How to Maximize your Science per Watt: Energy-Efficient GPU Computing at ISC 2026
GPUs power many of today’s large-scale scientific simulations, data analysis workflows, and AI applications. However, all that computing power comes at a ...
Stijn Heldens
I’m a Dutch computer scientist, currently working as a Research Software Engineer (RSE) at the Netherlands eScience Center and also serving as a visiting researcher at the University of Amsterdam. I enjoy scientific research where my interests lie in high-performance computing, with a particular focus on parallel algorithms, distributed systems, programming languages/compilers, and GPU programming.
Accuracy-Aware Mixed-Precision GPU Auto-Tuning
February 2, 2026 - IEEE Transactions on Parallel and Distributed Systems (TPDS) has just published our latest research paper, “Accuracy-Aware Mixed-Precisio...
Kernel Float: Unlocking Mixed-Precision GPU Programming
December 4, 2025 - ACM Transactions on Mathematical Software (TOMS) has just published our latest research paper, “Kernel Float: Unlocking Mixed-Precision GP...
Stijn Heldens wins ASCI Best PhD Thesis Award 2024
May 23, 2025 – I was honored to receive ASCI’s Best PhD Thesis 2024 Award at CompSys’25! 🏆 Huge thanks to everyone at ASCI for the award and the CompSys25 o...
Best Paper Award at Euro-PAR 2024: Bringing Auto-tuning to HIP
August 28, 2024 — I traveled to Madrid, Spain, to present our paper titled “Bringing Auto-tuning to HIP: Analysis of Tuning Impact and Difficulty on AMD and ...
CompSys Best Presentation Award for Kernel Launcher
May 27, 2024 - At the Dutch national CompSys conference, I gave a presentation about the paper “Kernel Launcher: C++ library for creating optimal-performance...
Stijn Heldens receives PhD degree
March 6, 2024 — Stijn Heldens has successfully defended his PhD thesis titled “Parallel Programming Systems for Scalable Scientific Computing” at the Agniete...
Kernel Launcher: C++ library for creating optimal-performance portable CUDA applications
IPDPS 2023 - I traveled to St. Petersburg Florida to present our new paper on Kernel Launcher at iWAPT2023, the International Workshop on Automatic Performan...
Lightning: Scaling the GPU Programming Model Beyond a Single GPU
IPDPS 2022 - I presented my paper on Lightning, a programming model that allows you to create applications for GPU clusters in way that is very similar to de...