High-Performance Computing in Sciences

This seminar series will focus on computing, numerics, software development, and their applications across scientific disciplines. Our goal is to invite leading experts from both academia and industry to give talks a few times each semester. Seminars are live streamed through Zoom.
Next seminar
- “Roihu, CSC’s new flagship national supercomputer” by Dr. Yann Pfau-Kempf from CSC
- Friday, April 24 at 13:15-14, 2026
- E204, Physicum, Gustaf Hällströmin katu 2, Helsinki
- This time our speaker is Dr. Yann Pfau-Kempf, a former University researcher in space physics, is now an HPC specialist at CSC – IT Center for Science, Ltd.
- Roihu, CSC’s new flagship national supercomputer, is replacing Puhti and Mahti in the upcoming months. Come and hear about its new features and how it will accelerate your science! At the end of the presentation, there will be a possibility to discuss first experiences with the pilot teams.
Past seminars
- “A collection of tricks to efficiently run massive simulations on HPC machines: The Vlasiator perspective” by Dr. Urs Ganse
- Friday, February 13 at 15:15-16, 2026
- E207, Physicum, Gustaf Hällströmin katu 2, Helsinki
- This time our speaker is Dr. Urs Ganse from the Space Physics research group at University of Helsinki. There he leads the modeling efforts through kinetic simulation of the near-Earth plasma environment. This includes, among other things, development of a 6-dimensional Vlasov theory-based HPC simulation called Vlasiator.
- “C++ Destructors and RAII” by Ville Voutilainen from the Qt Group
- Friday, December 12 at 15:15-16
- Ville Voutilainen is a Principal Software Engineer working at The Qt Company, and has been programming in C++ as a hobby since 1994 and professionally since 1998. He has been a member of the ISO C++ Standards Committee since 2009, and has authored and implemented various standard proposals over the years.
- The talk explains how and why destructors are fundamental and idiomatic, and what RAII is and how and why RAII is also fundamental and idiomatic. The talk covers resource management with the use of destructors and RAII, and also covers cases that are not resource management.
- “State-of-the-Art Communication Software for Supercomputers and Its Applications” by Jeff Hammond from NVIDIA
- Friday, October 31 at 15:15-16
- jeffhammond.github.io
- I will talk about high-performance communication software for GPU supercomputers. I will explain NCCL and NVSHMEM, including their historical context from MPI and SHMEM. The functionality and performance will be demonstrated through an example from linear algebra. Real world results from both scientific and commercial AI use cases will be described.