Bug fixes

Author: ChSonnabend

GPU/GPUTracking/Global/GPUChainTrackingClusterizer.cxx

@@ -1023,7 +1023,7 @@ int32_t GPUChainTracking::RunTPCClusterizer(bool synchronizeOutput)
             // Filling the data
             if (mRec->IsGPU()) {
               // Fills element by element of each input matrix -> better parallelizability, but worse on CPU due to unnecessary computations
-              runKernel<GPUTPCNNClusterizerKernels, GPUTPCNNClusterizerKernels::fillInputNNGPU>({GetGrid(iSize * clustererNNShadow.mNnClusterizerElementSize, lane), krnlRunRangeNone}, iSector, clustererNNShadow.mNnInferenceInputDType, propagateMCLabels, batchStart);
+              runKernel<GPUTPCNNClusterizerKernels, GPUTPCNNClusterizerKernels::fillInputNNGPU>({GetGrid(iSize * clustererNNShadow.mNnClusterizerRowTimeSizeFull, lane), krnlRunRangeNone}, iSector, clustererNNShadow.mNnInferenceInputDType, propagateMCLabels, batchStart);
             } else {
               // Fills the whole input matrix at once -> better performance on CPU, but worse parallelizability
               runKernel<GPUTPCNNClusterizerKernels, GPUTPCNNClusterizerKernels::fillInputNNCPU>({GetGrid(iSize, lane), krnlRunRangeNone}, iSector, clustererNNShadow.mNnInferenceInputDType, propagateMCLabels, batchStart);

GPU/GPUTracking/TPCClusterFinder/GPUTPCNNClusterizerKernels.cxx

@@ -335,7 +335,7 @@ GPUdii() void GPUTPCNNClusterizerKernels::Thread<GPUTPCNNClusterizerKernels::pub
     return;
   }
 
-  tpc::ClusterNative* clusterOut = (withMC) ? nullptr : clusterer.mPclusterByRow;
+  tpc::ClusterNative* clusterOut = clusterer.mPclusterByRow;
 
   // LOG(info) << glo_idx << " -- " << model_output_index << " / " << clustererNN.outputDataReg1.size() << " / " << clustererNN.mNnClusterizerModelReg1NumOutputNodes << " -- " << clusterer.peakPositions.size() << " -- " << clusterer.centralCharges.size();