Adding deterministic mode

Author: ChSonnabend

GPU/GPUTracking/Global/GPUChainTrackingClusterizer.cxx

@@ -664,7 +664,7 @@ int32_t GPUChainTracking::RunTPCClusterizer(bool synchronizeOutput)
     int32_t maxThreads = mRec->getNKernelHostThreads(true);
     // bool recreateMemoryAllocator = false;
     mRec->runParallelOuterLoop(doGPU, numLanes, [&](uint32_t lane) {
-      nnApplications[lane].init(nn_settings);
+      nnApplications[lane].init(nn_settings, GetProcessingSettings().deterministicGPUReconstruction);
       if (nnApplications[lane].mModelsUsed[0]) {
         SetONNXGPUStream(*(nnApplications[lane].mModelClass).getSessionOptions(), lane, &deviceId);
         (nnApplications[lane].mModelClass).setDeviceId(deviceId);

GPU/GPUTracking/TPCClusterFinder/GPUTPCNNClusterizerHost.cxx

@@ -28,7 +28,7 @@
 
 using namespace o2::gpu;
 
-void GPUTPCNNClusterizerHost::init(const GPUSettingsProcessingNNclusterizer& settings)
+void GPUTPCNNClusterizerHost::init(const GPUSettingsProcessingNNclusterizer& settings, bool useDeterministicMode)
 {
   std::string class_model_path = settings.nnClassificationPath, reg_model_path = settings.nnRegressionPath;
   std::vector<std::string> reg_model_paths_local;
@@ -54,7 +54,7 @@ void GPUTPCNNClusterizerHost::init(const GPUSettingsProcessingNNclusterizer& set
     {"intra-op-num-threads", std::to_string(settings.nnInferenceIntraOpNumThreads)},
     {"inter-op-num-threads", std::to_string(settings.nnInferenceInterOpNumThreads)},
     {"enable-optimizations", std::to_string(settings.nnInferenceEnableOrtOptimization)},
-    {"deterministic-compute", std::to_string(settings.nnInferenceUseDeterministicCompute)}, // TODO: This unfortunately doesn't guarantee determinism (25.07.2025)
+    {"deterministic-compute", std::to_string(useDeterministicMode? 1 : settings.nnInferenceUseDeterministicCompute)}, // TODO: This unfortunately doesn't guarantee determinism (25.07.2025)
     {"enable-profiling", std::to_string(settings.nnInferenceOrtProfiling)},
     {"profiling-output-path", settings.nnInferenceOrtProfilingPath},
     {"logging-level", std::to_string(settings.nnInferenceVerbosity)},

GPU/GPUTracking/TPCClusterFinder/GPUTPCNNClusterizerHost.h

@@ -45,9 +45,9 @@ class GPUTPCNNClusterizerHost
 {
  public:
   GPUTPCNNClusterizerHost() = default;
-  GPUTPCNNClusterizerHost(const GPUSettingsProcessingNNclusterizer& settings) { init(settings); }
+  GPUTPCNNClusterizerHost(const GPUSettingsProcessingNNclusterizer& settings, bool useDeterministicMode = false) { init(settings, useDeterministicMode); }
 
-  void init(const GPUSettingsProcessingNNclusterizer&);
+  void init(const GPUSettingsProcessingNNclusterizer&, bool = false);
   void initClusterizer(const GPUSettingsProcessingNNclusterizer&, GPUTPCNNClusterizer&);
   void createBoundary(GPUTPCNNClusterizer&);
   void createIndexLookup(GPUTPCNNClusterizer&);