Research

Data Flow Processing for DAQ Systems

New advances in the field of telecommunications are leading to increasing demands on the bandwidth of digital signal processing. New standards are capable of transmitting sub-terabit data rates. Characterization of such systems requires processing, validation and storage of the generated measurement data. Stream processors play a key role in the development of data acquisition systems (DAQ systems). At ITIV, we aim to develop a framework for reconfigurable DAQ systems that will enable the specification of future transmission standards.

Implementation of GNNs on Hardware Accelerators

Graph Neural Networks (GNNs) extend conventional deep learning methods to graphical structures. Their generalized formulation opens up new possibilities in application areas such as image processing, monitoring or network analysis. Especially when implementing them in real-time applications, bandwidth and memory latency are significant bottlenecks. Therefore, the use of reprogrammable hardware platforms such as FPGAs is a central topic in current studies. At ITIV, we are trying to improve the usability of GNNs in embedded systems.

Data-driven design of trigger systems

Particle accelerators generate huge amounts of data during their experiments and therefore require so-called trigger systems. These systems implement filter mechanisms to distinguish between relevant and irrelevant detector events. Varying hyperparameters during physics experiments require automated training and reconfiguration of the firmware in the detector. Here at ITIV, we are investigating measures to adapt latency-optimized trigger systems to changing environmental variables.

Teaching

LV 231162 Practical course System-on-Chip

Student Work
Title	Type
Decoding Decay - Real-Time Particle Detection from Point Clouds	Masterarbeit
Compiler-Based Integration of Neural Network Accelerators	Masterarbeit

HIWI Jobs
Title
Empowering Tomorrow's Engineers: MLIR-Based Toolchain for Transforming Python Neural Networks into Verilog Hardware

Publications

2026

PhD Theses

Template-Based Deployment for Real-Time Deep Learning on Point Clouds. PhD dissertation
Neu, M.
2026, September 3. Karlsruher Institut für Technologie (KIT). doi:10.5445/IR/1000196764

Journal Articles

Development of deep neural network first-level hardware track trigger for the Belle II experiment
Liu, Y.-X.; Koga, T.; Bae, H.; Yang, Y.; Kiesling, C.; Meggendorfer, F.; Unger, K.; Hiesl, S.; Forsthofer, T.; Ishikawa, A.; Ahn, Y.; Ferber, T.; Haide, I.; Heine, G.; Hsu, C.-L.; Little, A.; Nakazawa, H.; Neu, M.; Reuter, L.; Savinov, V.; Unno, Y.; Yuan, J.; Xu, Z.
2026. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1084, Art.-Nr.: 171248. doi:10.1016/j.nima.2025.171248

Conference Papers

Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science
Neu, M.; Baptist, F.; Lobmaier, T.; Papagno, F.; Ferber, T.; Becker, J.
2026. 2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 289–293, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/FCCM68464.2026.00074