43th SPEEDUP Workshop on High-Performance Computing

University of Geneva
September 4/5, 2014

Sponsored by:
Speedup   UniGE   CADMOS


This workshop's focus: Multiscale Modelling

The intention of this workshop is to present and discuss the state-of-the-art in high-performance and parallel scientific computing. Presentations will focus on algorithms, applications, and software issues related to high-performance parallel computing. The focus of the workshop on September 4 will be on Multiscale Modeling. The scientific program of September 4 consists of six 45-minute talks and a poster session. Please encourage your collaborators to upload an abstract for the poster session. The deadline is Aug 31, 2014.

Directions

The conference will take place at University of Geneva.

Program

Thursday September 4th

Venue: Uni Bastions

8:30-9:30
Registration / Coffee
9:30-9:40
Opening (B. Chopard)
9:40-10:10
Derek Groen (University College, London): Multiscale computing with MAPPER: tools, techniques and applications
10:10-10:50
Laurent Debreu (INRIA): Schwarz waveform relaxation for heterogeneous cluster computing and applications
10:50-11:20
Coffee break
11:20-12:00
Igor Pivkin (University of Lugano): Multiscale modeling of biological systems
12:00-13:30
Lunch
13:30-14:00
Coffee
14:00-14:40
Diego Rossinelli (ETH Zurich): Petascale simulations of cloud cavitation collapse
14:40-15:10
Martin Steinhauser (University of Basel): Shockwave-Induced Damage in Tumor Cells: Experiments and Multiscale Simulations
15:10-15:50
Tim Warburton (Rice University): OCCA: An Extensible Portability Layer for Many-Core Programming
16:00-17:00
Coffee/Apero + Poster session
17:00-17:30
General Assembly of the speedup society

Friday September 5th

Venue: Battelle Campus, Carouge

Full-day Tutorial on hybrid MPI / OpenMP / CUDA programming, taught by Prof.Dr DI Gundolf Haase, University of Graz, Institute for Mathematics and Scientific Computing

Goals

This tutorial introduces into the field of High Performance Computing (HPC) in mathematical areas and engineering sciences with special focus on MPI, OpenMP, OpenACC and CUDA. The students will acquire specialties of recent and future hardware concepts as well as on supported software and compilers. The course work will be organized such that all course topics will be implemented on the appropriate hardware ranging from a single CPU via multiple CPUs to clusters of CPUs and GPUs/Xeon Phi. The students will be able to adapt research specific code such that they can take advantage of available computer resources. The four main goals of the tutorial consist of

  1. Knowledge of the students on algorithms and data structures for HPC and active use of this knowledge.

  2. The students get in touch with HPC related concepts and architectures, and the students are able to adopt new developments in this area onto the problem under consideration.

  3. Standard compiler and software support for parallel computer architectures is known and used by the students for solving mathematical problems by means of HPC hardware.

  4. The students are able to write/adapt parallel programs on various parallel platforms.

Comprehensive first steps for the impatient and some code.


Schedule

9:00-10:00
Introduction into Hardware and parallel concepts
10:00-10:30
Coffee break
10:30-11:15
A simple FEM solver and its data parallelism
11:15-12:00
OpenMP and MPI parallelization
12:00-13:00
Lunch break
13:00-15:00
OpenACC and CUDA parallelization for GPUs
15:00-15:30
Coffee break
15:30-17:00
Combined MPI + accelerator parallelization
Fees: Details and the registration form can be found here.

Organizing committee

A. Adelmann (PSI Villigen), P. Arbenz (ETH Zurich), H. Burkhart (U of Basel), B. Chopard (U Geneva), S. Deparis (EPF Lausanne), A. Janka (EIA Fribourg), R. Krause (USI Lugano), H. Nordborg (HSR), D. Obrist (U Berne), V. Rezzonico (EPF Lausanne), O. Schenk (USI Lugano), J. VandeVondele (ETH Zurich).