Login

Alice Weekly Meeting: Software for Hardware Accelerators

→ Europe/Zurich
ALICE GPU Meeting
Zoom Meeting ID
61230224927
Host
David Rohr
Useful links
Join via phone
Zoom URL
    • 1
      Discussion
      Speaker: David Rohr (CERN)

      Color code: (critical, news from this week: blue, news from last week: purple, no news: black)

      Sync reconstruction

       

      Async reconstruction

      • Need to investigate short GPU stall problem.
      • Limiting factor for pp workflow is now the TPC time series, which is to slow and creates backpressure (costs ~20% performance on EPNs). Enabled multi-threading as recommended by Matthias - need to check if it works.
      • Will tune existing 16-core settings, add a SITEARCH for 16core CPU, and 16coreCPU + generic NVIDIA / AMD GPU, like for 8 core.
      • Will retune EPN async workflow for TPC + ITS on GPU on 2025 data.

       

      GPU ROCm / compiler topics:

      • Problem with building ONNXRuntime with MigraphX support.
      • Need to find a way to build ONNXRuntime with support for CUDA and for ROCm.
      • Try to find a better solution for the problem with __device__ inline functions leaking symbols in the host code.
      • Need to check ROCm 7.2 corrtecness.
      • Need to understand deterministic mode issue on AMD Pro 9700 reported by Oliver - Status?

       

      TPC / GPU Processing 

      • WIP: Use alignas() or find a better solution to fix alignment of monte carlo labels: https://its.cern.ch/jira/browse/O2-5314
      • Need to check the problem with ONNX external memory allocator.
      • Next high priority topic: Improvements for cluster sharing and cluster attachment at lower TPC pad rows. PR: https://github.com/AliceO2Group/AliceO2/pull/14542
      • Check for unnecessary f64 instructions in GPU code.
      • PR with changes for qTot-reading / dEdx code, to support >16 bit range for saturated signals: merged

       

      Other topics:

      • Need to bump ONNXRuntime to 1.24, Giulio is checking, needed for ROCm 7.2 - Status?
      • GCC bump - Status?

       

      EPN GPU Topics:

       

    • 2
      TPC ML Clustering
      Speaker: Christian Sonnabend (CERN, Heidelberg University (DE))

      Tangent vector application in track seeding

      • Neural network can predict tangent vector to track trajectory -> This can be used in seeding
      • Network predicts sector-local dy/dx and dz/dx => In neighbour finding we can use e.g. y + NN_dydx*dx

       

      Implemented. Draft-PR for discussion: https://github.com/AliceO2Group/AliceO2/pull/15582

      So far reproducing the same number of tracks within 0.5‰. Slow-down due to additional computations: 2.93±0.01 s/TF (NN class + reg, epn000) -> 3.15±0.013 s/TF (NN class + reg + mom vector, epn000). (Default reco is 2.06±0.01 s/TF)

      Need to do MC investigation now.

       

      LHCP proceedings: https://alice-conferences.web.cern.ch/node/70501

      CHEP proceedings: https://alice-conferences.web.cern.ch/node/70535

      ICHEP slides: In preparation

    • 3
      GPU Parameter Optimizations
      Speaker: Gabriele Cimador (CERN, Università and INFN Torino)
    • 4
      Efficient Data Structures
      Speaker: Dr Oliver Gregor Rietmann (CERN)
    • 5
      TPC Clusterization / OpenCL / Highly Ionizing Particles
      Speaker: Felix Weiglhofer (CERN)
    • 6
      ITS Tracking
      Speakers: Felix Schlepper (CERN, Heidelberg University (DE)), Gabriele Cimador (CERN, Università and INFN Torino), Matteo Concas (CERN)
    • 7
      System Run Coordination Topics
      Speaker: Ernst Hellbar