The special interest group on GPU Computing of the Netherlands eScience Center comes together roughly every two weeks to share knowledge and experience on the latest research and technological developments relevant to accelerated computing.
The meetings are usually centered around a single presentation about GPU-related research or its application within a project. However, we also encourage anyone to present applications that have compute-related performance issues, which allows the group to give advice on how to improve performance and fix performance issues in the code, possibly with GPUs. Occasionally we invite external speakers, for example academic or industry experts, or students who did a related masters projects.
If you would like to present or invite an external speaker, please feel free to subscribe for any of the upcoming sessions in the table below using a pull request.
Contact persons:
- Alessio Sclocco (a.sclocco@esciencecenter.nl)
- Stijn Heldens (s.heldens@esciencecenter.nl)
| Date | Presenter | Topic |
|---|---|---|
| 2024-01-25 | Tim Besard (JuliaHub) | Introduction to GPU programming in Julia |
| 2024-02-08 | Hanno Spreeuw | Porting the Python Source Extractor (PySE) to GPU without writing a single kernel |
| 2024-02-22 | Richard Schoonhoven (CWI) | Going green: optimizing GPUs for energy efficiency through model-steered auto-tuning |
| 2024-03-06 | Stijn Heldens | Parallel programming systems for scalable scientific computing |
| 2024-03-21 | SIG | Highlights from GTC 2024 |
| 2024-04-04 | Leon Oostrum | Making your CUDA life easier with cudawrappers |
| 2024-05-02 | SIG | Project update session |
| 2024-05-16 | Denis Kumar (Student VU) | Auto-tuning OpenMP GPU applications |
| 2024-05-30 | Alessio Sclocco | Auto-tuning OpenACC applications |
| 2024-06-13 | Alessio Sclocco and Stijn Heldens | KMM: a lightweight C++ middleware for accelerated computing |
| 2024-06-27 | Hanno Spreeuw | From cudawrappers to HIPwrappers |
| 2024-07-11 | SIG | Report on second ESiWACE3 hackathon |
| 2024-08-15 | Denis Kumar (Student VU) | Optimizing GPU Performance with OpenMP: An Advanced Auto-Tuning Framework Utilizing Kernel Tuner |
| 2024-09-26 | Stijn Heldens | Bringing Auto-Tuning to HIP: Analysis of Tuning Impact and Difficulty on AMD and Nvidia GPUs |
| 2024-10-10 | Hanno Spreeuw | Real-time processing of 4K * 4K images from the Square Kilometre Array on a single core of a high-end CPU |
| 2024-10-24 | Ariana Torres-Knoop (SURF) | Quantum computers in HPC centers |
| 2024-11-07 | SIG | Testing of GPU code |
| 2024-11-21 | SIG | Joint meeting with SURF |
| 2024-12-05 | Lucas Esclapez | TBA |
| 2024-12-19 | -- | -- |
| Date | Presenter | Topic |
|---|---|---|
| 2023-02-16 | Floris-Jan Willemsen | A Methodology for Comparing Auto-Tuning Optimization Algorithms |
| 2023-03-02 | SIG | Continuous Integration (CI) and Profiling |
| 2023-03-16 | Bouwe Andela | Scaling data-intensive computations with Dask in the ESMValTool KD project |
| 2023-03-30 | SIG | Profiling GPU applications |
| 2023-04-13 | Benjamin Czaja (SURF) | Performance and Energy analysis of Large scale applications on Snellius |
| 2023-05-11 | Jaro Camphuijsen | The environmental impact of High Perfomance Computing in Science |
| 2023-05-25 | Gijs van den Oord | Using OpenACC to accelerate Earth System Models: experiences from ESiWACE2 |
| 2023-06-08 | Leon Oostrum | Accelerating medical and astronomical beamforming with the RECRUIT project |
| 2023-06-22 | SIG | Projects update session |
| 2023-07-06 | Milo Lurati (Student VU) | Comparing the Impact & Difficulty of Auto-Tuning on AMD and Nvidia GPUs |
| 2023-09-21 | Lucas Esclapez | Bringing reactive flow simulations to the ExaScale using Pele |
| 2023-10-05 | Ömer Şakar (UT Twente) | Alpinist: an Annotation-Aware GPU Program Optimizer |
| 2023-10-19 | Gijs van den Oord | GPU optimizations in the proton structure project |
| 2023-11-02 | SIG | ESiWACE3 Hackathon and MPI PotreeConverter |
| 2023-11-30 | Stijn Heldens | Kernel Float: Auto-tuning mixed precision GPU kernels |
| Date | Presenter | Topic |
|---|---|---|
| 2022-01-20 | Patrick Bos | SSI call kickoff discussion |
| 2022-02-10 | Ben van Werkhoven | Generic Autotuning Technology for GPU Applications |
| 2022-03-03 | Gijs van den Oord | Optimization of the RTE+RRTMGP-C++ library |
| 2022-03-24 | SIG | OpenSSI Optimization updates |
| 2022-04-14 | Jeff Larkin (NVIDIA) | Introduction to OpenACC |
| 2022-06-16 | Jeff Larkin (NVIDIA) | Standard language parallelism |
| 2022-07-14 | SIG | OpenSSI Optimization updates |
| 2022-09-08 | Merijn Verstraaten | Analysis and Prediction of GPU Graph Algorithm Performance (PhD defence @ UvA) |
| 2022-09-29 | Tom Deakin (University of Bristol) | Introduction to Heterogeneous Programming with SYCL |
| 2022-10-20 | SIG | OpenSSI Optimization updates |
| 2022-11-10 | Lars van den Haak (TU Eindhoven) | Verifying and Optimizing GPU software using the Domain Specific Language Halide |
| 2022-12-01 | Stijn Heldens | Kernel Launcher: Integrating Kernel-Tuner into C++ |
| Date | Presenter | Topic |
|---|---|---|
| 2021-02-25 | Gijs van den Oord | Performance portability: are DSL's the answer? |
| 2021-03-18 | Hanno Spreeuw | Parallellisation of kappa, sigma clipping of subimages from large astronomical maps: Ray vs. Dask |
| 2021-04-08 | Sven-Bodo Scholz (RU) | High-Performance Computing for everyone |
| 2021-04-29 | Ben van Werkhoven and Floris Jan Willemsen | Auto-tuning research update |
| 2021-06-10 | Alessio Sclocco | GPU Computing carpentry lesson |
| 2021-07-01 | Jens Wehner | Brainstorming session: linking eScience engineers and applied mathematicians |
| 2021-07-22 | Floris-Jan Willemsen | Bayesian Optimization for Auto-Tuning GPU kernels |
| 2021-09-02 | Alessio & Ben | Preparations for Kernel Tuner tutorial |
| 2021-09-23 | Niels Drost | SSI Optimize call |
| 2021-10-14 | Jens Wehner | GPU parallelisation and scheduling in a quantum chemistry software, a simple attempt |
| 2021-11-04 | SIG | Projects update session |
| 2021-11-25 | Gijs van den Oord | Using OpenACC to accelerate an ocean model |
| Date | Presenter | Topic |
|---|---|---|
| 2020-01-23 | Merijn Verstraaten | Futhark: a Functional Array Language |
| 2020-02-13 | Felipe Zapata | An Eigen-Cuda interface for Tensor-matrix multiplications |
| 2020-03-05 | Ben van Werkhoven | New features in CUDA |
| 2020-03-26 | Alessio Sclocco | GPU workshops/hackatons/trainings |
| 2020-05-07 | Ben van Werkhoven | Auto-tuning research update |
| 2020-05-28 | Alessio Sclocco | News roundup |
| 2020-06-18 | Victor Azizi and Gijs van den Oord | Medina, atmospheric chemistry on the GPU |
| 2020-07-09 | Sagar Dolas (SURF) | The future of Supercomputing |
| 2020-09-10 | Dennis Klein (Student VU) | Survey of optimization methods for auto-tuning energy efficiency |
| 2020-10-01 | SIG | Project updates session |
| 2020-10-22 | Hanno Spreeuw | Parallellisation of kappa, sigma clipping of radio astronomical images by distributing rows of subimages over multiple CPU cores using Ray |
| 2020-11-12 | Alessio Sclocco | Porting the FESOM 2.0 model to GPUs |
| 2020-12-03 | Federico Fadda (UvA) | GPU simulation of active Brownian particle interactions via the Lennard-Jones force |
| Date | Presenter | Topic |
|---|---|---|
| 2019-01-28 | Souley Madougou | Introduction and overview of earlier GPU-related research |
| 2019-02-25 | Daan Siepelinga (Student VU) | A performance analysis of auto-tuned matrix multiplication GPU kernels |
| 2019-03-21 | Ehsan Sharifi (Student VU) | A survey on solutions for improving energy-efficiency in GPUs |
| 2019-04-25 | Hanno Spreeuw | Running your GPU based applications from Singularity containers |
| 2019-05-16 | Johan Hidding | Inline FFTs and code generators |
| 2019-06-27 | Stephen Swatman (Student UvA) | Performance Engineering in the ATLAS Particle Physics Experiment |
| 2019-07-18 | Thom Visser (Student UvA) | Building Predictive Models for Optimal GPU Kernel Configurations |
| 2019-08-29 | Ehsan Sharifi (Student VU) | Auto-tuning GPU Kernels for Energy Efficiency |
| 2019-09-19 | Hanno Spreeuw | Self-calibration using SAGECal on an NVIDIA Jetson Nano |
| 2019-10-10 | Ben van Werkhoven | best practices when benchmarking cuda applications |
| 2019-10-31 | Hanno Spreeuw | Conclusions from running SAGECal on the Nano and Intel Xeon E5-2660v3 |
| 2019-11-14 | Ben van Werkhoven | Lessons learned in a decade of research software engineering GPU applications |
| 2019-12-12 | Stijn Heldens | Highlights from Supercomputing 2019 |