@STRING{jan = "January"} @STRING{feb = "February"} @STRING{mar = "March"} @STRING{apr = "April"} @STRING{may = "May"} @STRING{jun = "June"} @STRING{jul = "July"} @STRING{aug = "August"} @STRING{sep = "September"} @STRING{oct = "October"} @STRING{nov = "November"} @STRING{dec = "December"} @Misc{lagraph-2021-10-13, author = {Jason Riedy and Shannon Kuntz}, title = {Lightning talks: Updates/news from the {GraphBLAS} implementers}, howpublished = {LAGraph meeting}, month = oct, year = 2021, dom = 13, url = {https://www.slideshare.net/jasonriedy/lagraph-20211013} } @Misc{hpec-graphblas-2021, OPTkey = {}, author = {Jason Riedy}, title = {Lightning talks: Updates/news from the {GraphBLAS} implementers}, howpublished = {HPEC GraphBLAS BoF}, month = sep, year = 2021, dom = 21, url = {https://www.slideshare.net/jasonriedy/lucata-at-the-hpec-graphblas-bof-250439305} } @Misc{sparse-days-2020, OPTkey = {}, author = {Jason Riedy}, title = {Graph Analysis and Novel Architectures}, howpublished = {CERFACS Sparse Days}, month = sep, year = 2020, dom = 24, url = {https://www2.slideshare.net/jasonriedy/graph-analysis-and-novel-architectures}, } @Misc{hpec-graphblas-bof, author = {Jason Riedy}, title = {{GraphBLAS} and {Emus}}, howpublished = {IEEE HPEC GraphBLAS BoF}, month = sep, year = 2020, dom = 22, url = {https://www2.slideshare.net/jasonriedy/graphblas-and-emus}, } @Misc{nsf-icerm-ejr, title = {Potential Directions for Moving IEEE-754 Forward}, author = {Jason Riedy}, howpublished = {NSF ICERM Workshop on Variable Precision in Mathematical and Scientific Computing}, dom = 7, month = may, year = 2020, url = {https://icerm.brown.edu/materials/Slides/htw-20-vp/Potential_Directions_for_Moving_IEEE-754_Forward_\%5D_Jason_Riedy,_Georgia_Institute_of_Technology.pdf}, } @Misc{siam-pp20-repro, title = {Reproducible Linear Algebra from Application to Architecture}, author = {Jason Riedy and James Demmel and Peter Ahrens}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 15, month = feb, year = 2020, OPTrole = {presentation}, address = {Seattle, WA}, url = {https://www.slideshare.net/jasonriedy/reproducible-linear-algebra-from-application-to-architecture-228263588}, } @Misc{arm19-panel, title = {Specializing Architectures for Data Analytics}, author = {David Donofrio and Jason Riedy}, howpublished = {ARM Research Summit BOF on High Performance Graph Analytics: Algorithms, Programming, Architectures}, dom = 18, month = sep, year = 2019, note = {Introduction to invited panel on "We can't build specialized architectures for graphs that can work efficiently with other workloads, so we just need to hand-optimize each and every algorithm for each and every architecture"}, address = {Austin, TX}, url = {https://hpc.pnl.gov/armbof/}, } @Misc{iciam19-repro, title = {Reproducible Linear Algebra from Application to Architecture}, author = {Jason Riedy and James Demmel and Peter Ahrens}, howpublished = {International Congress on Industrial and Applied Mathematics}, dom = 19, month = jul, year = 2019, OPTrole = {presentation}, address = {Valencia, Spain}, url = {https://www.slideshare.net/jasonriedy/reproducible-linear-algebra-from-application-to-architecture}, } @Misc{iciam19-graph, title = {A New Algorithm Model for Massive-Scale Streaming Graph Analysis}, author = {Chunxing Yin and Jason Riedy}, howpublished = {International Congress on Industrial and Applied Mathematics}, dom = 16, month = jul, year = 2019, OPTrole = {presentation}, address = {Valencia, Spain}, url = {https://www.slideshare.net/jasonriedy/a-new-algorithm-model-for-massivescale-streaming-graph-analysis-156808819}, } @Misc{cse19-novel-arch, title = {Novel Architectures for Applications in Data Science and Beyond}, author = {Jason Riedy and Jeffrey Young and Tom Conte}, howpublished = {SIAM Conference on Computational Science and Engineering}, dom = 1, month = mar, year = 2019, note = {Minisymposium organizer with Jeffrey Young and Tom Conte.}, OPTrole = {presentation}, address = {Spokane, WA}, url = {http://www.crnch.gatech.edu/content/siam-cse-2019-go-bananas}, } @Misc{cse19-blas, author = {Mark Gates and James W. Demmel and Greg Henry and Xiaoye S. Li and E. Jason Riedy and Peter Tang}, title = {A Proposal for Next-Generation {BLAS}}, howpublished = {SIAM Conference on Computational Science and Engineering}, dom = 26, month = feb, year = 2019, OPTrole = {presentation}, address = {Spokane, WA}, url = {http://icl.utk.edu/bblas/siam-cse19/}, } @Misc{emu-lps19, author = {E. Jason Riedy}, title = {Characterization of {Emu} with Microbenchmarks}, howpublished = {Emu Workshop at the Laboratory for Physical Sciences}, dom = 23, month = jan, year = 2019, OPTrole = {presentation}, address = {Catonsville, MD}, } @Misc{sc18-blas-bof, author = {E. Jason Riedy and Greg Henry and James Demmel and Mark Gates and Xiaoye S. Li and Ping Tak P. Tang}, title = {Updated Proposal for a Next-Generation {BLAS}}, howpublished = {Batched, Reproducible, and Reduced Precision BLAS Birds-of-a-Feather at the International Conference for High Performance Computing, Networking, Storage and Analysis}, month = nov, year = 2018, abstract = {The classic BLAS interface is concise and mostly predictable. The BLAS Technical Forum produced a 301-page document in 2001 that incorporated mixed precision and extended operations. And now we face different implementations for reproducibility, even more precisions, and the batched interfaces. The explosion of interfaces causes problems for platform optimization and interface generation. The "Next-Generation BLAS Proposal" provides a unified naming scheme and semantic requirements for extensions. Inspired by the BLIS project, we also consider a minimal set of microkernels to provide a smaller optimization surface.}, url = {http://icl.utk.edu/bblas/sc18/files/NG_BLAS_SC18.pdf}, projtag = {lapack, ieee754, xscala}, keywords = {linear algebra, blas}, ejr-proj = {floating-point, linear-algebra}, } @Misc{pp18-ejr, author = {Jason Riedy}, title = {Graph Analysis: New Algorithm Models, New Architectures }, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 8, month = mar, year = 2018, note = {Minisymposium organizer with Oded Green and David A. Bader.}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Tokyo, Japan}, projtag = {hpda, memory-centric, crnch-rg}, keywords = {hpda, graph analysis, streaming data, memory-centric, novel architectures}, ejr-proj = {high-performance-data-analysis, graph-analysis, novel-arch}, ejr-grant = {hpda, grateful}, } @Misc{sc17-blas-bof, author = {E. Jason Riedy and Greg Henry and James Demmel and Mark Gates and Xiaoye S. Li and Ping Tak P. Tang}, title = {A Proposal for a Next-Generation {BLAS}}, howpublished = {Batched, Reproducible, and Reduced Precision BLAS Birds-of-a-Feather at the International Conference for High Performance Computing, Networking, Storage and Analysis}, month = nov, year = 2017, url = {http://icl.utk.edu/bblas/sc17/files/bblas-sc17-riedy.pdf}, projtag = {lapack, ieee754, xscala}, keywords = {linear algebra, blas}, ejr-proj = {floating-point, linear-algebra}, ejr-grant = {xscala, grateful}, } @Misc{ieeecluster2017, author = {Eisha Nathan and Anita Zakrzewska and Chunxing Yin and Jason Riedy}, title = {A New Direction for Streaming Graph Analysis}, howpublished = {IEEE Cluster}, month = sep, dom = 6, year = 2017, address = {Honolulu, HI}, OPTtags = {graph analysis; parallel algorithms}, projtag = {hpda, memory-centric, grateful, crnch-rg}, abstract = {Applications in computer network security, social media analysis, and other areas rely on analyzing a changing environment. The data is rich in relationships and lends itself to graph analysis. Traditional static graph analysis cannot keep pace with network security applications analyzing nearly one million events per second and social networks like Facebook collecting 500 thousand comments per second. Streaming frameworks like STINGER support ingesting up three million of edge changes per second but there are few streaming analysis kernels that keep up with these rates. Here we introduce a new, non-stop model and use it to decouple the analysis from the data ingest.}, keywords = {hpda, graph analysis, streaming data, memory-centric, novel architectures}, ejr-proj = {high-performance-data-analysis, graph-analysis, novel-arch}, ejr-grant = {hpda, iarpa-emu, grateful}, } @Misc{acs-2017, author = {Jason Riedy}, title = {High-Performance Analysis of Streaming Graphs}, howpublished = {HPC Analytic Workshop}, month = jun, year = 2017, dom = 28, address = {Hanover, MD}, url = {https://www.slideshare.net/jasonriedy/highperformance-analysis-of-streaming-graphs-77348572}, projtag = {hpda, grateful, memory-centric, crnch-rg}, abstract = {Graph-structured data in social networks, finance, network security, and others not only are massive but also under continual change. These changes often are scattered across the graph. Stopping the world to run a single, static query is infeasible. Repeating complex global analyses on massive snapshots to capture only what has changed is inefficient. We discuss requirements for single-shot queries on changing graphs as well as recent high-performance algorithms that update rather than recompute results. These algorithms are incorporated into our software framework for streaming graph analysis, STINGER.}, keywords = {hpda, graph analysis, streaming data, memory-centric, novel architectures}, ejr-proj = {high-performance-data-analysis, graph-analysis, novel-arch}, ejr-grant = {hpda, iarpa-emu, grateful}, } @Misc{cse17-streaming-ms, author = {E. Jason Riedy}, title = {High-Performance Analysis of Streaming Graphs}, howpublished = {SIAM Conference on Computational Science and Engineering}, dom = 2, month = mar, year = 2017, note = {Minisymposium organizer with Henning Meyerhenke.}, url = {https://www.slideshare.net/jasonriedy/highperformance-analysis-of-streaming-graphs}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Atlanta, GA}, abstract = {Graph-structured data in social networks, finance, network security, and others not only are massive but also under continual change. These changes often are scattered across the graph. Stopping the world to run a single, static query is infeasible. Repeating complex global analyses on massive snapshots to capture only what has changed is inefficient. We discuss requirements for single-shot queries on changing graphs as well as recent high-performance algorithms that update rather than recompute results. These algorithms are incorporated into our software framework for streaming graph analysis, STING (Spatio-Temporal Interaction Networks and Graphs).}, projtag = {hpda, grateful, memory-centric, xscala, crnch-rg}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis, novel-arch}, ejr-grant = {hpda, iarpa-emu, grateful}, } @Misc{blas-ng-feb-2017, author = {James Demmel and Greg Henry and Xiaoye Li and Jason Riedy and Peter Tang}, title = {A Proposal for a Next-Generation {BLAS}}, howpublished = {Workshop on Batched, Reproducible, and Reduced Precision BLAS}, month = feb, year = 2017, dom = 24, address = {Atlanta, Georgia}, url = {http://www.netlib.org/utk/people/JackDongarra/WEB-PAGES/Batched-BLAS-2017/talk05-demmel.pdf}, projtag = {lapack, ieee754, xscala}, keywords = {linear algebra, blas}, ejr-proj = {floating-point, linear-algebra}, ejr-grant = {xscala, grateful}, } @Misc{pp16-streaming-ms, author = {E. Jason Riedy and David A. Bader}, ejr-withauthor ={David A. Bader}, title = {Scalable Network Analysis: Tools, Algorithms, Applications}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 15, month = apr, year = 2016, note = {Minisymposium organizer with Henning Meyerhenke and David A. Bader.}, url = {http://www.slideshare.net/jasonriedy/scalable-and-efficient-algorithms-for-analysis-of-massive-streaming-graphs-60975076}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Paris, France}, abstract = {Graph analysis provides tools for analyzing the irregular data sets common in health informatics, computational biology, climate science, sociology, security, finance, and many other fields. These graphs possess different structures than typical finite element meshes. Scaling graph analysis to the scales of data being gathered and created has spawned many directions of exciting new research. This minisymposium includes talks on massive graph generation for testing and evaluating parallel algorithms, novel streaming techniques, and parallel graph algorithms for new and existing problems. It also covers existing parallel frameworks and interdisciplinary applications, e.g. the analysis of climate networks.}, projtag = {hpda, grateful, xscala}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {cassmt, grateful}, } @Misc{dmml-2015, file = {material/dmml-2015-ejr.pdf}, author = {E. Jason Riedy}, title = {Graph Analysis Beyond Linear Algebra}, howpublished = {Development of Modern Methods for Linear Algebra}, month = oct, dom = 24, year = 2015, abstract = {High-performance graph analysis is unlocking knowledge in computer security, bioinformatics, social networks, and many other data integration areas. Graphs provide a convenient abstraction for many data problems beyond linear algebra. Some problems map directly to linear algebra. Others, like community detection, look eerily similar to sparse linear algebra techniques. And then there are algorithms that strongly resist attempts at making them look like linear algebra. This talk will cover recent results with an emphasis on streaming graph problems where the graph changes and results need updated with minimal latency. We’ll also touch on issues of sensitivity and reliability where graph analysis needs to learn from numerical analysis and linear algebra.}, note = {Invited presentation}, url = {http://www.slideshare.net/jasonriedy/graph-analysis-beyond-linear-algebra}, projtag = {xscala, grateful, hpda, lapack}, keywords = {lapack, blas, linear algebra, graph analysis, streaming data}, ejr-proj = {linear-algebra, graph-analysis, high-performance-data-analysis}, ejr-grant = {xscala, grateful, hpda} } @Misc{graphlab-2014, file = {material/graphlab14-poster.pdf}, author = {Jason Riedy}, title = {{STINGER}: Analyzing massive, streaming graphs}, howpublished = {3rd GraphLab Workshop}, month = jul, dom = 21, year = 2014, address = {San Francisco, CA}, role = {invited poster and demo}, OPTtags = {graph analysis; parallel algorithms}, projtag = {intel-sting, hpda, xscala, grateful}, keywords = {hpda, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt, grateful}, } @Misc{intel.graph.2014, file = {material/intel-2014-01-17.pdf}, author = {Jason Riedy and David A. Bader and David Ediger and Rob McColl and Timothy G. Mattson}, ejr-withauthor ={David A. Bader and David Ediger and Rob McColl and Timothy G. Mattson}, title = {{STING}: Spatio-Temporal Interaction Networks and Graphs for {Intel} Platforms}, howpublished = {Presentation at Intel Corporation, Santa Clara, CA}, dom = 17, month = jan, year = 2014, OPTrole = {presentation}, url = {http://www.slideshare.net/jasonriedy/intel-20140117}, projtag = {intel-sting}, keywords = {hpda, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt, grateful}, } @Misc{graphlab-2013, file = {material/graphlab13-poster.pdf}, author = {Jason Riedy}, title = {{STINGER}: Analyzing massive, streaming graphs}, howpublished = {2nd GraphLab Workshop}, month = jul, dom = 1, year = 2013, address = {San Francisco, CA}, role = {invited poster and demo}, OPTtags = {graph analysis; parallel algorithms}, projtag = {intel-sting, cassmt, xscala, grateful}, keywords = {hpda, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt, grateful}, } @Misc{siamcse13-largescalegraph, author = {David A. Bader and Henning Meyerhenke and Jason Riedy}, ejr-withauthor ={David A. Bader and Henning Meyerhenke}, title = {Applications and Challenges in Large-scale Graph Analysis}, howpublished = {SIAM Conference on Computational Science and Engineering}, month = feb, year = 2013, address = {Boston, MA}, OPTrole = {presentation}, OPTtags = {siam; parallel algorithms}, url = {http://www.graphanalysis.org/SIAM-CSE13/01_Bader.pdf}, abstract = {Emerging real-world graph problems include detecting community structure in large social networks, improving the resilience of the electric power grid, and detecting and preventing disease in human populations. We discuss the opportunities and challenges in massive data-intensive computing for applications in social network analysis, genomics, and security. The explosion of real-world graph data poses substantial challenges for software, hardware, algorithms, and application experts.}, projtag = {intel-sting, cassmt, grateful}, keywords = {hpda, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt, grateful}, } @Misc{siamcse13-streaminggraph, file = {material/cse2013-streaming.pdf}, author = {Robert C. McColl and David Ediger and David A. Bader and Jason Riedy}, ejr-withauthor ={Robert C. McColl and David Ediger and David A. Bader}, title = {Analyzing Graph Structure in Streaming Data with {STINGER}}, howpublished = {SIAM Conference on Computational Science and Engineering}, month = feb, year = 2013, address = {Boston, MA}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, abstract = {Analyzing static snapshots of massive, graph-structured data cannot keep pace with the growth of social networks, financial transactions, and other valuable data sources. Our software framework, STING (Spatio-Temporal Interaction Networks and Graphs), uses a scalable, high-performance graph data structure to enable these applications. STING supports fast insertions, deletions, and updates on graphs with semantic information and skewed degree distributions. STING achieves large speed-ups over parallel, static recomputation on both common multicore and specialized multithreaded platforms.}, projtag = {intel-sting, cassmt, grateful}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt, grateful}, } @Misc{intel.graph.2012, file = {material/intel-2012-07-12.pdf}, author = {Jason Riedy and David A. Bader and David Ediger and Rob McColl and Timothy G. Mattson}, ejr-withauthor ={David A. Bader and David Ediger and Rob McColl and Timothy G. Mattson}, title = {{STING}: Spatio-Temporal Interaction Networks and Graphs for {Intel} Platforms}, howpublished = {Presentation at Intel Corporation, Santa Clara, CA}, dom = 24, month = jul, year = 2012, OPTrole = {presentation}, url = {http://www.slideshare.net/jasonriedy/gt-stingintelslides}, projtag = {intel-sting}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting}, } @Misc{an12-streaming-ms, file = {material/siam-an-2012.pdf}, author = {David A. Bader and David Ediger and Jason Riedy}, ejr-withauthor ={David A. Bader and David Ediger}, title = {Streaming Graph Analytics for Massive Graphs}, howpublished = {SIAM Annual Meeting}, dom = 10, month = jul, year = 2012, url = {http://www.slideshare.net/jasonriedy/streaming-graph-analytics-for-massive-graphs}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Minneapolis, MN}, abstract = {Emerging real-world graph problems include detecting community structure in large social networks, improving the resilience of the electric power grid, and detecting and preventing disease in human populations. The volume and richness of data combined with its rate of change renders monitoring properties at scale by static recomputation infeasible. We approach these problems with massive, fine-grained parallelism across different shared memory architectures both to compute solutions and to explore the sensitivity of these solutions to natural bias and omissions within the data.}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{pp12-streaming-ms, file = {material/siam-pp-2012.pdf}, author = {E. Jason Riedy and Henning Meyerhenke}, ejr-withauthor ={Henning Meyerhenke}, title = {Scalable Algorithms for Analysis of Massive, Streaming Graphs}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 15, month = feb, year = 2012, note = {Minisymposium organizer with Henning Meyerhenke.}, url = {http://www.slideshare.net/jasonriedy/siam-pp-2012-scalable-algorithms-for-analysis-of-massive-streaming-graphs}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Savannah, GA}, abstract = {Graph-structured data in social networks, finance, network security, and others not only are massive but also under continual change. These changes often are scattered across the graph. Repeating complex global analyses on massive snapshots to capture only what has changed is inefficient. We discuss analysis algorithms for streaming graph data that maintain both local and global metrics. We extract parallelism from both analysis kernel and graph data to scale performance to real-world sizes.}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{pp12-community-ms, author = {Henning Meyerhenke and E. Jason Riedy and David A. Bader}, ejr-withauthor ={Henning Meyerhenke and David A. Bader}, title = {Parallel Community Detection in Streaming Graphs}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 15, month = feb, year = 2012, role = {minisymposium organizer}, OPTrole = {presentation}, OPTtags = {siam; streaming data; parallel algorithms}, address = {Savannah, GA}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{pp12-GraphCT, author = {David Ediger and E. Jason Riedy and Henning Meyerhenke and David A. Bader}, eir-withauthor ={David Ediger and Henning Meyerhenke and David A. Bader}, title = {Analyzing Massive Networks with GraphCT}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 16, month = feb, year = 2012, role = {poster}, OPTtags = {siam; parallel algorithms}, address = {Savannah, GA}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{pp12-STING, file = {material/siam-pp12-stinger-poster.pdf}, author = {E. Jason Riedy and David Ediger and Henning Meyerhenke and David A. Bader}, eir-withauthor ={David Ediger and Henning Meyerhenke and David A. Bader}, title = {{STING}: Software for Analysis of Spatio-Temporal Interaction Networks and Graphs}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 16, month = feb, year = 2012, role = {poster}, OPTtags = {siam; parallel algorithms}, address = {Savannah, GA}, abstract = {Current tools for analyzing graph-structured data and semantic networks focus on static graphs. Our STING package tackles analysis of streaming graphs like today's social networks and communication tools. STING maintains a massive graph under changes while coordinating analysis kernels to achieve analysis at real-world data rates. We show examples of local metrics like clustering coefficients and global metrics like connected components and agglomerative clustering. STING supports parallel Intel architectures as well as the Cray XMT.}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{GraphEx11, author = {Jason Riedy and David Ediger and David A. Bader and Henning Meyerhenke}, ejr-withauthor ={David Ediger and David A. Bader and Henning Meyerhenke}, title = {Tracking Structure of Streaming Social Networks}, dom = 9, month = aug, year = 2011, note = {Invited presentation.}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/GraphEx-2011.pdf}, file = {material/GraphEx-2011.pdf}, OPTtags = {graph; streaming}, howpublished = {2011 Graph Exploitation Symposium hosted by MIT Lincoln Labs}, projtag = {intel-sting, cassmt}, keywords = {hpda, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {cassmt, intel-sting}, } @Misc{intel.graph.2011, file = {material/intel-2011-08-09.pdf}, author = {Jason Riedy and David A. Bader and Henning Meyerhenke and David Ediger and Timothy Mattson}, ejr-withauthor ={David A. Bader and Henning Meyerhenke and David Ediger and Timothy Mattson}, title = {{STING}: Spatio-Temporal Interaction Networks and Graphs for {Intel} Platforms}, howpublished = {Presentation at Intel Corporation, Santa Clara, CA}, dom = 9, month = aug, year = 2011, OPTrole = {presentation}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/GT-STING-for-Intel-beamer.pdf}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @InProceedings{nsfaccelws10, file = {material/nsf-workshop-socnet.pdf}, author = {Jason Riedy and David Bader and David Ediger}, ejr-withauthor ={David Bader and David Ediger}, title = {Applications in Social Networks}, booktitle = {NSF Workshop on Accelerators for Data-Intensive Applications}, dom = 13, year = 2010, month = oct, OPTrole = {presentation}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/nsf-workshop-socnet.pdf}, OPTtags = {graph; NSF; streaming}, projtag = {intel-sting, cassmt}, keywords = {hpda, parallel algorithm, graph analysis, streaming data}, ejr-proj = {high-performance-data-analysis, graph-analysis}, ejr-grant = {intel-sting, cassmt}, } @Misc{gt09, file = {material/gt-2009-08-21.pdf}, author = {E. Jason Riedy}, title = {Dependable direct solutions for linear systems using a little extra precision}, howpublished = {CSE Seminar at Georgia Institute of Technology}, dom = 21, month = aug, year = 2009, url = {http://hdl.handle.net/1853/29795}, OPTtags = {linear algebra; floating point; lapack}, note = {Invited presentation}, abstract = {Solving a square linear system $Ax=b$ often is considered a black box. It's supposed to "just work," and failures often are blamed on the original data or subtleties of floating-point. Now that we have an abundance of cheap computations, however, we can do much better. A little extra precision in just the right places produces accurate solutions cheaply or demonstrates when problems are too hard to solve without significant cost. This talk will outline the method, iterative refinement with a new twist; the benefits, small backward and forward errors; and the trade-offs and unexpected benefits.}, projtag = {lapack, sparse-methods, ieee754}, keywords = {linear algebra, sparse matrix, foating point, lapack}, ejr-proj = {linear-algebra}, } @Misc{bascd2007-poster, author = {James W. Demmel and Yozo Hida and Xiaoye S. Li and E. Jason Riedy and Meghana Vishvanath and David Vu}, ejr-withauthor ={James W. Demmel and Yozo Hida and Xiaoye S. Li and Meghana Vishvanath and David Vu}, title = {Precise Solutions for Overdetermined Least Squares Problems}, howpublished = {Stanford 50 -- Eighth Bay Area Scientific Computing Day}, month = mar, year = 2007, role = {poster}, address = {Stanford, CA}, OPTrole = {poster}, OPTtags = {bascd; least squares}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/bascd2007-poster.pdf}, abstract = {Linear least squares (LLS) fitting is the most widely used data modeling technique and is included in almost every data analysis system (e.g. spreadsheets). These software systems often give no feedback on the conditioning of the LLS problem or the floating-point calculation errors present in the solution. With limited use of extra precision, we can eliminate these concerns for all but the most ill-conditioned LLS problems. Our algorithm provides either a solution and residual with relatively tiny error or a notice that the LLS problem is too ill-conditioned.}, projtag = {lapack, ieee754}, keywords = {least squares, lapack, blas, linear algebra, floating point}, ejr-proj = {linear-algebra, floating-point}, } @Misc{bascd2006-poster, author = {E. Jason Riedy}, title = {Making Static Pivoting Dependable}, howpublished = {Seventh Bay Area Scientific Computing Day}, month = mar, year = 2006, role = {poster}, address = {Livermore, CA}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/bascd2006-poster.pdf}, file = {material/bascd2006-poster.pdf}, OPTrole = {poster}, OPTtags = {bascd; sparse matrix; linear algebra}, abstract = {For sparse LU factorization, dynamic pivoting tightly couples symbolic and numerical computation. Dynamic structural changes limit parallel scalability. Demmel and Li use static pivoting in distributed SuperLU for performance, but intentionally perturbing the input may lead silently to erroneous results. Are there experimentally stable static pivoting heuristics that lead to a dependable direct solver? The answer is currently a qualified yes. Current heuristics fail on a few systems, but all failures are detectable.}, projtag = {lapack, sparse-methods}, keywords = {sparse matrix, linear algebra, floating point, graph analysis}, ejr-proj = {linear-algebra, floating-point, graph-analysis}, } @Misc{lapack-future, author = {E. Jason Riedy and Yozo Hida and James W. Demmel}, ejr-withauthor ={Yozo Hida and James W. Demmel}, title = {The Future of {LAPACK} and {ScaLAPACK}}, howpublished = {Robert C. Thompson Matrix Meeting}, dom = 18, month = nov, year = 2005, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/future-of-scalapack.pdf}, file = {material/future-of-scalapack.pdf}, OPTrole = {presentation}, OPTtags = {lapack; software engineering}, abstract = {We are planning new releases of the widely used LAPACK and ScaLAPACK numerical linear algebra libraries. Based on an on-going user survey (http://www.netlib.org/lapack-dev) and research by many people, we are proposing the following improvements: Faster algorithms (including better numerical methods, memory hierarchy optimizations, parallelism, and automatic performance tuning to accomodate new architectures), more accurate algorithms (including better numerical methods, and use of extra precision), expanded functionality (including updating and downdating, new eigenproblems, etc. and putting more of LAPACK into ScaLAPACK), and improved ease of use (friendlier interfaces in multiple languages). To accomplish these goals we are also relying on better software engineering techniques and contributions from collaborators at many institutions. This is joint work with Jack Dongarra.}, projtag = {lapack, ieee754}, keywords = {lapack, linear algebra, floating point}, ejr-proj = {linear-algebra, floating-point}, } @Misc{comb-sparse-cse05, author = {E. Jason Riedy}, title = {Parallel Combinatorial Computing and Sparse Matrices}, howpublished = {SIAM Conference on Computational Science and Engineering}, dom = 14, month = feb, year = 2005, OPTrole = {minisymposium speaker}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/cse05.pdf}, file = {material/cse05.pdf}, OPTrole = {presentation}, OPTtags = {combinatorial optimization; sparse matrix; parallel algorithms; siam}, abstract = {Increasingly, sparse matrix applications produce matrices too large for a single computer's memory. Distributed, parallel computers provide an avenue around memory limitations, but distributing combinatorial algorithms is historically difficult. We use insights from combinatorial optimization to design loosely coupled algorithms for sparse matrix matching, ordering, and symbolic factorization. These algorithms' performance depends on both problem instance and computer architecture. We investigate these aspects of performance and demonstrate issues that affect distributed combinatorial computing.}, projtag = {sparse-methods}, keywords = {sparse matrix, parallel algorithm, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, } @Misc{sparse-ds-csc04, author = {E. Jason Riedy}, title = {Sparse Data Structures for Weighted Bipartite Matching}, howpublished = {SIAM Workshop on Combinatorial Scientific Computing}, dom = 28, month = feb, year = 2004, OPTrole = {presentation}, OPTtags = {siam; combinatorial optimization; sparse matrix}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/csc04.pdf}, file = {material/csc04.pdf}, projtag = {sparse-methods}, keywords = {sparse matrix, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, } @Misc{par-bipart-pp04, author = {E. Jason Riedy}, title = {Parallel Weighted Bipartite Matching and Applications}, howpublished = {SIAM Parallel Processing for Scientific Computing}, dom = 27, month = feb, year = 2004, OPTrole = {minisymposium speaker}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/pp04.pdf}, file = {material/pp04.pdf}, OPTrole = {presentation}, OPTtags = {siam; combinatorial optimization; parallel algorithms; sparse matrix}, abstract = {Bipartite matching is one of graph theory's workhorses, occuring in the solution or approximation of many problems. Increasingly, applications' data spans multiple memory spaces, but there is little recent experience with distributed matching algorithms. We present a distributed, parallel implementation for weighted bipartite matching based on Bertsekas's auction algorithm. The bidding process finds local matchings while summarizing updates for occasional communication, leading to superlinear speed-ups on some sparse problems and modest performance on others.}, projtag = {sparse-methods}, keywords = {sparse matrix, parallel algorithm, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, } @Misc{siam-am03, author = {E. Jason Riedy}, title = {Practical Alternatives for Parallel Pivoting}, howpublished = {SIAM Annual Meeting}, month = jun, year = 2003, OPTrole = {presentation}, OPTtags = {siam; sparse matrix; linear algebra}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/siam-am03.pdf}, file = {material/siam-am03.pdf}, abstract = {Traditional pivoting during parallel, unsymmetric $LU$ factorization introduces heavy communication and restructuring costs. Possible alternatives include pre-pivoting to place heavy elements along the diagonal and limited pivoting that maintains the factors' structures. Each alternative comes with trade-offs that affect accuracy and performance.}, projtag = {sparse-methods}, keywords = {sparse matrix, linear algebra, parallel algorithm, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, } @Misc{siam-cse03, author = {E. Jason Riedy}, title = {Parallel Bipartite Matching for Sparse Matrix Computations}, howpublished = {SIAM Conference on Computational Science and Engineering}, month = feb, year = 2003, role = {poster}, OPTtags = {siam; parallel algorithms; combinatorial optimization; sparse matrix}, url = {http://purl.oclc.org/NET/jason-riedy/resume/material/siam-cse03-poster.pdf}, file = {material/siam-cse03-poster.pdf}, abstract = {Practical and efficient methods exist for parallelizing the numerical work in sparse matrix calculations. The initial symbolic analysis is now becoming a sequential bottleneck, limiting problems' sizes. One such analysis is the weighted bipartite matching used to achieve scalable, unsymmetric $LU$ factorization in Super\textsc{lu}. Applying a mathematical optimization algorithm produces a distributed-memory implementation with explicit trade-offs between speed and matching quality. We present accuracy and performance results for this phase alone and in the context of Super\textsc{lu}.}, projtag = {sparse-methods}, keywords = {sparse matrix, parallel algorithm, linear algebra, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, } @Misc{ieee754-exceptions, author = {David Bindel and E. Jason Riedy}, ejr-withauthor ={David Bindel}, title = {Exception Handling Interfaces, Implementations, and Evaluation}, howpublished = {IEEE-754r revision meeting}, month = aug, year = 2002, url = {http://grouper.ieee.org/groups/754/meeting-materials/2002-08-22-pres.pdf}, OPTrole = {presentation}, OPTtags = {ieee754; floating point}, file = {material/ieee754-2002-08-22-pres.pdf}, projtag = {ieee754}, keywords = {floating point, ieee754}, ejr-proj = {floating-point}, } @Misc{bascd2002-poster, author = {E. Jason Riedy}, title = {Parallel Bipartite Matching for Sparse Matrix Computation}, howpublished = {Third Bay Area Scientific Computing Day}, month = mar, year = 2002, address = {Livermore, CA}, role = {poster}, OPTtags = {bascd; sparse matrix; combinatorial optimization; parallel algorithms}, projtag = {sparse-methods}, keywords = {sparse matrix, parallel algorithm, graph analysis}, ejr-proj = {linear-algebra, graph-analysis}, }