DIPSA: Data-Intensive Parallel and Scaleable Algorithms
The DIPSA group at Queen’s University, led by Hans Vandierendonck, specialises in creating high-performance, parallel computing solutions for data-heavy applications across scientific computing and machine learning.
Our research focuses on optimising both computing systems and algorithms across four main areas:
Designing algorithms and systems capable of handling massive, rapidly growing graph datasets, specifically addressing challenges like memory locality and combinatorial explosion. READ MORE.
Improving system speed, power, and energy efficiency by strategically trading off exact computational precision in applications where absolute accuracy is unnecessary. READ MORE.
Developing solutions for new machine learning tasks, building upon their foundational research in transprecise computing and graph algorithms. READ MORE.
Improving parallel scalability of scientific computations by speculating around communication bottlenecks.
Latest Posts
- User behaviour on Kelvin2 HPC
1. User Job Distribution: A Heavy-Tailed Workload The cluster’s workload is heavily concentrated among a… Read more: User behaviour on Kelvin2 HPC - Analysis of Kelvin2 SLURM logs1. What predicts the waiting time? The factors that best predict how long a job… Read more: Analysis of Kelvin2 SLURM logs
- The Role of Research Software in Sustainable ComputingOn 29 April 2026, during the Software Sustainability Institute’s (SSI) Collaborations Workshop 2026 (CW26) organised… Read more: The Role of Research Software in Sustainable Computing
- Introducing URJAIn the world of high-performance computing, we often prioritise speed above all else. But as… Read more: Introducing URJA
- ParaGrapher: A Parallel and Distributed Graph Loading Library for Large-Scale Compressed Graphs – BigData’25 (Short Paper)DOI: 10.1109/BigData66926.2025.11401782 Whereas the literature describes an increasing number of graph algorithms, loading graphs remains… Read more: ParaGrapher: A Parallel and Distributed Graph Loading Library for Large-Scale Compressed Graphs – BigData’25 (Short Paper)
- Talk and poster presentation at the NI-HPC 2025 conferenceWe attended the NI-HPC conference held on 4 November 2025 at Riddel Hall, Queen’s University,… Read more: Talk and poster presentation at the NI-HPC 2025 conference
- OrbitSI is now on PyPiOrbitSI is an open-source Python framework designed to efficiently solve the subgraph isomorphism enumeration problem,… Read more: OrbitSI is now on PyPi
- Wasp: Efficient Asynchronous Single-Source Shortest Path on Multicore Systems via Work Stealing – SC’25DIPSA presents a research paper at SC’25!
- New Research Paper – A Novel Multi-View Perspective on XAI for Time Series Classification 🤖🔍The “black box” nature of many AI models causes hesitation in trusting their predictions, especially… Read more: New Research Paper – A Novel Multi-View Perspective on XAI for Time Series Classification 🤖🔍
- Invited Talk – Efficient Computation through Tuned Approximation by David Keyes21 February 2024 Abstract Numerical software is being reinvented to provide opportunities to tune dynamically the accuracy… Read more: Invited Talk – Efficient Computation through Tuned Approximation by David Keyes
