[TEST]UPSTREAM: Pick some source changes from 48080d0a97

* Sync new folder structure

AMSS_NCKU_source/makefile.inc

@@ -3,8 +3,35 @@
 ## filein  = -I/usr/include/ -I/usr/include/openmpi-x86_64/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
 ## LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
 
+SOURCE_DIRS = . \
+              ./AHF_Direct \
+              ./BSSN \
+              ./BSSN_GPU \
+              ./cgh \
+              ./Check_Point \
+              ./Derivative \
+              ./Initial_Data_Solver \
+              ./KO_dissipation \
+              ./misc \
+              ./Monitor \
+              ./Null_Evolve \
+              ./Parallel \
+              ./Patch \
+              ./Psi4 \
+              ./Read_and_Write \
+              ./Runge_Kutta \
+              ./Scalar \
+              ./Shell_Patch \
+              ./Special_Function \
+              ./Surface_Integral \
+              ./System_Performance \
+              ./Two_Puncture \
+              ./Variable \
+              ./Z4C
+SRC_INC_FLAGS = $(foreach dir,$(SOURCE_DIRS),-I$(dir))
+
 ## Intel oneAPI version with oneMKL (Optimized for performance)
-filein  = -I/usr/include/ -I${MKLROOT}/include
+filein  = -I/usr/include/ -I${MKLROOT}/include $(SRC_INC_FLAGS)
 
 ## Using sequential MKL (OpenMP disabled for better single-threaded performance)
 ## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
@@ -60,6 +87,6 @@ CC           = icx
 CLINKER      = mpiicpx
 
 Cu = nvcc
-CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
+CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include $(SRC_INC_FLAGS)
 #CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
 CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc