Assign final sum in Cuda parallel_scan ThreadVectorRange

masterleinad · Sep 19, 2023 · fb20a48 · fb20a48
1 parent 4a819b6
commit fb20a48
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/core/src/Cuda/Kokkos_Cuda_Team.hpp b/core/src/Cuda/Kokkos_Cuda_Team.hpp
@@ -815,6 +815,7 @@ parallel_scan(const Impl::ThreadVectorRangeBoundariesStruct<
       }
 
       ))
+  reducer.reference() = accum;
 }
 
 //----------------------------------------------------------------------------