Replace MKL with OpenBLAS

- TwoPunctures.C: <mkl_cblas.h> → <cblas.h>
- gaussj.C: <mkl_lapacke.h> → <lapacke.h>
- makefile.inc: use -lopenblaso, remove MKLROOT dependency
- makefile: remove -I${MKLROOT}/include from all flag variables
- Add OpenMPI include path to filein (needed since g++ is used for .C
  compilation, not the mpicxx wrapper)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

AMSS_NCKU_source/TwoPunctures.C

@@ -27,7 +27,7 @@ using namespace std;
 #endif
 
 #include "TwoPunctures.h"
-#include <mkl_cblas.h>
+#include <cblas.h>
 
 TwoPunctures::TwoPunctures(double mp, double mm, double b,
                            double P_plusx, double P_plusy, double P_plusz,

AMSS_NCKU_source/gaussj.C

@@ -18,7 +18,7 @@ using namespace std;
 #endif
 
 // Intel oneMKL LAPACK interface
-#include <mkl_lapacke.h>
+#include <lapacke.h>
 /* Linear equation solution using Intel oneMKL LAPACK.
 a[0..n-1][0..n-1] is the input matrix. b[0..n-1] is input
 containing the right-hand side vectors. On output a is

AMSS_NCKU_source/makefile

@@ -43,10 +43,10 @@ ESCALAR_KERNEL_FLAG = -DBSSN_USE_ESCALAR_C_KERNEL=$(EFFECTIVE_USE_CXX_ESCALAR_KE
 ## GCC build flags (optimized for x86-64-v4)
 ## PGO disabled (used negative optimization on Intel; not tested on GCC)
 CXXAPPFLAGS = -O3 -march=x86-64-v4 -ffast-math -mfma -flto \
-              -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS) \
+              -Dfortran3 -Dnewc $(INTERP_LB_FLAGS) \
               $(TRANSFER_CACHE_FLAG) $(ESCALAR_KERNEL_FLAG)
 f90appflags = -O3 -march=x86-64-v4 -ffast-math -mfma -flto \
-              -cpp -I${MKLROOT}/include $(POLINT6_FLAG)
+              -cpp $(POLINT6_FLAG)
 
 .SUFFIXES: .o .f90 .C .for .cu
 
@@ -89,7 +89,7 @@ z4c_rhs_c.o: z4c_rhs_c.C
 
 ## TwoPunctureABE flags (no PGO; PGO was negative optimization)
 TP_OPTFLAGS = -O3 -march=x86-64-v4 -ffast-math -mfma -flto \
-              -Dfortran3 -Dnewc -I${MKLROOT}/include
+              -Dfortran3 -Dnewc
 
 TwoPunctures.o: TwoPunctures.C
 	${CXX} $(TP_OPTFLAGS) -fopenmp -c $< -o $@

AMSS_NCKU_source/makefile.inc

@@ -1,8 +1,8 @@
-## GCC version with OpenMPI and oneMKL
-filein  = -I/usr/include/ -I${MKLROOT}/include
+## GCC version with OpenMPI and OpenBLAS
+filein  = -I/usr/include/ -I/usr/mpi/gcc/openmpi-4.1.9a1/include
 
-## Using MKL with gfortran interface (-lmkl_gf_lp64 instead of -lmkl_intel_lp64)
-LDLIBS  = -L${MKLROOT}/lib -lmkl_gf_lp64 -lmkl_sequential -lmkl_core -lgfortran -lpthread -lm -ldl -lgomp
+## OpenBLAS (OpenMP variant) + gfortran runtime
+LDLIBS  = -lopenblaso -lgfortran -lpthread -lm -ldl -lgomp
 
 ## Memory allocator switch
 ##   0 (default) : use system default allocator (ptmalloc)