1-1: General Purpose GPU Computing Session (11:00-12:15 EDT)
Co-Chairs: Mark Barnell & Dan Campbell
Minesweeper: A Novel and Fast Ordered-Statistic CFAR Algorithm [Outstanding Paper Award]
Carl Colena, Michael Russell, Stephen Braun (Lockheed Martin ATL)
Design, Optimization, and Benchmarking of Dense Linear Algebra Algorithms on AMD GPUs
Cade E Brown, Ahmad Abdelfattah, Stanimire Tomov, Jack Dongarra (UTK)
A Deep Q-Learning Approach for GPU Task Scheduling
Ryan S Luley (AFRL), Qinru Qiu (Syracuse)
GPU-Accelerated Discontinuous Galerkin Methods: 30x Speedup on 345 Billion Unknowns
Andrew C Kirby (MIT LLSC), Dimitri J. Mavriplis (Univ Wyoming )
Energy-Efficient Analysis of Synchrophasor Data using the NVIDIA Jetson Nano
Suzanne J Matthews, Aaron St. Leger (USMA)
1-2: High Performance Data Analysis Session (12:30-13:45 EDT)
Co-Chairs: SeungWoo Son & Hameed Badawy
Large--scale Sparse Tensor Decomposition Using a Damped Gauss--Newton Method
Teresa M Ranadive (LPS), Muthu M Baskaran (Reservoir Labs)
Multiscale Data Analysis Using Binning, Tensor Decompositions, and Backtracking
Dimitri Leggas, Thomas S Henretty, James Ezick, Muthu Baskaran, Brendan von Hofe, Grace Cimaszewski, M. Harper Langston, Richard Lethin (Reservoir Labs)
SparTen: Leveraging Kokkos for On-node Parallelism in a Second-Order Method for Fitting Canonical Polyadic Tensor Models to Poisson Data
Keita Teranishi, Daniel Dunlavy (Sandia), Jeremy M Myers (William & Mary, Sandia), Richard F Barrett (Sandia)
Scalable Data Generation for Evaluating Mixed-Precision Solvers
Piotr Luszczek, Yaohung M Tsai, Neil Lindquist (UTK), Hartwig Anzt (UTK and Karlsruhe), Jack Dongarra (UTK, ORNL, Univ Manchester)
Parameter Sensitivity Analysis of the SparTen High Performance Sparse Tensor Decomposition Software
Jeremy M Myers (William & Mary, Sandia), Daniel Dunlavy, Keita Teranishi, D.S. Hollman (Sandia)
1-3: Multicore Software Technologies Session (14:15-15:30 EDT)
Co-Chairs: Dan Campbell & Hameed Badawy
Work-Efficient Parallel Algorithms for Accurate Floating-Point Prefix Sums
Helen Xu, Sean Fraser, Charles E. Leiserson (MIT)
Machine Learning Algorithm Performance on the Lucata Computer
Paul Springer, Thomas Schibler (JPL), Gé,raud Krawezik (Lucata), Jack Lightholder (JPL), Peter Kogge (Notre Dame)
Automatic Mapping and Optimization to Kokkos with Polyhedral Compilation
Muthu M Baskaran (Reservoir Labs), Charles Jin (MIT), Benoit Meister, Jonathan Springer (Reservoir Labs)
Implementing Sparse Linear Algebra Kernels on the Lucata Pathfinder-A Computer
Geraud P Krawezik, Shannon Kuntz (Lucata), Peter Kogge (Notre Dame)
A Scalable Architecture for CNN Accelerators Leveraging High-Performance Memories
Maarten Hattink, Giuseppe Di Guglielmo, Luca Carloni, Keren Bergman (Columbia Univ)
1-4: Quantum & Novel Computing Session (15:45-17:00 EDT)
Co-Chairs: Patrick Dreher & Dan Campbell
Invited Talk: The Need for Hardware-Accelerated Combinatorial Optimization
Dr. Jeffrey Chou and Dr. Suraj Bramhavar (Sync Computing)
Invited Talk: Advances in Algorithms for Near-Term Quantum Computers
Dr. Yudong Cao (Zapata Computing)
Invited Talk: Post Quantum Cryptography
Manoj Kumar and Pratap Pattnaik (IBM)
Homomorphic Encryption for Quantum Annealing with Spin Reversal Transformations
Daniel O'Malley, John Golden (LANL)
Constrained-optimization Approach Delivers Superior Classical Performance for Graph Partitioning via Quantum-ready Method
Uchenna Chukwu, Raouf Dridi, Jesse Berwald, Michael Booth, John Dawson, DeYung Le, Mark Wainger, Steven P. Reinhardt (Quantum Computing Inc.)
1-S1: Quantum Tutorial Special (17:30-19:30 EDT)
Organizers: Patrick Dreher
1-S2: BRAIDS Special (17:30-19:30 EDT)
Organizers: Alexia Schultz & Pierre Trepagnier
Invited Talk: Introduction to the Autonomous Intelligent Cyber-defense Agents (AICA) International Working Group
Paul Theron (Thales)
Invited Talk: Cyber-defense Agents (AICA) International Working Group
Jeffrey Gottschalk (MIT LL)
Invited Talk: Actionable and Interpretable AI (AI2) and Resilience
Igor Linkov (Army ERDC)
Alexia Schulz, Pierre Trepagnier (MIT LL)
Multi-Temporal Analysis and Scaling Relations of 100,000,000,000 Network Packets
Jeremy Kepner (MIT LLSC), Chad Meiners (MIT LL), Chansup Byun (MIT LLSC), Sarah McGuire (MIT LL), Timothy A Davis (Texas A&M), William Arcand (MIT LLSC), Jonathan Bernays (MIT LL), David Bestor, William Bergeon, Vijay Gadepally (MIT LLSC), Raul Harnasch (MIT LL), Matthew Hubbell, Michael Houle, Michael Jones, Andrew Kirby, Anna Klein (MIT LLSC), Lauren Milechin (MIT), Julie Mullen, Andrew Prout, Albert Reuther, Antonio Rosa, Siddharth Samsi (MIT LLSC), Doug Stetson, Adam Tse (MIT LL), Chuck Yee, Peter Michaleas (MIT LLSC)
Nvidia/VastData Sponsor Spotlight Talk (10:30-11:00 EDT)
2-1: Graph Analytics & Network Science 1 Session (11:00-12:15 EDT)
Co-Chairs: Bruce Kinney & John Gilbert
A GraphBLAS solution to the SIGMOD 2014 Programming Contest using multi-source BFS
Má,rton Elekes, Attila Nagy, Dá,vid Sá,ndor (Budapest Univ of Tech and Econ), Já,nos Benjamin Antal (unaffiliated), Timothy A Davis (Texas A&M Univ), Gabor Szarnyas (Budapest Univ of Tech and Econ)
LessMine: Reducing Sample Space and Data Access for Dense Pattern Mining
Tianyu Fu, Ziqian Wan, Guohao Dai, Yu Wang, Huazhong Yang (Tsinghua Univ)
Fast Graphlet Transform of Sparse Graphs
Dimitris Floros, Nikos P Pitsianis (Aristotle Univ of Thessaloniki), Xiaobai Sun (Duke Univ)
Half-Precision Floating-Point Formats for PageRank: Opportunities and Challenges
Amir Sabbagh Molahosseini, Hans Vandierendonck (Queen's Univ Belfast)
GraphSDH: A General Graph Sampling Framework with Distribution and Hierarchy
Jingbo Hu, Guohao Dai, Yu Wang, Huazhong Yang (Tsinghua Univ)
Poster Session: 2-P (12:15-15:45 EDT)
Chair/Host: TBD
Scalable Parallel File Write from a Large NUMA System
Dong-In Kang, John Paul Walters, Stephen Crago (USC ISI)
Variable Precision Multiplication for Software-Based Neural Networks
Richa Singh, Tom Conroy (Virginia Tech), Patrick Schaumont (WPI)
Offline Machine Learning for Human Activity Recognition with Smartphone
Yanjia Zhang, Kandethody Ramachandran (Univ South Florida)
Execution of Complete Molecular Dynamics Simulations on Multiple FPGAs
Carlo J Pascoe, Larry Stewart, Woody Sherman, Vipin Sachdeva (Silicon Therapeutics), Martin Herbordt (Boston Univ)
Optimizing Use of Different Types of Memory for FPGAs in High Performance Computing
Kai Huang, Mehmet Gungor, Stratis Ioannidis, Miriam Leeser (Northeastern)
2-2: Graph Analytics & Network Science 2 Session (12:30-13:45 EDT)
Co-Chairs: Bruce Kinney & John Gilbert
Fast GPU Graph Contraction by Combining Efficient Shallow Searches and Post-Culling
Roozbeh Karimi, David M Koppelman (LSU), Chris Michael (NRL)
Using Graphlet Spectrograms for Temporal Pattern Analysis of Virus-Research Collaboration Networks
Dimitris Floros (Aristotle Univ of Thessaloniki), Tiancheng Liu (Duke Univ), Nikos P Pitsianis (Aristotle Univ of Thessaloniki, Duke), Xiaobai Sun (Duke Univ)
Computing PageRank Scores of Web Crawl Data Using DGX A100 Clusters
Seunghwa Kang, Alex Fender, Joe Eaton, Brad Rees (NVIDIA)
Triangle Counting with Cyclic Distributions
Andrew Lumsdaine (PNNL and Univ Washington), Luke D'Alessandro (Indiana Univ), Kevin Deweese (Univ Washington), Jesun S Firoz (PNNL), Scott McMillan (CMU SEI)
Towards an Objective Metric for thePerformance of Exact Triangle Count
Mark P Blanco (CMU), Scott McMillan (CMU SEI), Tze Meng Low (CMU)
2-3: Graph Analytics & Network Science 3 Session (14:15-15:30 EDT)
Co-Chairs: Viktor Prasanna & Steve Reinhardt
Leveraging Linear Algebra to Count and Enumerate Simple Subgraphs [Best Paper Award]
Vitaliy Gleyzer, Andrew Soszynski, Edward K Kao (MIT LL)
GBTLX: A First Look [Outstanding Student Paper Award]
Sanil Rao, Anurag Kutuluru, Paul Brower (CMU), Scott McMillan (CMU SEI), Franz Franchetti (CMU)
GraphBLAS Programmability: Python and MATLAB Interfaces
Timothy Mattson (Intel), Michel Pelletier (Graphegon), Timothy A Davis (Texas A&M)
On the Feasibility of Using Reduced-Precision Tensor Core Operations for Graph Analytics
Jesun S Firoz, Ang Li, Jiajia Li, Kevin Barker (PNNL)
Efficient Sparse Matrix-Vector Multiplication on Intel UMA Architecture
Sriram Aananthakrishnan, Robert Pawlowski, Joshua Fryman, Ibrahim Hur (Intel)
2-4: Big Data & Distributed Computing 1 Session (15:45-17:00 EDT)
Co-Chairs: SeungWoo Son & Mark Barnell
A Framework for Task Mapping onto Heterogeneous Platforms
Ta-Yang Wang, Ajitesh Srivastava, Viktor K Prasanna (USC)
Best of Both Worlds: High Performance Interactive and Batch Launching
Chansup Byun, Jeremy Kepner, William Arcand, David Bestor, Bill Bergeron, Vijay Gadepally, Michael Houle, Matthew Hubbell, Michael Jones, Andrew Kirby, Anna Klein, Peter Michaleas (MIT LLSC), Lauren Milechin (MIT), Julie Mullen, Andrew Prout, Antonio Rosa, Siddharth Samsi, Charles Yee, Albert Reuther (MIT LLSC)
Approximate Inverse Chain Preconditioner: IterationCount Case Study for Spectral Support Solvers
M. Harper Langston (Reservoir Labs), Meifeng Lin (Brookhaven), Eric Papenhausen (Akai Kaeru), Pierre-David Letourneau, Julia Wei, Larry Weintraub, Mitchell Harris, Richard Lethin (Reservoir Labs)
Accelerating Distributed Inference of Sparse Deep Neural Networks via Mitigating the Straggler Effect
Mohammad Hasanzadeh Mofrad, Rami Melhem (Pitt), Yousuf Ahmad, Mohammad Hammoud (CMU in Qatar)
Distributed Non-Negative Tensor Train Decomposition
Manish Bhattarai, Gopinath Chennupati, Erik Skau, Raviteja Vangara, Hirsto Djidjev, Boian Alexandroe (LANL)
2-S1: GraphBLAS BoF Special (17:30-19:30 EDT)
Organizers: Tim Mattson & Scott McMillan
2-S2: Remote Sensing for Disaster Relief Special (17:30-19:30 EDT)
Organizers: John Aldridge & Dan Dumanis & Andrew Weinert
Invited Talk: Disaster Scene Description and Indexing
Dr. Asad Butt (NIST)
Fast Mapping onto Census Blocks
Jeremy Kepner (MIT LLSC), Andreas Kipf (MIT), Darren Engwirda (Columbia Univ), Navin Vembar (Camber Systems), Michael S Jones (MIT LLSC), Lauren Milechin (MIT), Vijay Gadepally (MIT LLSC), Chris Hill (MIT), Tim Kraska (MIT), William Arcand, David Bestor, William Bergeron, Chansup Byun, Matthew Hubbell, Michael Houle, Andrew Kirby, Anna Klein, Julie Mullen, Andrew Prout, Albert Reuther, Antonio Rosa, Sid Samsi, Charles Yee, Peter Michaleas (MIT LLSC)
Train and Deploy an Image Classifier for Disaster Response
Jianyu Mao, Kiana Harris, Nae-Rong Chang, Caleb Pennell, Yiming Ren (Penn State)
Integrating Multiple Deep Learning Models to Classify Disaster Scene Videos
Yuan Li, Haili Wang, Shuo Sun, Bill P Buckles (Univ North Texas)
A Hierarchical Auto-Labeling Deep Neural Network for Disaster Scene Videos
Shuo Sun, Yuan Li, Haili Wang, Bill P Buckles (Univ North Texas)
3-1: Big Data & Distributed Computing 2 Session (11:00-12:15 EDT)
Co-Chairs: SeungWoo Son & Nikos Pitsianis
High-Throughput Image Alignment for Connectomics using Frugal Snap Judgments [Best Student Paper Award]
Tim Kaler (MIT), Brian Wheatman (JHU), Sarah Wooders (MIT)
DS-SHMEM: Staging-enabled PGAS Programming for Data-intensive Workflows
Daihou Wang (Rutgers)
Self-Scaling Clusters and Reproducible Containers to Enable Scientific Computing
Peter Z Vaillancourt (Cornell), John Eric Coulter (Indiana Univ), Richard Knepper, Brandon Barker (Cornell University)
A Feasibility Study for MPI over HDFS
Wu-chun Feng, Da Zhang, Jing Zhang, Kaixi Hou, Sarunya Pumma, and Hao Wang (Virginia Tech)
Invited Talk: Optimizing Data Access with Next-Generation Storage Engine, Persistent Memory and Smart NICs - Slide Deck
Kenneth Cain, Venkata Krishnan, Johann Lombardi (Intel)
Poster Session: 3-P (12:15-15:45 EDT)
Chair/Host: Brian Sroka
Human Balance Models Optimized Using a Large-Scale, Parallel Architecture with Applications to Mild Traumatic Brain Injury
Gregory Ciccarelli (MIT LL), Michael Nolan (U. Washington), Hrishikesh Rao (MIT LL), Tanya Talkar (Harvard), Anne O'Brien, Gloria Vergara-Diaz, Ross Zafonte (Spaulding RH), Thomas Quatieri, Ryan McKindles (MIT LL), Paolo Bonato (Spaulding RH), Adam Lammert (WPI)
Hardware Acceleration of Nonlocal Means-Based Speckle Noise Removal Applied to SAR Imagery
Hector A Li Sanchez (Univ Pittsburgh), Alan George (NSF SHREC)
Storage Area Networks in Embedded Processing
Jason Harnish, John Holland, Jeremy Horner, Timothy Linden, Steve Mattson (Norhtrop Grumman)
Evaluating SEU Resilience of CNNs with Fault Injection [Outstanding Student Paper Award]
Evan Kain (COSMIAC), Alan George (NSF CHREC), Tyler M Lovelly (AFRL)
Packing Narrow-Width Operands to Improve Energy Efficiency of General-Purpose GPU Computing [Outstanding Student Paper Award]
Xin Wang (VCU), Wei Zhang (Univ Louisville)
3-2: Data Intensive Computing Session (12:30-13:45 EDT)
Co-Chairs: Muthu Baskaran & Julie Mullen
Invited Talk: The Need for Integrated Analytic Platforms and Multithreaded Runtime Systems
Dr. John Feo (PNNL)
Exploiting GPU Direct Access to Non-Volatile Memory to Accelerate Big Data Processing [Outstanding Student Paper Award]
Mahsa Bayati, Miriam Leeser, Ningfang Mi (Northeastern Univ)
Profiling and Optimization of CT Reconstruction on Nvidia Quadro GV100
Shekhar Dwivedi, Andreas Heumann (Nvidia)
A Communication-Efficient Multi-Chip Design for Range-Limited Molecular Dynamics
Chunshu Wu, Tong Geng (Boston Univ), Vipin Sachdeva, Woody Sherman (Silicon Therapeutics), Martin Herbordt (Boston Univ)
Bit-Error Aware Quantization for DCT-based Lossy Compression
Jialing Zhang, Jiaxi Chen (UMass Lowell), Aekyeung Moon (ETRI), Xiaoyan Zhuo, Seung Woo Son (UMass Lowell)
3-3: Case Studies & Benchmarking Session (14:15-15:30 EDT)
Co-Chairs: Chansup Byun & Dan Campbell
Accelerating MRI Reconstruction on TPUs
Tianjian Lu (Google), Thibault Marin, Yue Zhuo (Harvard Med), Yi-Fan Chen (Google), Chao Ma (Massachusetts General)
Processing of Crowdsourced Observations of Aircraft in a High Performance Computing Environment
Andrew Weinert, Ngaire Underhill, Bilal Gill, Ashley Wicks (MIT LL)
Northeast Cyberteam Building an Environment for Sharing Best Practices and Solutions for Research Computing
John Goodhue (MGHPCC), Julie Ma (MGHPCC), Adrian Del Maestro (Univ Vermont), Sia Najafi (WPI), Bruce Segee (Univ Maine), Scott A Valcourt (UNH), Ralph Zottola (Univ Alabama)
Benchmarking Network Fabrics for Data Distributed Training of Deep Neural Networks
Siddharth Samsi, Andrew Prout, Michael S Jones, Andrew C Kirby, Bill Arcand, Bill Bergeron, Chansup Byun, Vijay Gadepally, Michael Houle, Matthew Hubbell, Anna Klein, Peter Michaleas, Lauren Milechin, Julie Mullen, Antonio Rosa, Charles Yee, Albert Reuther, Jeremy Kepner (MIT LLSC)
A congestion control mechanism for SDN-based fat-tree networks
Haitham A Ghalwash (UConn), Chun-Hsi Huang (Southern Illinois Univ)
3-4: Case Studies & Benchmarking Session (15:45-17:00 EDT)
Co-Chairs: Dan Campbell & Muthu Baskaran
Invited Talk: High Order Efficient Methods for Black Hole Simulations
Prof. Sigal Gottlieb (UMass Dartmouth Mathematics)
Performance Strategies for Parallel Bitonic Sort on a Migratory Thread Architecture [Outstanding Student Paper Award]
Kaushik Velusamy (UMBC), Thomas Rolinger (UMD, LPS), Janice McMahon (Lucata)
Hash Table Scalability on Intel UMA
Balasubramanian Seshasayee, Joshua Fryman, Ibrahim Hur (Intel Corp)
Enhanced Parallel Simulation for ACAS X Development
Adam Gjersvik (MIT LL)
Architectural Analysis of Deep Learning on Edge Accelerators
Luke Kljucaric, Alex Johnson, Alan George (NSF SHREC)
3-S1: Graph Challenge Special (17:30-19:30 EDT)
Organizers: Jeremy Kepner
3-S2: Scaling HPC Education Special (17:30-19:30 EDT)
Organizers: Julie Mullen & Lauren Milechin
Focus: Professional/Career Training and Education (17:30 - 18:25 Eastern Time)
Timothy Mattson, Ph.D, (Intel) Active Learning: Teaching Programmers the Same Way We Teach Kayakers
Ian A Cosden, Ph.D, (Princeton) US-RSE: The US Research Software Engineer Association
Julia Mullen, Ph.D (MIT Lincoln Laboratory) and Lauren Milechin (MIT) Using the HPC Certification Framework to Build Your Own HPC Curriculum
Open Discussion (30 mins): Professional/Career Training and Education
Break (18:25 - 18:35)
Focus: User Training (18:35 - 19:30 Eastern Time)
Robert E. Thoelen III (Pratt & Whitney), Training and Development of System Administrators at Pratt and Whitney
Julie Ma (Northeast CyberTeam Initiative) Ask.CI and the Cyberteam Portal - Community building resources from the Northeast Cyberteam
Ann Backhaus, (Pawsey Supercomputing Center) Hub and Spoke: A Practical Approach to User Training Design
Open Discussion: (30 mins) User Training
IBM Sponsor Spotlight Talk (10:30-11:00 EDT)
4-1: AI / Machine Learning 1 Session (11:00-12:15 EDT)
Co-Chairs: Sanjeev Mohindra & Luke Wilson
Fast Training of Deep Neural Networks Robust to Adversarial Perturbations
Justin Goodwin (MIT LL), Olivia Brown (MIT LL), Victoria Helus (MIT LL)
Active Learning Pipeline for Brain Mapping in a High Performance Computing Environment
Adam Michaleas, Lars Gjesteby, Michael Snyder, David Chavez (MIT LL), Meagan Ash, Matthew A Melton, Damon Lamb, Sara Nicole Burke, Kevin Otto (Univ Florida), Lee Kamentsky, Webster Guan, Kwanghun Chung (MIT), Laura Brattain (MIT LL)
Beyond Floating-Point Ops: CNN Performance Prediction with Critical Datapath Length
David Langerman, Alex Johnson, Kyle Buettner (Univ Pittsburgh), Alan George (NSF CHREC)
Optimising AI Training Deployments using Graph Compilers and Containers
Nina Mujkanovic, Karthee Sivalingam, Alfio Lazzaro (HPE HPC/AI EMEA Research Lab)
A Hybrid-Pipelined Architecture for FPGA-based Binary Weight DenseNet with High Performance-Efficiency
Shihao Zeng, Yihua Huang (Sun Yat-sen Univ)
Poster Session: 4-P (12:15-15:45 EDT)
Chair/Host: Kurt Keville
Denial of Service in CPU-GPU Heterogeneous Architectures
Hao Wen (VCU), Wei Zhang (Univ Louisville)
A Comprehensive comparison and analysis of OpenACC and OpenMP 4.5 for NVIDIA GPUs
Prachi P, Usha R., Mangala N (CDAC)
Using RAPIDS AI to Accelerate Graph Data Science Workflows
Todd R Hricik, David Bader (NJIT), Oded Green (NVIDIA)
GPU Accelerated Anomaly Detection of Large Scale Light Curves
Austin Minor (Tsinghua Univ), Zhihui Du (NJIT), Yankui Sun (Tsinghua Univ), David Bader (NJIT), Chao Wu, Jianyan Wei (National Astronomical Observations of China)
AI/ML trained analysis for the residence time of the drug and carrier particles in a Dry Powder Inhaler
V M Krushnarao Kotteda (Univ Wyoming), Vinod Kumar, Antara Badhan (UTEP)
Bandwidth Allocation in Silicon Photonic Networks using Application Instrumentation
Aditya Narayan, Ajay Joshi, Ayse Coskun (Boston Univ)
4-2: AI / Machine Learning 2 Session (12:30-13:45 EDT)
Co-Chairs: Sanjeev Mohindra & Luke Wilson
Stability-Optimized High Order Methods and Stiffness Detection for Pathwise Stiff Stochastic Differential Equations [Outstanding Paper Award]
Christopher V Rackauckas (MIT), Qing Nie (UC Irvine)
Compute, Time and Energy Characterization of Encoder-Decoder Networks with Automatic Mixed Precision Training
Siddharth Samsi, Michael Jones (MIT LLSC), Mark Veillette (MIT LL)
Accuracy and Performance Comparison of Video Action Recognition Approaches
Matthew Hutchinson (MIT), Siddharth Samsi, William Arcand, David Bestor, Bill Bergeron, Chansup Byun, Micheal Houle, Matthew Hubbell, Micheal Jones, Jeremy Kepner, Andrew Kirby, Peter Michaleas (MIT LLSC), Lauren Milechin (MIT), Julie Mullen, Andrew Prout, Antonio Rosa, Albert Reuther, Charles Yee, Vijay Gadepally (MIT LLSC)
Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine
Prasanth Chatarasi (Georgia Tech), Stephen Neuendorffer, Samuel Bayliss, Kees Vissers (Xilinx Inc.), Vivek Sarkar (Georgia Tech)
CQNN: a CGRA-based QNN Framework
Tong Geng, Chunshu Wu (Boston Univ), Cheng Tan, Bo Fang, Ang Li (PNNL), Martin Herbordt (Boston Univ)
4-3: AI / Machine Learning 3 Session (14:15-15:30 EDT)
Co-Chairs: Sanjeev Mohindra & Laura Brattain
Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research [Outstanding Paper Award]
Yutai Zhou (MIT LL), Shawn Manuel (Stanford), Peter Morales (MIT LL), Sheng Li (Stanford), Jaime Pena, Ross E Allen (MIT LL)
iBench: a distributed inference benchmark for HPC [Outstanding Paper Award]
Wesley Brewer, Greg Behm (HPCMP PET), Alan Scheinine (HPCMP Benchmark Team), Ben Parsons (HPCMP), Wesley Emeneker, Robert P. Trevino (Maui HPC Center)
Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks Via Nonlinear Multigrid [Outstanding Paper Award]
Andrew C Kirby, Siddharth Samsi, Michael S Jones, Albert Reuther, Jeremy Kepner, Vijay Gadepally (MIT LLSC)
Survey of Machine Learning Accelerators
Albert Reuther, Jeremy Kepner, Vijay Gadepally, Siddharth Samsi, Michael S Jones, Peter Michaleas (MIT LLSC)
Inference Benchmarking on HPC Systems
Wesley Brewer, Greg Behm (HPCMP PET), Alan Scheinine (HPCMP Benchmark Team), Ben Parsons (HPCMP), Wesley Emeneker, Robert P. Trevino (Maui HPC Center)
4-4: Advanced Processor Architectures Session (15:45-17:00 EDT)
Co-Chairs: Wei Zhang & Dan Campbell
Target Classification in Synthetic Aperture Radar and Optical Imagery Using Loihi Neuromorphic Hardware [Outstanding Paper Award]
Mark Barnell, Courney Raymond (AFRL), Matthew Wilson, Darrek Isereau, Chris Cicotta (SRC)
A Dynamically Configurable Network for Software-Defined Hardware [Outstanding Paper Award]
William J Butera (Intel Corp)
Scalability of Streaming on Migrating Threads
Brian A Page, Peter Kogge (Notre Dame)
Projecting Performance for Intel UMA using Down-Scaled Simulation
Stijn Eyerman, Wim Heirman, Yigit Demir, Kristof Du Bois, Ibrahim Hur (Intel Corp)
Chip-to-chip Optical Data Communications using Polarization Division Multiplexing
Darko Ivanovich (WUSTL), Amit Deliwala (UIUC), Chenfeng Zhao (WUSTL), Viktor Gruev (UIUC), Xuan Zhang, Roger Chamberlain (WUSTL)
4-S1: AI Challenges Special (17:30-19:30 EDT)
Organizers: Vijay Gadepally
4-S2: OpenSuperComputing BoF Special (17:30-19:30 EDT)
Organizers: Kurt Keville
5-1: Fault-Tolerant Computing Session (11:00-12:15 EDT)
Co-Chairs: Kurt Keville & Sigal Gottlieb
Hybrid Approach to HPC Cluster Telemetry and Hardware Log Analytics
Justin Thaler (IBM), Woong Shin (ORNL), Steven L Roberts (IBM), James H. Rogers (ORNL), Todd Rosedahl (IBM)
Identifying Execution Anomalies for Data IntensiveWorkflows Using Lightweight ML Techniques
Cong Wang (RENCI/UNC Chapel Hill), George Papadimitriou (USC ISI), Mariam Kiran (LBNL), Anirban Mandal (RENCI/UNC Chapel Hill), Ewa Deelman (USC ISI)
Total Ionizing Dose Radiation Testing of NVIDIA Jetson Nano GPUs
Windy Slater (Univ New Mexico), Nayana Tiwari (Cal Poly), Tyler M Lovelly, Jesse Mee (AFRL)
An Efficient LP Rounding Scheme for Replica Placement
ZHIHUI DU (NJIT), Sen Zhang (SUNY Oneonta), David Bader (NJIT), Jingkun Hu (Worldmoney Blockchain Mgmt)
A Fault Tolerant Implementation for a Massively Parallel Seismic Framework
Suha Kayum, Hussain Alsalim, Thierry-Laurent Tonellot, Ali Momin (Saudi Aramco)
5-2: High Performance & Secure Hardware 1 Session (12:30-13:45 EDT)
Co-Chairs: Bruce Kinney & Doug Enright
Discrete Integrated Circuit Electronics (DICE)
Zach Fredin (MIT), Jiri Zemanek (MIT, Czech Tech Univ), Camron Blackburn, Erik Strand, Amira Abdel-Rahman, Premila Rowles, Neil Gershenfeld (MIT)
Arithmetic and Boolean Secret Sharing MPC on FPGAs in the Data Center
Rushi Patel, Pierre-Francois W Wolfe, Robert Munafo, Mayank Varia, Martin Herbordt (Boston Univ)
Evaluating Cryptographic Performance of Raspberry Pi Clusters
Daniel Hawthorne, Michael Kapralos, Raymond Blaine, Suzanne J Matthews (USMA)
MetaCL: Automated Meta OpenCL Code Generation for High-Level Synthesis on FPGA
Paul Sathre, Atharva M Gondhalekar, Mohamed W Hassan, Wu-chun Feng (Virginia Tech)
A High Throughput Parallel Hash Table on FPGA using XOR-based Memory
Ruizhi Zhang, Sasindu Wijeratne, Yang Yang, Sanmukh Rao Kuppannagari, Viktor K Prasanna (USC)
5-3: High Performance & Secure Hardware 2 Session (14:15-15:30 EDT)
Co-Chairs: Bruce Kinney & Michael Vai
Homomorphic Encryption Based Secure Sensor Data Processing
Vijay Gadepally (MIT LLSC), Mihailo Isakov, Rashmi Agrawal (Boston Univ), Karen Gettings (MIT LL), Michel Kinsy (Boston Univ)
Accelerator Design and Performance Modeling for Homomorphic Encrypted CNN Inference
Tian Ye, Rajgopal Kannan, Viktor K Prasanna (USC)
FPGAs in the Network and Novel Communicator Support Accelerate MPI Collectives
Martin Herbordt, Pouya Haghi, Anqi Guo, Qingqing Xiong, Chen Yang, Rushi Patel (Boston Univ), Anthony Skjellum, Ryan Marshall, Justin Broaddus (UTC)
Design and Performance Evaluation of Optimizations for OpenCL FPGA Kernels
Anthony M Cabrera (WUSTL), Roger Chamberlain (WUSTL)
Hardware Foundation for Secure Computing
Donato Kava, Alice Lee, Michael M Vai, Aaron Mills (MIT LL)
5-4: High Performance & Secure Hardware 3 Session (15:45-17:00 EDT)
Co-Chairs: Michael Vai & Doug Enright
How to Efficiently Train Your AI Agent? Characterizing and Evaluating Deep Reinforcement Learning on Heterogeneous Platforms [Outstanding Student Paper Award]
Yuan Meng, Yang Yang, Sanmukh Rao Kuppannagari, Rajgopal Kannan, Viktor K Prasanna (USC)
A Hardware Root-of-Trust Design for Low-Power SoC Edge Devices [Outstanding Student Paper Award]
Alan Ehret (Boston Univ), Karen Gettings, Bruce R Jordan (MIT LL), Michel Kinsy (Boston Univ)
Dynamic Computational Diversity with Multi-Radix Logic and Memory
Paul Flikkema, James Palmer, Tolga Yalcin, Bertrand Cambou (Northern Arizona Univ)
OpenCL Performance on the Intel Heterogeneous Architecture Research Platform
Steven D Harris, Roger Chamberlain, Christopher Gill (WUSTL)