. Second, we offer an account of some of the problems involved with creating a converged infrastructure for peripheral environments, that is, a shared infrastructure that can be deployed throughout the network in a scalable manner to meet the highly diverse requirements for processing, communication, and buffering/storage of massive data workflows of many different scientific domains. Third, we focus on some opportunities for software ecosystem convergence in big, logically centralized facilities that execute large-scale simulations and models and/or perform large-scale data analytics. We close by offering some conclusions and recommendations for future investment and policy review.}, doi = {https://doi.org/10.1177/1094342018778123}, author = {Mark Asch and Terry Moore and Rosa M. Badia and Micah Beck and Pete Beckman and Thierry Bidot and Fran{\c c}ois Bodin and Franck Cappello and Alok Choudhary and Bronis R. de Supinski and Ewa Deelman and Jack Dongarra and Anshu Dubey and Geoffrey Fox and Haohuan Fu and Sergi Girona and Michael Heroux and Yutaka Ishikawa and Kate Keahey and David Keyes and William T. Kramer and Jean-Fran{\c c}ois Lavignon and Yutong Lu and Satoshi Matsuoka and Bernd Mohr and St{\'e}phane Requena and Joel Saltz and Thomas Schulthess and Rick Stevens and Martin Swany and Alexander Szalay and William Tang and Ga{\"e}l Varoquaux and Jean-Pierre Vilotte and Robert W. Wisniewski and Zhiwei Xu and Igor Zacharov} } @techreport {1397, title = {A Collection of White Papers from the BDEC2 Workshop in Bloomington, IN}, journal = {Innovative Computing Laboratory Technical Report}, number = {ICL-UT-18-15}, year = {2018}, month = {2018-11}, publisher = {University of Tennessee, Knoxville}, author = {James Ahrens and Christopher M. Biwer and Alexandru Costan and Gabriel Antoniu and Maria S. P{\'e}rez and Nenad Stojanovic and Rosa Badia and Oliver Beckstein and Geoffrey Fox and Shantenu Jha and Micah Beck and Terry Moore and Sunita Chandrasekaran and Carlos Costa and Thierry Deutsch and Luigi Genovese and Tarek El-Ghazawi and Ian Foster and Dennis Gannon and Toshihiro Hanawa and Tevfik Kosar and William Kramer and Madhav V. Marathe and Christopher L. Barrett and Takemasa Miyoshi and Alex Pothen and Ariful Azad and Judy Qiu and Bo Peng and Ravi Teja and Sahil Tyagi and Chathura Widanage and Jon Koskey and Maryam Rahnemoonfar and Umakishore Ramachandran and Miles Deegan and William Tang and Osamu Tatebe and Michela Taufer and Michel Cuende and Ewa Deelman and Trilce Estrada and Rafael Ferreira Da Silva and Harrel Weinstein and Rodrigo Vargas and Miwako Tsuji and Kevin G. Yager and Wanling Gao and Jianfeng Zhan and Lei Wang and Chunjie Luo and Daoyi Zheng and Xu Wen and Rui Ren and Chen Zheng and Xiwen He and Hainan Ye and Haoning Tang and Zheng Cao and Shujie Zhang and Jiahui Dai} } @inbook {883, title = {Dense Symmetric Indefinite Factorization on GPU Accelerated Architectures}, booktitle = {Lecture Notes in Computer Science}, series = {11th International Conference, PPAM 2015, Krakow, Poland, September 6-9, 2015. Revised Selected Papers, Part I}, volume = {9573}, year = {2016}, month = {2015-09}, pages = {86-95}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, chapter = {Parallel Processing and Applied Mathematics}, abstract = {We study the performance of dense symmetric indefinite factorizations (Bunch-Kaufman and Aasen{\textquoteright}s algorithms) on multicore CPUs with a Graphics Processing Unit (GPU). Though such algorithms are needed in many scientific and engineering simulations, obtaining high performance of the factorization on the GPU is difficult because the pivoting that is required to ensure the numerical stability of the factorization leads to frequent synchronizations and irregular data accesses. As a result, until recently, there has not been any implementation of these algorithms on hybrid CPU/GPU architectures. To improve their performance on the hybrid architecture, we explore different techniques to reduce the expensive communication and synchronization between the CPU and GPU, or on the GPU. We also study the performance of an LDL^T factorization with no pivoting combined with the preprocessing technique based on Random Butterfly Transformations. Though such transformations only have probabilistic results on the numerical stability, they avoid the pivoting and obtain a great performance on the GPU. }, keywords = {Communication-avoiding, Dense symmetric indefinite factorization, gpu computation, randomization}, isbn = {978-3-319-32149-3}, doi = {10.1007/978-3-319-32149-3_9}, author = {Marc Baboulin and Jack Dongarra and Adrien Remy and Stanimire Tomov and Ichitaro Yamazaki}, editor = {Roman Wyrzykowski and Ewa Deelman and Konrad Karczewski and Jacek Kitowski and Kazimierz Wiatr} }