ipeweb/templates/README.txt

Texte für PDV-Webseiten:

Abfrage:

- Anwendungsgebiete (In welchen Gebieten, insb. aus Sicht der Physik, forschen wir?)

	Aktuell: 
	- DAQ-Systems, data management and slow control for Neutrinophysics 
	- Scientific computing for high-speed tomographgy in Photon science and material science
	

- Technologien (Welche Technologien entwickeln wir?)

	s.u.

- Projekte (Welche Projekte sollen auf der Website dediziert erwähnt werden?)

	Eine Liste aktuelle und abgeschlossenen Projekte 
	https://ufo.kit.edu/dis/index.php/project/

- Technologietransfer-Projekte (Gleiche Frage wie bei Projekten)

	Gibt es aktuell nicht / ist auch nichts absehbar

- Infrastruktur (Welche Infrastruktur betreiben wir, die sich lohnt mit Bild auf der Website zu nennen?)

	Parallel computing lab
	- GPU Computing Cluster     
	- Real-time Storage Systems
	- High-speed Imaging Systems

	DAQ+ slow control lab
	- FPGA-based DAQ systems
	- KATRIN test setup  – A test system for the KATRIN Detector data acquisition system
	- NI based slow control systems



Progress of detector technology in recent years enables largely increased temporal and spatial resolution of scientific experiments. This innovation has led to large amounts of data that need to be transferred, processed and analyzed. The PDV group aims to apply latest technologies in order to face the challenges of data-intensive sciences.

Core Technologies: 
- high-throughput interconnects to link detector systems, computing nodes and archival
- scientific GPU computing + hardware-aware programming and optimizations
- IT infrastructure for scientific experiments and cloud-based services
- Experimental control, data management and automation


Results:


Reviewing GPU architectures to build efficient back projection for parallel geometries 
https://link.springer.com/article/10.1007/s11554-019-00883-w
26.6.2019

A survey of parallel architectures presented during the past 10 years. 

Similarities and differences between these architectures are analyzed and we highlight how specific features can be used to enhance the reconstruction performance. In particular, we build a performance model to find hardware hotspots and propose several optimizations to balance the load between texture engine, computational and special function units, as well as different types of memory maximizing the utilization of all GPU subsystems in parallel. We further show that targeting architecture-specific features allows one to boost the performance 2–7 times compared to the current state-of-the-art algorithms used in standard codes.



Balancing Load of GPU Subsystems to Accelerate Image Reconstruction in Parallel Beam Tomography
https://ieeexplore.ieee.org/document/8645862
21.2.2019

How to implement the algorithm on nowadays GPGPU architectures efficiently? 

We present two highly optimized algorithms to perform back projection on parallel hardware. One is relying on the texture engine to perform reconstruction, while another one utilizes the core computational units of the GPU. Both methods outperform current state-of-the-art techniques found in the standard reconstructions codes significantly. Finally, we propose a hybrid approach combining both algorithms to better balance load between GPU subsystems. It further boosts the performance by about 30% on NVIDIA Pascal micro-architecture.



Investigation of the flow structure in thin polymer films using 3D µPTV enhanced by GPU


Digital visual exploration library

WAVE: A 3D Online Previewing Framework for Big Data Archives.


Parasitoid biology preserved in mineralized fossils


The Common Data Acquisition Platform in the Helmholtz Association


Evaluation of GPUs as a level-1 track trigger for the High-Luminosity LHC


The NOVA project: maximizing beam time efficiency through synergistic analyses of SRμCT data.


Real-time image-content-based beamline control for smart 4D X-ray imaging


High-throughput data acquisition and processing for real-time x-ray imaging

A scalable DAQ system with high-rate channels and FPGA- and GPU-Trigger for the dark matter experiment EDELWEISS-III

KITcube – a mobile observation platform for convection studies deployed during HyMeX

A unified energy footprint for simulation software

Focal-plane detector system for the KATRIN experiment

UFO: A Scalable GPU-based Image Processing Framework for On-line Monitoring




NOVA Paper 

WAVE

KITcube

UFO Framework 

KATRIN Detector Paper 

HDRI Paper

Auger Paper