JUNE 19–23, 2016
FRANKFURT AM MAIN, GERMANY
 
Research Papers 01 - Award Session
Monday, June 20, 2016, 04:00 pm - 06:00 pm
  Panorama 1, Forum
Chair:
Jack Dongarra, University of Tennessee & ORNL
Pavan Balaji, ANL
Michael M. Resch, HLRS
Alison Kennedy, STFC Hartree Centre
  
  Introduction
  04:00 pm - 04:05 pm
  Pavan Balaji, ANL
  Jack Dongarra, University of Tennessee & ORNL
  
  Hans Meuer Award Ceremony
  04:05 pm - 04:10 pm
  Pavan Balaji, ANL
  Jack Dongarra, University of Tennessee & ORNL
  
  Hans Meuer Award Winning Paper: Mitigating MPI Message Matching Misery
  04:10 pm - 04:50 pm
  James Dinan, Intel
  
  PRACE ISC Award Ceremony
  04:50 pm - 04:55 pm
  Alison Kennedy, STFC Hartree Centre
  
  PRACE ISC Award Winning Paper: Dynamic Sparse-Matrix Allocation on GPUs
  04:55 pm - 05:25 pm
  James King, University of Utah
  
  Gauss Award Ceremony
  05:25 pm - 05:30 pm
  Michael M. Resch, HLRS
  
  Gauss Award Winning Paper: Predictive Modeling for Job Power Consumption in HPC Systems
  05:30 pm - 06:00 pm
  Andrea Borghesi, University of Bologna
 
Research Papers 02 – Autotuning & Thread Mapping
Tuesday, June 21, 2016, 11:00 am - 12:30 pm
  Analog 1+2, Forum
Chair:
Kengo Nakajima, University of Tokyo
  
  An Analytical Model-Based Auto-Tuning Framework for Locality-Aware Loop Scheduling
  11:00 am - 11:30 am
  Sandra Wienke, RWTH Aachen University
  
  Performance, Design & Autotuning of Batched GEMM for GPUs
  11:30 am - 12:00 pm
  Azzam Haidar, University of Tennessee
  
  TCU: A Multi-Objective Hardware Thread Mapping Unit for HPC Clusters
  12:00 pm - 12:30 pm
  Ravi Kumar Pujari, TU München
 
Research Papers 03 – Data Locality & Decomposition
Tuesday, June 21, 2016, 11:00 am - 12:30 pm
Substanz 1+2, Forum  
Chair:
Fang-Pang Lin, NCHC
  
  An Efficient Parallel Load-Balancing Strategy for Orthogonal Decomposition of Geometrical Data
  11:00 am - 11:30 am
  Bruno Magalhaes, EPFL
  
  Parallel Community Detection Algorithm Using a Data Partitioning Strategy with Pairwise Subdomain Duplication
  11:30 am - 12:00 pm
  Alok Choudhary, Northwestern University
  
  TiDA: High-Level Programming Abstractions for Data Locality Management
  12:00 pm - 12:30 pm
  Didem Unat, Koç University
 
Research Papers 04 – Scalable Applications
Tuesday, June 21, 2016, 01:45 pm - 02:45 pm
  Analog 1+2, Forum
Chair:
Michela Taufer, University of Delaware
  
  OpenAtom: Scalable Ab-Initio Molecular Dynamics with Diverse Capability
  01:45 pm - 02:15 pm
  Laxmikant Kale, University of Illinois at Urbana-Champaign
  
  SPRITE: A Fast Parallel SNP Detection Pipeline
  02:15 pm - 02:45 pm
  Vasudevan Rengasamy, Pennsylvania State University
 
Research Papers 05 – Machine Learning
Tuesday, June 21, 2016, 01:45 pm - 02:45 pm
Substanz 1+2, Forum  
Chair:
Xavier Vigouroux, Bull
  
  Towards Machine Learning on the Automata Processor
  01:45 pm - 02:15 pm
  Tom Tracy II, University of Virginia
  
  AutoMOMML: Automatic Multi-Objective Modeling with Machine Learning
  02:15 pm - 02:45 pm
  Prasanna Balaprakash, ANL
 
Research Papers 06 – Datacenters & Cloud
Tuesday, June 21, 2016, 03:30 pm - 04:30 pm
  Analog 1+2, Forum
Chair:
Dhabaleswar K. Panda, Ohio State University
  
  Supercomputing Centers & Electricity Service Providers: A Geographically Distributed Perspective on Demand Management in Europe & the United States
  03:30 pm - 04:00 pm
  Tapasya Patki, LLNL
  
  Resource Management for Running HPC Applications in Container Clouds
  04:00 pm - 04:30 pm
  Michela Taufer, University of Delaware
 
Research Papers 07 – Communication Runtime
Tuesday, June 21, 2016, 03:30 pm - 04:30 pm
Substanz 1+2, Forum  
Chair:
Julian Kunkel, DKRZ
  
  INAM^2: InfiniBand Network Analysis & Monitoring with MPI
  03:30 pm - 04:00 pm
  Khaled Hamidouche, Ohio State University
  
  Comparing Runtime Systems with Exascale Ambitions Using the Parallel Research Kernels
  04:00 pm - 04:30 pm
  Jeff R. Hammond, Intel
 
Research Papers 08 – Intel Xeon Phi
Wednesday, June 22, 2016, 11:00 am - 12:00 pm
Substanz 1+2, Forum  
Chair:
Federico Silla, Technical University of Valencia
  
  High Order Seismic Simulations on the Intel Xeon Phi Processor (Knights Landing)
  11:00 am - 11:30 am
  Alexander Heinecke, Intel Parallel Computing Lab
  
  Leveraging a Cluster-Booster Architecture for Brain-Scale Simulations
  11:30 am - 12:00 pm
  Pramod Kumbhar, EPFL
 
Research Papers 09 – Manycore Architectures
Wednesday, June 22, 2016, 01:45 pm - 02:45 pm
  Analog 1+2, Forum
Chair:
Peter Ziegenhein, Institute of Cancer Research
  
  Efficient & Predictable Group Communication for Manycore NoCs
  01:45 pm - 02:15 pm
  Frank Mueller, North Carolina State University
  
  Distributed Job Allocation for Large-Scale Manycores
  02:15 pm - 02:45 pm
  Frank Mueller, North Carolina State University
 
Research Papers 10 – Extreme-Scale Computations
Wednesday, June 22, 2016, 01:45 pm - 02:45 pm
Substanz 1+2, Forum  
Chair:
David Abramson, University of Queensland
  
  Many-Core Acceleration of a Discrete Ordinates Transport Mini-App at Extreme Scale
  01:45 pm - 02:15 pm
  Tom Deakin, University of Bristol
  
  Efficiency of High Order Spectral Element Methods on Petascale Architectures
  02:15 pm - 02:45 pm
  Alexander Heinecke, Intel Parallel Computing Lab
 
Research Papers 11 – Resilience
Wednesday, June 22, 2016, 03:30 pm - 04:30 pm
  Analog 1+2, Forum
Chair:
Simon McIntosh-Smith, University of Bristol
  
  Scalability of Partial Differential Equations Preconditioner Resilient to Soft & Hard Faults
  03:30 pm - 04:00 pm
  Karla V. Morris, Sandia National Laboratories
  
  Multi-Versioning Performance Opportunities in BGAS System for Resilience
  04:00 pm - 04:30 pm
  Dirk Pleiter, JSC