Skip to content

NN Clusterizer: Bug-fix for memory allocation #14554

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ChSonnabend merged 1 commit into from
Jul 31, 2025
+18 −16
Merged

NN Clusterizer: Bug-fix for memory allocation #14554

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 18 additions & 16 deletions GPU/GPUTracking/Global/GPUChainTrackingClusterizer.cxx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,26 +643,28 @@ int32_t GPUChainTracking::RunTPCClusterizer(bool synchronizeOutput)

// Maximum of 4 lanes supported
HighResTimer* nnTimers[12];
if (GetProcessingSettings().nn.applyNNclusterizer && GetProcessingSettings().debugLevel >= 1) {
nnTimers[0] = &getTimer<GPUTPCNNClusterizer, 0>("GPUTPCNNClusterizer_ONNXClassification_0_", 0);
nnTimers[1] = &getTimer<GPUTPCNNClusterizer, 1>("GPUTPCNNClusterizer_ONNXRegression_1_", 1);
nnTimers[2] = &getTimer<GPUTPCNNClusterizer, 2>("GPUTPCNNClusterizer_ONNXRegression2_2_", 2);
nnTimers[3] = &getTimer<GPUTPCNNClusterizer, 3>("GPUTPCNNClusterizer_ONNXClassification_0_", 3);
nnTimers[4] = &getTimer<GPUTPCNNClusterizer, 4>("GPUTPCNNClusterizer_ONNXRegression_1_", 4);
nnTimers[5] = &getTimer<GPUTPCNNClusterizer, 5>("GPUTPCNNClusterizer_ONNXRegression2_2_", 5);
nnTimers[6] = &getTimer<GPUTPCNNClusterizer, 6>("GPUTPCNNClusterizer_ONNXClassification_0_", 6);
nnTimers[7] = &getTimer<GPUTPCNNClusterizer, 7>("GPUTPCNNClusterizer_ONNXRegression_1_", 7);
nnTimers[8] = &getTimer<GPUTPCNNClusterizer, 8>("GPUTPCNNClusterizer_ONNXRegression2_2_", 8);
nnTimers[9] = &getTimer<GPUTPCNNClusterizer, 9>("GPUTPCNNClusterizer_ONNXClassification_0_", 9);
nnTimers[10] = &getTimer<GPUTPCNNClusterizer, 10>("GPUTPCNNClusterizer_ONNXRegression_1_", 10);
nnTimers[11] = &getTimer<GPUTPCNNClusterizer, 11>("GPUTPCNNClusterizer_ONNXRegression2_2_", 11);
}

if (GetProcessingSettings().nn.applyNNclusterizer) {
int32_t deviceId = -1;
int32_t numLanes = GetProcessingSettings().nTPCClustererLanes;
int32_t maxThreads = mRec->getNKernelHostThreads(true);
// bool recreateMemoryAllocator = false;

if (GetProcessingSettings().debugLevel >= 1) {
nnTimers[0] = &getTimer<GPUTPCNNClusterizer, 0>("GPUTPCNNClusterizer_ONNXClassification_0_", 0);
nnTimers[1] = &getTimer<GPUTPCNNClusterizer, 1>("GPUTPCNNClusterizer_ONNXRegression_1_", 1);
nnTimers[2] = &getTimer<GPUTPCNNClusterizer, 2>("GPUTPCNNClusterizer_ONNXRegression2_2_", 2);
nnTimers[3] = &getTimer<GPUTPCNNClusterizer, 3>("GPUTPCNNClusterizer_ONNXClassification_0_", 3);
nnTimers[4] = &getTimer<GPUTPCNNClusterizer, 4>("GPUTPCNNClusterizer_ONNXRegression_1_", 4);
nnTimers[5] = &getTimer<GPUTPCNNClusterizer, 5>("GPUTPCNNClusterizer_ONNXRegression2_2_", 5);
nnTimers[6] = &getTimer<GPUTPCNNClusterizer, 6>("GPUTPCNNClusterizer_ONNXClassification_0_", 6);
nnTimers[7] = &getTimer<GPUTPCNNClusterizer, 7>("GPUTPCNNClusterizer_ONNXRegression_1_", 7);
nnTimers[8] = &getTimer<GPUTPCNNClusterizer, 8>("GPUTPCNNClusterizer_ONNXRegression2_2_", 8);
nnTimers[9] = &getTimer<GPUTPCNNClusterizer, 9>("GPUTPCNNClusterizer_ONNXClassification_0_", 9);
nnTimers[10] = &getTimer<GPUTPCNNClusterizer, 10>("GPUTPCNNClusterizer_ONNXRegression_1_", 10);
nnTimers[11] = &getTimer<GPUTPCNNClusterizer, 11>("GPUTPCNNClusterizer_ONNXRegression2_2_", 11);
}

mRec->runParallelOuterLoop(doGPU, numLanes, [&](uint32_t lane) {
nnApplications[lane].init(nn_settings, GetProcessingSettings().deterministicGPUReconstruction);
if (nnApplications[lane].mModelsUsed[0]) {
Expand Down Expand Up @@ -708,7 +710,7 @@ int32_t GPUChainTracking::RunTPCClusterizer(bool synchronizeOutput)
LOG(info) << "(ORT) Allocated ONNX stream for lane " << lane << " and device " << deviceId;
}
});
mRec->runParallelOuterLoop(doGPU, NSECTORS, [&](uint32_t sector) {
for (int32_t sector = 0; sector < NSECTORS; sector++) {
GPUTPCNNClusterizer& clustererNN = processors()->tpcNNClusterer[sector];
GPUTPCNNClusterizer& clustererNNShadow = doGPU ? processorsShadow()->tpcNNClusterer[sector] : clustererNN;
int32_t lane = sector % numLanes;
Expand All @@ -725,7 +727,7 @@ int32_t GPUChainTracking::RunTPCClusterizer(bool synchronizeOutput)
AllocateRegisteredMemory(clustererNN.mMemoryId);
// nnApplications[lane].createBoundary(clustererNNShadow);
// nnApplications[lane].createIndexLookup(clustererNNShadow);
});
}
if (doGPU) {
WriteToConstantMemory(RecoStep::TPCClusterFinding, (char*)&processors()->tpcNNClusterer - (char*)processors(), &processorsShadow()->tpcNNClusterer, sizeof(GPUTPCNNClusterizer) * NSECTORS, mRec->NStreams() - 1, &mEvents->init);
}
Expand Down