diff --git a/AMSS_NCKU_source/makefile b/AMSS_NCKU_source/makefile
index 04978c2..bcf4923 100644
--- a/AMSS_NCKU_source/makefile
+++ b/AMSS_NCKU_source/makefile
@@ -65,10 +65,10 @@ PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
 
 ifeq ($(PGO_MODE),instrument)
 ## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
-CXXAPPFLAGS = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+CXXAPPFLAGS = -O3 -march=x86-64-v4 -fma -fprofile-instr-generate -ipo \
               -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS) \
               $(TRANSFER_CACHE_FLAG) $(ESCALAR_KERNEL_FLAG) $(EM_KERNEL_FLAG)
-f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+f90appflags = -O3 -march=x86-64-v4 -fma -fprofile-instr-generate -ipo \
               -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
 else
 ## opt (default): maximum performance with PGO profile data -fprofile-instr-use=$(PROFDATA) \
@@ -76,10 +76,10 @@ else
 ## INTERP_LB_FLAGS has been turned off too, now tested and found to be negative optimization
 
 
-CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+CXXAPPFLAGS = -O3 -march=x86-64-v4 -fp-model fast=2 -fma -ipo \
               -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS) \
               $(TRANSFER_CACHE_FLAG) $(ESCALAR_KERNEL_FLAG) $(EM_KERNEL_FLAG)
-f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
+f90appflags = -O3 -march=x86-64-v4 -fp-model fast=2 -fma -ipo \
               -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
 endif
 
@@ -147,7 +147,7 @@ z4c_rhs_c.o: z4c_rhs_c.C
 
 ## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
 TP_PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/TwoPunctureABE.profdata
-TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+TP_OPTFLAGS = -O3 -march=x86-64-v4 -fp-model fast=2 -fma -ipo \
               -fprofile-instr-use=$(TP_PROFDATA) \
               -Dfortran3 -Dnewc -I${MKLROOT}/include
 
diff --git a/AMSS_NCKU_source/makefile.inc b/AMSS_NCKU_source/makefile.inc
index 632381d..2f4ecf9 100755
--- a/AMSS_NCKU_source/makefile.inc
+++ b/AMSS_NCKU_source/makefile.inc
@@ -44,20 +44,20 @@ INTERP_LB_FLAGS =
 endif
 
 ## Kernel implementation switch
-##   1 (default) : use C++ rewrite of bssn_rhs and helper kernels (faster)
-##   0           : fall back to original Fortran kernels
-USE_CXX_KERNELS ?= 1
+##   1           : use C++ rewrite of bssn_rhs and helper kernels (faster)
+##   0 (default): fall back to original Fortran kernels
+USE_CXX_KERNELS ?= 0
 
 ## Z4C Cartesian RHS kernel switch
-##   1 (default) : use C++ rewrite of Z4c_rhs (main Cartesian path faster)
-##   0           : use original Fortran Z4c_rhs.o
-USE_CXX_Z4C_KERNELS ?= 1
+##   1           : use C++ rewrite of Z4c_rhs (main Cartesian path faster)
+##   0 (default): use original Fortran Z4c_rhs.o
+USE_CXX_Z4C_KERNELS ?= 0
 
 ## BSSN-EScalar RHS switch
-##   1 (default) : use BSSN-EScalar C wrapper on the normal patch path
+##   1           : use BSSN-EScalar C wrapper on the normal patch path
 ##   0           : keep the original Fortran BSSN-EScalar RHS for precision-safe runs
 ## Note: this requires USE_CXX_KERNELS=1 because the wrapper reuses the C BSSN kernel.
-USE_CXX_ESCALAR_KERNEL ?= 1
+USE_CXX_ESCALAR_KERNEL ?= 0
 
 ## BSSN-EM RHS switch
 ##   1 : use BSSN-EM C kernel (bssn_em_rhs_c.C) on the normal patch path
@@ -72,9 +72,9 @@ USE_CXX_EM_KERNEL ?= 0
 USE_TRANSFER_CACHE ?= auto
 
 ## RK4 kernel implementation switch
-##   1 (default) : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
-##   0           : use original Fortran rungekutta4_rout.o
-USE_CXX_RK4 ?= 1
+##   1           : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
+##   0 (default): use original Fortran rungekutta4_rout.o
+USE_CXX_RK4 ?= 0
 
 f90          = ifx
 f77          = ifx