feat: Implement hybrid MPI+OpenMP parallelization

- Enable -qopenmp in makefile.inc - Add OpenMP directives to 4th order derivatives in diff_new.f90 - Update makefile_and_run.py to dynamic calculate OMP_NUM_THREADS based on 96 cores and remove hardcoded CPU binding
2026-02-06 13:25:07 +08:00
10 changed files with 1254 additions and 2026 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -1,7 +1,6 @@
 __pycache__
 GW150914
 GW150914-origin
-GW150914-mini
 docs
 *.tmp

--- a/AMSS_NCKU_Input.py
+++ b/AMSS_NCKU_Input.py
@@ -16,14 +16,12 @@ import numpy
 File_directory   = "GW150914"                    ## output file directory
 Output_directory = "binary_output"               ## binary data file directory
                                                 ## The file directory name should not be too long
-MPI_processes    = 8                             ## number of mpi processes used in the simulation
+MPI_processes    = 48                             ## number of mpi processes used in the simulation

 GPU_Calculation  = "no"                          ## Use GPU or not 
                                                 ## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
 CPU_Part         = 1.0
 GPU_Part         = 0.0
-Debug_NaN_Check          = 0                       ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
-

 #################################################

--- a/AMSS_NCKU_Input_Mini.py
+++ b/AMSS_NCKU_Input_Mini.py
@@ -1,233 +0,0 @@
-
-#################################################
-##
-## This file provides the input parameters required for numerical relativity.
-## XIAOQU
-## 2024/03/19 --- 2025/09/14
-## Modified for GW150914-mini test case
-##
-#################################################
-
-import numpy    
-
-#################################################
-
-## Setting MPI processes and the output file directory
-
-File_directory   = "GW150914-mini"               ## output file directory
-Output_directory = "binary_output"               ## binary data file directory
-                                                 ## The file directory name should not be too long
-MPI_processes    = 4                             ## number of mpi processes used in the simulation (Reduced for laptop)
-
-GPU_Calculation  = "no"                          ## Use GPU or not 
-                                                 ## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
-CPU_Part         = 1.0
-GPU_Part         = 0.0
-
-#################################################
-
-
-#################################################
-
-## Setting the physical system and numerical method
-
-Symmetry                 = "equatorial-symmetry"   ## Symmetry of System: choose equatorial-symmetry、no-symmetry、octant-symmetry
-Equation_Class           = "BSSN"                  ## Evolution Equation: choose "BSSN", "BSSN-EScalar", "BSSN-EM", "Z4C" 
-                                                   ## If "BSSN-EScalar" is chosen, it is necessary to set other parameters below
-Initial_Data_Method      = "Ansorg-TwoPuncture"    ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
-Time_Evolution_Method    = "runge-kutta-45"        ## time evolution method: choose "runge-kutta-45"
-Finite_Diffenence_Method = "4th-order"             ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
-Debug_NaN_Check          = 0                       ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
-
-#################################################
-
-
-#################################################
-
-## Setting the time evolutionary information
-
-Start_Evolution_Time     = 0.0                    ## start evolution time t0
-Final_Evolution_Time     = 100.0                  ## final evolution time t1 (Reduced for quick test)
-Check_Time               = 10.0
-Dump_Time                = 10.0                   ## time inteval dT for dumping binary data
-D2_Dump_Time             = 10.0                   ## dump the ascii data for 2d surface after dT'
-Analysis_Time            = 1.0                    ## dump the puncture position and GW psi4 after dT"
-Evolution_Step_Number    = 10000000               ## stop the calculation after the maximal step number
-Courant_Factor           = 0.5                    ## Courant Factor
-Dissipation              = 0.15                   ## Kreiss-Oliger Dissipation Strength
-
-#################################################
-
-
-#################################################
-
-## Setting the grid structure
-
-basic_grid_set    = "Patch"                          ## grid structure: choose "Patch" or "Shell-Patch"
-grid_center_set   = "Cell"                           ## grid center: chose "Cell" or "Vertex"
-
-grid_level        = 7                                ## total number of AMR grid levels (Reduced from 9)
-static_grid_level = 4                                ## number of AMR static grid levels (Reduced from 5)
-moving_grid_level = grid_level - static_grid_level   ## number of AMR moving grid levels
-
-analysis_level    = 0
-refinement_level  = 3                                ## time refinement start from this grid level
-
-largest_box_xyz_max = [320.0, 320.0, 320.0]          ## scale of the largest box
-                                                     ## not ne cess ary to be cubic for "Patch" grid s tructure
-                                                     ## need to be a cubic box for "Shell-Patch" grid structure
-largest_box_xyz_min = - numpy.array(largest_box_xyz_max)  
-
-static_grid_number = 48                              ## grid points of each static AMR grid (in x direction) (Reduced from 96)
-                                                     ## (grid points in y and z directions are automatically adjusted)
-moving_grid_number = 24                              ## grid points of each moving AMR grid (Reduced from 48)
-shell_grid_number  = [32, 32, 100]                   ## grid points of Shell-Patch grid
-                                                     ## in (phi, theta, r) direction
-devide_factor      = 2.0                             ## resolution between different grid levels dh0/dh1, only support 2.0 now
-                                                     
-
-static_grid_type   = 'Linear'                        ## AMR static grid structure , only supports "Linear"
-moving_grid_type   = 'Linear'                        ## AMR moving grid structure , only supports "Linear"
-
-quarter_sphere_number = 48                           ## grid number of 1/4 s pher ical surface (Reduced from 96)
-                                                     ## (which is needed for evaluating the spherical surface integral)
-
-#################################################
-
-
-#################################################
-
-## Setting the puncture information
-
-puncture_number       = 2                                     
-
-position_BH           = numpy.zeros( (puncture_number, 3) )   
-parameter_BH          = numpy.zeros( (puncture_number, 3) )   
-dimensionless_spin_BH = numpy.zeros( (puncture_number, 3) )   
-momentum_BH           = numpy.zeros( (puncture_number, 3) )   
-
-puncture_data_set     = "Manually"                       ## Method to give Puncture’s positions and momentum
-                                                         ## choose "Manually" or "Automatically-BBH"
-                                                         ## Prefer to choose "Manually", because "Automatically-BBH" is developing now
-
-## initial orbital distance and ellipticity for BBHs system
-## ( needed for "Automatically-BBH" case , not affect the "Manually" case )
-Distance = 10.0
-e0       = 0.0
-
-## black hole parameter (M Q* a*)
-parameter_BH[0] = [ 36.0/(36.0+29.0),  0.0,  +0.31 ]   
-parameter_BH[1] = [ 29.0/(36.0+29.0),  0.0,  -0.46 ]  
-## dimensionless spin in each direction
-dimensionless_spin_BH[0] = [ 0.0,  0.0,  +0.31 ]   
-dimensionless_spin_BH[1] = [ 0.0,  0.0,  -0.46 ]  
-
-## use Brugmann's convention
-##  -----0-----> y
-##   -      +     
-
-#---------------------------------------------
-
-## If puncture_data_set is chosen to be "Manually", it is necessary to set the position and momentum of each puncture manually
-
-## initial position for each puncture
-position_BH[0]  = [  0.0,  10.0*29.0/(36.0+29.0), 0.0 ]  
-position_BH[1]  = [  0.0, -10.0*36.0/(36.0+29.0), 0.0 ] 
-
-## initial mumentum for each puncture
-## (needed for "Manually" case, does not affect the "Automatically-BBH" case)
-momentum_BH[0]  = [ -0.09530152296974252,  -0.00084541526517121,   0.0 ]
-momentum_BH[1]  = [ +0.09530152296974252,  +0.00084541526517121,   0.0 ]
-
-
-#################################################
-
-
-#################################################
-
-## Setting the gravitational wave information
-
-GW_L_max        = 4                      ## maximal L number in gravitational wave
-GW_M_max        = 4                      ## maximal M number in gravitational wave
-Detector_Number = 12                     ## number of dector
-Detector_Rmin   = 50.0                   ## nearest dector distance
-Detector_Rmax   = 160.0                  ## farest dector distance
-
-#################################################
-
-
-#################################################
-
-## Setting the apprent horizon
-
-AHF_Find       = "no"                    ## whether to find the apparent horizon: choose "yes" or "no"
-
-AHF_Find_Every = 24
-AHF_Dump_Time  = 20.0
-
-#################################################
-
-
-#################################################
-
-## Other parameters (testing)
-## Only influence the Equation_Class = "BSSN-EScalar" case
-
-FR_a2     = 3.0        ## f(R) = R + a2 * R^2    
-FR_l2     = 10000.0
-FR_phi0   = 0.00005
-FR_r0     = 120.0
-FR_sigma0 = 8.0
-FR_Choice = 2          ## Choice options: 1 2 3 4 5
-                       ## 1: phi(r) = phi0 * Exp(-(r-r0)**2/sigma0)   
-                       ##    V(r)   = 0
-                       ## 2: phi(r) =  phi0 * a2^2/(1+a2^2)  
-                       ##    V(r)   = Exp(-8*Sqrt(PI/3)*phi(r)) * (1-Exp(4*Sqrt(PI/3)*phi(r)))**2 / (32*PI*a2)
-                       ## 3: Schrodinger-Newton gived by system phi(r) 
-                       ##    V(r)   = Exp(-8*Sqrt(PI/3)*phi(r)) * (1-Exp(4*Sqrt(PI/3)*phi(r)))**2 / (32*PI*a2)
-                       ## 4: phi(r) = phi0 * 0.5 * ( tanh((r+r0)/sigma0) - tanh((r-r0)/sigma0) )  
-                       ##    V(r)   = 0
-                       ##    f(R)   = R + a2*R^2  with a2 = +oo
-                       ## 5: phi(r) = phi0 * Exp(-(r-r0)**2/sigma)   
-                       ##    V(r)   = 0
-
-#################################################
-
-
-#################################################
-
-## Other parameters (testing)
-## (please do not change if not necessary)
-
-boundary_choice = "BAM-choice"     ## Sommerfeld boundary condition : choose "BAM-choice" or "Shibata-choice" 
-                                   ## prefer "BAM-choice"
-
-gauge_choice  = 0                  ## gauge choice
-                                   ## 0: B^i gauge
-                                   ## 1: David's puncture gauge
-                                   ## 2: MB B^i gauge               
-                                   ## 3: RIT B^i gauge
-                                   ## 4: MB beta gauge 
-                                   ## 5: RIT beta gauge 
-                                   ## 6: MGB1 B^i gauge
-                                   ## 7: MGB2 B^i gauge
-                                   ## prefer 0 or 1
-                                   
-tetrad_type  = 2                   ## tetradtype 
-                                   ##  v:r; u: phi; w: theta
-                                   ##      v^a = (x,y,z)
-                                   ## 0: orthonormal order: v,u,w
-                                   ##    v^a = (x,y,z)   
-                                   ##    m = (phi - i theta)/sqrt(2) 
-                                   ##    following Frans, Eq.(8) of  PRD 75, 124018(2007)
-                                   ## 1: orthonormal order: w,u,v
-                                   ##    m = (theta + i phi)/sqrt(2) 
-                                   ##    following Sperhake, Eq.(3.2) of  PRD 85, 124062(2012)    
-                                   ## 2: orthonormal order: v,u,w
-                                   ##    v_a = (x,y,z)
-                                   ##    m = (phi - i theta)/sqrt(2) 
-                                   ##    following Frans, Eq.(8) of  PRD 75, 124018(2007)
-                                   ## this version recommend set to 2
-                                   ## prefer 2
-                                   
-#################################################
--- a/AMSS_NCKU_MiniProgram.py
+++ b/AMSS_NCKU_MiniProgram.py
@@ -1,224 +0,0 @@
-##################################################################
-##
-## AMSS-NCKU Numerical Relativity Mini Test Program
-## Author: Assistant (based on Xiaoqu's code)
-## 2026/01/20
-##
-## This script runs a scaled-down version of the GW150914 test case
-## suitable for laptop testing.
-##
-##################################################################
-
-import os
-import shutil
-import sys
-import time
-
-# --- Context Manager for Input File Swapping ---
-class InputFileSwapper:
-    def __init__(self, mini_file="AMSS_NCKU_Input_Mini.py", target_file="AMSS_NCKU_Input.py"):
-        self.mini_file = mini_file
-        self.target_file = target_file
-        self.backup_file = target_file + ".bak"
-        self.swapped = False
-
-    def __enter__(self):
-        print(f"[MiniProgram] Swapping {self.target_file} with {self.mini_file}...")
-        if os.path.exists(self.target_file):
-            shutil.move(self.target_file, self.backup_file)
-        shutil.copy(self.mini_file, self.target_file)
-        self.swapped = True
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        if self.swapped:
-            print(f"[MiniProgram] Restoring original {self.target_file}...")
-            os.remove(self.target_file)
-            if os.path.exists(self.backup_file):
-                shutil.move(self.backup_file, self.target_file)
-
-def main():
-    # Use the swapper to ensure all imported modules see the mini configuration
-    with InputFileSwapper():
-        
-        # Import modules AFTER swapping input file
-        try:
-            import AMSS_NCKU_Input as input_data
-            import print_information
-            import setup
-            import numerical_grid
-            import generate_macrodef
-            import makefile_and_run
-            import generate_TwoPuncture_input
-            import renew_puncture_parameter
-            import plot_xiaoqu
-            import plot_GW_strain_amplitude_xiaoqu
-        except ImportError as e:
-            print(f"Error importing modules: {e}")
-            return
-
-        print_information.print_program_introduction()
-        
-        print("\n" + "#"*60)
-        print(" RUNNING MINI TEST CASE: GW150914-mini")
-        print("#"*60 + "\n")
-
-        # --- Directory Setup ---
-        File_directory = os.path.join(input_data.File_directory)
-        
-        if os.path.exists(File_directory):
-            print(f" Output directory '{File_directory}' exists. Removing for mini test...")
-            shutil.rmtree(File_directory, ignore_errors=True)
-        
-        os.mkdir(File_directory)
-        shutil.copy("AMSS_NCKU_Input.py", File_directory) # Copies the current (mini) input
-
-        output_directory = os.path.join(File_directory, "AMSS_NCKU_output")
-        os.mkdir(output_directory)
-
-        binary_results_directory = os.path.join(output_directory, input_data.Output_directory)
-        os.mkdir(binary_results_directory)
-
-        figure_directory = os.path.join(File_directory, "figure")
-        os.mkdir(figure_directory)
-
-        print(" Output directories generated.\n")
-
-        # --- Setup and Input Generation ---
-        setup.print_input_data(File_directory)
-        setup.generate_AMSSNCKU_input()
-        setup.print_puncture_information()
-
-        print("\n Generating AMSS-NCKU input parfile...")
-        numerical_grid.append_AMSSNCKU_cgh_input()
-        
-        print("\n Plotting initial grid...")
-        numerical_grid.plot_initial_grid()
-
-        print("\n Generating macro files...")
-        generate_macrodef.generate_macrodef_h()
-        generate_macrodef.generate_macrodef_fh()
-        
-        # --- Compilation Preparation ---
-        print("\n Preparing to compile and run...")
-        
-        AMSS_NCKU_source_path = "AMSS_NCKU_source"
-        AMSS_NCKU_source_copy = os.path.join(File_directory, "AMSS_NCKU_source_copy")
-
-        if not os.path.exists(AMSS_NCKU_source_path):
-             print(" Error: AMSS_NCKU_source not found! Please run in the project root.")
-             return
-
-        shutil.copytree(AMSS_NCKU_source_path, AMSS_NCKU_source_copy)
-        
-        macrodef_h_path  = os.path.join(File_directory, "macrodef.h") 
-        macrodef_fh_path = os.path.join(File_directory, "macrodef.fh") 
-
-        shutil.copy2(macrodef_h_path,  AMSS_NCKU_source_copy)
-        shutil.copy2(macrodef_fh_path, AMSS_NCKU_source_copy)
-
-        # --- Compilation ---
-        cwd = os.getcwd()
-        os.chdir(AMSS_NCKU_source_copy)
-        
-        print(" Compiling ABE...")
-        makefile_and_run.makefile_ABE()
-        
-        if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ): 
-            print(" Compiling TwoPunctureABE...")
-            makefile_and_run.makefile_TwoPunctureABE()
-            
-        os.chdir(cwd)
-
-        # --- Copy Executables ---
-        if (input_data.GPU_Calculation == "no"):
-            ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABE")
-        else:
-            ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABEGPU")
-            
-        if not os.path.exists(ABE_file):
-            print(" Error: ABE executable compilation failed.")
-            return
-            
-        shutil.copy2(ABE_file, output_directory)
-
-        TwoPuncture_file = os.path.join(AMSS_NCKU_source_copy, "TwoPunctureABE")
-        if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
-            if not os.path.exists(TwoPuncture_file):
-                print(" Error: TwoPunctureABE compilation failed.")
-                return
-            shutil.copy2(TwoPuncture_file, output_directory)
-
-        # --- Execution ---
-        start_time = time.time()
-        
-        if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
-             print("\n Generating TwoPuncture input...")
-             generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input()
-             
-             AMSS_NCKU_TwoPuncture_inputfile = 'AMSS-NCKU-TwoPuncture.input'
-             AMSS_NCKU_TwoPuncture_inputfile_path = os.path.join( File_directory, AMSS_NCKU_TwoPuncture_inputfile )
-             shutil.copy2( AMSS_NCKU_TwoPuncture_inputfile_path, os.path.join(output_directory, 'TwoPunctureinput.par') )
-             
-             print(" Running TwoPunctureABE...")
-             os.chdir(output_directory)
-             makefile_and_run.run_TwoPunctureABE()
-             os.chdir(cwd)
-
-        # Update Puncture Parameter
-        renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory)
-        
-        AMSS_NCKU_inputfile = 'AMSS-NCKU.input'
-        AMSS_NCKU_inputfile_path = os.path.join(File_directory, AMSS_NCKU_inputfile)
-        shutil.copy2( AMSS_NCKU_inputfile_path, os.path.join(output_directory, 'input.par') )
-        
-        print("\n Input files ready. Launching ABE...")
-        
-        os.chdir(output_directory)
-        makefile_and_run.run_ABE()
-        os.chdir(cwd)
-        
-        end_time = time.time()
-        elapsed_time = end_time - start_time
-        
-        # --- Post-processing ---
-        print("\n Copying output files for inspection...")
-        AMSS_NCKU_error_file_path = os.path.join(binary_results_directory, "setting.par")
-        if os.path.exists(AMSS_NCKU_error_file_path):
-            shutil.copy( AMSS_NCKU_error_file_path, os.path.join(output_directory, "AMSSNCKU_setting_parameter") )
-
-        AMSS_NCKU_error_file_path = os.path.join(binary_results_directory, "Error.log")
-        if os.path.exists(AMSS_NCKU_error_file_path):
-            shutil.copy( AMSS_NCKU_error_file_path, os.path.join(output_directory, "Error.log") )
-
-        for fname in ["bssn_BH.dat", "bssn_ADMQs.dat", "bssn_psi4.dat", "bssn_constraint.dat"]:
-            fpath = os.path.join(binary_results_directory, fname)
-            if os.path.exists(fpath):
-                shutil.copy(fpath, os.path.join(output_directory, fname))
-
-        # --- Plotting ---
-        print("\n Plotting results...")
-        try:
-            plot_xiaoqu.generate_puncture_orbit_plot(   binary_results_directory, figure_directory )
-            plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
-            plot_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
-            
-            for i in range(input_data.Detector_Number):
-                plot_xiaoqu.generate_gravitational_wave_psi4_plot( binary_results_directory, figure_directory, i )
-                plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot( binary_results_directory, figure_directory, i )
-
-            for i in range(input_data.Detector_Number):
-                plot_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
-
-            for i in range(input_data.grid_level):
-                plot_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
-                
-            plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )
-        except Exception as e:
-            print(f"Warning: Plotting failed: {e}")
-
-        print(f"\n Program Cost = {elapsed_time:.2f} Seconds \n")
-        print(" AMSS-NCKU-Python simulation finished (Mini Test).\n")
-
-if __name__ == "__main__":
-    main()
--- a/AMSS_NCKU_source/bssn_rhs.f90
+++ b/AMSS_NCKU_source/bssn_rhs.f90
@@ -61,9 +61,7 @@
  real*8, dimension(ex(1),ex(2),ex(3)),intent(inout) :: ham_Res, movx_Res, movy_Res, movz_Res
  real*8, dimension(ex(1),ex(2),ex(3)),intent(inout) :: Gmx_Res, Gmy_Res, Gmz_Res
 !  gont = 0: success; gont = 1: something wrong
-  integer::gont,i,j,k
-  real*8 :: val1, val2
-  real*8 :: det, t_gupxx, t_gupxy, t_gupxz, t_gupyy, t_gupyz, t_gupzz
+  integer::gont

 !~~~~~~> Other variables:

@@ -86,10 +84,7 @@
  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz

  real*8,dimension(3) ::SSS,AAS,ASA,SAA,ASS,SAS,SSA
-  real*8            :: PI
-#if (DEBUG_NAN_CHECK)
-  real*8            :: dX
-#endif
+  real*8            :: dX, dY, dZ, PI
  real*8, parameter :: ZEO = 0.d0,ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
  real*8, parameter :: EIGHT = 8.D0, HALF = 0.5D0, THR = 3.d0
  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
@@ -111,7 +106,6 @@
  call getpbh(BHN,Porg,Mass)
 #endif

-#if (DEBUG_NAN_CHECK)
 !!! sanity check
  dX = sum(chi)+sum(trK)+sum(dxx)+sum(gxy)+sum(gxz)+sum(dyy)+sum(gyz)+sum(dzz) &
      +sum(Axx)+sum(Axy)+sum(Axz)+sum(Ayy)+sum(Ayz)+sum(Azz)                   &
@@ -142,10 +136,13 @@
     gont = 1
     return
  endif
-#endif

  PI = dacos(-ONE)

+  dX = X(2) - X(1)
+  dY = Y(2) - Y(1)
+  dZ = Z(2) - Z(1)
+
  alpn1 = Lap + ONE
  chin1 = chi + ONE
  gxx = dxx + ONE
@@ -159,16 +156,16 @@
  div_beta = betaxx + betayy + betazz
 
  call fderivs(ex,chi,chix,chiy,chiz,X,Y,Z,SYM,SYM,SYM,symmetry,Lev)
-  call fderivs(ex,dxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
-  call fderivs(ex,dyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
-  call fderivs(ex,dzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
-
-  call fderivs(ex,gxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,Lev)
-  call fderivs(ex,gxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,Lev)
-  call fderivs(ex,gyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,Lev)

  chi_rhs = F2o3 *chin1*( alpn1 * trK - div_beta ) !rhs for chi

+  call fderivs(ex,dxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
+  call fderivs(ex,gxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,Lev)
+  call fderivs(ex,gxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,Lev)
+  call fderivs(ex,dyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
+  call fderivs(ex,gyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,Lev)
+  call fderivs(ex,dzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
+
  gxx_rhs = - TWO * alpn1 * Axx    -  F2o3 * gxx * div_beta          + &
              TWO *(  gxx * betaxx +   gxy * betayx +   gxz * betazx)

@@ -193,99 +190,71 @@
                                       gyz * betayx +   gzz * betazx   &
                                                    -   gxz * betayy     !rhs for gij

-! fused loop for metric inversion and connections
-  !DIR$ SIMD
-  do k=1,ex(3)
-  do j=1,ex(2)
-  do i=1,ex(1)
-     ! 1. Metric Inversion
-     det = ONE / ( &
-            gxx(i,j,k) * gyy(i,j,k) * gzz(i,j,k) + gxy(i,j,k) * gyz(i,j,k) * gxz(i,j,k) + &
-            gxz(i,j,k) * gxy(i,j,k) * gyz(i,j,k) - gxz(i,j,k) * gyy(i,j,k) * gxz(i,j,k) - &
-            gxy(i,j,k) * gxy(i,j,k) * gzz(i,j,k) - gxx(i,j,k) * gyz(i,j,k) * gyz(i,j,k) )
+! invert tilted metric
+  gupzz =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
+           gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
+  gupxx =   ( gyy * gzz - gyz * gyz ) / gupzz
+  gupxy = - ( gxy * gzz - gyz * gxz ) / gupzz
+  gupxz =   ( gxy * gyz - gyy * gxz ) / gupzz
+  gupyy =   ( gxx * gzz - gxz * gxz ) / gupzz
+  gupyz = - ( gxx * gyz - gxy * gxz ) / gupzz
+  gupzz =   ( gxx * gyy - gxy * gxy ) / gupzz

-     t_gupxx =   ( gyy(i,j,k) * gzz(i,j,k) - gyz(i,j,k) * gyz(i,j,k) ) * det
-     t_gupxy = - ( gxy(i,j,k) * gzz(i,j,k) - gyz(i,j,k) * gxz(i,j,k) ) * det
-     t_gupxz =   ( gxy(i,j,k) * gyz(i,j,k) - gyy(i,j,k) * gxz(i,j,k) ) * det
-     t_gupyy =   ( gxx(i,j,k) * gzz(i,j,k) - gxz(i,j,k) * gxz(i,j,k) ) * det
-     t_gupyz = - ( gxx(i,j,k) * gyz(i,j,k) - gxy(i,j,k) * gxz(i,j,k) ) * det
-     t_gupzz =   ( gxx(i,j,k) * gyy(i,j,k) - gxy(i,j,k) * gxy(i,j,k) ) * det
+  if(co == 0)then
+! Gam^i_Res = Gam^i + gup^ij_,j
+  Gmx_Res = Gamx - (gupxx*(gupxx*gxxx+gupxy*gxyx+gupxz*gxzx)&
+                   +gupxy*(gupxx*gxyx+gupxy*gyyx+gupxz*gyzx)&
+                   +gupxz*(gupxx*gxzx+gupxy*gyzx+gupxz*gzzx)&
+                   +gupxx*(gupxy*gxxy+gupyy*gxyy+gupyz*gxzy)&
+                   +gupxy*(gupxy*gxyy+gupyy*gyyy+gupyz*gyzy)&
+                   +gupxz*(gupxy*gxzy+gupyy*gyzy+gupyz*gzzy)&
+                   +gupxx*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupxy*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupxz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  Gmy_Res = Gamy - (gupxx*(gupxy*gxxx+gupyy*gxyx+gupyz*gxzx)&
+                   +gupxy*(gupxy*gxyx+gupyy*gyyx+gupyz*gyzx)&
+                   +gupxz*(gupxy*gxzx+gupyy*gyzx+gupyz*gzzx)&
+                   +gupxy*(gupxy*gxxy+gupyy*gxyy+gupyz*gxzy)&
+                   +gupyy*(gupxy*gxyy+gupyy*gyyy+gupyz*gyzy)&
+                   +gupyz*(gupxy*gxzy+gupyy*gyzy+gupyz*gzzy)&
+                   +gupxy*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupyy*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupyz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  Gmz_Res = Gamz - (gupxx*(gupxz*gxxx+gupyz*gxyx+gupzz*gxzx)&
+                   +gupxy*(gupxz*gxyx+gupyz*gyyx+gupzz*gyzx)&
+                   +gupxz*(gupxz*gxzx+gupyz*gyzx+gupzz*gzzx)&
+                   +gupxy*(gupxz*gxxy+gupyz*gxyy+gupzz*gxzy)&
+                   +gupyy*(gupxz*gxyy+gupyz*gyyy+gupzz*gyzy)&
+                   +gupyz*(gupxz*gxzy+gupyz*gyzy+gupzz*gzzy)&
+                   +gupxz*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupyz*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupzz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  endif

-     gupxx(i,j,k) = t_gupxx
-     gupxy(i,j,k) = t_gupxy
-     gupxz(i,j,k) = t_gupxz
-     gupyy(i,j,k) = t_gupyy
-     gupyz(i,j,k) = t_gupyz
-     gupzz(i,j,k) = t_gupzz
+! second kind of connection
+  Gamxxx =HALF*( gupxx*gxxx + gupxy*(TWO*gxyx - gxxy ) + gupxz*(TWO*gxzx - gxxz ))
+  Gamyxx =HALF*( gupxy*gxxx + gupyy*(TWO*gxyx - gxxy ) + gupyz*(TWO*gxzx - gxxz ))
+  Gamzxx =HALF*( gupxz*gxxx + gupyz*(TWO*gxyx - gxxy ) + gupzz*(TWO*gxzx - gxxz ))
 
-     if(co == 0)then
-        Gmx_Res(i,j,k) = Gamx(i,j,k) - (t_gupxx*(t_gupxx*gxxx(i,j,k)+t_gupxy*gxyx(i,j,k)+t_gupxz*gxzx(i,j,k))&
-                         +t_gupxy*(t_gupxx*gxyx(i,j,k)+t_gupxy*gyyx(i,j,k)+t_gupxz*gyzx(i,j,k))&
-                         +t_gupxz*(t_gupxx*gxzx(i,j,k)+t_gupxy*gyzx(i,j,k)+t_gupxz*gzzx(i,j,k))&
-                         +t_gupxx*(t_gupxy*gxxy(i,j,k)+t_gupyy*gxyy(i,j,k)+t_gupyz*gxzy(i,j,k))&
-                         +t_gupxy*(t_gupxy*gxyy(i,j,k)+t_gupyy*gyyy(i,j,k)+t_gupyz*gyzy(i,j,k))&
-                         +t_gupxz*(t_gupxy*gxzy(i,j,k)+t_gupyy*gyzy(i,j,k)+t_gupyz*gzzy(i,j,k))&
-                         +t_gupxx*(t_gupxz*gxxz(i,j,k)+t_gupyz*gxyz(i,j,k)+t_gupzz*gxzz(i,j,k))&
-                         +t_gupxy*(t_gupxz*gxyz(i,j,k)+t_gupyz*gyyz(i,j,k)+t_gupzz*gyzz(i,j,k))&
-                         +t_gupxz*(t_gupxz*gxzz(i,j,k)+t_gupyz*gyzz(i,j,k)+t_gupzz*gzzz(i,j,k)))
-        Gmy_Res(i,j,k) = Gamy(i,j,k) - (t_gupxx*(t_gupxy*gxxx(i,j,k)+t_gupyy*gxyx(i,j,k)+t_gupyz*gxzx(i,j,k))&
-                         +t_gupxy*(t_gupxy*gxyx(i,j,k)+t_gupyy*gyyx(i,j,k)+t_gupyz*gyzx(i,j,k))&
-                         +t_gupxz*(t_gupxy*gxzx(i,j,k)+t_gupyy*gyzx(i,j,k)+t_gupyz*gzzx(i,j,k))&
-                         +t_gupxy*(t_gupxy*gxxy(i,j,k)+t_gupyy*gxyy(i,j,k)+t_gupyz*gxzy(i,j,k))&
-                         +t_gupyy*(t_gupxy*gxyy(i,j,k)+t_gupyy*gyyy(i,j,k)+t_gupyz*gyzy(i,j,k))&
-                         +t_gupyz*(t_gupxy*gxzy(i,j,k)+t_gupyy*gyzy(i,j,k)+t_gupyz*gzzy(i,j,k))&
-                         +t_gupxy*(t_gupxz*gxxz(i,j,k)+t_gupyz*gxyz(i,j,k)+t_gupzz*gxzz(i,j,k))&
-                         +t_gupyy*(t_gupxz*gxyz(i,j,k)+t_gupyz*gyyz(i,j,k)+t_gupzz*gyzz(i,j,k))&
-                         +t_gupyz*(t_gupxz*gxzz(i,j,k)+t_gupyz*gyzz(i,j,k)+t_gupzz*gzzz(i,j,k)))
-        Gmz_Res(i,j,k) = Gamz(i,j,k) - (t_gupxx*(t_gupxz*gxxx(i,j,k)+t_gupyz*gxyx(i,j,k)+t_gupzz*gxzx(i,j,k))&
-                         +t_gupxy*(t_gupxz*gxyx(i,j,k)+t_gupyz*gyyx(i,j,k)+t_gupzz*gyzx(i,j,k))&
-                         +t_gupxz*(t_gupxz*gxzx(i,j,k)+t_gupyz*gyzx(i,j,k)+t_gupzz*gzzx(i,j,k))&
-                         +t_gupxy*(t_gupxz*gxxy(i,j,k)+t_gupyz*gxyy(i,j,k)+t_gupzz*gxzy(i,j,k))&
-                         +t_gupyy*(t_gupxz*gxyy(i,j,k)+t_gupyz*gyyy(i,j,k)+t_gupzz*gyzy(i,j,k))&
-                         +t_gupyz*(t_gupxz*gxzy(i,j,k)+t_gupyz*gyzy(i,j,k)+t_gupzz*gzzy(i,j,k))&
-                         +t_gupxz*(t_gupxz*gxxz(i,j,k)+t_gupyz*gxyz(i,j,k)+t_gupzz*gxzz(i,j,k))&
-                         +t_gupyz*(t_gupxz*gxyz(i,j,k)+t_gupyz*gyyz(i,j,k)+t_gupzz*gyzz(i,j,k))&
-                         +t_gupzz*(t_gupxz*gxzz(i,j,k)+t_gupyz*gyzz(i,j,k)+t_gupzz*gzzz(i,j,k)))
-     endif
+  Gamxyy =HALF*( gupxx*(TWO*gxyy - gyyx ) + gupxy*gyyy + gupxz*(TWO*gyzy - gyyz ))
+  Gamyyy =HALF*( gupxy*(TWO*gxyy - gyyx ) + gupyy*gyyy + gupyz*(TWO*gyzy - gyyz ))
+  Gamzyy =HALF*( gupxz*(TWO*gxyy - gyyx ) + gupyz*gyyy + gupzz*(TWO*gyzy - gyyz ))

-     ! 2. Christoffel Symbols
-     val1 = TWO * gxyx(i,j,k) - gxxy(i,j,k)
-     val2 = TWO * gxzx(i,j,k) - gxxz(i,j,k)
-     Gamxxx(i,j,k) =HALF*( t_gupxx*gxxx(i,j,k) + t_gupxy*val1 + t_gupxz*val2 )
-     Gamyxx(i,j,k) =HALF*( t_gupxy*gxxx(i,j,k) + t_gupyy*val1 + t_gupyz*val2 )
-     Gamzxx(i,j,k) =HALF*( t_gupxz*gxxx(i,j,k) + t_gupyz*val1 + t_gupzz*val2 )
+  Gamxzz =HALF*( gupxx*(TWO*gxzz - gzzx ) + gupxy*(TWO*gyzz - gzzy ) + gupxz*gzzz)
+  Gamyzz =HALF*( gupxy*(TWO*gxzz - gzzx ) + gupyy*(TWO*gyzz - gzzy ) + gupyz*gzzz)
+  Gamzzz =HALF*( gupxz*(TWO*gxzz - gzzx ) + gupyz*(TWO*gyzz - gzzy ) + gupzz*gzzz)

-     val1 = TWO * gxyy(i,j,k) - gyyx(i,j,k)
-     val2 = TWO * gyzy(i,j,k) - gyyz(i,j,k)
-     Gamxyy(i,j,k) =HALF*( t_gupxx*val1 + t_gupxy*gyyy(i,j,k) + t_gupxz*val2 )
-     Gamyyy(i,j,k) =HALF*( t_gupxy*val1 + t_gupyy*gyyy(i,j,k) + t_gupyz*val2 )
-     Gamzyy(i,j,k) =HALF*( t_gupxz*val1 + t_gupyz*gyyy(i,j,k) + t_gupzz*val2 )
-
-     val1 = TWO * gxzz(i,j,k) - gzzx(i,j,k)
-     val2 = TWO * gyzz(i,j,k) - gzzy(i,j,k)
-     Gamxzz(i,j,k) =HALF*( t_gupxx*val1 + t_gupxy*val2 + t_gupxz*gzzz(i,j,k) )
-     Gamyzz(i,j,k) =HALF*( t_gupxy*val1 + t_gupyy*val2 + t_gupyz*gzzz(i,j,k) )
-     Gamzzz(i,j,k) =HALF*( t_gupxz*val1 + t_gupyz*val2 + t_gupzz*gzzz(i,j,k) )
-
-     val1 = gxzy(i,j,k) + gyzx(i,j,k) - gxyz(i,j,k)
-     Gamxxy(i,j,k) =HALF*( t_gupxx*gxxy(i,j,k) + t_gupxy*gyyx(i,j,k) + t_gupxz*val1 )
-     Gamyxy(i,j,k) =HALF*( t_gupxy*gxxy(i,j,k) + t_gupyy*gyyx(i,j,k) + t_gupyz*val1 )
-     Gamzxy(i,j,k) =HALF*( t_gupxz*gxxy(i,j,k) + t_gupyz*gyyx(i,j,k) + t_gupzz*val1 )
-
-     val1 = gxyz(i,j,k) + gyzx(i,j,k) - gxzy(i,j,k)
-     Gamxxz(i,j,k) =HALF*( t_gupxx*gxxz(i,j,k) + t_gupxy*val1 + t_gupxz*gzzx(i,j,k) )
-     Gamyxz(i,j,k) =HALF*( t_gupxy*gxxz(i,j,k) + t_gupyy*val1 + t_gupyz*gzzx(i,j,k) )
-     Gamzxz(i,j,k) =HALF*( t_gupxz*gxxz(i,j,k) + t_gupyz*val1 + t_gupzz*gzzx(i,j,k) )
-
-     val1 = gxyz(i,j,k) + gxzy(i,j,k) - gyzx(i,j,k)
-     Gamxyz(i,j,k) =HALF*( t_gupxx*val1 + t_gupxy*gyyz(i,j,k) + t_gupxz*gzzy(i,j,k) )
-     Gamyyz(i,j,k) =HALF*( t_gupxy*val1 + t_gupyy*gyyz(i,j,k) + t_gupyz*gzzy(i,j,k) )
-     Gamzyz(i,j,k) =HALF*( t_gupxz*val1 + t_gupyz*gyyz(i,j,k) + t_gupzz*gzzy(i,j,k) )
-  enddo
-  enddo
-  enddo
+  Gamxxy =HALF*( gupxx*gxxy + gupxy*gyyx + gupxz*( gxzy + gyzx - gxyz ) )
+  Gamyxy =HALF*( gupxy*gxxy + gupyy*gyyx + gupyz*( gxzy + gyzx - gxyz ) )
+  Gamzxy =HALF*( gupxz*gxxy + gupyz*gyyx + gupzz*( gxzy + gyzx - gxyz ) )

+  Gamxxz =HALF*( gupxx*gxxz + gupxy*( gxyz + gyzx - gxzy ) + gupxz*gzzx )
+  Gamyxz =HALF*( gupxy*gxxz + gupyy*( gxyz + gyzx - gxzy ) + gupyz*gzzx )
+  Gamzxz =HALF*( gupxz*gxxz + gupyz*( gxyz + gyzx - gxzy ) + gupzz*gzzx )

+  Gamxyz =HALF*( gupxx*( gxyz + gxzy - gyzx ) + gupxy*gyyz + gupxz*gzzy )
+  Gamyyz =HALF*( gupxy*( gxyz + gxzy - gyzx ) + gupyy*gyyz + gupyz*gzzy )
+  Gamzyz =HALF*( gupxz*( gxyz + gxzy - gyzx ) + gupyz*gyyz + gupzz*gzzy )
 ! Raise indices of \tilde A_{ij} and store in R_ij

  Rxx =    gupxx * gupxx * Axx + gupxy * gupxy * Ayy + gupxz * gupxz * Azz + &
@@ -316,40 +285,30 @@
  call fderivs(ex,Lap,Lapx,Lapy,Lapz,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
  call fderivs(ex,trK,Kx,Ky,Kz,X,Y,Z,SYM,SYM,SYM,symmetry,Lev)

-  ! reuse fxx/fxy/fxz as temporaries for matter-source combinations
-  fxx = F2o3 * Kx + EIGHT * PI * Sx
-  fxy = F2o3 * Ky + EIGHT * PI * Sy
-  fxz = F2o3 * Kz + EIGHT * PI * Sz
-
-  ! reuse Gamxa/Gamya/Gamza as temporaries for chix*R combinations
-  Gamxa = chix * Rxx + chiy * Rxy + chiz * Rxz
-  Gamya = chix * Rxy + chiy * Ryy + chiz * Ryz
-  Gamza = chix * Rxz + chiy * Ryz + chiz * Rzz
-
   Gamx_rhs = - TWO * (   Lapx * Rxx +   Lapy * Rxy +   Lapz * Rxz ) + &
        TWO * alpn1 * (                                                &
-        -F3o2 * ONE/chin1 * Gamxa - &
-              gupxx * fxx - &
-              gupxy * fxy - &
-              gupxz * fxz + &
+        -F3o2/chin1 * (   chix * Rxx +   chiy * Rxy +   chiz * Rxz ) - &
+              gupxx * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
+              gupxy * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
+              gupxz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
                        Gamxxx * Rxx + Gamxyy * Ryy + Gamxzz * Rzz   + &
                TWO * ( Gamxxy * Rxy + Gamxxz * Rxz + Gamxyz * Ryz ) )

   Gamy_rhs = - TWO * (   Lapx * Rxy +   Lapy * Ryy +   Lapz * Ryz ) + &
        TWO * alpn1 * (                                                &
-        -F3o2 * ONE/chin1 * Gamya - &
-              gupxy * fxx - &
-              gupyy * fxy - &
-              gupyz * fxz + &
+        -F3o2/chin1 * (   chix * Rxy +  chiy * Ryy +    chiz * Ryz ) - &
+              gupxy * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
+              gupyy * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
+              gupyz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
                        Gamyxx * Rxx + Gamyyy * Ryy + Gamyzz * Rzz   + &
                TWO * ( Gamyxy * Rxy + Gamyxz * Rxz + Gamyyz * Ryz ) )

   Gamz_rhs = - TWO * (   Lapx * Rxz +   Lapy * Ryz +   Lapz * Rzz ) + &
        TWO * alpn1 * (                                                &
-        -F3o2 * ONE/chin1 * Gamza - &
-              gupxz * fxx - &
-              gupyz * fxy - &
-              gupzz * fxz + &
+        -F3o2/chin1 * (   chix * Rxz +  chiy * Ryz +    chiz * Rzz ) - &
+              gupxz * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
+              gupyz * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
+              gupzz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
                        Gamzxx * Rxx + Gamzyy * Ryy + Gamzzz * Rzz   + &
                TWO * ( Gamzxy * Rxy + Gamzxz * Rxz + Gamzyz * Ryz ) )

@@ -651,47 +610,47 @@
  fzz = fzz - Gamxzz * chix - Gamyzz * chiy - Gamzzz * chiz
 ! Store D^l D_l chi - 3/(2*chi) D^l chi D_l chi in f

-  f =        gupxx * ( fxx - F3o2 * ONE/chin1 * chix * chix ) + &
-             gupyy * ( fyy - F3o2 * ONE/chin1 * chiy * chiy ) + &
-             gupzz * ( fzz - F3o2 * ONE/chin1 * chiz * chiz ) + &
-       TWO * gupxy * ( fxy - F3o2 * ONE/chin1 * chix * chiy ) + &
-       TWO * gupxz * ( fxz - F3o2 * ONE/chin1 * chix * chiz ) + &
-       TWO * gupyz * ( fyz - F3o2 * ONE/chin1 * chiy * chiz ) 
+  f =        gupxx * ( fxx - F3o2/chin1 * chix * chix ) + &
+             gupyy * ( fyy - F3o2/chin1 * chiy * chiy ) + &
+             gupzz * ( fzz - F3o2/chin1 * chiz * chiz ) + &
+       TWO * gupxy * ( fxy - F3o2/chin1 * chix * chiy ) + &
+       TWO * gupxz * ( fxz - F3o2/chin1 * chix * chiz ) + &
+       TWO * gupyz * ( fyz - F3o2/chin1 * chiy * chiz ) 
 ! Add chi part to Ricci tensor:

-  Rxx = Rxx + (fxx - chix*chix*ONE/chin1*HALF + gxx * f) * ONE/chin1 * HALF
-  Ryy = Ryy + (fyy - chiy*chiy*ONE/chin1*HALF + gyy * f) * ONE/chin1 * HALF
-  Rzz = Rzz + (fzz - chiz*chiz*ONE/chin1*HALF + gzz * f) * ONE/chin1 * HALF
-  Rxy = Rxy + (fxy - chix*chiy*ONE/chin1*HALF + gxy * f) * ONE/chin1 * HALF
-  Rxz = Rxz + (fxz - chix*chiz*ONE/chin1*HALF + gxz * f) * ONE/chin1 * HALF
-  Ryz = Ryz + (fyz - chiy*chiz*ONE/chin1*HALF + gyz * f) * ONE/chin1 * HALF
+  Rxx = Rxx + (fxx - chix*chix/chin1/TWO + gxx * f)/chin1/TWO
+  Ryy = Ryy + (fyy - chiy*chiy/chin1/TWO + gyy * f)/chin1/TWO
+  Rzz = Rzz + (fzz - chiz*chiz/chin1/TWO + gzz * f)/chin1/TWO
+  Rxy = Rxy + (fxy - chix*chiy/chin1/TWO + gxy * f)/chin1/TWO
+  Rxz = Rxz + (fxz - chix*chiz/chin1/TWO + gxz * f)/chin1/TWO
+  Ryz = Ryz + (fyz - chiy*chiz/chin1/TWO + gyz * f)/chin1/TWO

 ! covariant second derivatives of the lapse respect to physical metric
  call fdderivs(ex,Lap,fxx,fxy,fxz,fyy,fyz,fzz,X,Y,Z, &
                SYM,SYM,SYM,symmetry,Lev)

-  gxxx = (gupxx * chix + gupxy * chiy + gupxz * chiz) * ONE/chin1
-  gxxy = (gupxy * chix + gupyy * chiy + gupyz * chiz) * ONE/chin1
-  gxxz = (gupxz * chix + gupyz * chiy + gupzz * chiz) * ONE/chin1
+  gxxx = (gupxx * chix + gupxy * chiy + gupxz * chiz)/chin1
+  gxxy = (gupxy * chix + gupyy * chiy + gupyz * chiz)/chin1
+  gxxz = (gupxz * chix + gupyz * chiy + gupzz * chiz)/chin1
 ! now get physical second kind of connection
-  Gamxxx = Gamxxx - ( TWO * chix * ONE/chin1 - gxx * gxxx )*HALF
+  Gamxxx = Gamxxx - ( (chix + chix)/chin1 - gxx * gxxx )*HALF
  Gamyxx = Gamyxx - (                     - gxx * gxxy )*HALF
  Gamzxx = Gamzxx - (                     - gxx * gxxz )*HALF
  Gamxyy = Gamxyy - (                     - gyy * gxxx )*HALF
-  Gamyyy = Gamyyy - ( TWO * chiy * ONE/chin1 - gyy * gxxy )*HALF
+  Gamyyy = Gamyyy - ( (chiy + chiy)/chin1 - gyy * gxxy )*HALF
  Gamzyy = Gamzyy - (                     - gyy * gxxz )*HALF
  Gamxzz = Gamxzz - (                     - gzz * gxxx )*HALF
  Gamyzz = Gamyzz - (                     - gzz * gxxy )*HALF
-  Gamzzz = Gamzzz - ( TWO * chiz * ONE/chin1 - gzz * gxxz )*HALF
-  Gamxxy = Gamxxy - (  chiy * ONE/chin1 - gxy * gxxx )*HALF
-  Gamyxy = Gamyxy - (  chix * ONE/chin1 - gxy * gxxy )*HALF
+  Gamzzz = Gamzzz - ( (chiz + chiz)/chin1 - gzz * gxxz )*HALF
+  Gamxxy = Gamxxy - (  chiy        /chin1 - gxy * gxxx )*HALF
+  Gamyxy = Gamyxy - (         chix /chin1 - gxy * gxxy )*HALF
  Gamzxy = Gamzxy - (                     - gxy * gxxz )*HALF
-  Gamxxz = Gamxxz - (  chiz * ONE/chin1 - gxz * gxxx )*HALF
+  Gamxxz = Gamxxz - (  chiz        /chin1 - gxz * gxxx )*HALF
  Gamyxz = Gamyxz - (                     - gxz * gxxy )*HALF
-  Gamzxz = Gamzxz - (  chix * ONE/chin1 - gxz * gxxz )*HALF
+  Gamzxz = Gamzxz - (         chix /chin1 - gxz * gxxz )*HALF
  Gamxyz = Gamxyz - (                     - gyz * gxxx )*HALF
-  Gamyyz = Gamyyz - (  chiz * ONE/chin1 - gyz * gxxy )*HALF
-  Gamzyz = Gamzyz - (  chiy * ONE/chin1 - gyz * gxxz )*HALF
+  Gamyyz = Gamyyz - (  chiz        /chin1 - gyz * gxxy )*HALF
+  Gamzyz = Gamzyz - (         chiy /chin1 - gyz * gxxz )*HALF

  fxx = fxx - Gamxxx*Lapx - Gamyxx*Lapy - Gamzxx*Lapz
  fyy = fyy - Gamxyy*Lapx - Gamyyy*Lapy - Gamzyy*Lapz
@@ -734,7 +693,7 @@
       gupxz * (Axy * Azz + Ayz * Axz) + &
       gupyz * (Ayy * Azz + Ayz * Ayz) ) )) -1.6d1*PI*rho + EIGHT * PI * S
  f = - F1o3 *(  gupxx * fxx + gupyy * fyy + gupzz * fzz + &
-        TWO* ( gupxy * fxy + gupxz * fxz + gupyz * fyz ) + alpn1 * ONE/chin1 * f)
+        TWO* ( gupxy * fxy + gupxz * fxz + gupyz * fyz ) + alpn1/chin1*f)
  
  fxx = alpn1 * (Rxx - EIGHT * PI * Sxx) - fxx
  fxy = alpn1 * (Rxy - EIGHT * PI * Sxy) - fxy
@@ -854,8 +813,7 @@
  call fderivs(ex,chi,dtSfx_rhs,dtSfy_rhs,dtSfz_rhs,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
  reta = gupxx * dtSfx_rhs * dtSfx_rhs + gupyy * dtSfy_rhs * dtSfy_rhs + gupzz * dtSfz_rhs * dtSfz_rhs + &
       TWO * (gupxy * dtSfx_rhs * dtSfy_rhs + gupxz * dtSfx_rhs * dtSfz_rhs + gupyz * dtSfy_rhs * dtSfz_rhs)
-  fxx = dsqrt(chin1)
-  reta = 1.31d0/2*dsqrt(reta*ONE/chin1)/(ONE-fxx)**2
+  reta = 1.31d0/2*dsqrt(reta/chin1)/(1-dsqrt(chin1))**2
  dtSfx_rhs = Gamx_rhs - reta*dtSfx
  dtSfy_rhs = Gamy_rhs - reta*dtSfy
  dtSfz_rhs = Gamz_rhs - reta*dtSfz
@@ -867,7 +825,7 @@
  call fderivs(ex,chi,dtSfx_rhs,dtSfy_rhs,dtSfz_rhs,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
  reta = gupxx * dtSfx_rhs * dtSfx_rhs + gupyy * dtSfy_rhs * dtSfy_rhs + gupzz * dtSfz_rhs * dtSfz_rhs + &
       TWO * (gupxy * dtSfx_rhs * dtSfy_rhs + gupxz * dtSfx_rhs * dtSfz_rhs + gupyz * dtSfy_rhs * dtSfz_rhs)
-  reta = 1.31d0/2*dsqrt(reta*ONE/chin1)/(ONE-chin1)**2
+  reta = 1.31d0/2*dsqrt(reta/chin1)/(1-chin1)**2
  dtSfx_rhs = Gamx_rhs - reta*dtSfx
  dtSfy_rhs = Gamy_rhs - reta*dtSfy
  dtSfz_rhs = Gamz_rhs - reta*dtSfz
@@ -875,8 +833,7 @@
  call fderivs(ex,chi,dtSfx_rhs,dtSfy_rhs,dtSfz_rhs,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
  reta = gupxx * dtSfx_rhs * dtSfx_rhs + gupyy * dtSfy_rhs * dtSfy_rhs + gupzz * dtSfz_rhs * dtSfz_rhs + &
       TWO * (gupxy * dtSfx_rhs * dtSfy_rhs + gupxz * dtSfx_rhs * dtSfz_rhs + gupyz * dtSfy_rhs * dtSfz_rhs)
-  fxx = dsqrt(chin1)
-  reta = 1.31d0/2*dsqrt(reta*ONE/chin1)/(ONE-fxx)**2
+  reta = 1.31d0/2*dsqrt(reta/chin1)/(1-dsqrt(chin1))**2
  betax_rhs = FF*Gamx - reta*betax
  betay_rhs = FF*Gamy - reta*betay
  betaz_rhs = FF*Gamz - reta*betaz
@@ -888,7 +845,7 @@
  call fderivs(ex,chi,dtSfx_rhs,dtSfy_rhs,dtSfz_rhs,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
  reta = gupxx * dtSfx_rhs * dtSfx_rhs + gupyy * dtSfy_rhs * dtSfy_rhs + gupzz * dtSfz_rhs * dtSfz_rhs + &
       TWO * (gupxy * dtSfx_rhs * dtSfy_rhs + gupxz * dtSfx_rhs * dtSfz_rhs + gupyz * dtSfy_rhs * dtSfz_rhs)
-  reta = 1.31d0/2*dsqrt(reta*ONE/chin1)/(ONE-chin1)**2
+  reta = 1.31d0/2*dsqrt(reta/chin1)/(1-chin1)**2
  betax_rhs = FF*Gamx - reta*betax
  betay_rhs = FF*Gamy - reta*betay
  betaz_rhs = FF*Gamz - reta*betaz
@@ -1120,48 +1077,48 @@ endif
 ! mov_Res_j = gupkj*(-1/chi d_k chi*A_ij + D_k A_ij) - 2/3 d_j trK - 8 PI s_j where D respect to physical metric
 ! store D_i A_jk - 1/chi d_i chi*A_jk in gjk_i
  call fderivs(ex,Axx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,Ayy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,Azz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
  call fderivs(ex,Axy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
  call fderivs(ex,Axz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
+  call fderivs(ex,Ayy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
  call fderivs(ex,Ayz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
+  call fderivs(ex,Azz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)

  gxxx = gxxx - (  Gamxxx * Axx + Gamyxx * Axy + Gamzxx * Axz &
-                 + Gamxxx * Axx + Gamyxx * Axy + Gamzxx * Axz) - chix*Axx*ONE/chin1
+                 + Gamxxx * Axx + Gamyxx * Axy + Gamzxx * Axz) - chix*Axx/chin1
  gxyx = gxyx - (  Gamxxy * Axx + Gamyxy * Axy + Gamzxy * Axz &
-                 + Gamxxx * Axy + Gamyxx * Ayy + Gamzxx * Ayz) - chix*Axy*ONE/chin1
+                 + Gamxxx * Axy + Gamyxx * Ayy + Gamzxx * Ayz) - chix*Axy/chin1
  gxzx = gxzx - (  Gamxxz * Axx + Gamyxz * Axy + Gamzxz * Axz &
-                 + Gamxxx * Axz + Gamyxx * Ayz + Gamzxx * Azz) - chix*Axz*ONE/chin1
+                 + Gamxxx * Axz + Gamyxx * Ayz + Gamzxx * Azz) - chix*Axz/chin1
  gyyx = gyyx - (  Gamxxy * Axy + Gamyxy * Ayy + Gamzxy * Ayz &
-                 + Gamxxy * Axy + Gamyxy * Ayy + Gamzxy * Ayz) - chix*Ayy*ONE/chin1
+                 + Gamxxy * Axy + Gamyxy * Ayy + Gamzxy * Ayz) - chix*Ayy/chin1
  gyzx = gyzx - (  Gamxxz * Axy + Gamyxz * Ayy + Gamzxz * Ayz &
-                 + Gamxxy * Axz + Gamyxy * Ayz + Gamzxy * Azz) - chix*Ayz*ONE/chin1
+                 + Gamxxy * Axz + Gamyxy * Ayz + Gamzxy * Azz) - chix*Ayz/chin1
  gzzx = gzzx - (  Gamxxz * Axz + Gamyxz * Ayz + Gamzxz * Azz &
-                 + Gamxxz * Axz + Gamyxz * Ayz + Gamzxz * Azz) - chix*Azz*ONE/chin1
+                 + Gamxxz * Axz + Gamyxz * Ayz + Gamzxz * Azz) - chix*Azz/chin1
  gxxy = gxxy - (  Gamxxy * Axx + Gamyxy * Axy + Gamzxy * Axz &
-                 + Gamxxy * Axx + Gamyxy * Axy + Gamzxy * Axz) - chiy*Axx*ONE/chin1
+                 + Gamxxy * Axx + Gamyxy * Axy + Gamzxy * Axz) - chiy*Axx/chin1
  gxyy = gxyy - (  Gamxyy * Axx + Gamyyy * Axy + Gamzyy * Axz &
-                 + Gamxxy * Axy + Gamyxy * Ayy + Gamzxy * Ayz) - chiy*Axy*ONE/chin1
+                 + Gamxxy * Axy + Gamyxy * Ayy + Gamzxy * Ayz) - chiy*Axy/chin1
  gxzy = gxzy - (  Gamxyz * Axx + Gamyyz * Axy + Gamzyz * Axz &
-                 + Gamxxy * Axz + Gamyxy * Ayz + Gamzxy * Azz) - chiy*Axz*ONE/chin1
+                 + Gamxxy * Axz + Gamyxy * Ayz + Gamzxy * Azz) - chiy*Axz/chin1
  gyyy = gyyy - (  Gamxyy * Axy + Gamyyy * Ayy + Gamzyy * Ayz &
-                 + Gamxyy * Axy + Gamyyy * Ayy + Gamzyy * Ayz) - chiy*Ayy*ONE/chin1
+                 + Gamxyy * Axy + Gamyyy * Ayy + Gamzyy * Ayz) - chiy*Ayy/chin1
  gyzy = gyzy - (  Gamxyz * Axy + Gamyyz * Ayy + Gamzyz * Ayz &
-                 + Gamxyy * Axz + Gamyyy * Ayz + Gamzyy * Azz) - chiy*Ayz*ONE/chin1
+                 + Gamxyy * Axz + Gamyyy * Ayz + Gamzyy * Azz) - chiy*Ayz/chin1
  gzzy = gzzy - (  Gamxyz * Axz + Gamyyz * Ayz + Gamzyz * Azz &
-                 + Gamxyz * Axz + Gamyyz * Ayz + Gamzyz * Azz) - chiy*Azz*ONE/chin1
+                 + Gamxyz * Axz + Gamyyz * Ayz + Gamzyz * Azz) - chiy*Azz/chin1
  gxxz = gxxz - (  Gamxxz * Axx + Gamyxz * Axy + Gamzxz * Axz &
-                 + Gamxxz * Axx + Gamyxz * Axy + Gamzxz * Axz) - chiz*Axx*ONE/chin1
+                 + Gamxxz * Axx + Gamyxz * Axy + Gamzxz * Axz) - chiz*Axx/chin1
  gxyz = gxyz - (  Gamxyz * Axx + Gamyyz * Axy + Gamzyz * Axz &
-                 + Gamxxz * Axy + Gamyxz * Ayy + Gamzxz * Ayz) - chiz*Axy*ONE/chin1
+                 + Gamxxz * Axy + Gamyxz * Ayy + Gamzxz * Ayz) - chiz*Axy/chin1
  gxzz = gxzz - (  Gamxzz * Axx + Gamyzz * Axy + Gamzzz * Axz &
-                 + Gamxxz * Axz + Gamyxz * Ayz + Gamzxz * Azz) - chiz*Axz*ONE/chin1
+                 + Gamxxz * Axz + Gamyxz * Ayz + Gamzxz * Azz) - chiz*Axz/chin1
  gyyz = gyyz - (  Gamxyz * Axy + Gamyyz * Ayy + Gamzyz * Ayz &
-                 + Gamxyz * Axy + Gamyyz * Ayy + Gamzyz * Ayz) - chiz*Ayy*ONE/chin1
+                 + Gamxyz * Axy + Gamyyz * Ayy + Gamzyz * Ayz) - chiz*Ayy/chin1
  gyzz = gyzz - (  Gamxzz * Axy + Gamyzz * Ayy + Gamzzz * Ayz &
-                 + Gamxyz * Axz + Gamyyz * Ayz + Gamzyz * Azz) - chiz*Ayz*ONE/chin1
+                 + Gamxyz * Axz + Gamyyz * Ayz + Gamzyz * Azz) - chiz*Ayz/chin1
  gzzz = gzzz - (  Gamxzz * Axz + Gamyzz * Ayz + Gamzzz * Azz &
-                 + Gamxzz * Axz + Gamyzz * Ayz + Gamzzz * Azz) - chiz*Azz*ONE/chin1
+                 + Gamxzz * Axz + Gamyzz * Ayz + Gamzzz * Azz) - chiz*Azz/chin1
 movx_Res = gupxx*gxxx + gupyy*gxyy + gupzz*gxzz &
          +gupxy*gxyx + gupxz*gxzx + gupyz*gxzy &
          +gupxy*gxxy + gupxz*gxxz + gupyz*gxyz
--- a/AMSS_NCKU_source/diff_new.f90
+++ b/AMSS_NCKU_source/diff_new.f90
@@ -69,6 +69,7 @@
  fy = ZEO
  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -151,6 +152,7 @@

  fx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -218,6 +220,7 @@

  fy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -282,6 +285,7 @@

  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -371,6 +375,7 @@
  fxz = ZEO
  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -469,6 +474,7 @@

  fxx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -531,6 +537,7 @@

  fyy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -594,6 +601,7 @@

  fzz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -657,6 +665,7 @@

  fxy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -719,6 +728,7 @@

  fxz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -780,6 +790,7 @@

  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -866,6 +877,7 @@
  fxz = ZEO
  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -997,6 +1009,7 @@
  fy = ZEO
  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1151,6 +1164,7 @@

  fx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1227,6 +1241,7 @@

  fy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1297,6 +1312,7 @@

  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1401,6 +1417,7 @@
  fxz = ZEO
  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1576,6 +1593,7 @@

  fxx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1643,6 +1661,7 @@

  fyy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1712,6 +1731,7 @@

  fzz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1781,6 +1801,7 @@

  fxy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1851,6 +1872,7 @@

  fxz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1919,6 +1941,7 @@

  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -1939,309 +1962,6 @@
  return

  end subroutine fddyz
-  subroutine fderivs_batch4(ex,f1,f2,f3,f4, &
-                            f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z,f4x,f4y,f4z, &
-                            X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
-  implicit none
-
-  integer,                               intent(in ):: ex(1:3),symmetry,onoff
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3,f4
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f4x,f4y,f4z
-  real*8,                                intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
-  real*8,                                intent(in ):: SYM1,SYM2,SYM3
-
-!~~~~~~ other variables
-
-  real*8 :: dX,dY,dZ
-  real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3,fh4
-  real*8, dimension(3) :: SoA
-  integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
-  real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
-  integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
-  real*8,  parameter :: ZEO=0.d0,ONE=1.d0
-  real*8,  parameter :: TWO=2.d0,EIT=8.d0
-  real*8,  parameter :: F12=1.2d1
-
-  dX = X(2)-X(1)
-  dY = Y(2)-Y(1)
-  dZ = Z(2)-Z(1)
-
-  imax = ex(1)
-  jmax = ex(2)
-  kmax = ex(3)
-
-  imin = 1
-  jmin = 1
-  kmin = 1
-  if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
-
-  SoA(1) = SYM1
-  SoA(2) = SYM2
-  SoA(3) = SYM3
-
-  call symmetry_bd(2,ex,f1,fh1,SoA)
-  call symmetry_bd(2,ex,f2,fh2,SoA)
-  call symmetry_bd(2,ex,f3,fh3,SoA)
-  call symmetry_bd(2,ex,f4,fh4,SoA)
-
-  d12dx = ONE/F12/dX
-  d12dy = ONE/F12/dY
-  d12dz = ONE/F12/dZ
-
-  d2dx = ONE/TWO/dX
-  d2dy = ONE/TWO/dY
-  d2dz = ONE/TWO/dZ
-
-  f1x = ZEO; f1y = ZEO; f1z = ZEO
-  f2x = ZEO; f2y = ZEO; f2z = ZEO
-  f3x = ZEO; f3y = ZEO; f3z = ZEO
-  f4x = ZEO; f4y = ZEO; f4z = ZEO
-
-  do k=1,ex(3)-1
-  do j=1,ex(2)-1
-  do i=1,ex(1)-1
-   if(i+2 <= imax .and. i-2 >= imin .and. &
-      j+2 <= jmax .and. j-2 >= jmin .and. &
-      k+2 <= kmax .and. k-2 >= kmin) then
-      f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
-      f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
-      f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
-
-      f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
-      f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
-      f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
-
-      f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
-      f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
-      f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
-
-      f4x(i,j,k)=d12dx*(fh4(i-2,j,k)-EIT*fh4(i-1,j,k)+EIT*fh4(i+1,j,k)-fh4(i+2,j,k))
-      f4y(i,j,k)=d12dy*(fh4(i,j-2,k)-EIT*fh4(i,j-1,k)+EIT*fh4(i,j+1,k)-fh4(i,j+2,k))
-      f4z(i,j,k)=d12dz*(fh4(i,j,k-2)-EIT*fh4(i,j,k-1)+EIT*fh4(i,j,k+1)-fh4(i,j,k+2))
-   elseif(i+1 <= imax .and. i-1 >= imin .and. &
-          j+1 <= jmax .and. j-1 >= jmin .and. &
-          k+1 <= kmax .and. k-1 >= kmin) then
-      f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
-      f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
-      f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
-
-      f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
-      f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
-      f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
-
-      f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
-      f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
-      f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
-
-      f4x(i,j,k)=d2dx*(-fh4(i-1,j,k)+fh4(i+1,j,k))
-      f4y(i,j,k)=d2dy*(-fh4(i,j-1,k)+fh4(i,j+1,k))
-      f4z(i,j,k)=d2dz*(-fh4(i,j,k-1)+fh4(i,j,k+1))
-   endif
-  enddo
-  enddo
-  enddo
-
-  return
-
-  end subroutine fderivs_batch4
-!-----------------------------------------------------------------------------
-! batch first derivatives (3 fields), same symmetry setup
-!-----------------------------------------------------------------------------
-  subroutine fderivs_batch3(ex,f1,f2,f3, &
-                            f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z, &
-                            X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
-  implicit none
-
-  integer,                               intent(in ):: ex(1:3),symmetry,onoff
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
-  real*8,                                intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
-  real*8,                                intent(in ):: SYM1,SYM2,SYM3
-
-!~~~~~~ other variables
-
-  real*8 :: dX,dY,dZ
-  real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3
-  real*8, dimension(3) :: SoA
-  integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
-  real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
-  integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
-  real*8,  parameter :: ZEO=0.d0,ONE=1.d0
-  real*8,  parameter :: TWO=2.d0,EIT=8.d0
-  real*8,  parameter :: F12=1.2d1
-
-  dX = X(2)-X(1)
-  dY = Y(2)-Y(1)
-  dZ = Z(2)-Z(1)
-
-  imax = ex(1)
-  jmax = ex(2)
-  kmax = ex(3)
-
-  imin = 1
-  jmin = 1
-  kmin = 1
-  if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
-
-  SoA(1) = SYM1
-  SoA(2) = SYM2
-  SoA(3) = SYM3
-
-  call symmetry_bd(2,ex,f1,fh1,SoA)
-  call symmetry_bd(2,ex,f2,fh2,SoA)
-  call symmetry_bd(2,ex,f3,fh3,SoA)
-
-  d12dx = ONE/F12/dX
-  d12dy = ONE/F12/dY
-  d12dz = ONE/F12/dZ
-
-  d2dx = ONE/TWO/dX
-  d2dy = ONE/TWO/dY
-  d2dz = ONE/TWO/dZ
-
-  f1x = ZEO; f1y = ZEO; f1z = ZEO
-  f2x = ZEO; f2y = ZEO; f2z = ZEO
-  f3x = ZEO; f3y = ZEO; f3z = ZEO
-
-  do k=1,ex(3)-1
-  do j=1,ex(2)-1
-  do i=1,ex(1)-1
-   if(i+2 <= imax .and. i-2 >= imin .and. &
-      j+2 <= jmax .and. j-2 >= jmin .and. &
-      k+2 <= kmax .and. k-2 >= kmin) then
-      f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
-      f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
-      f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
-
-      f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
-      f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
-      f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
-
-      f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
-      f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
-      f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
-   elseif(i+1 <= imax .and. i-1 >= imin .and. &
-          j+1 <= jmax .and. j-1 >= jmin .and. &
-          k+1 <= kmax .and. k-1 >= kmin) then
-      f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
-      f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
-      f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
-
-      f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
-      f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
-      f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
-
-      f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
-      f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
-      f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
-   endif
-  enddo
-  enddo
-  enddo
-
-  return
-
-  end subroutine fderivs_batch3
-!-----------------------------------------------------------------------------
-! batch first derivatives (2 fields), same symmetry setup
-!-----------------------------------------------------------------------------
-  subroutine fderivs_batch2(ex,f1,f2, &
-                            f1x,f1y,f1z,f2x,f2y,f2z, &
-                            X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
-  implicit none
-
-  integer,                               intent(in ):: ex(1:3),symmetry,onoff
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
-  real*8,  dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
-  real*8,                                intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
-  real*8,                                intent(in ):: SYM1,SYM2,SYM3
-
-!~~~~~~ other variables
-
-  real*8 :: dX,dY,dZ
-  real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2
-  real*8, dimension(3) :: SoA
-  integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
-  real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
-  integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
-  real*8,  parameter :: ZEO=0.d0,ONE=1.d0
-  real*8,  parameter :: TWO=2.d0,EIT=8.d0
-  real*8,  parameter :: F12=1.2d1
-
-  dX = X(2)-X(1)
-  dY = Y(2)-Y(1)
-  dZ = Z(2)-Z(1)
-
-  imax = ex(1)
-  jmax = ex(2)
-  kmax = ex(3)
-
-  imin = 1
-  jmin = 1
-  kmin = 1
-  if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
-  if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
-
-  SoA(1) = SYM1
-  SoA(2) = SYM2
-  SoA(3) = SYM3
-
-  call symmetry_bd(2,ex,f1,fh1,SoA)
-  call symmetry_bd(2,ex,f2,fh2,SoA)
-
-  d12dx = ONE/F12/dX
-  d12dy = ONE/F12/dY
-  d12dz = ONE/F12/dZ
-
-  d2dx = ONE/TWO/dX
-  d2dy = ONE/TWO/dY
-  d2dz = ONE/TWO/dZ
-
-  f1x = ZEO; f1y = ZEO; f1z = ZEO
-  f2x = ZEO; f2y = ZEO; f2z = ZEO
-
-  do k=1,ex(3)-1
-  do j=1,ex(2)-1
-  do i=1,ex(1)-1
-   if(i+2 <= imax .and. i-2 >= imin .and. &
-      j+2 <= jmax .and. j-2 >= jmin .and. &
-      k+2 <= kmax .and. k-2 >= kmin) then
-      f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
-      f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
-      f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
-
-      f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
-      f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
-      f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
-   elseif(i+1 <= imax .and. i-1 >= imin .and. &
-          j+1 <= jmax .and. j-1 >= jmin .and. &
-          k+1 <= kmax .and. k-1 >= kmin) then
-      f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
-      f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
-      f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
-
-      f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
-      f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
-      f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
-   endif
-  enddo
-  enddo
-  enddo
-
-  return
-
-  end subroutine fderivs_batch2

 #elif (ghost_width == 4)
 ! sixth order code
@@ -2314,6 +2034,7 @@
  fy = ZEO
  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2380,9 +2101,6 @@

  end subroutine fderivs
 !-----------------------------------------------------------------------------
-! batch first derivatives (4 fields), same symmetry setup
-!-----------------------------------------------------------------------------
-!-----------------------------------------------------------------------------
 !
 ! single derivatives dx
 !
@@ -2433,6 +2151,7 @@

  fx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2518,6 +2237,7 @@

  fy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2594,6 +2314,7 @@

  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2712,6 +2433,7 @@
  fxz = ZEO
  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2899,6 +2621,7 @@

  fxx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -2971,6 +2694,7 @@

  fyy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3046,6 +2770,7 @@

  fzz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3121,6 +2846,7 @@

  fxy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3201,6 +2927,7 @@

  fxz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3279,6 +3006,7 @@

  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3386,6 +3114,7 @@
  fy = ZEO
  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3522,6 +3251,7 @@

  fx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3617,6 +3347,7 @@

  fy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3701,6 +3432,7 @@

  fz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -3836,6 +3568,7 @@
  fxz = ZEO
  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4108,6 +3841,7 @@

  fxx = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4189,6 +3923,7 @@

  fyy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4273,6 +4008,7 @@
  
  fzz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4357,6 +4093,7 @@

  fxy = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4459,6 +4196,7 @@

  fxz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
@@ -4559,6 +4297,7 @@

  fyz = ZEO

+  !$omp parallel do collapse(3) schedule(static)
  do k=1,ex(3)-1
  do j=1,ex(2)-1
  do i=1,ex(1)-1
--- a/AMSS_NCKU_source/makefile.inc
+++ b/AMSS_NCKU_source/makefile.inc
@@ -15,16 +15,16 @@ LDLIBS  = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore
 ## -xHost: Optimize for the host CPU architecture (Intel/AMD compatible)
 ## -fp-model fast=2: Aggressive floating-point optimizations
 ## -fma: Enable fused multiply-add instructions
-## Note: OpenMP has been disabled (-qopenmp removed) due to performance issues
-CXXAPPFLAGS  = -O3 -xHost -fp-model fast=2 -fma \
+## Note: OpenMP enabled for hybrid MPI+OpenMP
+CXXAPPFLAGS  = -O3 -xHost -fp-model fast=2 -fma -qopenmp \
               -Dfortran3 -Dnewc -I${MKLROOT}/include
-f90appflags  = -O3 -xHost -fp-model fast=2 -fma \
+f90appflags  = -O3 -xHost -fp-model fast=2 -fma -qopenmp \
               -fpp -I${MKLROOT}/include
 f90          = ifx
 f77          = ifx
 CXX          = icpx
 CC           = icx
-CLINKER      = mpiicpx 
+CLINKER      = mpiicpx -qopenmp 

 Cu = nvcc
 CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
--- a/generate_macrodef.py
+++ b/generate_macrodef.py
@@ -392,17 +392,6 @@ def generate_macrodef_fh():
        print( "# Finite_Difference_Method #define ghost_width setting error!!!",   file=file1 )
        print(                                                   file=file1 )

-    # Define macro DEBUG_NAN_CHECK
-    # 0: off (default), 1: on
-
-    debug_nan_check = getattr(input_data, "Debug_NaN_Check", 0)
-    if debug_nan_check:
-        print( "#define DEBUG_NAN_CHECK 1", file=file1 )
-        print(                             file=file1 )
-    else:
-        print( "#define DEBUG_NAN_CHECK 0", file=file1 )
-        print(                             file=file1 )
-
    # Whether to use a shell-patch grid
    # use shell or not

@@ -525,9 +514,6 @@ def generate_macrodef_fh():
    print( "    6th order: 4",                                                                      file=file1 )
    print( "    8th order: 5",                                                                      file=file1 )
    print(                                                                                          file=file1 )
-    print( "define DEBUG_NAN_CHECK",                                                                file=file1 )
-    print( "    0: off (default), 1: on",                                                           file=file1 )
-    print(                                                                                          file=file1 )
    print( "define WithShell",                                                                      file=file1 )
    print( "    use shell or not",                                                                  file=file1 )
    print(                                                                                          file=file1 )
--- a/inputfile_example/AMSS_NCKU_Input.py
+++ b/inputfile_example/AMSS_NCKU_Input.py
@@ -36,7 +36,6 @@ Equation_Class           = "BSSN"                  ## Evolution Equation: choose
 Initial_Data_Method      = "Ansorg-TwoPuncture"    ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
 Time_Evolution_Method    = "runge-kutta-45"        ## time evolution method: choose "runge-kutta-45"
 Finite_Diffenence_Method = "4th-order"             ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
-Debug_NaN_Check          = 0                       ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)

 #################################################

--- a/makefile_and_run.py
+++ b/makefile_and_run.py
@@ -11,17 +11,14 @@
 import AMSS_NCKU_Input as input_data
 import subprocess

-## CPU core binding configuration using taskset
-## taskset ensures all child processes inherit the CPU affinity mask
-## This forces make and all compiler processes to use only nohz_full cores (4-55, 60-111)
-## Format: taskset -c 4-55,60-111 ensures processes only run on these cores
-#NUMACTL_CPU_BIND = "taskset -c 4-55,60-111"
+## CPU core binding configuration
+## Removed hardcoded taskset to allow full utilization of 96 cores via MPI+OpenMP
 NUMACTL_CPU_BIND = ""

 ## Build parallelism configuration
 ## Use nohz_full cores (4-55, 60-111) for compilation: 52 + 52 = 104 cores
 ## Set make -j to utilize available cores for faster builds
-BUILD_JOBS = 14
+BUILD_JOBS = 96


 ##################################################################
@@ -38,7 +35,7 @@ def makefile_ABE():
    print( " Compiling the AMSS-NCKU executable file ABE/ABEGPU " ) 
    print(                                                        )

-    ## Build command with CPU binding to nohz_full cores
+    ## Build command
    if (input_data.GPU_Calculation == "no"):
        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABE"
    elif (input_data.GPU_Calculation == "yes"):
@@ -79,7 +76,7 @@ def makefile_TwoPunctureABE():
    print( " Compiling the AMSS-NCKU executable file TwoPunctureABE " )
    print(                                                            )
    
-    ## Build command with CPU binding to nohz_full cores
+    ## Build command
    makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} TwoPunctureABE"

    ## Execute the command with subprocess.Popen and stream output
@@ -114,13 +111,23 @@ def run_ABE():
    print( " Running the AMSS-NCKU executable file ABE/ABEGPU " ) 
    print(                                                      )

+    ## Calculate OMP_NUM_THREADS
+    ## User has 96 cores. Calculate threads per MPI process.
+    total_physical_cores = 96
+    omp_num_threads = total_physical_cores // input_data.MPI_processes
+    if omp_num_threads < 1:
+        omp_num_threads = 1
+    
+    print( f" Configuration: {input_data.MPI_processes} MPI processes, {omp_num_threads} OpenMP threads per process." )
+    print( f" Total cores utilized: {input_data.MPI_processes * omp_num_threads}" )
+
    ## Define the command to run; cast other values to strings as needed
    
    if (input_data.GPU_Calculation == "no"):
-        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
+        mpi_command         = f"{NUMACTL_CPU_BIND} mpirun -genv OMP_NUM_THREADS {omp_num_threads} -np {input_data.MPI_processes} ./ABE"
        mpi_command_outfile = "ABE_out.log"
    elif (input_data.GPU_Calculation == "yes"):
-        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
+        mpi_command         = f"{NUMACTL_CPU_BIND} mpirun -genv OMP_NUM_THREADS {omp_num_threads} -np {input_data.MPI_processes} ./ABEGPU"
        mpi_command_outfile = "ABEGPU_out.log"
 
    ## Execute the MPI command and stream output