2016 IEEE High Performance Extreme Computing Conference(HPEC ‘16)Twentieth Annual HPEC Conference13 - 15 September 2016Westin Hotel, Waltham, MA USA
Plenary Session 9:00-10:00 in Eden Vale BChair: Jeremy Kepner / MIT Lincoln LaboratoryKeynote Speaker:HPEC: The Past, Present and Future OutlookMr. David Martinez (HPEC Founder; IEEE Fellow; MIT Lincoln Laboratory Associate Head Cyber Security & Information Sciences Division)Break10:00 - 10:20Eden Vale FoyerAdvanced ASIC & FPGA Technologies10:20-12:00 in Eden Vale A1/A2Chair: Paul Monticciolo / MIT[Best Paper Finalist] On-chip Memory Efficient Data Layout for 2D FFT on 3D Memory Integrated FPGAShreyas Singapura, Viktor Prasanna, Rajgopal Kannan (University of Southern California)[Best Student Paper Finalist] Real-Time, Low-Latency Image Processing with High Throughput on a Multi-Core SoCBarath Ramesh, Alan D. George, Herman Lam (University of Florida)A Hardware Prototype for In-Brain Neural Spike-SortingMartin Herbordt, Yinan Liu, Jiayi Sheng (Boston University)Optimizing Simulation Speed of FPGA Model Based SynthesisJeff Caldwell, Bo Marr, David Bloom, Dan Thompson (Raytheon)Invited TalkStrong Scaling in FPGA-Centric Clouds and ClustersProf. Martin Herbordt (Boston University)Graphs & Sparse Data10:20-12:00 in Eden Vale C1/C2 Chair: Michael Wolf / SandiaInvited TalkFinding the Important Part of a Matrix or GraphProf. Gilbert Strang (MIT Mathematics Department)A Sparse Multi-Dimensional Fast Fourier Transform with Stability to Noise in the Context of Image Processing and Change DetectionPierre-David Letourneau, M. Harper Langston, Richard Lethin (Reservoir Labs)Efficient implementation of scatter-gather operations for large scale graph analyticsManoj Kumar, Mauricio Serrano, Jose Moreira, Pratap Pattnaik, W P Horn, Joefon Jann, Gabriel Tanase (IBM)Landmark Routing for Large Graphs in Fixed-Memory EnvironmentsNewton Campbell Jr. (BBN), Michael J. Laszlo, Sumitra Mukherjee (Nova Southeastern University)Mathematical Foundations of the GraphBLASJeremy Kepner (MIT), Peter Aaltonen (Indiana University), David Bader (Georgia Institute of Technology), Aydın Buluc ̧ (Lawrence Berkeley National Laboratory), Franz Franchetti (Carnegie Mellon University), John Gilbert (University of California, Santa Barbara), Dylan Hutchison (University of Washington), Manoj Kumar (IBM), Andrew Lumsdaine (Indiana University), Henning Meyerhenke (Karlsruhe Institute of Technology), Scott McMillan (CMU Software Engineering Institute), Jose Moreira (IBM), John D. Owens (University of California, Davis), Carl Yang (University of California, Davis), Marcin Zalewski (Indiana University), Timothy Mattson (Intel)High Performance & Cloud Computing 1 10:20-12:00 in Eden Vale C3Chair: Patrick Dreher / NC StateThe Open Community Runtime: A Runtime System for Extreme Scale ComputingTimothy G. Mattson, Romain Cledat, Vincent Cave (Intel), Vivek Sarkar (Rice University), Zoran Budimlic, Sanjay Chatterjee (Rice University), Josh Fryman, Ivan Ganev, Robin Knauerhase, Min Lee (Intel), Benoıt Meister (Reservoir Labs), Brian Nickerson, Nick Pepperling, Bala Seshasayee (Intel), Sagnak Tasirlar (Two Sigma), Justin Teller (Facebook), Nick Vrvilo (Rice University)High-Performance Algorithms and Data Structures to Catch Elephant FlowsJordi Ros-Giralt, Alan Commike, Richard Lethin (Reservoir Labs), Sourav Maji, Malathi Veeraraghavan (University of Virginia)Scheduler Technologies in Support of High Performance Data AnalysisAlbert Reuther, Chansup Byun, William Arcand, David Bestor, Bill Bergeron, Matthew Hubbell, Michael Jones, Peter Michaleas, Andrew Prout, Antonio Rosa, Jeremy Kepner (MIT)Optimizing Communication for a 2D-Partitioned Scalable BFSJeffrey Young (Georgia Institute of Technology), Julian Romera, Matthias Hauck, Holger Froning (Ruprecht-Karls University of Heidelberg)Node Level Power Measurements on a Petaflop SystemDavid Brayford, Christoph Bernau, Carla Guillen, Carmen Navarrete (Leibniz Supercomputing Centre)Lunch; View Posters and Demos 1 12:00-1:00 in EmersonPosters3D DRAM Based Application Specific Hardware Accelerator for SpMVFazle Sadi, Larry Pileggi, Franz Franchetti (Carnegie Mellon University)Rapid Prototyping with Symbolic Computation: Fast Development of Quantum Annealing SolutionsMark Hodson, Duncan Fletcher, Dan Padilha, Tristan Cook (QxBranch)CUDA Implementation of an Optimal Online Gaussian-Signal-in-Gaussian-Noise DetectorNir Nossenson (Northeastern University), Ariel J. Jaffe (Weizmann Institute)Designing a New High Performance Computing Education Strategy for Professional Scientists and EngineersJulia S. Mullen, William Arcand, David Bestor, Bill Bergeron, Chansup Byun, Vijay Gadepally, Michael Houle, Matthew Hubbell, Michael Jones, Anna Klein, Peter Michaeleas, Lauren Milechin, Andrew Prout, Antonio Rosa, Siddharth Samsi, Charles Yee, Jeremy Kepner, Albert Reuther (MIT)GPU Processing of Streaming Data: a CUDA Implementation of the FireHose BenchmarkMauro Bisson (Nvidia), Massimo Bernaschi (Italian Research Council), Massimiliano Fatica (Nvidia)Leveraging Trilinos’s Next Generation Computing Framework for an Exa-Scale Poro-Elastic Network Simulator ImplementationAshesh Chattopadhyay, Vinod Kumar, VMK Kotteda (University of Texas El Paso), William Spotz (Sandia National Laboratory)Performance Characterization and Parallelization of Tesseract Optical Character Recognition on Multicore ArchitecturesSunghwan Bae, Jialing Zhang, Seung Woo Son (University of Massachusetts Lowell)Using Natural Language Processing Models for Understanding Network AnomaliesKetul Barot, Jialing Zhang, Seung Woo Son (University of Massachusetts Lowell)Hardware Accelerators for High Performance ComputingVirginia W. Ross, Kevin L. Schoen (Air Force Research Laboratory)Architecting Processing System Applications Past Moore’s LawJeremy W. Horner, John Holland, Eliot Glaser, Gary Petrosky (Northrop Grumman)CUDA Library for T2OURNAMINTYajaira Gonzalez Gonzalez, Jeffrey C. McHarg ( MIT Lincoln Laboratory)Advanced ASIC & FPGA Technologies 21:00-2:40 in Eden Vale A1/A2Chair: Karen Gettings / MIT[Best Student Paper Finalist] Novo-G#: Large-Scale Reconfigurable Computing with Direct and Programmable InterconnectsAlan D. George (University of Florida), Martin C. Herbordt (Boston University), Herman Lam, Abhijeet G. Lawande (University of Florida), Jiayi Sheng, Chen Yang (Boston University)In-Storage Embedded Accelerator for Sparse Pattern ProcessingSang-Woo Jun, Huy T. Nguyen, Vijay Gadepally, Arvind (MIT)Computational and Memory Analysis of Tegra SoCsAndrew Milluzzi, Alan George, Herman Lam (University of Florida)PERFECT Case Studies Demonstrating Order of Magnitude Reduction in Power ConsumptionWittenberg (Brandeis University), Edin Kadric, Andre DeHon (University of Pennsylvania), Jonathan Edwards (BAE Systems), Jeffrey Smith (Sierra Nevada Corporation), Silviu Chiricescu (BAE Systems)Invited Talk:Graph Analytics on FPGAsProf. Viktor Prasanna (University of Southern California)Graphs & Sparse Data 21:00-2:40 in Eden Vale C1/C2Chair: Scott McMillan / CMU SEIKokkos/Qthreads Task-Parallel Approach to Linear Algebra Based Graph AnalyticsMichael M. Wolf, H. Carter Edwards, Stephen Olivier (Sandia National Laboratory)Generating massive complex networks with hyperbolic geometry faster in practiceMoritz von Looz (Karlsruhe Institute of Technology), Mustafa Safa Ozdayi (Istanbul Technical University), Soren Laue (Friedrich Schiller University), Henning Meyerhenke (Karlsruhe Institute of Technology)Invited Talk: The Future of Scalable Analytics and Machine LearningDr. Jennifer Roberts (DARPA I20 - Program Manager)Accelerated Low-rank Updates to Tensor DecompositionsMuthu Baskaran, M. Harper Langston, Tahina Ramananandro, David Bruns-Smith, Tom Henretty, James Ezick, Richard Lethin (Reservoir Labs)cuSTINGER : Supporting Dynamic Graph Algorithms for GPUSOded Green, David A. Bader (Georgia Institute of Technology)High Performance & Cloud Computing1:00-2:40 in Eden Vale C3Chair: Franz Franchetti / CMUInvited Talk: The Massachusetts Open Cloud: Vision and Early ExperiencesProf. Orran Krieger (Boston University)Hypervisor Performance Analysis for Real-Time WorkloadsGeoffrey Phi C. Tran, Yu-An Chen, Dong-In Kang, John Paul Walters, Stephen P. Crago (University of Southern California)On SDN-Based Extreme-Scale NetworksHaitham Ghalwash, Chun-Hsi Huang (University of Connecticut)Cross-Institutional Research Cyberinfrastructure for Data Intensive ScienceW.Christopher Lenhardt, Mike Conway, Erik Scott, Brian Blanton, Ashok Krishnamorthy (Renaissance Computing Institute)Scalability of VM Provisioning SystemsMike Jones, Bill Arcand, Bill Bergeron, David Bestor, Chansup Byun, Lauren Milechin, Vijay Gadepally, Matt Hubbell, Jeremy Kepner, Pete Michaleas, Julie Mullen, Andy Prout, Tony Rosa, Siddharth Samsi, Charles Yee, Albert Reuther (MIT)Break2:40-3:00Eden Vale FoyerGraphs & Sparse Data 3 3:00-4:40 in Eden Vale C1/C2Chair: John Gilbert / UCSBInvited Talk: Linear-Algebraic Methods in Algorithmic Graph TheoryProf. Aleksander Madry (MIT CSAIL)Novel Graph Processor Architecture, Prototype System, and ResultsWilliam S. Song, Vitaliy Gleyzer, Alexei Lomakin, Jeremy Kepner (MIT)Advantages to Modeling Relational Data using Hypergraphs versus GraphsMichael M. Wolf, Alicia M. Klinvex, Daniel M. Dunlavy (Sandia National Laboratory)KNN in the Jaccard SpaceMing Ouyang (University of Massachusetts Boston)A Scale-Free Structure for Power-Law GraphRichard M. Veras, Tze Meng Low, Franz Franchetti (Carnegie Mellon University)High Performance & Cloud Computing 33:00-4:40 in Eden Vale C3Chair: Vijay Gadepally / MITEnhancing the Performance and Robustness of the FEAST EigensolverBrendan Gavin, Eric Polizzi (University of Massachusetts Amherst)LLMapReduce: Multi-Level Map-Reduce for High Performance Data AnalysisChansup Byun, Jeremy Kepner, William Arcand, David Bestor, Bill Bergeron, Vijay Gadepally, Matthew Hubbell, Peter Michaleas, Julie Mullen, Andrew Prout, Antonio Rosa, Charles Yee, Albert Reuther (MIT)A Framework to Integrate MFiX with Trilinos for High Fidelity Fluidized Bed ComputationsV M Krushnarao Kotteda, Ashesh Chattopadhyay, Vinod Kumar (University of Texas El Paso), William Spotz (Sandia National Laboratory)Havens: Explicit Reliable Memory Regions for HPC ApplicationsSaurabh Hukerikar, Christian Engelmann (Oak Ridge National Laboratory)Invited Talk: High Throughput Connectomics: The Building of a Brain-ScopeProf. Nir Shavit (MIT Computer Science & AI Laboratory)Best Student Paper Award Presentation 4:40 in Eden Vale BChair: Brian Sroka / MITREBest Paper Award Presentation4:50 in Eden Vale BChair: Jeremy Kepner / MIT Lincoln LaboratoryReception; View Posters and Demos; Attend BoFs5:00 - 8:00 in Emerson & Foyer & Eden Vale BoFs6:00 - 7:00EEHPC BoF6:00-7:00 in Eden Vale A1Chair: Kurt Keville / MITGraphBLAS BoF6:00-7:00 in Eden Vale C1Co-Chairs: John Gilbert / USCB; Scott McMillan / CMUDemos: