Color code: (critical, news during the meeting: green, news from this week: blue, news from last week: purple, no news: black)
Run Coordination / Framework Topics:
- Stabilize calibration / fix EoS: New scheme: https://its.cern.ch/jira/browse/O2-4308:
- Using 20/25 and 20/40 as EndOfStream timeouts.
- Improvement deployed to treat all sporadic messages as calibration data (prevents dropping calibration data that was started to process before EndOfStream but finished after the first timeout).
- Still missing: Processes should go to error when the second timeout expires - Will indicate that calibration failed, and will take out servers from the run which did not finish in a clean state - needed for future START/STOP/START development.
- PR with InfoLogger improvements still WIP - Status?
- Processes crashing at shutdown if STOP timeout was short, not clear if related, but should be checked. This still seems to happen, e.g. in the STOP tests with 1/1 and 5/10.
- Fix problem with ccdb-populator and cpv calib: no idea yet - since Ole left, someone else will have to take care.
- TF-status message (from https://github.com/AliceO2Group/AliceO2/pull/13495) sent by readout-proxy.
- Trying to get devices with Lifetime::Sporadic / Lifetime::Timer inputs last, to work around the issue mentioned yesterday by Ruben
AliECS related topics:
- Extra env var field still not multi-line by default., created https://its.cern.ch/jira/browse/OGUI-1624. Deployed by FLP, seems to work
EPN major topics:
- Fast movement of nodes between async / online without EPN expert intervention.
- 2 goals I would like to set for the final solution:
- It should not be needed to stop the SLURM schedulers when moving nodes, there should be no limitation for ongoing runs at P2 and ongoing async jobs.
- We must not lose which nodes are marked as bad while moving.
- Interface to change SHM memory sizes when no run is ongoing. Otherwise we cannot tune the workflow for both Pb-Pb and pp: https://alice.its.cern.ch/jira/browse/EPN-250
- Lubos to provide interface to querry current EPN SHM settings - ETA July 2023, Status?
- Improve DataDistribution file replay performance, currently cannot do faster than 0.8 Hz, cannot test MI100 EPN in Pb-Pb at nominal rate, and cannot test pp workflow for 100 EPNs in FST since DD injects TFs too slowly. https://alice.its.cern.ch/jira/browse/EPN-244 NO ETA.
- DataDistribution distributes data round-robin in absense of backpressure, but it would be better to do it based on buffer utilization, and give more data to MI100 nodes. Now, we are driving the MI50 nodes at 100% capacity with backpressure, and then only backpressured TFs go on MI100 nodes. This increases the memory pressure on the MI50 nodes, which is anyway a critical point. https://alice.its.cern.ch/jira/browse/EPN-397
- TfBuilders should stop in ERROR when they lose connection.
- Allow epn user and grid user to set nice level of processes: https://its.cern.ch/jira/browse/EPN-349
- Slurm bump
Other EPN topics:
GPU Benchmarks in HS23 Contribution from ALICE
- Will have a meeting with Gabriele and Domenico today to discuss details.
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.
- Managed to run offline build in singularity container on my Laptop with NVIDIA GPU.
- Waiting for gpu-system.sh to be updated (needs new aliBuild) to build with NVIDIA A100 support, then we can test on NERST Perlmutter. At least I can not start the standalone benchmark on Perlmutter, NVIDIA library issues solved.
- Problem was due to older ITS code (from current async build) using special NVIDIA tracing libraries, which were moved to header-only with CUDA 12.8, so the problem was already fixed in the latest O2/dev.
GPU ROCm / compiler topics:
- Issues that disappeared but not yet understood: random server reboot with alma 9.4, miscompilation with ROCm 6.2, GPU getting stuck when DMA engine turned off, MI100 stalling with ROCm 5.5.
- Problem with building ONNXRuntime with MigraphX support, to be checked.
- 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.
- LLVM Bump to 20.1: status?
- ROCm 6.4.1 status:
- AMD is checking the reproducer. I have some idea how to narrow down where it miscompiles using different compile flags in per-kernel mode.
- New gpu-system package:
- After some alibuild refactoring, needed more fixes. Now, new aliBuild tagged. Sergio is debugging some issues on MacOS, then we should be able to bump it everywhere.
- Improved Standalone Benchmark CI, now compiles with -Werror and checks for CMake errors, suppressed some warnings from clang / nvcc / CMake.
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
- Waiting for TPC to fix bogus TPC transformations for good, then we can revert the workaround.
- Waiting for TPC to check PR which uses full cluster errors including average charge and occupancy map errors during seeding.
- Final solution: merging transformation maps on the fly into a single flat object: Still WIP
- Pending OpenCL2 issues:
- printf not working due to confirmed bug in clang, fix is being prepared. Prevents further debugging for now.
- Crash in merger, which can be worked around by disabling clang SPIRV optimization. Probably bug in clang, but need to fix printf first to debug.
- Also with optimization disabled, crashing later in TPC merging, need printf to debug.
- Felix debugged the OpenCL clusterization problem to be due to off-by-one offset in NoiseSuppression. Need to check how that can happen only in OpenCL.
- Next high priority topic: Improvements for cluster sharing and cluster attachment at lower TPC pad rows.
- Need to check the problem with ONNX external memory allocator.