Monday, September 10th9:00am-10:30amWelcome and Registration Workshop 10:30am-11:00amBreak Other 11:00am-12:30pmWorkshop sessions I Workshop 12:30pm-1:30pmBreak Other 1:30pm-3:00pmWorkshop sessions II Workshop 3:00pm-3:30pmBreak Other 3:30pm-5:00pmWorkshop sessions III Workshop 6:15pm-7:30pmDrinks Reception & Self-Guided Tours, Naughton Gallery, Queen’s University Belfast Other | Tuesday, September 11th9:00am-10:15amWelcome and Keynote I Assembly Hall Paul H. J. Kelly Crossing the Chasm: How to develop weather and climate models for next generation computers Plenary 10:15am-10:45amBreak Other 10:45am-12:15pmSession I: best papers (Areas 1 and 2) Assembly Hall Harald Koestler PaSTRI: Error-Bounded Lossy Compression for Two-Electron Integrals in Quantum Chemistry SALaR: Scalable and Adaptive Designs for Large Message Reduction Collectives Plenary, Paper 12:15pm-1:30pmLunch Other 1:30pm-3:00pmPaper session II: Matrix algorithms Assembly Hall Dheeraj Sreedhar Energy Analysis and Optimization for Resilient Linear Systems Load-balancing-aware Parallel Algorithms of H-matrices with Adaptive Cross Approximation for GPUs A New Approach for Sparse Matrix Classification Based on Deep Learning Techniques Paper Paper session III: Architecture and Interconnect Minor Hall Ann Gentile The Tofu Interconnect D Janus: A Generic QoS Framework for Software-as-a-Service Applications Exploring HPC and Big Data Convergence: A Graph Processing Study on Intel Knights Landing Paper 3:00pm-3:30pmBreak Other 3:30pm-5:15pmPaper session IV: Generating and Optimizing Applications Assembly Hall Nathan Tallent Whole Program Generation of Massively Parallel Shallow Water Equation Solvers OpenACC vs the Native Programming on Sunway TaihuLight: A Case Study with GTC-P Parallel Approximation of the Maximum Likelihood Estimation for the Prediction of Large-Scale Geostatistics Simulations Modeling I/O performance variability using conditional variational auto encoders Paper Paper session V: Filesystems and Applications Minor Hall Hans Vandierendonck SciDP: Support HPC and Big Data Applications via Integrated Scientific Data Processing Applying Pwrake Workflow System and Gfarm File System to Telescope Data Processing UniviStor: Integrated Hierarchical and Distributed Storage for HPC HIDStore: A Hierarchical Intermediate Data Storage System for Seismic Processing Application Paper 5:15pm-7:00pmPoster reception Other | Wednesday, September 12th9:00am-10:15amAnnouncements and keynote II Assembly Hall Dimitrios Nikolopoulos Unconventional Computing with Reconfigurable Devices in the Cloud Plenary 10:15am-10:45amBreak Other 10:45am-12:15pmSession VI: Best papers - Areas 3 and 4 Assembly Hall Ron Brightwell Neural network based silent error detector An Efficient Transformation Scheme for Lossy Data Compression with Point-wise Relative Error Bound Plenary, Paper 12:15pm-1:30pmLunch Other 1:30pm-3:00pmPaper session VII: Benchmarking and Modeling Assembly Hall Tal Ben-Nun A Methodology for Characterizing the Correspondence Between Real and Proxy Applications Lightweight Requirements Engineering for Exascale Co-design Next Stop “NoOps": Enabling Cross-System Diagnostics Through Graph-based Composition of Logs and Metrics Paper Paper session VIII: Managing Heterogeneity and Imbalance Minor Hall Rong Ge Cutting the Tail: Designing High Performance Message Brokers to Reduce Tail Latencies in Stream Processing Dynamic Control of CPU Usage in a Lambda Platform A Heterogeneity-Aware Task Scheduler for Spark Paper 3:00pm-3:30pmBreak Other 3:30pm-5:00pmPaper session IX: Graphs and Big Data Analytics Assembly Hall Ali R. Butt Computing Exact Vertex Eccentricity on Massive-scale Distributed Graphs A Scalable Distributed Louvain Algorithm for Large-scale Graph Community Detection Optimizing Distributed Data-Intensive Workflows Paper Paper session X: Performance Engineering in Filesystems Minor Hall Anthony Skjellum Harmonia: An Interference-Aware Dynamic I/O Scheduler for Shared Non-Volatile Burst Buffers CRUM: Checkpoint-Restart Support for CUDA's Unified Memory Fixed-PSNR Lossy Compression for Scientific Data GekkoFS - A temporary distributed file system for HPC applications Paper 6:00pm-7:00pmArrival and Tour of Titanic Belfast Other 7:00pm-10:00pmDrinks Reception and Banquet at Titanic Belfast Other | Thursday, September 13th9:00am-10:15amCluster 2019 presentation and Keynote III Assembly Hall Bronis R. de Supinski Programmability, Portability and Performance: Challenges and Opportunities in Enabling Usable Systems in the Exascale Era Plenary 10:15am-10:45amBreak Other 10:45am-12:15pmPaper session XI: Hierarchy and Sharing in System Architecture Assembly Hall Giorgis Georgakoudis Hierarchical Clock Synchronization in MPI Hybrid MPI+OpenMP Reactive Work Stealing in Distributed Memory in the PDE Framework sam(oa)^2 Co-scheduling HPC workloads on cache-partitioned CMP platforms Paper Paper session XII: Scheduling, Elasticity and Energy Minor Hall Felix Wolf Leveraging Dependency in Scheduling and Preemption for High Throughput in Data-Parallel Clusters Self-Consumption Optimization of Renewable Energy Production in Distributed Clouds Elasticity in Graph Analytics? A Benchmarking Framework for Elastic Graph Processing Paper 12:15pm-1:30pmLunch Other 1:30pm-3:00pmPaper session XIII: Deep Learning Assembly Hall Michela Taufer Efficient Training of Convolutional Neural Nets on Large Distributed Systems Accelerating Deep Learning Frameworks with Micro-batches swCaffe: a Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight Paper Paper session XIV: Languages and Programming Models Minor Hall Sebastian Kuckuk Charmpy: A Python Parallel Programming Model And Now for Something Completely Different: Running Lisp on GPUs The AllScale Runtime Application Model Paper 3:00pm-3:30pmBreak Other 3:30pm-5:00pmPaper session XV: Scalable Filesystems Assembly Hall Jay Lofstead PDFE: Flexible Parallel State Machine Replication for Cloud Computing IOMiner: Large-scale Analytics Framework for Gaining Knowledge from I/O Logs A Server-managed Transparent Object Storage Abstraction for HPC Paper Paper session XVI: Algorithms, Applications and Performance Minor Hall Kenneth B. Kent Efficient Algorithms for the Summed Area Tables Primitive on GPUs Relaxing Scalability Limits with Speculative Parallelism in Sequential Monte Carlo Predicting Performance Using Collaborative Filtering Paper |