IXPUG Workshop Live Stream
from
Tuesday, 15 March 2016 (13:30)
to
Wednesday, 16 March 2016 (18:00)
Monday, 14 March 2016
Tuesday, 15 March 2016
13:30
Opening: Vít Vondrák (IT4I): Welcome in Ostrava
Opening: Vít Vondrák (IT4I): Welcome in Ostrava
13:30 - 13:45
13:45
Thomas Steinke (ZIB, Berlin): The Intel Xeon Phi User's Group
Thomas Steinke (ZIB, Berlin): The Intel Xeon Phi User's Group
13:45 - 14:00
14:00
Keynote: Joe Curley (Intel): Road to Many Core & the View Ahead
Keynote: Joe Curley (Intel): Road to Many Core & the View Ahead
14:00 - 15:00
15:00
Thomas Steinke (ZIB, Berlin), Georg Zitzlsberger (Intel), CJ Newburn (Intel), Michael Lysaght (ICHEC, Dublin): IXPUG Working Groups
Thomas Steinke (ZIB, Berlin), Georg Zitzlsberger (Intel), CJ Newburn (Intel), Michael Lysaght (ICHEC, Dublin): IXPUG Working Groups
15:00 - 15:30
15:30
Break
Break
15:30 - 16:00
16:00
Vectorization I: James Willis, Richard Bower and Matthieu Schaller (ICC Durham): Optimisation of the core kernels of the particle-based code SWIFT on AVX and AVX2 leading to ~3x speed-up
Vectorization I: James Willis, Richard Bower and Matthieu Schaller (ICC Durham): Optimisation of the core kernels of the particle-based code SWIFT on AVX and AVX2 leading to ~3x speed-up
16:00 - 16:30
16:30
Vectorization I: Luigi Iapichino and Fabio Baruffa (LRZ Munich): Improving the vectorisation of a Gadget kernel: efficiency and potential on multiple platforms
Vectorization I: Luigi Iapichino and Fabio Baruffa (LRZ Munich): Improving the vectorisation of a Gadget kernel: efficiency and potential on multiple platforms
16:30 - 17:00
17:00
Vectorization I: Sergi Siso, Luke Mason and Michael Seaton (Hartree Centre, Daresbury): Code modernization of DL_MESO LBE to achieve good performance on the Intel Xeon Phi
Vectorization I: Sergi Siso, Luke Mason and Michael Seaton (Hartree Centre, Daresbury): Code modernization of DL_MESO LBE to achieve good performance on the Intel Xeon Phi
17:00 - 17:30
17:30
Vectorization I: Discussion
Vectorization I: Discussion
17:30 - 18:00
Wednesday, 16 March 2016
09:00
Keynote: CJ Newburn (Intel): Bigger, faster, persistent storage and how you get to it (HBM, 3DXP, OmniPath)
Keynote: CJ Newburn (Intel): Bigger, faster, persistent storage and how you get to it (HBM, 3DXP, OmniPath)
09:00 - 10:00
10:00
Break
Break
10:00 - 10:30
10:30
New Application Areas: Servesh Muralidharan, Oisin Robinson, Gilles Civario and Michael Lysaght (ICHEC, Dublin): A comparison study of vectorization approaches to optimize multiplication of large integers on Intel Xeon/Xeon Phi platforms
New Application Areas: Servesh Muralidharan, Oisin Robinson, Gilles Civario and Michael Lysaght (ICHEC, Dublin): A comparison study of vectorization approaches to optimize multiplication of large integers on Intel Xeon/Xeon Phi platforms
10:30 - 10:55
10:55
New Application Areas: Marcel Ehrhardt and Hannes Hauswedell (FU Berlin): The SeqAn C++ library for efficient NGS sequence analysis - HPC modernisation using generic programming
New Application Areas: Marcel Ehrhardt and Hannes Hauswedell (FU Berlin): The SeqAn C++ library for efficient NGS sequence analysis - HPC modernisation using generic programming
10:55 - 11:20
11:20
New Application Areas: Milan Jaros (IT4I, Ostrava): The Fundamentals: How to accelerate Blender with the Intel Xeon Phi coprocessors
New Application Areas: Milan Jaros (IT4I, Ostrava): The Fundamentals: How to accelerate Blender with the Intel Xeon Phi coprocessors
11:20 - 11:45
11:45
New Application Areas: Discussion
New Application Areas: Discussion
11:45 - 12:00
12:00
Break
Break
12:00 - 13:00
13:00
Tools session: Florent Lebeau (Allinea): Experiences preparing HPC codes for Intel Knights Landing with Allinea's tools
Tools session: Florent Lebeau (Allinea): Experiences preparing HPC codes for Intel Knights Landing with Allinea's tools
13:00 - 14:00
14:00
Vectorization II: Lubomir Riha, Michal Merta and Jan Zapletal (IT4I, Ostrava): Acceleration of FETI Solvers and the BEM4I library using the Intel Xeon Phi coprocessors
Vectorization II: Lubomir Riha, Michal Merta and Jan Zapletal (IT4I, Ostrava): Acceleration of FETI Solvers and the BEM4I library using the Intel Xeon Phi coprocessors
14:00 - 14:25
14:25
Vectorization II: Vladimir Mironov and Alexander Moskovsky (Lomonossov Moscow Univ.): Parallelization and optimization of Hartree-Fock method in GAMESS-US quantum chemistry code
Vectorization II: Vladimir Mironov and Alexander Moskovsky (Lomonossov Moscow Univ.): Parallelization and optimization of Hartree-Fock method in GAMESS-US quantum chemistry code
14:25 - 14:50
14:50
Vectorization II: Nikola Tchipev, Steffen Seckler, Philipp Neumann and Hans-Joachim Bungartz (TU Munich):Optimizing ls1-mardyn for Xeon Phi
Vectorization II: Nikola Tchipev, Steffen Seckler, Philipp Neumann and Hans-Joachim Bungartz (TU Munich):Optimizing ls1-mardyn for Xeon Phi
14:50 - 15:15
15:15
Vectorization II: Discussion
Vectorization II: Discussion
15:15 - 15:30
15:30
Break
Break
15:30 - 16:00
16:00
Middleware: Adrian Jackson, Michele Weiland and Nick Johnson (EPCC, Edinburgh): Power monitoring using Adept tools and RAPL
Middleware: Adrian Jackson, Michele Weiland and Nick Johnson (EPCC, Edinburgh): Power monitoring using Adept tools and RAPL
16:00 - 16:25
16:25
Middleware: Wojciech Waśko, Piotr Uminski and Krzysztof Kulakowski (Intel): Memkind: the API to leverage heterogeneous memory architectures
Middleware: Wojciech Waśko, Piotr Uminski and Krzysztof Kulakowski (Intel): Memkind: the API to leverage heterogeneous memory architectures
16:25 - 16:50
16:50
Middleware: Discussion
Middleware: Discussion
16:50 - 17:00
17:00
CJ Newburn (Intel): hStreams: Easing the way to heterogeneous platforms like Knights Landing
CJ Newburn (Intel): hStreams: Easing the way to heterogeneous platforms like Knights Landing
17:00 - 18:00