CSCS organized in Lugano on December 14-15, 2015 a workshop on Advanced C++ for HPC. The course aimed at providing the fundamental tools for effective C++ programming in the context of HPC. The tools include generic programming techniques, API development, usage of already existing C++ libraries, and specific C++-11/14 constructs. Starting from a basic knowledge […]
This webinar video shows how to collect the performance data required for production project proposal at CSCS. In this webinar, it is explained how to use the Craypat analysis tool for hybrid (CUDA, OpenACC) and non hybrid (MPI, OpenMP) high performance parallel computing codes on the Piz Daint system and how to submit a successful […]
CSCS organized May 15-17 a 2-day training course aimed to teach performance engineering approaches on the compute node level. “Performance engineering” is intended as developing a thorough understanding of the interactions between software and hardware. The instructors were Prof. Gerhard Wellen and Dr. Georg Hager from RRZE, Germany. CSCS organized May 15-17 a 2-day training course aimed to teach performance […]
CSCS organized last March (24-27 March) a 4-day training course on “Piz Daint”, CSCS hybrid Cray XC30 system. “Piz Daint” has 5.272 compute nodes (with Intel® Xeon® E5-2670 and NVIDIA® Tesla® K20X) and a peak performance of 7.8 Petaflops. The presentations have being given by experts from Cray, NVIDIA and Allinea. The Cray Programming Environment […]
This is the second part of the slidecasts of the two day course on visualization and graphics organized by CSCS in Lugano. Speaker was Jean Favre (CSCS). VisIt, an open-source turn-key 3D data visualizer VisIt-specific Features Parallel and client-server usage from the outside to CSCS Interactive sessions vs. batch-oriented scripting Customization via plugins for ParaView and […]
