@misc{ title = {Apache Mahout Scalable machine learning and data mining }, volume = {2012}, number = {August 22}, url = {http://mahout.apache.org/}, type = {Web Page} } @misc{ title = {HPC-ABDS Kaleidoscope of 120 Apache Big Data Stack and HPC Tecnologies}, volume = {2014}, number = {April 8}, url = {http://hpc-abds.org/kaleidoscope/}, type = {Web Page} } @misc{ title = {Machine Learning Library (MLlib)}, volume = {2014}, number = {April 1}, url = {http://spark.apache.org/docs/0.9.0/mllib-guide.html}, type = {Web Page} } @misc{ title = {R open source statistical library}, volume = {2012}, number = {December 8}, url = {http://www.r-project.org/}, type = {Web Page} } @misc{ title = {PARKBENCH (PARallel Kernels and BENCHmarks)}, volume = {2014}, number = {July 19}, url = {http://www.netlib.org/parkbench/}, year = {1996}, type = {Web Page} } @misc{ author = {A. Petitet and R. C. Whaley and J. Dongarra and A. Cleary}, title = {HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers}, volume = {2014}, number = {July 19,}, month = {September 10}, url = {http://www.netlib.org/benchmark/hpl/}, year = {2008}, type = {Web Page} } @inproceedings{ author = {Adam Coates and Brody Huval and Tao Wang and David Wu and Bryan Catanzaro and Andrew Ng}, title = {Deep learning with COTS HPC systems}, booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML-13)}, pages = {1337-1345}, type = {Conference Proceedings} } @misc{Preproposal5.7, author = {Asanovic, Krste and Bodik, Ras and Catanzaro, Bryan Christopher and Gebis, Joseph James and Husbands, Parry and Keutzer, Kurt and Patterson, David A. and Plishker, William Lester and Shalf, John and Williams, Samuel Webb and Yelick, Katherine A.}, title = {The Landscape of Parallel Computing Research: A View from Berkeley}, volume = {2009}, number = {December}, month = {December 18}, url = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-183.html}, year = {2006}, type = {Web Page} } @article{ author = {Berry, M. and Chen, D. and Koss, P. and Kuck, D. and Lo, S. and Pang, Y. and Pointer, L. and Roloff, R. and Sameh, A. and Clementi, E. and Chin, S. and Schneider, D. and Fox, G. and Messina, P. and Walker, D. and Hsiung, C. and Schwarzmeier, J. and Lue, K. and Orszag, S. and Seidl, F. and Johnson, O. and Goodrum, R. and Martin, J.}, title = {The Perfect Club Benchmarks: Effective Performance Evaluation of Supercomputers}, journal = {International Journal of High Performance Computing Applications}, volume = {3}, number = {3}, pages = {5-40}, abstract = {This report presents a methodology for measuring the performance of supercomputers. It includes 13 Fortran programs that total over 50,000 lines of source code. They represent applications in several areas of engi neering and scientific computing, and in many cases the codes are currently being used by computational re search and development groups. We also present the PERFECT Fortran standard, a set of guidelines that allow portability to several types of machines. Furthermore, we present some performance measures and a method ology for recording and sharing results among diverse users on different machines. The results presented in this paper should not be used to compare machines, except in a preliminary sense. Rather, they are presented to show how the methodology has been applied, and to encourage others to join us in this effort. The results should be regarded as the first step toward our objec tive, which is to develop a publicly accessible data base of performance information of this type.}, DOI = {10.1177/109434208900300302}, url = {http://hpc.sagepub.com/content/3/3/5.abstract}, year = {1989}, type = {Journal Article} } @misc{ author = {Bingjing Zhang and Yang Ruan and Tak-Lon Wu and Judy Qiu and Adam Hughes and Geoffrey Fox}, title = {Applying Twister to Scientific Applications}, month = {November 30-December 3}, url = {http://grids.ucs.indiana.edu/ptliupages/publications/PID1510523.pdf}, year = {2010}, type = {Conference Paper} } @misc{ author = {Cisco}, title = {Visual Networking Index: Forecast and Methodology, 2012–2017}, volume = {2013}, number = {August 14}, month = {May 29}, url = {http://www.cisco.com/en/US/solutions/collateral/ns341/ns525/ns537/ns705/ns827/white_paper_c11-481360_ns827_Networking_Solutions_White_Paper.html}, year = {2013}, type = {Web Page} } @misc{ author = {Cisco Internet Business Solutions Group (IBSG) (Dave Evans)}, title = {The Internet of Things: How the Next Evolution of the Internet Is Changing Everything}, volume = {2013}, number = {August 14}, month = {April}, url = {http://www.cisco.com/web/about/ac79/docs/innov/IoT_IBSG_0411FINAL.pdf}, year = {2011}, type = {Web Page} } @book{ author = {Committee on the Analysis of Massive Data and Committee on Applied and Theoretical Statistics and Board on Mathematical Sciences and Their Applications and Division on Engineering and Physical Sciences}, title = {Frontiers in Massive Data Analysis}, publisher = {The National Academies Press,}, url = {http://www.nap.edu/catalog.php?record_id=18374 }, year = {2013}, type = {Book} } @misc{ author = {Geoffrey Fox and Judy Qiu and Shantenu Jha}, title = {High Performance High Functionality Big Data Software Stack}, url = {http://www.exascale.org/bdec/sites/www.exascale.org.bdec/files/whitepapers/fox.pdf}, year = {2014}, type = {Conference Paper} } @misc{ author = {J.Ekanayake and H.Li and B.Zhang and T.Gunarathne and S.Bae and J.Qiu and G.Fox}, title = {Twister: A Runtime for iterative MapReduce}, publisher = {ACM}, url = {http://grids.ucs.indiana.edu/ptliupages/publications/hpdc-camera-ready-submission.pdf}, year = {2010}, type = {Conference Paper} } @misc{ author = {Jack Dongarra and Erich Strohmaier and Michael Resch}, title = {Top 500 Supercomputer Sites}, volume = {2014}, number = {July 19}, url = {http://www.top500.org/}, year = {2014}, type = {Web Page} } @misc{ author = {Jack Dongarra and Michael A. Heroux}, title = {Toward a New Metric for Ranking High Performance Computing Systems}, volume = {2014}, number = {July 19,}, pages = {SANDIA REPORT SAND2013-4744 (Defines HPCG)}, month = {June}, url = {http://www.sandia.gov/~maherou/docs/HPCG-Benchmark.pdf}, year = {2013}, type = {Web Page} } @techreport{ author = {Jaliya Ekanayake and Thilina Gunarathne and Judy Qiu and Geoffrey Fox and Scott Beason and Jong Youl Choi and Yang Ruan and Seung-Hee Bae and Hui Li}, title = {Applicability of DryadLINQ to Scientific Applications}, institution = {Community Grids Laboratory, Indiana University.}, month = {January 30}, url = {http://grids.ucs.indiana.edu/ptliupages/publications/DryadReport.pdf}, year = {2010}, type = {Report} } @inbook{ author = {Judy Qiu and Jaliya Ekanayake and Thilina Gunarathne and Jong Youl Choi and Seung-Hee Bae and Yang Ruan and Saliya Ekanayake and Stephen Wu and Scott Beason and Geoffrey Fox and Mina Rho and Haixu Tang}, title = {Data Intensive Computing for Bioinformatics}, booktitle = {Data Intensive Distributed Computing}, editor = {Tevik Kosar}, publisher = {IGI Publishers}, ISBN = {978-1-61520-971-2}, DOI = {10.4018/978-1-6152—971-2}, url = {http://grids.ucs.indiana.edu/ptliupages/publications/DataIntensiveComputing_BookChapter.pdf}, year = {2011}, type = {Book Section} } @misc{ author = {NASA Advanced Supercomputing Division}, title = {NAS Parallel Benchmarks}, volume = {2014}, number = {March 28}, url = {https://www.nas.nasa.gov/publications/npb.html}, year = {1991}, type = {Web Page} } @misc{ author = {NIST}, title = {Big Data Initiative Reports from V1}, volume = {2014}, number = {March 26}, pages = {Report at http://bigdatawg.nist.gov/V1_output_docs.php}, url = {http://bigdatawg.nist.gov/home.php}, year = {2013}, type = {Web Page} } @article{ author = {NIST}, title = {NIST Big Data Public Working Group (NBD-PWG) Use Cases and Requirements}, url = {http://bigdatawg.nist.gov/usecases.php}, year = {2013}, type = {Journal Article} } @misc{ author = {Om Malik}, title = {Internet of things will have 24 billion devices by 2020 from GSMA, the global mobile industry trade group}, volume = {2014}, number = {July 19}, url = {http://gigaom.com/2011/10/13/internet-of-things-will-have-24-billion-devices-by-2020/}, year = {2011}, type = {Web Page} } @inproceedings{ author = {P. Ram and D. Lee and W. March and A.G. Gray}, title = {Linear-time algorithms for pairwise statistical problems}, booktitle = {Advances in Neural Information Processing Systems. NIPS}, pages = {1527-1535}, url = {http://papers.nips.cc/paper/3796-linear-time-algorithms-for-pairwise-statistical-problems.pdf}, type = {Conference Proceedings} } @book{ author = {R. Barrett and M. Berry and T. F. Chan and J. Demmel and J. Donato and J. Dongarra and V. Eijkhout and R. Pozo and C. Romine and H. Van der Vorst}, title = {Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd Edition}, publisher = {SIAM}, address = {Philadelphia, PA}, url = {http://www.netlib.org/linalg/html_templates/Templates.html}, year = {1994}, type = {Book} } @misc{ author = {Rob F. Van der Wijngaart and Srinivas Sridharan and Victor W. Lee}, title = {Extending the BT NAS parallel benchmark to exascale computing}, publisher = {IEEE Computer Society Press}, pages = {1-9}, year = {2012}, type = {Conference Paper} } @article{ author = {S. Jha and M. Cole and D. Katz and O. Rana and M. Parashar and J. Weissman}, title = {Distributed Computing Practice for Large-Scale Science & Engineering Applications}, journal = {Concurrency and Computation: Practice and Experience}, volume = {25}, number = {11}, pages = {1559-1585}, DOI = {http://dx.doi.org/10.1002/cpe.2897}, year = {2013}, type = {Journal Article} } @misc{ author = {Shantenu Jha and Judy Qiu and Andre Luckow and Pradeep Mantha and Geoffrey C. Fox}, title = {A Tale of Two Data-Intensive Approaches: Applications, Architectures and Infrastructure}, month = {June 27- July 2}, url = {http://arxiv.org/abs/1403.1528}, year = {2014}, type = {Conference Paper} } @unpublished{ author = {Shantenu Jha and Neil Chue Hong and Simon Dobson and Daniel S. Katz and Andre Luckow and Omer Rana and Yogesh Simmhan}, title = {Introducing Distributed Dynamic Data-intensive (D3) Science: Understanding Applications and Infrastructure}, url = {https://dl.dropboxusercontent.com/u/52814242/3dpas-draft.v0.1.pdf}, year = {2014}, type = {Unpublished Work} } @book{ author = {Timothy G. Mattson and Beverly A. Sanders and Berna L. Massingill}, title = {Patterns for Parallel Programming}, publisher = {Addison-Wesley Professional}, ISBN = {0321940784}, year = {2013}, type = {Book} } @inproceedings{ author = {Wo Chang}, title = {ISO/IEC JTC 1 Study Group on Big Data }, booktitle = {1st Big Data Interoperability Framework Workshop: Building Robust Big Data Ecosystem}, publisher = {NIST}, volume = {2014}, url = {http://jtc1bigdatasg.nist.gov/flyer_BigDataEcosystem_Workshop_US.pdf}, type = {Conference Proceedings} } @misc{ author = {Yang Ruan and Geoffrey Fox}, title = {A Robust and Scalable Solution for Interpolative Multidimensional Scaling with Weighting}, month = {October 22-25}, DOI = {http://dx.doi.org/10.1109/eScience.2013.30}, year = {2013}, type = {Conference Paper} } @misc{ author = {Yang Ruan and Geoffrey L. House and Saliya Ekanayake and Ursel Schütte and James D. Bever and Haixu Tang and Geoffrey Fox}, title = {Integration of Clustering and Multidimensional Scaling to Determine Phylogenetic Trees as Spherical Phylograms Visualized in 3 Dimensions}, pages = {26-29}, month = {May 26-29}, url = {http://grids.ucs.indiana.edu/ptliupages/publications/PhylogeneticTreeDisplayWithClustering.pdf}, year = {2014}, type = {Conference Paper} }