Conference Programme

The conference will run from 0900 – 1900 on Tuesday 17th, 0930 – 1740 on Wednesday 18th, and 0930 – 1320 on Thursday 19th.

Tuesday 17th April

0900-0930	Registration and coffee
0930-0950	Welcome
0950-1050	Keynote – Andreas Olofsson Programme Manager, DARPA
1050-1120	Coffee Break
1120-1300	Parallel Session A Roman Uskov On the Calculation Distribution between CPU and GPU in the Hybrid Supercomputing the Radiation Transport Mads Ohm Larsen Case study: Bohrium – Powering Oceanography Simulation Matthew Smith Port Out, Motherboard Home: Accelerating CASTEP on CPU-GPU clusters	Parallel Session B Sergio Rivas-Gomez MPI Storage Windows for a Data-centric Era Keeran Brabazon Performance of HPC I/O Strategies at Scale Juan F.R. Herrera Evaluation Methodology of an NVRAM-based Platform for the Exascale James Hawkes Scalable I/O Funnelling for ECMWF’s Integrated Forecast System
1300-1400	Lunch Break
1400-1500	Keynote – Berk Hess GROMACS
1500-1530	Coffee Break
1530-1620	Parallel Session A Justs Zarins Progressive load balancing of asynchronous algorithms in distributed memory Sudeep Pasricha An Exploration of Fault Resilience Protocols for Large-Scale Application Execution on Exascale Computing Platforms	Parallel Session B Dana Akhmetova Speeding up a high-performance scientific code with GASPI shared notifications Niclas Jansson Efficient Gather-Scatter Operations in Nek5000 Using PGAS
1620-1730	Poster Lightning Talks
1730-1900	Poster and Drinks Reception

Wednesday 18th April

0930-1030	Keynote – Dominic Harlow Consultant, Federation Internationale de l’Automobile (FIA)
1030-1100	Coffee Break
1100-1215	Parallel Session A Nick Brown Leveraging SLEPc in modelling the earth’s magnetic environment Christopher Maynard LFRic and PSyclone: Building a Domain Specific Embedded Language for weather and Climate models Mirko Rahn A directory/cache for leveraging the efficient use of distributed memory by task-based runtime systems	Parallel Session B Arjen Tamerus Adapting CASTEP for the Exascale age: Hybrid OpenMP and vectorisation Jing Gong OpenACC accelerator for the PN–PN-2 algorithm in Nek5000 Mike Ashworth First steps in porting the LFRic Weather and Climate model to the FPGAs of the EuroExa architecture
1215-1315	Lunch
1315-1415	Keynote – Jeffrey Vetter Leader, Future Technologies Group, Oak Ridge National Laboratory
1415-1530	Panel Discussion Chair: Professor Mark Parsons (EPCC Director) Panel members: Satoshi Matsuoka (R-CCS), Dominic Harlow (FIA), Jeffrey Vetter (ORNL), Michele Weiland (EPCC) and Andreas Olofsson (DARPA)
1530-1600	Coffee Break
1600-1740	Parallel Session A Nick Johnson NEXTGenSim: a workflow and hardware-aware workload simulator for HPC systems Alexandru Calotoiu Extra-P: Automatic Empirical Performance Modeling of Parallel Programs Patrick Vogler Wavelet-Based Compression Algorithm Roman Iakymchuk A Task-Based Particle-in-Cell Method with Automatic Load-Balancing using the AllScale Environment	Parallel Session B Richard Gilham Controllable data precision in the Met Office Unified Model Alan Stokes Running Distributed Computations Using the SpiNNaker platform Holger Brunst Performance Tracing of Heterogeneous Exascale Applications: Pitfalls and Opportunities Grenville Lister In-flight ensemble processing for exascale
1900-2300	Conference Dinner

Thursday 19th April

0930-1030	Keynote – Satoshi Matsuoka Director, Riken Center for Computational Science (R-CCS)
1030-1120	Parallel Session A Dominic Etienne Charrier Reducing the number of load rebalancings and increasing concurrency in mesh-based dynamically adaptive simulations Rupert Nash Accelerating simulations of cerebrovascular blood flow through parallelization in time	Parallel Session B Blair Archibald High Performance Combinatorial Search with YewPar Jun Zhang An Evaluation of the TensorFlow Programming Model for Solving Traditional HPC Problems
1120-1150	Coffee Break
1150-1305	Parallel Session A Maurice Jamieson Leveraging hierarchical memories for micro-core architectures Xiaohu Guo Developing An Extensible, Portable, Scalable Toolkit for Projection Based Particle Methods Tom Vander Aa SMURFF: a High-Performance Framework for Matrix Factorization	Parallel Session B Diego González-Herrero Using modular supercomputing to propel Particle-in-Cell methods to exascale Martin Berzins A portable runtime system approach to engineering design at exascale using the Uintah software Gladys Utrera Mitigating performance degradation of frequently synchronised applications in presence of coarse grain jitter
1305-1320	Close