Alice Weekly Meeting: Software for Hardware Accelerators / PDP-SRC

Wednesday 30 Jul 2025, 10:00 → 11:00 Europe/Zurich

1 Discussion

Speakers: David Rohr (CERN), Giulio Eulisse (CERN)

2 Following up JIRA tickets

Speaker: Ernst Hellbar (CERN)

3 TPC ML Clustering

Speaker: Christian Sonnabend (CERN, Heidelberg University (DE))

Framework

• Added GPU timer to ONNX inference for profiling
• Added deconvolution flags to NN inference for exact matching with GPU CF

 

Physics

• Cluster attachment efficiency vs. fake rate for different network inputs and thresholds
  • Attachment efficiency = (correctly attached cls NN / total cls) * (correctly attached cls NN / correctly attached cls GPU CF)

 

• Network outperforms GPU CF under all thresholds and input sizes. Choice for threshold is determined by number of correctly attached clusters in the next plot
• Significant benefits from using 3D networks
  
  
• Number of correctly attached clusters

• Threshold choice for classification network:
  • <= 0.01: Almost no loss in number of correctly attached clusters
  • >0.01 && <0.1: Maximum loss of 5% correctly attached clusters, but can lead to 18% savings in total clusters (see next plot)
    
    
• Number of total clusters

• CoG (pad) resolution as a function of occupancy for different network sizes (2 to 5 hidden layers; 16, 32, 64, 128 neurons per layer)

• More layers work better
• Network with L5 and N128 -> Not great performance, reason: Overtraining! Immediately visible in the logs. Validation loss goes up while training loss goes down / remains constant.
  -> Improvement for the future: Save network at best training loss, best validation loss and network after all epochs are done.

4 ITS Tracking

Speaker: Matteo Concas (CERN)

5 TPC Track Model Decoding on GPU

Speaker: Gabriele Cimador (Universita e INFN Torino (TO))

6 Efficient Data Structures

Speaker: Dr Oliver Gregor Rietmann (CERN)

7 Following up GPU to-dos

Speaker: Dr Vikas Singhal (Department of Atomic Energy (IN))

8 TPC Clusterization / OpenCL / Highly Ionizing Particles

Speaker: Felix Weiglhofer (Goethe University Frankfurt (DE))