Fix BSSN C gauge RHS parity

Shell C functions must export Fortran-compatible symbols with trailing
underscore so bssn_rhs_ss.f90 and getnp4.f90 can link when WithShell is
active and USE_CXX_SHELL_KERNELS=1 replaces Fortran diff_new_sh.o.

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

.gitignore

@@ -1,6 +1,6 @@
 __pycache__
 GW150914
-GW150914-origin
+GW150914*
 docs
 *.tmp
-
+.codex

.idea/vcs.xml

@@ -1,6 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="VcsDirectoryMappings">
-    <mapping directory="" vcs="Git" />
-  </component>
-</project>

AMSS_NCKU_Input.py

@@ -16,9 +16,9 @@ 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    = 64                             ## number of mpi processes used in the simulation
+MPI_processes    = 2                             ## number of mpi processes used in the simulation
 
-GPU_Calculation  = "no"                          ## Use GPU or not 
+GPU_Calculation  = "yes"                          ## 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
@@ -158,7 +158,7 @@ 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       = "yes"                    ## whether to find the apparent horizon: choose "yes" or "no"
 
 AHF_Find_Every = 24
 AHF_Dump_Time  = 20.0

AMSS_NCKU_Program.py

@@ -58,31 +58,36 @@ File_directory = os.path.join(input_data.File_directory)
 
 ## If the specified output directory exists, ask the user whether to continue
 if os.path.exists(File_directory):
-    print( " Output dictionary has been existed !!!  "                                                              )
-    print( " If you want to overwrite the existing file directory, please input 'continue' in the terminal !! "     ) 
-    print( " If you want to retain the existing file directory, please input 'stop' in the terminal to stop the "   ) 
-    print( " simulation. Then you can reset the output dictionary in the input script file AMSS_NCKU_Input.py !!! " )
-    print(                                                                                                          )
-    ## Prompt whether to overwrite the existing directory
-    while True:
-        try:
-            inputvalue = input()
-            ## If the user agrees to overwrite, proceed and remove the existing directory
-            if ( inputvalue == "continue" ):
-                print( " Continue the calculation !!! " )
-                print(                                  )
-                break  
-            ## If the user chooses not to overwrite, exit and keep the existing directory
-            elif ( inputvalue == "stop" ):
-                print( " Stop the calculation !!! "    )
-                sys.exit() 
-            ## If the user input is invalid, prompt again
-            else:
+    auto_overwrite = str(getattr(input_data, "Auto_Overwrite_Output", "yes")).strip().lower()
+    if auto_overwrite in ("1", "yes", "y", "true", "on", "continue"):
+        print( " Output dictionary has been existed; Auto_Overwrite_Output=yes, continue the calculation. " )
+        print(                                                                                              )
+    else:
+        print( " Output dictionary has been existed !!!  "                                                              )
+        print( " If you want to overwrite the existing file directory, please input 'continue' in the terminal !! "     ) 
+        print( " If you want to retain the existing file directory, please input 'stop' in the terminal to stop the "   ) 
+        print( " simulation. Then you can reset the output dictionary in the input script file AMSS_NCKU_Input.py !!! " )
+        print(                                                                                                          )
+        ## Prompt whether to overwrite the existing directory
+        while True:
+            try:
+                inputvalue = input()
+                ## If the user agrees to overwrite, proceed and remove the existing directory
+                if ( inputvalue == "continue" ):
+                    print( " Continue the calculation !!! " )
+                    print(                                  )
+                    break  
+                ## If the user chooses not to overwrite, exit and keep the existing directory
+                elif ( inputvalue == "stop" ):
+                    print( " Stop the calculation !!! "    )
+                    sys.exit() 
+                ## If the user input is invalid, prompt again
+                else:
+                    print( " Please input your choice !!! "                   )
+                    print( " Input 'continue' or 'stop' in the terminal !!! " )
+            except ValueError:
                 print( " Please input your choice !!! "                   )
                 print( " Input 'continue' or 'stop' in the terminal !!! " )
-        except ValueError:
-            print( " Please input your choice !!! "                   )
-            print( " Input 'continue' or 'stop' in the terminal !!! " )
         
 ## Remove the existing output directory if present
 shutil.rmtree(File_directory, ignore_errors=True)
@@ -126,7 +131,12 @@ setup.generate_AMSSNCKU_input()
 #inputvalue = input()  ## Wait for user input (press Enter) to proceed
 #print()
 
-## Generate AMSS-NCKU program input files based on the configured parameters
+setup.print_puncture_information()
+
+
+##################################################################
+
+## Generate AMSS-NCKU program input files based on the configured parameters
 
 print(                                                                                   )
 print( " Generating the AMSS-NCKU input parfile for the ABE executable. " ) 
@@ -253,7 +263,7 @@ print()
 if (input_data.GPU_Calculation == "no"):
     ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABE")
 elif (input_data.GPU_Calculation == "yes"):
-    ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABEGPU")
+    ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABE_CUDA")
 
 if not os.path.exists( ABE_file ):
     print(                                                                                                  )
@@ -307,7 +317,7 @@ if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
     
     import generate_TwoPuncture_input
     
-    generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input(numerical_grid.puncture_data)
+    generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input()
     
     print(                                                                                              )
     print( " The input parfile for the TwoPunctureABE executable has been generated. " )
@@ -349,7 +359,7 @@ if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
 
 import renew_puncture_parameter
     
-renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory, numerical_grid.puncture_data)
+renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory)
 
 
 ## Generated AMSS-NCKU input filename

AMSS_NCKU_Program_Plot.py

@@ -0,0 +1,100 @@
+##################################################################
+##
+## AMSS-NCKU Plot-Only Restart Script
+## Author: Xiaoqu / Claude
+## 2026/05/12
+##
+## This script checks for existing output data from AMSS_NCKU_Program.py.
+## If data exists, it skips all computation and goes directly to plotting,
+## saving time when plotting was interrupted.
+## If no data is found, it exits with a message.
+##
+##################################################################
+
+## Guard against re-execution by multiprocessing child processes.
+if __name__ != '__main__':
+    import sys as _sys
+    _sys.exit(0)
+
+
+import os
+import sys
+
+import AMSS_NCKU_Input as input_data
+
+##################################################################
+
+## Construct paths from input configuration
+File_directory         = os.path.join(input_data.File_directory)
+output_directory       = os.path.join(File_directory, "AMSS_NCKU_output")
+binary_results_directory = os.path.join(output_directory, input_data.Output_directory)
+figure_directory       = os.path.join(File_directory, "figure")
+
+##################################################################
+
+## Check whether the required output data files exist
+
+required_files = [
+    os.path.join(binary_results_directory, "bssn_BH.dat"),
+    os.path.join(binary_results_directory, "bssn_ADMQs.dat"),
+    os.path.join(binary_results_directory, "bssn_psi4.dat"),
+    os.path.join(binary_results_directory, "bssn_constraint.dat"),
+]
+
+missing_files = [f for f in required_files if not os.path.exists(f)]
+
+if missing_files:
+    print(" No existing AMSS_NCKU_Program.py output data found. ")
+    print(" The following required files are missing: ")
+    for f in missing_files:
+        print(f"   {f}")
+    print()
+    print(" Please run AMSS_NCKU_Program.py first to generate the simulation data. ")
+    print(" Exiting. ")
+    sys.exit(1)
+
+print(" Found existing AMSS_NCKU_Program.py output data. "          )
+print(" Skipping all computation and going directly to plotting. " )
+print()
+
+## Ensure the figure directory exists (it should, but be safe)
+os.makedirs(figure_directory, exist_ok=True)
+
+##################################################################
+
+## Plot the AMSS-NCKU program results
+
+import plot_xiaoqu
+import plot_GW_strain_amplitude_xiaoqu
+from parallel_plot_helper import run_plot_tasks_parallel
+
+plot_tasks = []
+
+## Plot black hole trajectory
+plot_tasks.append((plot_xiaoqu.generate_puncture_orbit_plot,   (binary_results_directory, figure_directory)))
+plot_tasks.append((plot_xiaoqu.generate_puncture_orbit_plot3D, (binary_results_directory, figure_directory)))
+
+## Plot black hole separation vs. time
+plot_tasks.append((plot_xiaoqu.generate_puncture_distence_plot, (binary_results_directory, figure_directory)))
+
+## Plot gravitational waveforms (psi4 and strain amplitude)
+for i in range(input_data.Detector_Number):
+    plot_tasks.append((plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i)))
+    plot_tasks.append((plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot, (binary_results_directory, figure_directory, i)))
+
+## Plot ADM mass evolution
+for i in range(input_data.Detector_Number):
+    plot_tasks.append((plot_xiaoqu.generate_ADMmass_plot, (binary_results_directory, figure_directory, i)))
+
+## Plot Hamiltonian constraint violation over time
+for i in range(input_data.grid_level):
+    plot_tasks.append((plot_xiaoqu.generate_constraint_check_plot, (binary_results_directory, figure_directory, i)))
+
+run_plot_tasks_parallel(plot_tasks)
+
+## Plot stored binary data (runs serially, not in the parallel pool)
+plot_xiaoqu.generate_binary_data_plot(binary_results_directory, figure_directory)
+
+print()
+print(" Plotting completed successfully. ")
+print()

AMSS_NCKU_source/ABE.C

@@ -198,16 +198,16 @@ int main(int argc, char *argv[])
       if (myrank == 0)
       {
             string out_dir;
-            char filename[50];
-            map<string, string>::iterator iter;
-            iter = parameters::str_par.find("output dir");
-            if (iter != parameters::str_par.end())
-            {
-                  out_dir = iter->second;
-            }
-            sprintf(filename, "%s/setting.par", out_dir.c_str());
-            ofstream setfile;
-            setfile.open(filename, ios::trunc);
+            string filename;
+            map<string, string>::iterator iter;
+            iter = parameters::str_par.find("output dir");
+            if (iter != parameters::str_par.end())
+            {
+                  out_dir = iter->second;
+            }
+            filename = out_dir + "/setting.par";
+            ofstream setfile;
+            setfile.open(filename.c_str(), ios::trunc);
 
             if (!setfile.good())
             {
@@ -484,7 +484,11 @@ int main(int argc, char *argv[])
             cout << endl;
       }
 
-      delete ADM;
+      // Let the process teardown reclaim the simulation object.  Some derived
+      // equation classes keep MPI/CUDA-backed state whose destructor ordering
+      // is fragile at program shutdown.
+      if (getenv("AMSS_DELETE_ADM_ON_EXIT"))
+            delete ADM;
 
       //=======================caculation done=============================================================
 

AMSS_NCKU_source/Ansorg.h

@@ -1,53 +1,53 @@
-
-#ifndef Ansorg_H
-#define Ansorg_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#define PI M_PI
-
-class Ansorg
-{
-protected:
-  int n1, n2, n3, ntotal;
-  int order;
-  double *coordA, *coordB, *coordphi;
-  int ps_rxx, ps_rxy, ps_ryx, ps_ryy;
-  double ps_b, ps_dx;
-  double PIh;
-  double *pu_ps;
-  int myrank;
-
-public:
-  Ansorg(char *filename, int orderi);
-  ~Ansorg();
-  double ps_u_at_xyz(double x, double y, double z);
-  void set_ABp();
-  void xyz_to_ABp(double x, double y, double z,
-                  double *A, double *B, double *phi);
-  double interpolate_tri_bar(double x, double y, double z,
-                             int n1, int n2, int n3,
-                             double *x1, double *x2, double *x3, double *yp);
-  int find_point_bisection(double x, int n, double *xp, int o);
-  void barycentric_omega(int n, int s, double *x, double *omega);
-  double barycentric(double x0, int n, int s, double *x, double *y,
-                     double *omega);
-};
-#endif /* Ansorg_H */
+
+#ifndef Ansorg_H
+#define Ansorg_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <string>
+#include <cmath>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include <mpi.h>
+
+#define PI M_PI
+
+class Ansorg
+{
+protected:
+  int n1, n2, n3, ntotal;
+  int order;
+  double *coordA, *coordB, *coordphi;
+  int ps_rxx, ps_rxy, ps_ryx, ps_ryy;
+  double ps_b, ps_dx;
+  double PIh;
+  double *pu_ps;
+  int myrank;
+
+public:
+  Ansorg(char *filename, int orderi);
+  ~Ansorg();
+  double ps_u_at_xyz(double x, double y, double z);
+  void set_ABp();
+  void xyz_to_ABp(double x, double y, double z,
+                  double *A, double *B, double *phi);
+  double interpolate_tri_bar(double x, double y, double z,
+                             int n1, int n2, int n3,
+                             double *x1, double *x2, double *x3, double *yp);
+  int find_point_bisection(double x, int n, double *xp, int o);
+  void barycentric_omega(int n, int s, double *x, double *omega);
+  double barycentric(double x0, int n, int s, double *x, double *y,
+                     double *omega);
+};
+#endif /* Ansorg_H */

AMSS_NCKU_source/BH_diagnostics.h

@@ -1,101 +1,101 @@
-#ifndef BH_DIAGNOSTICS_H
-#define BH_DIAGNOSTICS_H
-namespace AHFinderDirect
-{
-
-	struct BH_diagnostics
-	{
-	public:
-		// mean x,y,z
-		fp centroid_x, centroid_y, centroid_z;
-
-		// these are quadrupole moments about the centroid, i.e.
-		// mean(xi*xj) - centroid_i*centroid_j
-		fp quadrupole_xx, quadrupole_xy, quadrupole_xz,
-			quadrupole_yy, quadrupole_yz,
-			quadrupole_zz;
-
-		// min,max,mean surface radius about local coordinate origin
-		fp min_radius, max_radius, mean_radius;
-
-		// xyz bounding box
-		fp min_x, max_x,
-			min_y, max_y,
-			min_z, max_z;
-
-		// proper circumference
-		// (computed using induced metric along these local-coordinate planes)
-		fp circumference_xy,
-			circumference_xz,
-			circumference_yz;
-
-		// surface area (computed using induced metric)
-		// and quantities derived from it
-		fp area, irreducible_mass, areal_radius;
-
-		double Px, Py, Pz, Sx, Sy, Sz;
-
-	public:
-		// position of diagnostics in buffer and number of diagnostics
-		enum
-		{
-			posn__centroid_x = 0,
-			posn__centroid_y,
-			posn__centroid_z,
-			posn__quadrupole_xx,
-			posn__quadrupole_xy,
-			posn__quadrupole_xz,
-			posn__quadrupole_yy,
-			posn__quadrupole_yz,
-			posn__quadrupole_zz,
-			posn__min_radius,
-			posn__max_radius,
-			posn__mean_radius,
-
-			posn__min_x,
-			posn__max_x,
-			posn__min_y,
-			posn__max_y,
-			posn__min_z,
-			posn__max_z,
-
-			posn__circumference_xy,
-			posn__circumference_xz,
-			posn__circumference_yz,
-
-			posn__area,
-			posn__irreducible_mass,
-			posn__areal_radius,
-
-			N_buffer // no comma	// size of buffer
-		};
-
-		// copy diagnostics to/from buffer
-		void copy_to_buffer(double buffer[N_buffer]) const;
-		void copy_from_buffer(const double buffer[N_buffer]);
-
-	public:
-		void compute(patch_system &ps);
-
-		void compute_signature(patch_system &ps, const double dT);
-
-		FILE *setup_output_file(int N_horizons, int hn)
-			const;
-
-		void output(FILE *fileptr, double time)
-			const;
-
-		BH_diagnostics();
-
-	private:
-		static double surface_integral(const patch_system &ps,
-									   int src_gfn, bool src_gfn_is_even_across_xy_plane,
-									   bool src_gfn_is_even_across_xz_plane,
-									   bool src_gfn_is_even_across_yz_plane,
-									   enum patch::integration_method method);
-	};
-
-	//******************************************************************************
-
-} // namespace AHFinderDirect
-#endif /* BH_DIAGNOSTICS_H */
+#ifndef BH_DIAGNOSTICS_H
+#define BH_DIAGNOSTICS_H
+namespace AHFinderDirect
+{
+
+	struct BH_diagnostics
+	{
+	public:
+		// mean x,y,z
+		fp centroid_x, centroid_y, centroid_z;
+
+		// these are quadrupole moments about the centroid, i.e.
+		// mean(xi*xj) - centroid_i*centroid_j
+		fp quadrupole_xx, quadrupole_xy, quadrupole_xz,
+			quadrupole_yy, quadrupole_yz,
+			quadrupole_zz;
+
+		// min,max,mean surface radius about local coordinate origin
+		fp min_radius, max_radius, mean_radius;
+
+		// xyz bounding box
+		fp min_x, max_x,
+			min_y, max_y,
+			min_z, max_z;
+
+		// proper circumference
+		// (computed using induced metric along these local-coordinate planes)
+		fp circumference_xy,
+			circumference_xz,
+			circumference_yz;
+
+		// surface area (computed using induced metric)
+		// and quantities derived from it
+		fp area, irreducible_mass, areal_radius;
+
+		double Px, Py, Pz, Sx, Sy, Sz;
+
+	public:
+		// position of diagnostics in buffer and number of diagnostics
+		enum
+		{
+			posn__centroid_x = 0,
+			posn__centroid_y,
+			posn__centroid_z,
+			posn__quadrupole_xx,
+			posn__quadrupole_xy,
+			posn__quadrupole_xz,
+			posn__quadrupole_yy,
+			posn__quadrupole_yz,
+			posn__quadrupole_zz,
+			posn__min_radius,
+			posn__max_radius,
+			posn__mean_radius,
+
+			posn__min_x,
+			posn__max_x,
+			posn__min_y,
+			posn__max_y,
+			posn__min_z,
+			posn__max_z,
+
+			posn__circumference_xy,
+			posn__circumference_xz,
+			posn__circumference_yz,
+
+			posn__area,
+			posn__irreducible_mass,
+			posn__areal_radius,
+
+			N_buffer // no comma	// size of buffer
+		};
+
+		// copy diagnostics to/from buffer
+		void copy_to_buffer(double buffer[N_buffer]) const;
+		void copy_from_buffer(const double buffer[N_buffer]);
+
+	public:
+		void compute(patch_system &ps);
+
+		void compute_signature(patch_system &ps, const double dT);
+
+		FILE *setup_output_file(int N_horizons, int hn)
+			const;
+
+		void output(FILE *fileptr, double time)
+			const;
+
+		BH_diagnostics();
+
+	private:
+		static double surface_integral(const patch_system &ps,
+									   int src_gfn, bool src_gfn_is_even_across_xy_plane,
+									   bool src_gfn_is_even_across_xz_plane,
+									   bool src_gfn_is_even_across_yz_plane,
+									   enum patch::integration_method method);
+	};
+
+	//******************************************************************************
+
+} // namespace AHFinderDirect
+#endif /* BH_DIAGNOSTICS_H */

AMSS_NCKU_source/BSSN/lopsided_c.C

@@ -1,255 +0,0 @@
-#include "tool.h"
-/*
- * 你需要提供 symmetry_bd 的 C 版本（或 Fortran 绑到 C 的接口）。
- * Fortran: call symmetry_bd(3,ex,f,fh,SoA)
- *
- * 约定：
- *   nghost = 3
- *   ex[3]  = {ex1,ex2,ex3}
- *   f      = 原始网格 (ex1*ex2*ex3)
- *   fh     = 扩展网格 ((ex1+3)*(ex2+3)*(ex3+3))，对应 Fortran 的 (-2:ex1, ...)
- *   SoA[3] = 输入参数
- */
-void lopsided(const int ex[3],
-              const double *X, const double *Y, const double *Z,
-              const double *f, double *f_rhs,
-              const double *Sfx, const double *Sfy, const double *Sfz,
-              int Symmetry, const double SoA[3])
-{
-    const double ZEO = 0.0, ONE = 1.0, F3 = 3.0;
-    const double TWO = 2.0, F6 = 6.0, F18 = 18.0;
-    const double F12 = 12.0, F10 = 10.0, EIT = 8.0;
-
-    const int NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2;
-    (void)OCTANT; // 这里和 Fortran 一样只是定义了不用也没关系
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    // 对应 Fortran: dX = X(2)-X(1)  （Fortran 1-based）
-    // C: X[1]-X[0]
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    const double d12dx = ONE / F12 / dX;
-    const double d12dy = ONE / F12 / dY;
-    const double d12dz = ONE / F12 / dZ;
-
-    // Fortran 里算了 d2dx/d2dy/d2dz 但本 subroutine 里没用到（保持一致也算出来）
-    const double d2dx  = ONE / TWO / dX;
-    const double d2dy  = ONE / TWO / dY;
-    const double d2dz  = ONE / TWO / dZ;
-    (void)d2dx; (void)d2dy; (void)d2dz;
-
-    // Fortran:
-    // imax = ex(1); jmax = ex(2); kmax = ex(3)
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    // Fortran:
-    // imin=jmin=kmin=1; 若满足对称条件则设为 -2
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -2;
-
-    // 分配 fh：大小 (ex1+3)*(ex2+3)*(ex3+3)
-    const size_t nx = (size_t)ex1 + 3;
-    const size_t ny = (size_t)ex2 + 3;
-    const size_t nz = (size_t)ex3 + 3;
-    const size_t fh_size = nx * ny * nz;
-
-    double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return; // 内存不足：直接返回（你也可以改成 abort/报错）
-
-    // Fortran: call symmetry_bd(3,ex,f,fh,SoA)
-    symmetry_bd(3, ex, f, fh, SoA);
-
-    /*
-     * Fortran 主循环：
-     * do k=1,ex(3)-1
-     * do j=1,ex(2)-1
-     * do i=1,ex(1)-1
-     *
-     * 转成 C 0-based：
-     * k0 = 0..ex3-2, j0 = 0..ex2-2, i0 = 0..ex1-2
-     *
-     * 并且 Fortran 里的 i/j/k 在 fh 访问时，仍然是 Fortran 索引值：
-     * iF=i0+1, jF=j0+1, kF=k0+1
-     */
-    for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
-        const int kF = k0 + 1;
-        for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
-            const int jF = j0 + 1;
-            for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
-                const int iF = i0 + 1;
-
-                const size_t p = idx_ex(i0, j0, k0, ex);
-
-                // ---------------- x direction ----------------
-                const double sfx = Sfx[p];
-                if (sfx > ZEO) {
-                    // Fortran: if(i+3 <= imax)
-                    // iF+3 <= ex1  <=> i0+4 <= ex1 <=> i0 <= ex1-4
-                    if (i0 <= ex1 - 4) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    }
-                    // elseif(i+2 <= imax)  <=> i0 <= ex1-3
-                    else if (i0 <= ex1 - 3) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    }
-                    // elseif(i+1 <= imax)  <=> i0 <= ex1-2（循环里总成立）
-                    else if (i0 <= ex1 - 2) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    }
-                } else if (sfx < ZEO) {
-                    // Fortran: if(i-3 >= imin)
-                    // (iF-3) >= iminF  <=> (i0-2) >= iminF
-                    if ((i0 - 2) >= iminF) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    }
-                    // elseif(i-2 >= imin) <=> (i0-1) >= iminF
-                    else if ((i0 - 1) >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    }
-                    // elseif(i-1 >= imin) <=> i0 >= iminF
-                    else if (i0 >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    }
-                }
-
-                // ---------------- y direction ----------------
-                const double sfy = Sfy[p];
-                if (sfy > ZEO) {
-                    // jF+3 <= ex2 <=> j0+4 <= ex2 <=> j0 <= ex2-4
-                    if (j0 <= ex2 - 4) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    } else if (j0 <= ex2 - 3) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 <= ex2 - 2) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    }
-                } else if (sfy < ZEO) {
-                    if ((j0 - 2) >= jminF) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    } else if ((j0 - 1) >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    }
-                }
-
-                // ---------------- z direction ----------------
-                const double sfz = Sfz[p];
-                if (sfz > ZEO) {
-                    if (k0 <= ex3 - 4) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    } else if (k0 <= ex3 - 3) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 <= ex3 - 2) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    }
-                } else if (sfz < ZEO) {
-                    if ((k0 - 2) >= kminF) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    } else if ((k0 - 1) >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    }
-                }
-            }
-        }
-    }
-    free(fh);
-}
-
-
-
-
-

AMSS_NCKU_source/BSSN/lopsided_kodis_c.C

@@ -1,248 +0,0 @@
-#include "tool.h"
-
-/*
- * Combined advection (lopsided) + KO dissipation (kodis).
- * Uses one shared symmetry_bd buffer per call.
- */
-void lopsided_kodis(const int ex[3],
-                    const double *X, const double *Y, const double *Z,
-                    const double *f, double *f_rhs,
-                    const double *Sfx, const double *Sfy, const double *Sfz,
-                    int Symmetry, const double SoA[3], double eps)
-{
-    const double ZEO = 0.0, ONE = 1.0, F3 = 3.0;
-    const double F6 = 6.0, F18 = 18.0;
-    const double F12 = 12.0, F10 = 10.0, EIT = 8.0;
-    const double SIX = 6.0, FIT = 15.0, TWT = 20.0;
-    const double cof = 64.0; // 2^6
-
-    const int NO_SYMM = 0, EQ_SYMM = 1;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    const double d12dx = ONE / F12 / dX;
-    const double d12dy = ONE / F12 / dY;
-    const double d12dz = ONE / F12 / dZ;
-
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -2;
-
-    // fh for Fortran-style domain (-2:ex1,-2:ex2,-2:ex3)
-    const size_t nx = (size_t)ex1 + 3;
-    const size_t ny = (size_t)ex2 + 3;
-    const size_t nz = (size_t)ex3 + 3;
-    const size_t fh_size = nx * ny * nz;
-
-    double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    symmetry_bd(3, ex, f, fh, SoA);
-
-    // Advection (same stencil logic as lopsided_c.C)
-    for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
-        const int kF = k0 + 1;
-        for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
-            const int jF = j0 + 1;
-            for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
-                const int iF = i0 + 1;
-                const size_t p = idx_ex(i0, j0, k0, ex);
-
-                const double sfx = Sfx[p];
-                if (sfx > ZEO) {
-                    if (i0 <= ex1 - 4) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    } else if (i0 <= ex1 - 3) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    } else if (i0 <= ex1 - 2) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    }
-                } else if (sfx < ZEO) {
-                    if ((i0 - 2) >= iminF) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    } else if ((i0 - 1) >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    } else if (i0 >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    }
-                }
-
-                const double sfy = Sfy[p];
-                if (sfy > ZEO) {
-                    if (j0 <= ex2 - 4) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    } else if (j0 <= ex2 - 3) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 <= ex2 - 2) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    }
-                } else if (sfy < ZEO) {
-                    if ((j0 - 2) >= jminF) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    } else if ((j0 - 1) >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    }
-                }
-
-                const double sfz = Sfz[p];
-                if (sfz > ZEO) {
-                    if (k0 <= ex3 - 4) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    } else if (k0 <= ex3 - 3) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 <= ex3 - 2) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    }
-                } else if (sfz < ZEO) {
-                    if ((k0 - 2) >= kminF) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    } else if ((k0 - 1) >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    }
-                }
-            }
-        }
-    }
-
-    // KO dissipation (same domain restriction as kodiss_c.C)
-    if (eps > ZEO) {
-        const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
-        const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
-        const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
-        const int i0_hi = imaxF - 4; // inclusive
-        const int j0_hi = jmaxF - 4;
-        const int k0_hi = kmaxF - 4;
-
-        if (!(i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi)) {
-            for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
-                const int kF = k0 + 1;
-                for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
-                    const int jF = j0 + 1;
-                    for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
-                        const int iF = i0 + 1;
-                        const size_t p = idx_ex(i0, j0, k0, ex);
-
-                        const double Dx_term =
-                            ((fh[idx_fh_F(iF - 3, jF, kF, ex)] + fh[idx_fh_F(iF + 3, jF, kF, ex)]) -
-                             SIX * (fh[idx_fh_F(iF - 2, jF, kF, ex)] + fh[idx_fh_F(iF + 2, jF, kF, ex)]) +
-                             FIT * (fh[idx_fh_F(iF - 1, jF, kF, ex)] + fh[idx_fh_F(iF + 1, jF, kF, ex)]) -
-                             TWT *  fh[idx_fh_F(iF,     jF, kF, ex)]) / dX;
-
-                        const double Dy_term =
-                            ((fh[idx_fh_F(iF, jF - 3, kF, ex)] + fh[idx_fh_F(iF, jF + 3, kF, ex)]) -
-                             SIX * (fh[idx_fh_F(iF, jF - 2, kF, ex)] + fh[idx_fh_F(iF, jF + 2, kF, ex)]) +
-                             FIT * (fh[idx_fh_F(iF, jF - 1, kF, ex)] + fh[idx_fh_F(iF, jF + 1, kF, ex)]) -
-                             TWT *  fh[idx_fh_F(iF, jF,     kF, ex)]) / dY;
-
-                        const double Dz_term =
-                            ((fh[idx_fh_F(iF, jF, kF - 3, ex)] + fh[idx_fh_F(iF, jF, kF + 3, ex)]) -
-                             SIX * (fh[idx_fh_F(iF, jF, kF - 2, ex)] + fh[idx_fh_F(iF, jF, kF + 2, ex)]) +
-                             FIT * (fh[idx_fh_F(iF, jF, kF - 1, ex)] + fh[idx_fh_F(iF, jF, kF + 1, ex)]) -
-                             TWT *  fh[idx_fh_F(iF, jF, kF,     ex)]) / dZ;
-
-                        f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
-                    }
-                }
-            }
-        }
-    }
-
-    free(fh);
-}

AMSS_NCKU_source/BSSN_GPU/bssn_gpu_class.h

@@ -1,210 +0,0 @@
-
-#ifndef BSSN_GPU_CLASS_H
-#define BSSN_GPU_CLASS_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#include "macrodef.h"
-#include "cgh.h"
-#include "ShellPatch.h"
-#include "misc.h"
-#include "var.h"
-#include "MyList.h"
-#include "monitor.h"
-#include "surface_integral.h"
-#include "checkpoint.h"
-
-// added by yangquan
-#include "bssn_macro.h"
-
-extern void setpbh(int iBHN, double **iPBH, double *iMass, int rBHN);
-
-class bssn_class
-{
-public:
-       // added by yangquan
-       //----------------------
-       int gpu_num_mynode;
-       int cpu_core_num_mynode;
-       int mpi_process_num_mynode;
-       int my_sequence_mynode;
-       int mynode_id;
-       int use_gpu;
-
-       virtual void Step_GPU(int lev, int YN);
-       virtual void Get_runtime_envirment();
-       // virtual void Step_OPENMP(int lev,int YN);
-       //----------------------
-
-       int ngfs;
-       int nprocs, myrank;
-       cgh *GH;
-       ShellPatch *SH;
-       double PhysTime;
-
-       int checkrun;
-       char checkfilename[50];
-       int Steps;
-       double StartTime, TotalTime;
-       double AnasTime, DumpTime, d2DumpTime, CheckTime;
-       double LastAnas, LastConsOut;
-       double Courant;
-       double numepss, numepsb, numepsh;
-       int Symmetry;
-       int maxl, decn;
-       double maxrex, drex;
-       int trfls, a_lev;
-
-       double dT;
-       double chitiny;
-
-       double **Porg0, **Porgbr, **Porg, **Porg1, **Porg_rhs;
-       int BH_num, BH_num_input;
-       double *Mass, *Pmom, *Spin;
-       double ADMMass;
-
-       var *phio, *trKo;
-       var *gxxo, *gxyo, *gxzo, *gyyo, *gyzo, *gzzo;
-       var *Axxo, *Axyo, *Axzo, *Ayyo, *Ayzo, *Azzo;
-       var *Gmxo, *Gmyo, *Gmzo;
-       var *Lapo, *Sfxo, *Sfyo, *Sfzo;
-       var *dtSfxo, *dtSfyo, *dtSfzo;
-
-       var *phi0, *trK0;
-       var *gxx0, *gxy0, *gxz0, *gyy0, *gyz0, *gzz0;
-       var *Axx0, *Axy0, *Axz0, *Ayy0, *Ayz0, *Azz0;
-       var *Gmx0, *Gmy0, *Gmz0;
-       var *Lap0, *Sfx0, *Sfy0, *Sfz0;
-       var *dtSfx0, *dtSfy0, *dtSfz0;
-
-       var *phi, *trK;
-       var *gxx, *gxy, *gxz, *gyy, *gyz, *gzz;
-       var *Axx, *Axy, *Axz, *Ayy, *Ayz, *Azz;
-       var *Gmx, *Gmy, *Gmz;
-       var *Lap, *Sfx, *Sfy, *Sfz;
-       var *dtSfx, *dtSfy, *dtSfz;
-
-       var *phi1, *trK1;
-       var *gxx1, *gxy1, *gxz1, *gyy1, *gyz1, *gzz1;
-       var *Axx1, *Axy1, *Axz1, *Ayy1, *Ayz1, *Azz1;
-       var *Gmx1, *Gmy1, *Gmz1;
-       var *Lap1, *Sfx1, *Sfy1, *Sfz1;
-       var *dtSfx1, *dtSfy1, *dtSfz1;
-
-       var *phi_rhs, *trK_rhs;
-       var *gxx_rhs, *gxy_rhs, *gxz_rhs, *gyy_rhs, *gyz_rhs, *gzz_rhs;
-       var *Axx_rhs, *Axy_rhs, *Axz_rhs, *Ayy_rhs, *Ayz_rhs, *Azz_rhs;
-       var *Gmx_rhs, *Gmy_rhs, *Gmz_rhs;
-       var *Lap_rhs, *Sfx_rhs, *Sfy_rhs, *Sfz_rhs;
-       var *dtSfx_rhs, *dtSfy_rhs, *dtSfz_rhs;
-
-       var *rho, *Sx, *Sy, *Sz, *Sxx, *Sxy, *Sxz, *Syy, *Syz, *Szz;
-
-       var *Gamxxx, *Gamxxy, *Gamxxz, *Gamxyy, *Gamxyz, *Gamxzz;
-       var *Gamyxx, *Gamyxy, *Gamyxz, *Gamyyy, *Gamyyz, *Gamyzz;
-       var *Gamzxx, *Gamzxy, *Gamzxz, *Gamzyy, *Gamzyz, *Gamzzz;
-
-       var *Rxx, *Rxy, *Rxz, *Ryy, *Ryz, *Rzz;
-
-       var *Rpsi4, *Ipsi4;
-       var *t1Rpsi4, *t1Ipsi4, *t2Rpsi4, *t2Ipsi4;
-
-       var *Cons_Ham, *Cons_Px, *Cons_Py, *Cons_Pz, *Cons_Gx, *Cons_Gy, *Cons_Gz;
-
-#ifdef Point_Psi4
-       var *phix, *phiy, *phiz;
-       var *trKx, *trKy, *trKz;
-       var *Axxx, *Axxy, *Axxz;
-       var *Axyx, *Axyy, *Axyz;
-       var *Axzx, *Axzy, *Axzz;
-       var *Ayyx, *Ayyy, *Ayyz;
-       var *Ayzx, *Ayzy, *Ayzz;
-       var *Azzx, *Azzy, *Azzz;
-#endif
-       // FIXME: uc = StateList, up = OldStateList, upp = SynchList_cor; so never touch these three data
-       MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
-       MyList<var> *OldStateList, *DumpList;
-       MyList<var> *ConstraintList;
-
-       monitor *ErrorMonitor, *Psi4Monitor, *BHMonitor, *MAPMonitor;
-       monitor *ConVMonitor;
-       surface_integral *Waveshell;
-       checkpoint *CheckPoint;
-
-public:
-       bssn_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
-                  int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
-                  int a_levi, int maxli, int decni, double maxrexi, double drexi);
-       ~bssn_class();
-
-       void Evolve(int Steps);
-       void RecursiveStep(int lev);
-#if (PSTR == 1)
-       void ParallelStep();
-       void SHStep();
-#endif
-       void RestrictProlong(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
-       void RestrictProlong_aux(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
-       void RestrictProlong(int lev, int YN, bool BB);
-       void ProlongRestrict(int lev, int YN, bool BB);
-       void Setup_Black_Hole_position();
-       void compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, var *fory, var *forz, int lev);
-       bool read_Pablo_file(int *ext, double *datain, char *filename);
-       void write_Pablo_file(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
-                             char *filename);
-       void AnalysisStuff(int lev, double dT_lev);
-       void Setup_KerrSchild();
-       void Enforce_algcon(int lev, int fg);
-
-       void testRestrict();
-       void testOutBd();
-
-       virtual void Setup_Initial_Data_Lousto();
-       virtual void Setup_Initial_Data_Cao();
-       virtual void Initialize();
-       virtual void Read_Ansorg();
-       virtual void Read_Pablo() {};
-       virtual void Compute_Psi4(int lev);
-       virtual void Step(int lev, int YN);
-       virtual void Interp_Constraint(bool infg);
-       virtual void Constraint_Out();
-       virtual void Compute_Constraint();
-
-#ifdef With_AHF
-protected:
-       MyList<var> *AHList, *AHDList, *GaugeList;
-       int AHfindevery;
-       double AHdumptime;
-       int *lastahdumpid, HN_num; // number of possible horizons
-       int *findeveryl;
-       double *xc, *yc, *zc, *xr, *yr, *zr;
-       bool *trigger;
-       double *dTT;
-       int *dumpid;
-
-public:
-       void AH_Prepare_derivatives();
-       bool AH_Interp_Points(MyList<var> *VarList,
-                             int NN, double **XX,
-                             double *Shellf, int Symmetryi);
-       void AH_Step_Find(int lev, double dT_lev);
-#endif
-};
-#endif /* BSSN_GPU_CLASS_H */

AMSS_NCKU_source/Block.C

@@ -1,199 +1,258 @@
-
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
+
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
 #include <new>
 using namespace std;
 
 #include "Block.h"
 #include "misc.h"
 
-Block::Block(int DIM, int *shapei, double *bboxi, int ranki, int ingfsi, int fngfsi, int levi, const int cgpui) : rank(ranki), ingfs(ingfsi), fngfs(fngfsi), lev(levi), cgpu(cgpui)
+#if USE_CUDA_BSSN || USE_CUDA_Z4C
+#include <cuda_runtime_api.h>
+#endif
+
+namespace {
+
+bool cuda_pin_gridfuncs_enabled()
 {
-  for (int i = 0; i < dim; i++)
-    X[i] = 0;
-
-  if (DIM != dim)
+  static int enabled = -1;
+  if (enabled < 0)
   {
-    cout << "dimension is not consistent in Block construction" << endl;
-    MPI_Abort(MPI_COMM_WORLD, 1);
+    const char *env = getenv("AMSS_CUDA_PIN_GRIDFUNCS");
+    enabled = (env && atoi(env) != 0) ? 1 : 0;
   }
+  return enabled != 0;
+}
 
-  bool flag = false;
-  for (int i = 0; i < dim; i++)
+double *alloc_gridfunc(size_t count, unsigned char &pinned)
+{
+  pinned = 0;
+#if USE_CUDA_BSSN || USE_CUDA_Z4C
+  if (cuda_pin_gridfuncs_enabled())
   {
-    shape[i] = shapei[i];
-    if (shape[i] <= 0)
-      flag = true;
-    bbox[i] = bboxi[i];
-    bbox[dim + i] = bboxi[dim + i];
-  }
-
-  int myrank;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-  if (flag)
-  {
-    cout << "myrank: " << myrank << ", on rank: " << rank << endl;
-    cout << "error shape in Block construction: (" << shape[0] << "," << shape[1] << "," << shape[2] << ")" << endl;
-    cout << "box boundary: (" << bbox[0] << ":" << bbox[3] << "," << bbox[1] << ":" << bbox[4] << "," << bbox[2] << ":" << bbox[5] << ")" << endl;
-    cout << "belong to level " << lev << endl;
-    MPI_Abort(MPI_COMM_WORLD, 1);
-  }
-
-#ifndef FAKECHECK
-  if (myrank == rank)
-  {
-    for (int i = 0; i < dim; i++)
+    double *ptr = 0;
+    cudaError_t err = cudaMallocHost((void **)&ptr, count * sizeof(double));
+    if (err == cudaSuccess)
     {
-      X[i] = new double[shape[i]];
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-      double h = (bbox[dim + i] - bbox[i]) / (shape[i] - 1);
-      for (int j = 0; j < shape[i]; j++)
-        X[i][j] = bbox[i] + j * h;
-#else
-#ifdef Cell
-      double h = (bbox[dim + i] - bbox[i]) / shape[i];
-      for (int j = 0; j < shape[i]; j++)
-        X[i][j] = bbox[i] + (j + 0.5) * h;
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
+      pinned = 1;
+      return ptr;
     }
+    cudaGetLastError();
+  }
+#endif
+  return (double *)malloc(sizeof(double) * count);
+}
 
+void free_gridfunc(double *ptr, unsigned char pinned)
+{
+  if (!ptr)
+    return;
+#if USE_CUDA_BSSN || USE_CUDA_Z4C
+  if (pinned)
+  {
+    cudaFreeHost(ptr);
+    return;
+  }
+#else
+  (void)pinned;
+#endif
+  free(ptr);
+}
+
+}
+
+Block::Block(int DIM, int *shapei, double *bboxi, int ranki, int ingfsi, int fngfsi, int levi, const int cgpui) : rank(ranki), lev(levi), cgpu(cgpui), ingfs(ingfsi), fngfs(fngfsi), igfs(0), fgfs(0), fgfs_pinned(0)
+{
+  for (int i = 0; i < dim; i++)
+    X[i] = 0;
+
+  if (DIM != dim)
+  {
+    cout << "dimension is not consistent in Block construction" << endl;
+    MPI_Abort(MPI_COMM_WORLD, 1);
+  }
+
+  bool flag = false;
+  for (int i = 0; i < dim; i++)
+  {
+    shape[i] = shapei[i];
+    if (shape[i] <= 0)
+      flag = true;
+    bbox[i] = bboxi[i];
+    bbox[dim + i] = bboxi[dim + i];
+  }
+
+  int myrank;
+  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
+  if (flag)
+  {
+    cout << "myrank: " << myrank << ", on rank: " << rank << endl;
+    cout << "error shape in Block construction: (" << shape[0] << "," << shape[1] << "," << shape[2] << ")" << endl;
+    cout << "box boundary: (" << bbox[0] << ":" << bbox[3] << "," << bbox[1] << ":" << bbox[4] << "," << bbox[2] << ":" << bbox[5] << ")" << endl;
+    cout << "belong to level " << lev << endl;
+    MPI_Abort(MPI_COMM_WORLD, 1);
+  }
+
+#ifndef FAKECHECK
+  if (myrank == rank)
+  {
+    for (int i = 0; i < dim; i++)
+    {
+      X[i] = new double[shape[i]];
+#ifdef Vertex
+#ifdef Cell
+#error Both Cell and Vertex are defined
+#endif
+      double h = (bbox[dim + i] - bbox[i]) / (shape[i] - 1);
+      for (int j = 0; j < shape[i]; j++)
+        X[i][j] = bbox[i] + j * h;
+#else
+#ifdef Cell
+      double h = (bbox[dim + i] - bbox[i]) / shape[i];
+      for (int j = 0; j < shape[i]; j++)
+        X[i][j] = bbox[i] + (j + 0.5) * h;
+#else
+#error Not define Vertex nor Cell
+#endif
+#endif
+    }
+
     int nn = shape[0] * shape[1] * shape[2];
     fgfs = new double *[fngfs];
+    fgfs_pinned = new unsigned char[fngfs];
     for (int i = 0; i < fngfs; i++)
     {
-      fgfs[i] = (double *)malloc(sizeof(double) * nn);
+      fgfs[i] = alloc_gridfunc((size_t)nn, fgfs_pinned[i]);
       if (!(fgfs[i]))
       {
         cout << "on node#" << rank << ", out of memory when constructing Block." << endl;
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-      memset(fgfs[i], 0, sizeof(double) * nn);
-    }
-
-    igfs = new int *[ingfs];
-    for (int i = 0; i < ingfs; i++)
-    {
-      igfs[i] = (int *)malloc(sizeof(int) * nn);
-      if (!(igfs[i]))
-      {
-        cout << "on node#" << rank << ", out of memory when constructing Block." << endl;
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-      memset(igfs[i], 0, sizeof(int) * nn);
-    }
-  }
-#endif
-}
-Block::~Block()
-{
-  int myrank;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-  if (myrank == rank)
-  {
-    for (int i = 0; i < dim; i++)
-      delete[] X[i];
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
+      memset(fgfs[i], 0, sizeof(double) * nn);
+    }
+
+    igfs = new int *[ingfs];
+    for (int i = 0; i < ingfs; i++)
+    {
+      igfs[i] = (int *)malloc(sizeof(int) * nn);
+      if (!(igfs[i]))
+      {
+        cout << "on node#" << rank << ", out of memory when constructing Block." << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
+      memset(igfs[i], 0, sizeof(int) * nn);
+    }
+  }
+#endif
+}
+Block::~Block()
+{
+  int myrank;
+  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
+  if (myrank == rank)
+  {
+    for (int i = 0; i < dim; i++)
+      delete[] X[i];
     for (int i = 0; i < ingfs; i++)
       free(igfs[i]);
     delete[] igfs;
     for (int i = 0; i < fngfs; i++)
-      free(fgfs[i]);
+      free_gridfunc(fgfs[i], fgfs_pinned ? fgfs_pinned[i] : 0);
     delete[] fgfs;
+    delete[] fgfs_pinned;
     X[0] = X[1] = X[2] = 0;
     igfs = 0;
     fgfs = 0;
+    fgfs_pinned = 0;
   }
 }
-void Block::checkBlock()
-{
-  int myrank;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-  if (myrank == 0)
-  {
-    cout << "belong to level " << lev << endl;
-    cout << "shape: [";
-    for (int i = 0; i < dim; i++)
-    {
-      cout << shape[i];
-      if (i < dim - 1)
-        cout << ",";
-      else
-        cout << "]";
-    }
-    cout << " resolution: [";
-    for (int i = 0; i < dim; i++)
-    {
-      cout << getdX(i);
-      if (i < dim - 1)
-        cout << ",";
-      else
-        cout << "]" << endl;
-    }
-    cout << "locate on node " << rank << ", at (includes ghost zone):" << endl;
-    cout << "(";
-    for (int i = 0; i < dim; i++)
-    {
-      cout << bbox[i] << ":" << bbox[dim + i];
-      if (i < dim - 1)
-        cout << ",";
-      else
-        cout << ")" << endl;
-    }
-    cout << "has " << ingfs << " int type grids functions," << fngfs << " double type grids functions" << endl;
-  }
-}
-double Block::getdX(int dir)
-{
-  if (dir < 0 || dir >= dim)
-  {
-    cout << "Block::getdX: error input dir = " << dir << ", this Block has direction (0," << dim - 1 << ")" << endl;
-    MPI_Abort(MPI_COMM_WORLD, 1);
-  }
-  double h;
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-  if (shape[dir] == 1)
-  {
-    cout << "Block::getdX: for direction " << dir << ", this Block has only one point. Can not determine dX for vertex center grid." << endl;
-    MPI_Abort(MPI_COMM_WORLD, 1);
-  }
-  h = (bbox[dim + dir] - bbox[dir]) / (shape[dir] - 1);
-#else
-#ifdef Cell
-  h = (bbox[dim + dir] - bbox[dir]) / shape[dir];
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
-  return h;
-}
-void Block::swapList(MyList<var> *VarList1, MyList<var> *VarList2, int myrank)
-{
-  if (rank == myrank)
-  {
-    MyList<var> *varl1 = VarList1, *varl2 = VarList2;
+void Block::checkBlock()
+{
+  int myrank;
+  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
+  if (myrank == 0)
+  {
+    cout << "belong to level " << lev << endl;
+    cout << "shape: [";
+    for (int i = 0; i < dim; i++)
+    {
+      cout << shape[i];
+      if (i < dim - 1)
+        cout << ",";
+      else
+        cout << "]";
+    }
+    cout << " resolution: [";
+    for (int i = 0; i < dim; i++)
+    {
+      cout << getdX(i);
+      if (i < dim - 1)
+        cout << ",";
+      else
+        cout << "]" << endl;
+    }
+    cout << "locate on node " << rank << ", at (includes ghost zone):" << endl;
+    cout << "(";
+    for (int i = 0; i < dim; i++)
+    {
+      cout << bbox[i] << ":" << bbox[dim + i];
+      if (i < dim - 1)
+        cout << ",";
+      else
+        cout << ")" << endl;
+    }
+    cout << "has " << ingfs << " int type grids functions," << fngfs << " double type grids functions" << endl;
+  }
+}
+double Block::getdX(int dir)
+{
+  if (dir < 0 || dir >= dim)
+  {
+    cout << "Block::getdX: error input dir = " << dir << ", this Block has direction (0," << dim - 1 << ")" << endl;
+    MPI_Abort(MPI_COMM_WORLD, 1);
+  }
+  double h;
+#ifdef Vertex
+#ifdef Cell
+#error Both Cell and Vertex are defined
+#endif
+  if (shape[dir] == 1)
+  {
+    cout << "Block::getdX: for direction " << dir << ", this Block has only one point. Can not determine dX for vertex center grid." << endl;
+    MPI_Abort(MPI_COMM_WORLD, 1);
+  }
+  h = (bbox[dim + dir] - bbox[dir]) / (shape[dir] - 1);
+#else
+#ifdef Cell
+  h = (bbox[dim + dir] - bbox[dir]) / shape[dir];
+#else
+#error Not define Vertex nor Cell
+#endif
+#endif
+  return h;
+}
+void Block::swapList(MyList<var> *VarList1, MyList<var> *VarList2, int myrank)
+{
+  if (rank == myrank)
+  {
+    MyList<var> *varl1 = VarList1, *varl2 = VarList2;
     while (varl1 && varl2)
     {
       misc::swap<double *>(fgfs[varl1->data->sgfn], fgfs[varl2->data->sgfn]);
+      if (fgfs_pinned)
+        misc::swap<unsigned char>(fgfs_pinned[varl1->data->sgfn], fgfs_pinned[varl2->data->sgfn]);
       varl1 = varl1->next;
       varl2 = varl2->next;
     }
-    if (varl1 || varl2)
-    {
-      cout << "error in Block::swaplist, var lists does not match." << endl;
-      MPI_Abort(MPI_COMM_WORLD, 1);
-    }
-  }
-}
+    if (varl1 || varl2)
+    {
+      cout << "error in Block::swaplist, var lists does not match." << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
+  }
+}

AMSS_NCKU_source/Block.h

@@ -1,34 +1,35 @@
-
-#ifndef BLOCK_H
-#define BLOCK_H
-
-#include <mpi.h>
-#include "macrodef.h" //need dim here; Vertex or Cell
-#include "var.h"
-#include "MyList.h"
-class Block
-{
-
-public:
-   int shape[dim];
-   double bbox[2 * dim];
-   double *X[dim];
+
+#ifndef BLOCK_H
+#define BLOCK_H
+
+#include <mpi.h>
+#include "macrodef.h" //need dim here; Vertex or Cell
+#include "var.h"
+#include "MyList.h"
+class Block
+{
+
+public:
+   int shape[dim];
+   double bbox[2 * dim];
+   double *X[dim];
    int rank; // where the real data locate in
    int lev, cgpu;
    int ingfs, fngfs;
    int *(*igfs);
    double *(*fgfs);
-
-public:
-   Block() {};
-   Block(int DIM, int *shapei, double *bboxi, int ranki, int ingfsi, int fngfs, int levi, const int cgpui = 0);
-
-   ~Block();
-
-   void checkBlock();
-
-   double getdX(int dir);
-   void swapList(MyList<var> *VarList1, MyList<var> *VarList2, int myrank);
-};
-
-#endif /* BLOCK_H */
+   unsigned char *fgfs_pinned;
+
+public:
+   Block() : rank(0), lev(0), cgpu(0), ingfs(0), fngfs(0), igfs(0), fgfs(0), fgfs_pinned(0) {};
+   Block(int DIM, int *shapei, double *bboxi, int ranki, int ingfsi, int fngfs, int levi, const int cgpui = 0);
+
+   ~Block();
+
+   void checkBlock();
+
+   double getdX(int dir);
+   void swapList(MyList<var> *VarList1, MyList<var> *VarList2, int myrank);
+};
+
+#endif /* BLOCK_H */

AMSS_NCKU_source/DataCT.C

@@ -1,283 +1,283 @@
-
-//-----------------------------------------------------------------------
-// Read binary files and do fancy things with them...
-//-----------------------------------------------------------------------
-#ifdef newc
-#include <cmath>
-#include <iostream>
-#include <iomanip>
-#include <cstdlib>
-#include <cstdio>
-#include <cstring>
-#include <fstream>
-using namespace std;
-#else
-#include <math.h>
-#include <iostream.h>
-#include <iomanip.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <fstream.h>
-#endif
-
-#include "microdef.fh"
-
-int main(int argc, char *argv[])
-{
-  //
-  // USE:  DataCT flag file1 [ file2 ]
-  //
-  // where: - flag can be XY,XZ,YZ
-  //
-  void set_fname(char *fname);
-
-  if (argc < 3)
-  {
-    cout << "\aUsage: DataCT flag binaryfile1 [ binaryfile2 ] \n "
-         << "   where: - flag can be XY,XZ,YZ"
-         << endl;
-    exit(1);
-  }
-  ifstream infile1;
-  infile1.open(argv[2]);
-  if (!infile1)
-  {
-    cerr << "\a Can't open " << argv[2] << " for input." << endl;
-    exit(1);
-  }
-
-  /* read properties of the binary file */
-  double time;
-  int nx, ny, nz;
-  double xmin, xmax, ymin, ymax, zmin, zmax;
-  infile1.seekg(0, ios::beg);
-  infile1.read((char *)&time, sizeof(double));
-  infile1.read((char *)&nx, sizeof(int));
-  infile1.read((char *)&ny, sizeof(int));
-  infile1.read((char *)&nz, sizeof(int));
-  infile1.read((char *)&xmin, sizeof(double));
-  infile1.read((char *)&xmax, sizeof(double));
-  infile1.read((char *)&ymin, sizeof(double));
-  infile1.read((char *)&ymax, sizeof(double));
-  infile1.read((char *)&zmin, sizeof(double));
-  infile1.read((char *)&zmax, sizeof(double));
-
-  /* get rid of any 4 character suffix */
-  set_fname(argv[2]);
-
-  /* sanity check */
-  if (nx != ny || nx != nz)
-  {
-    cout << "\n"
-         << endl;
-    cout << " nx, ny and nz do not agree! Using a symmetry?... ";
-    cout << "\n"
-         << endl;
-  }
-
-  cout << "\n Reading file : " << argv[2] << endl;
-  cout << "\n  Time        : " << time << endl;
-  cout << "  Dimensions  : " << setw(16) << nx << setw(16) << ny << setw(16) << nz << endl;
-  cout << "   xmin, xmax : " << setw(16) << xmin << setw(16) << xmax << endl;
-  cout << "   ymin, ymax : " << setw(16) << ymin << setw(16) << ymax << endl;
-  cout << "   zmin, zmax : " << setw(16) << zmin << setw(16) << zmax << endl;
-  cout << "\n";
-
-  double *data;
-  data = new double[nx * ny * nz];
-  int i = 0, j = 0, k = 0;
-  infile1.read((char *)data, nx * ny * nz * sizeof(double));
-  infile1.close();
-  //
-  //
-  // if second file given, open second file and subtract from first one!
-  //
-  //
-  if (argc == 4)
-  {
-    infile1.open(argv[3]);
-    if (!infile1)
-    {
-      cerr << "\a Can't open " << argv[3] << " for input." << endl;
-      exit(1);
-    }
-    double *indata;
-    indata = new double[nx * ny * nz];
-    // read in header
-    infile1.seekg(0, ios::beg);
-    int nxin, nyin, nzin;
-    infile1.read((char *)&time, sizeof(double));
-    infile1.read((char *)&nxin, sizeof(int));
-    infile1.read((char *)&nyin, sizeof(int));
-    infile1.read((char *)&nzin, sizeof(int));
-    infile1.read((char *)&xmin, sizeof(double));
-    infile1.read((char *)&xmax, sizeof(double));
-    infile1.read((char *)&ymin, sizeof(double));
-    infile1.read((char *)&ymax, sizeof(double));
-    infile1.read((char *)&zmin, sizeof(double));
-    infile1.read((char *)&zmax, sizeof(double));
-    if (nxin != nx || nyin != ny || nzin != nz)
-    {
-      cerr << "\a Number of indices do not agree! " << endl;
-      exit(1);
-    }
-    cout << " Comparing with data at time " << time << "\n"
-         << endl;
-    infile1.read((char *)indata, nx * ny * nz * sizeof(double));
-    infile1.close();
-    for (i = 0; i < nx * ny * nz; i++)
-      data[i] -= indata[i];
-  }
-
-  double *X, *Y, *Z;
-  X = new double[nx];
-  Y = new double[ny];
-  Z = new double[nz];
-  double dd;
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-  dd = (xmax - xmin) / (nx - 1);
-  for (i = 0; i < nx; i++)
-    X[i] = xmin + i * dd;
-  dd = (ymax - ymin) / (ny - 1);
-  for (j = 0; j < ny; j++)
-    Y[j] = ymin + j * dd;
-  dd = (zmax - zmin) / (nz - 1);
-  for (k = 0; k < nz; k++)
-    Z[k] = zmin + k * dd;
-#else
-#ifdef Cell
-  dd = (xmax - xmin) / nx;
-  for (i = 0; i < nx; i++)
-    X[i] = xmin + (i + 0.5) * dd;
-  dd = (ymax - ymin) / ny;
-  for (j = 0; j < ny; j++)
-    Y[j] = ymin + (j + 0.5) * dd;
-  dd = (zmax - zmin) / nz;
-  for (k = 0; k < nz; k++)
-    Z[k] = zmin + (k + 0.5) * dd;
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
-
-  int ext[3];
-  ext[0] = nx;
-  ext[1] = ny;
-  ext[2] = nz;
-  void writefile(int *ext, double *XX, double *YY, double *ZZ, double *datain,
-                 char *filename, const char *flag);
-  writefile(ext, X, Y, Z, data, argv[2], argv[1]);
-
-  delete[] data;
-  delete[] X;
-  delete[] Y;
-  delete[] Z;
-}
-
-/*-----------------------------------*/
-/* get rid of any 4 character suffix */
-/*-----------------------------------*/
-void set_fname(char *fname)
-{
-  int len = strlen(fname) - 4;
-  char *n_fname;
-  n_fname = new char[len];
-
-  for (int i = 0; i < len; ++i)
-  {
-    n_fname[i] = fname[i];
-    //     cout << n_fname[i] << " " << i << endl;
-  }
-  n_fname[len] = '\0';
-
-  //      cout << "n_fname: " << n_fname << " fname: " << fname << ", "
-  // 	  << len << endl;
-
-  strcpy(fname, n_fname); /* Send back the old pointer */
-  delete n_fname;
-}
-//|----------------------------------------------------------------------------
-//  writefile
-//|----------------------------------------------------------------------------
-void writefile(int *ext, double *XX, double *YY, double *ZZ, double *datain,
-               char *filename, const char *flag)
-{
-  int nx = ext[0], ny = ext[1], nz = ext[2];
-  int i, j, k;
-  char filename_h[50];
-  //|--->open out put file
-  ofstream outfile;
-
-  if (!strcmp(flag, "YZ"))
-  {
-    for (i = 0; i < nx; i++)
-    {
-      sprintf(filename_h, "%s_%d.dat", filename, i);
-      outfile.open(filename_h);
-      outfile << "# CT along X at " << i << endl;
-      for (k = 0; k < nz; k++)
-      {
-        for (j = 0; j < ny; j++)
-        {
-          outfile << setw(10) << setprecision(10) << YY[j] << " "
-                  << setw(10) << setprecision(10) << ZZ[k] << " "
-                  << datain[i + j * nx + k * nx * ny] << " "
-                  << endl;
-        }
-        outfile << "\n"; /* blanck line for gnuplot */
-      }
-      outfile.close();
-    }
-  }
-  else if (!strcmp(flag, "XZ"))
-  {
-    for (j = 0; j < ny; j++)
-    {
-      sprintf(filename_h, "%s_%d.dat", filename, j);
-      outfile.open(filename_h);
-      outfile << "# CT along Y at " << j << endl;
-      for (k = 0; k < nz; k++)
-      {
-        for (i = 0; i < nx; i++)
-        {
-          outfile << setw(10) << setprecision(10) << XX[i] << " "
-                  << setw(10) << setprecision(10) << ZZ[k] << " "
-                  << datain[i + j * nx + k * nx * ny] << " "
-                  << endl;
-        }
-        outfile << "\n"; /* blanck line for gnuplot */
-      }
-      outfile.close();
-    }
-  }
-  else if (!strcmp(flag, "XY"))
-  {
-    for (k = 0; k < nz; k++)
-    {
-      sprintf(filename_h, "%s_%d.dat", filename, k);
-      outfile.open(filename_h);
-      outfile << "# CT along Z at " << k << endl;
-      for (j = 0; j < ny; j++)
-      {
-        for (i = 0; i < nx; i++)
-        {
-          outfile << setw(10) << setprecision(10) << XX[i] << " "
-                  << setw(10) << setprecision(10) << YY[j] << " "
-                  << datain[i + j * nx + k * nx * ny] << " "
-                  << endl;
-        }
-        outfile << "\n"; /* blanck line for gnuplot */
-      }
-      outfile.close();
-    }
-  }
-  else
-  {
-    cout << "In output_data: not recognized flag-->" << flag << endl;
-    exit(0);
-  }
-}
+
+//-----------------------------------------------------------------------
+// Read binary files and do fancy things with them...
+//-----------------------------------------------------------------------
+#ifdef newc
+#include <cmath>
+#include <iostream>
+#include <iomanip>
+#include <cstdlib>
+#include <cstdio>
+#include <cstring>
+#include <fstream>
+using namespace std;
+#else
+#include <math.h>
+#include <iostream.h>
+#include <iomanip.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <fstream.h>
+#endif
+
+#include "microdef.fh"
+
+int main(int argc, char *argv[])
+{
+  //
+  // USE:  DataCT flag file1 [ file2 ]
+  //
+  // where: - flag can be XY,XZ,YZ
+  //
+  void set_fname(char *fname);
+
+  if (argc < 3)
+  {
+    cout << "\aUsage: DataCT flag binaryfile1 [ binaryfile2 ] \n "
+         << "   where: - flag can be XY,XZ,YZ"
+         << endl;
+    exit(1);
+  }
+  ifstream infile1;
+  infile1.open(argv[2]);
+  if (!infile1)
+  {
+    cerr << "\a Can't open " << argv[2] << " for input." << endl;
+    exit(1);
+  }
+
+  /* read properties of the binary file */
+  double time;
+  int nx, ny, nz;
+  double xmin, xmax, ymin, ymax, zmin, zmax;
+  infile1.seekg(0, ios::beg);
+  infile1.read((char *)&time, sizeof(double));
+  infile1.read((char *)&nx, sizeof(int));
+  infile1.read((char *)&ny, sizeof(int));
+  infile1.read((char *)&nz, sizeof(int));
+  infile1.read((char *)&xmin, sizeof(double));
+  infile1.read((char *)&xmax, sizeof(double));
+  infile1.read((char *)&ymin, sizeof(double));
+  infile1.read((char *)&ymax, sizeof(double));
+  infile1.read((char *)&zmin, sizeof(double));
+  infile1.read((char *)&zmax, sizeof(double));
+
+  /* get rid of any 4 character suffix */
+  set_fname(argv[2]);
+
+  /* sanity check */
+  if (nx != ny || nx != nz)
+  {
+    cout << "\n"
+         << endl;
+    cout << " nx, ny and nz do not agree! Using a symmetry?... ";
+    cout << "\n"
+         << endl;
+  }
+
+  cout << "\n Reading file : " << argv[2] << endl;
+  cout << "\n  Time        : " << time << endl;
+  cout << "  Dimensions  : " << setw(16) << nx << setw(16) << ny << setw(16) << nz << endl;
+  cout << "   xmin, xmax : " << setw(16) << xmin << setw(16) << xmax << endl;
+  cout << "   ymin, ymax : " << setw(16) << ymin << setw(16) << ymax << endl;
+  cout << "   zmin, zmax : " << setw(16) << zmin << setw(16) << zmax << endl;
+  cout << "\n";
+
+  double *data;
+  data = new double[nx * ny * nz];
+  int i = 0, j = 0, k = 0;
+  infile1.read((char *)data, nx * ny * nz * sizeof(double));
+  infile1.close();
+  //
+  //
+  // if second file given, open second file and subtract from first one!
+  //
+  //
+  if (argc == 4)
+  {
+    infile1.open(argv[3]);
+    if (!infile1)
+    {
+      cerr << "\a Can't open " << argv[3] << " for input." << endl;
+      exit(1);
+    }
+    double *indata;
+    indata = new double[nx * ny * nz];
+    // read in header
+    infile1.seekg(0, ios::beg);
+    int nxin, nyin, nzin;
+    infile1.read((char *)&time, sizeof(double));
+    infile1.read((char *)&nxin, sizeof(int));
+    infile1.read((char *)&nyin, sizeof(int));
+    infile1.read((char *)&nzin, sizeof(int));
+    infile1.read((char *)&xmin, sizeof(double));
+    infile1.read((char *)&xmax, sizeof(double));
+    infile1.read((char *)&ymin, sizeof(double));
+    infile1.read((char *)&ymax, sizeof(double));
+    infile1.read((char *)&zmin, sizeof(double));
+    infile1.read((char *)&zmax, sizeof(double));
+    if (nxin != nx || nyin != ny || nzin != nz)
+    {
+      cerr << "\a Number of indices do not agree! " << endl;
+      exit(1);
+    }
+    cout << " Comparing with data at time " << time << "\n"
+         << endl;
+    infile1.read((char *)indata, nx * ny * nz * sizeof(double));
+    infile1.close();
+    for (i = 0; i < nx * ny * nz; i++)
+      data[i] -= indata[i];
+  }
+
+  double *X, *Y, *Z;
+  X = new double[nx];
+  Y = new double[ny];
+  Z = new double[nz];
+  double dd;
+#ifdef Vertex
+#ifdef Cell
+#error Both Cell and Vertex are defined
+#endif
+  dd = (xmax - xmin) / (nx - 1);
+  for (i = 0; i < nx; i++)
+    X[i] = xmin + i * dd;
+  dd = (ymax - ymin) / (ny - 1);
+  for (j = 0; j < ny; j++)
+    Y[j] = ymin + j * dd;
+  dd = (zmax - zmin) / (nz - 1);
+  for (k = 0; k < nz; k++)
+    Z[k] = zmin + k * dd;
+#else
+#ifdef Cell
+  dd = (xmax - xmin) / nx;
+  for (i = 0; i < nx; i++)
+    X[i] = xmin + (i + 0.5) * dd;
+  dd = (ymax - ymin) / ny;
+  for (j = 0; j < ny; j++)
+    Y[j] = ymin + (j + 0.5) * dd;
+  dd = (zmax - zmin) / nz;
+  for (k = 0; k < nz; k++)
+    Z[k] = zmin + (k + 0.5) * dd;
+#else
+#error Not define Vertex nor Cell
+#endif
+#endif
+
+  int ext[3];
+  ext[0] = nx;
+  ext[1] = ny;
+  ext[2] = nz;
+  void writefile(int *ext, double *XX, double *YY, double *ZZ, double *datain,
+                 char *filename, const char *flag);
+  writefile(ext, X, Y, Z, data, argv[2], argv[1]);
+
+  delete[] data;
+  delete[] X;
+  delete[] Y;
+  delete[] Z;
+}
+
+/*-----------------------------------*/
+/* get rid of any 4 character suffix */
+/*-----------------------------------*/
+void set_fname(char *fname)
+{
+  int len = strlen(fname) - 4;
+  char *n_fname;
+  n_fname = new char[len];
+
+  for (int i = 0; i < len; ++i)
+  {
+    n_fname[i] = fname[i];
+    //     cout << n_fname[i] << " " << i << endl;
+  }
+  n_fname[len] = '\0';
+
+  //      cout << "n_fname: " << n_fname << " fname: " << fname << ", "
+  // 	  << len << endl;
+
+  strcpy(fname, n_fname); /* Send back the old pointer */
+  delete n_fname;
+}
+//|----------------------------------------------------------------------------
+//  writefile
+//|----------------------------------------------------------------------------
+void writefile(int *ext, double *XX, double *YY, double *ZZ, double *datain,
+               char *filename, const char *flag)
+{
+  int nx = ext[0], ny = ext[1], nz = ext[2];
+  int i, j, k;
+  char filename_h[50];
+  //|--->open out put file
+  ofstream outfile;
+
+  if (!strcmp(flag, "YZ"))
+  {
+    for (i = 0; i < nx; i++)
+    {
+      sprintf(filename_h, "%s_%d.dat", filename, i);
+      outfile.open(filename_h);
+      outfile << "# CT along X at " << i << endl;
+      for (k = 0; k < nz; k++)
+      {
+        for (j = 0; j < ny; j++)
+        {
+          outfile << setw(10) << setprecision(10) << YY[j] << " "
+                  << setw(10) << setprecision(10) << ZZ[k] << " "
+                  << datain[i + j * nx + k * nx * ny] << " "
+                  << endl;
+        }
+        outfile << "\n"; /* blanck line for gnuplot */
+      }
+      outfile.close();
+    }
+  }
+  else if (!strcmp(flag, "XZ"))
+  {
+    for (j = 0; j < ny; j++)
+    {
+      sprintf(filename_h, "%s_%d.dat", filename, j);
+      outfile.open(filename_h);
+      outfile << "# CT along Y at " << j << endl;
+      for (k = 0; k < nz; k++)
+      {
+        for (i = 0; i < nx; i++)
+        {
+          outfile << setw(10) << setprecision(10) << XX[i] << " "
+                  << setw(10) << setprecision(10) << ZZ[k] << " "
+                  << datain[i + j * nx + k * nx * ny] << " "
+                  << endl;
+        }
+        outfile << "\n"; /* blanck line for gnuplot */
+      }
+      outfile.close();
+    }
+  }
+  else if (!strcmp(flag, "XY"))
+  {
+    for (k = 0; k < nz; k++)
+    {
+      sprintf(filename_h, "%s_%d.dat", filename, k);
+      outfile.open(filename_h);
+      outfile << "# CT along Z at " << k << endl;
+      for (j = 0; j < ny; j++)
+      {
+        for (i = 0; i < nx; i++)
+        {
+          outfile << setw(10) << setprecision(10) << XX[i] << " "
+                  << setw(10) << setprecision(10) << YY[j] << " "
+                  << datain[i + j * nx + k * nx * ny] << " "
+                  << endl;
+        }
+        outfile << "\n"; /* blanck line for gnuplot */
+      }
+      outfile.close();
+    }
+  }
+  else
+  {
+    cout << "In output_data: not recognized flag-->" << flag << endl;
+    exit(0);
+  }
+}

AMSS_NCKU_source/Derivative/fdderivs_c.C

@@ -1,332 +0,0 @@
-#include "tool.h"
-void fdderivs(const int ex[3],
-              const double *f,
-              double *fxx, double *fxy, double *fxz,
-              double *fyy, double *fyz, double *fzz,
-              const double *X, const double *Y, const double *Z,
-              double SYM1, double SYM2, double SYM3,
-              int Symmetry, int onoff)
-{
-    (void)onoff;
-
-    const int NO_SYMM = 0, EQ_SYMM = 1;
-    const double ZEO = 0.0, ONE = 1.0, TWO = 2.0;
-    const double F1o4   = 2.5e-1;          // 1/4
-    const double F8     = 8.0;
-    const double F16    = 16.0;
-    const double F30    = 30.0;
-    const double F1o12  = ONE / 12.0;
-    const double F1o144 = ONE / 144.0;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -1;
-
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    /* fh: (ex1+2)*(ex2+2)*(ex3+2) because ord=2 */
-    const size_t nx = (size_t)ex1 + 2;
-    const size_t ny = (size_t)ex2 + 2;
-    const size_t nz = (size_t)ex3 + 2;
-    const size_t fh_size = nx * ny * nz;
-
-    static double *fh = NULL;
-    static size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
-    // double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    symmetry_bd(2, ex, f, fh, SoA);
-
-    /* 系数：按 Fortran 原式 */
-    const double Sdxdx = ONE / (dX * dX);
-    const double Sdydy = ONE / (dY * dY);
-    const double Sdzdz = ONE / (dZ * dZ);
-
-    const double Fdxdx = F1o12 / (dX * dX);
-    const double Fdydy = F1o12 / (dY * dY);
-    const double Fdzdz = F1o12 / (dZ * dZ);
-
-    const double Sdxdy = F1o4 / (dX * dY);
-    const double Sdxdz = F1o4 / (dX * dZ);
-    const double Sdydz = F1o4 / (dY * dZ);
-
-    const double Fdxdy = F1o144 / (dX * dY);
-    const double Fdxdz = F1o144 / (dX * dZ);
-    const double Fdydz = F1o144 / (dY * dZ);
-
-    /* 只清零不被主循环覆盖的边界面 */
-    {
-        /* 高边界：k0=ex3-1 */
-        for (int j0 = 0; j0 < ex2; ++j0)
-            for (int i0 = 0; i0 < ex1; ++i0) {
-                const size_t p = idx_ex(i0, j0, ex3 - 1, ex);
-                fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-            }
-        /* 高边界：j0=ex2-1 */
-        for (int k0 = 0; k0 < ex3 - 1; ++k0)
-            for (int i0 = 0; i0 < ex1; ++i0) {
-                const size_t p = idx_ex(i0, ex2 - 1, k0, ex);
-                fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-            }
-        /* 高边界：i0=ex1-1 */
-        for (int k0 = 0; k0 < ex3 - 1; ++k0)
-            for (int j0 = 0; j0 < ex2 - 1; ++j0) {
-                const size_t p = idx_ex(ex1 - 1, j0, k0, ex);
-                fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-            }
-
-        /* 低边界：当二阶模板也不可用时，对应 i0/j0/k0=0 面 */
-        if (kminF == 1) {
-            for (int j0 = 0; j0 < ex2; ++j0)
-                for (int i0 = 0; i0 < ex1; ++i0) {
-                    const size_t p = idx_ex(i0, j0, 0, ex);
-                    fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                    fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-                }
-        }
-        if (jminF == 1) {
-            for (int k0 = 0; k0 < ex3; ++k0)
-                for (int i0 = 0; i0 < ex1; ++i0) {
-                    const size_t p = idx_ex(i0, 0, k0, ex);
-                    fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                    fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-                }
-        }
-        if (iminF == 1) {
-            for (int k0 = 0; k0 < ex3; ++k0)
-                for (int j0 = 0; j0 < ex2; ++j0) {
-                    const size_t p = idx_ex(0, j0, k0, ex);
-                    fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                    fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-                }
-        }
-    }
-
-    /*
-     * 两段式：
-     * 1) 二阶可用区域先计算二阶模板
-     * 2) 高阶可用区域再覆盖四阶模板
-     */
-    const int i2_lo = (iminF > 0) ? iminF : 0;
-    const int j2_lo = (jminF > 0) ? jminF : 0;
-    const int k2_lo = (kminF > 0) ? kminF : 0;
-    const int i2_hi = ex1 - 2;
-    const int j2_hi = ex2 - 2;
-    const int k2_hi = ex3 - 2;
-
-    const int i4_lo = (iminF + 1 > 0) ? (iminF + 1) : 0;
-    const int j4_lo = (jminF + 1 > 0) ? (jminF + 1) : 0;
-    const int k4_lo = (kminF + 1 > 0) ? (kminF + 1) : 0;
-    const int i4_hi = ex1 - 3;
-    const int j4_hi = ex2 - 3;
-    const int k4_hi = ex3 - 3;
-
-    /*
-     * Strategy A:
-     * Avoid redundant work in overlap of 2nd/4th-order regions.
-     * Only compute 2nd-order on shell points that are NOT overwritten by
-     * the 4th-order pass.
-     */
-    const int has4 = (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi);
-
-    if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
-        for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
-                    if (has4 &&
-                        i0 >= i4_lo && i0 <= i4_hi &&
-                        j0 >= j4_lo && j0 <= j4_hi &&
-                        k0 >= k4_lo && k0 <= k4_hi) {
-                        continue;
-                    }
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    fxx[p] = Sdxdx * (
-                        fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] -
-                        TWO * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] +
-                        fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)]
-                    );
-
-                    fyy[p] = Sdydy * (
-                        fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] -
-                        TWO * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] +
-                        fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)]
-                    );
-
-                    fzz[p] = Sdzdz * (
-                        fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] -
-                        TWO * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] +
-                        fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)]
-                    );
-
-                    fxy[p] = Sdxdy * (
-                        fh[idx_fh_F_ord2(iF - 1, jF - 1, kF, ex)] -
-                        fh[idx_fh_F_ord2(iF + 1, jF - 1, kF, ex)] -
-                        fh[idx_fh_F_ord2(iF - 1, jF + 1, kF, ex)] +
-                        fh[idx_fh_F_ord2(iF + 1, jF + 1, kF, ex)]
-                    );
-
-                    fxz[p] = Sdxdz * (
-                        fh[idx_fh_F_ord2(iF - 1, jF, kF - 1, ex)] -
-                        fh[idx_fh_F_ord2(iF + 1, jF, kF - 1, ex)] -
-                        fh[idx_fh_F_ord2(iF - 1, jF, kF + 1, ex)] +
-                        fh[idx_fh_F_ord2(iF + 1, jF, kF + 1, ex)]
-                    );
-
-                    fyz[p] = Sdydz * (
-                        fh[idx_fh_F_ord2(iF, jF - 1, kF - 1, ex)] -
-                        fh[idx_fh_F_ord2(iF, jF + 1, kF - 1, ex)] -
-                        fh[idx_fh_F_ord2(iF, jF - 1, kF + 1, ex)] +
-                        fh[idx_fh_F_ord2(iF, jF + 1, kF + 1, ex)]
-                    );
-                }
-            }
-        }
-    }
-
-    if (has4) {
-        for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i4_lo; i0 <= i4_hi; ++i0) {
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    fxx[p] = Fdxdx * (
-                        -fh[idx_fh_F_ord2(iF - 2, jF,     kF,     ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] -
-                        F30 * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] -
-                        fh[idx_fh_F_ord2(iF + 2, jF,     kF,     ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)]
-                    );
-
-                    fyy[p] = Fdydy * (
-                        -fh[idx_fh_F_ord2(iF,     jF - 2, kF,     ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] -
-                        F30 * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] -
-                        fh[idx_fh_F_ord2(iF,     jF + 2, kF,     ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)]
-                    );
-
-                    fzz[p] = Fdzdz * (
-                        -fh[idx_fh_F_ord2(iF,     jF,     kF - 2, ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] -
-                        F30 * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] -
-                        fh[idx_fh_F_ord2(iF,     jF,     kF + 2, ex)] +
-                        F16 * fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)]
-                    );
-
-                    {
-                        const double t_jm2 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF - 2, kF, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF - 2, kF, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF - 2, kF, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF - 2, kF, ex)] );
-
-                        const double t_jm1 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF - 1, kF, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF - 1, kF, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF - 1, kF, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF - 1, kF, ex)] );
-
-                        const double t_jp1 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF + 1, kF, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF + 1, kF, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF + 1, kF, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF + 1, kF, ex)] );
-
-                        const double t_jp2 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF + 2, kF, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF + 2, kF, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF + 2, kF, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF + 2, kF, ex)] );
-
-                        fxy[p] = Fdxdy * ( t_jm2 - F8 * t_jm1 + F8 * t_jp1 - t_jp2 );
-                    }
-
-                    {
-                        const double t_km2 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF, kF - 2, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF, kF - 2, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF, kF - 2, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF, kF - 2, ex)] );
-
-                        const double t_km1 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF, kF - 1, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF, kF - 1, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF, kF - 1, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF, kF - 1, ex)] );
-
-                        const double t_kp1 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF, kF + 1, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF, kF + 1, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF, kF + 1, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF, kF + 1, ex)] );
-
-                        const double t_kp2 =
-                            ( fh[idx_fh_F_ord2(iF - 2, jF, kF + 2, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF - 1, jF, kF + 2, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF + 1, jF, kF + 2, ex)]
-                             -    fh[idx_fh_F_ord2(iF + 2, jF, kF + 2, ex)] );
-
-                        fxz[p] = Fdxdz * ( t_km2 - F8 * t_km1 + F8 * t_kp1 - t_kp2 );
-                    }
-
-                    {
-                        const double t_km2 =
-                            ( fh[idx_fh_F_ord2(iF, jF - 2, kF - 2, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF, jF - 1, kF - 2, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF, jF + 1, kF - 2, ex)]
-                             -    fh[idx_fh_F_ord2(iF, jF + 2, kF - 2, ex)] );
-
-                        const double t_km1 =
-                            ( fh[idx_fh_F_ord2(iF, jF - 2, kF - 1, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF, jF - 1, kF - 1, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF, jF + 1, kF - 1, ex)]
-                             -    fh[idx_fh_F_ord2(iF, jF + 2, kF - 1, ex)] );
-
-                        const double t_kp1 =
-                            ( fh[idx_fh_F_ord2(iF, jF - 2, kF + 1, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF, jF - 1, kF + 1, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF, jF + 1, kF + 1, ex)]
-                             -    fh[idx_fh_F_ord2(iF, jF + 2, kF + 1, ex)] );
-
-                        const double t_kp2 =
-                            ( fh[idx_fh_F_ord2(iF, jF - 2, kF + 2, ex)]
-                             -F8*fh[idx_fh_F_ord2(iF, jF - 1, kF + 2, ex)]
-                             +F8*fh[idx_fh_F_ord2(iF, jF + 1, kF + 2, ex)]
-                             -    fh[idx_fh_F_ord2(iF, jF + 2, kF + 2, ex)] );
-
-                        fyz[p] = Fdydz * ( t_km2 - F8 * t_km1 + F8 * t_kp1 - t_kp2 );
-                    }
-                }
-            }
-        }
-    }
-
-    // free(fh);
-}

AMSS_NCKU_source/Derivative/fderivs_c.C

@@ -1,167 +0,0 @@
-#include "tool.h"
-
-/*
- * C 版 fderivs
- *
- * Fortran:
- * subroutine fderivs(ex,f,fx,fy,fz,X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
- *
- * 约定：
- *   f, fx, fy, fz: ex1*ex2*ex3，按 idx_ex 布局
- *   X: ex1, Y: ex2, Z: ex3
- */
-void fderivs(const int ex[3],
-             const double *f,
-             double *fx, double *fy, double *fz,
-             const double *X, const double *Y, const double *Z,
-             double SYM1, double SYM2, double SYM3,
-             int Symmetry, int onoff)
-{
-    (void)onoff; // Fortran 里没用到
-
-    const double ZEO = 0.0, ONE = 1.0;
-    const double TWO = 2.0, EIT = 8.0;
-    const double F12 = 12.0;
-
-    const int NO_SYMM = 0, EQ_SYMM = 1; // OCTANT=2 在本子程序里不直接用
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    // dX = X(2)-X(1) -> C: X[1]-X[0]
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    // Fortran 1-based bounds
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -1;
-
-    // SoA(1:3) = SYM1,SYM2,SYM3
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    // fh: (ex1+2)*(ex2+2)*(ex3+2) because ord=2
-    const size_t nx = (size_t)ex1 + 2;
-    const size_t ny = (size_t)ex2 + 2;
-    const size_t nz = (size_t)ex3 + 2;
-    const size_t fh_size = nx * ny * nz;
-    static double *fh = NULL;
-    static size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
-    // double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    // call symmetry_bd(2,ex,f,fh,SoA)
-    symmetry_bd(2, ex, f, fh, SoA);
-
-    const double d12dx = ONE / F12 / dX;
-    const double d12dy = ONE / F12 / dY;
-    const double d12dz = ONE / F12 / dZ;
-
-    const double d2dx  = ONE / TWO / dX;
-    const double d2dy  = ONE / TWO / dY;
-    const double d2dz  = ONE / TWO / dZ;
-
-    // fx = fy = fz = 0
-    const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
-    for (size_t p = 0; p < all; ++p) {
-        fx[p] = ZEO;
-        fy[p] = ZEO;
-        fz[p] = ZEO;
-    }
-
-    /*
-     * 两段式：
-     * 1) 先在二阶可用区域计算二阶模板
-     * 2) 再在高阶可用区域覆盖为四阶模板
-     *
-     * 与原 if/elseif 逻辑等价，但减少逐点分支判断。
-     */
-    const int i2_lo = (iminF > 0) ? iminF : 0;
-    const int j2_lo = (jminF > 0) ? jminF : 0;
-    const int k2_lo = (kminF > 0) ? kminF : 0;
-    const int i2_hi = ex1 - 2;
-    const int j2_hi = ex2 - 2;
-    const int k2_hi = ex3 - 2;
-
-    const int i4_lo = (iminF + 1 > 0) ? (iminF + 1) : 0;
-    const int j4_lo = (jminF + 1 > 0) ? (jminF + 1) : 0;
-    const int k4_lo = (kminF + 1 > 0) ? (kminF + 1) : 0;
-    const int i4_hi = ex1 - 3;
-    const int j4_hi = ex2 - 3;
-    const int k4_hi = ex3 - 3;
-
-    if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
-        for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    fx[p] = d2dx * (
-                        -fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +
-                         fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)]
-                    );
-
-                    fy[p] = d2dy * (
-                        -fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] +
-                         fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)]
-                    );
-
-                    fz[p] = d2dz * (
-                        -fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] +
-                         fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)]
-                    );
-                }
-            }
-        }
-    }
-
-    if (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi) {
-        for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i4_lo; i0 <= i4_hi; ++i0) {
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    fx[p] = d12dx * (
-                        fh[idx_fh_F_ord2(iF - 2, jF,     kF,     ex)] -
-                        EIT * fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +
-                        EIT * fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)] -
-                        fh[idx_fh_F_ord2(iF + 2, jF,     kF,     ex)]
-                    );
-
-                    fy[p] = d12dy * (
-                        fh[idx_fh_F_ord2(iF,     jF - 2, kF,     ex)] -
-                        EIT * fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] +
-                        EIT * fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)] -
-                        fh[idx_fh_F_ord2(iF,     jF + 2, kF,     ex)]
-                    );
-
-                    fz[p] = d12dz * (
-                        fh[idx_fh_F_ord2(iF,     jF,     kF - 2, ex)] -
-                        EIT * fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] +
-                        EIT * fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)] -
-                        fh[idx_fh_F_ord2(iF,     jF,     kF + 2, ex)]
-                    );
-                }
-            }
-        }
-    }
-
-    // free(fh);
-}

AMSS_NCKU_source/FFT.f90

@@ -1,87 +1,87 @@
-
-
-#if 0
-program checkFFT
-use dfport
-implicit none
-double precision::x
-integer,parameter::N=256
-double precision,dimension(N*2)::p
-double precision,dimension(N/2)::s
-integer::ncount,j,idum
-character(len=8)::tt
-tt=clock()
-idum=iachar(tt(8:8))-48
-p=0.0
-open(77,file='prime.dat',status='unknown')
-loop1:do ncount=1,N
-   x=ran(idum)
-   p(2*ncount-1)=x
-   write(77,'(f15.3)')x
-enddo loop1
-close(77)
-call four1(p,N,1)
-do j=1,N/2
-  s(j)=p(2*j)*p(2*j)+p(2*j-1)*p(2*j-1)
-enddo
-x=0.0
-do j=1,N/2
-  x=x+s(j)
-enddo
-s=s/x
-open(77,file='power.dat',status='unknown')
-do j=1,N/2
-  write(77,'(2(1x,f15.3))')dble(j-1)/dble(N),s(j)
-enddo
-close(77)
-end program checkFFT
-#endif
-
-!-------------
-! Optimized FFT using Intel oneMKL DFTI
-! Mathematical equivalence: Standard DFT definition
-!   Forward (isign=1):  X[k] = sum_{n=0}^{N-1} x[n] * exp(-2*pi*i*k*n/N)
-!   Backward (isign=-1): X[k] = sum_{n=0}^{N-1} x[n] * exp(+2*pi*i*k*n/N)
-! Input/Output: dataa is interleaved complex array [Re(0),Im(0),Re(1),Im(1),...]
-!-------------
-SUBROUTINE four1(dataa,nn,isign)
-use MKL_DFTI
-implicit none
-INTEGER, intent(in) :: isign, nn
-DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
-
-type(DFTI_DESCRIPTOR), pointer :: desc
-integer :: status
-
-! Create DFTI descriptor for 1D complex-to-complex transform
-status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
-if (status /= 0) return
-
-! Set input/output storage as interleaved complex (default)
-status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
-if (status /= 0) then
-   status = DftiFreeDescriptor(desc)
-   return
-endif
-
-! Commit the descriptor
-status = DftiCommitDescriptor(desc)
-if (status /= 0) then
-   status = DftiFreeDescriptor(desc)
-   return
-endif
-
-! Execute FFT based on direction
-if (isign == 1) then
-   ! Forward FFT: exp(-2*pi*i*k*n/N)
-   status = DftiComputeForward(desc, dataa)
-else
-   ! Backward FFT: exp(+2*pi*i*k*n/N)
-   status = DftiComputeBackward(desc, dataa)
-endif
-
-! Free descriptor
-status = DftiFreeDescriptor(desc)
-
-return
-END SUBROUTINE four1
+
+
+#if 0
+program checkFFT
+use dfport
+implicit none
+double precision::x
+integer,parameter::N=256
+double precision,dimension(N*2)::p
+double precision,dimension(N/2)::s
+integer::ncount,j,idum
+character(len=8)::tt
+tt=clock()
+idum=iachar(tt(8:8))-48
+p=0.0
+open(77,file='prime.dat',status='unknown')
+loop1:do ncount=1,N
+   x=ran(idum)
+   p(2*ncount-1)=x
+   write(77,'(f15.3)')x
+enddo loop1
+close(77)
+call four1(p,N,1)
+do j=1,N/2
+  s(j)=p(2*j)*p(2*j)+p(2*j-1)*p(2*j-1)
+enddo
+x=0.0
+do j=1,N/2
+  x=x+s(j)
+enddo
+s=s/x
+open(77,file='power.dat',status='unknown')
+do j=1,N/2
+  write(77,'(2(1x,f15.3))')dble(j-1)/dble(N),s(j)
+enddo
+close(77)
+end program checkFFT
+#endif
+
+!-------------
+! Optimized FFT using Intel oneMKL DFTI
+! Mathematical equivalence: Standard DFT definition
+!   Forward (isign=1):  X[k] = sum_{n=0}^{N-1} x[n] * exp(-2*pi*i*k*n/N)
+!   Backward (isign=-1): X[k] = sum_{n=0}^{N-1} x[n] * exp(+2*pi*i*k*n/N)
+! Input/Output: dataa is interleaved complex array [Re(0),Im(0),Re(1),Im(1),...]
+!-------------
+SUBROUTINE four1(dataa,nn,isign)
+use MKL_DFTI
+implicit none
+INTEGER, intent(in) :: isign, nn
+DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
+
+type(DFTI_DESCRIPTOR), pointer :: desc
+integer :: status
+
+! Create DFTI descriptor for 1D complex-to-complex transform
+status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
+if (status /= 0) return
+
+! Set input/output storage as interleaved complex (default)
+status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
+if (status /= 0) then
+   status = DftiFreeDescriptor(desc)
+   return
+endif
+
+! Commit the descriptor
+status = DftiCommitDescriptor(desc)
+if (status /= 0) then
+   status = DftiFreeDescriptor(desc)
+   return
+endif
+
+! Execute FFT based on direction
+if (isign == 1) then
+   ! Forward FFT: exp(-2*pi*i*k*n/N)
+   status = DftiComputeForward(desc, dataa)
+else
+   ! Backward FFT: exp(+2*pi*i*k*n/N)
+   status = DftiComputeBackward(desc, dataa)
+endif
+
+! Free descriptor
+status = DftiFreeDescriptor(desc)
+
+return
+END SUBROUTINE four1

AMSS_NCKU_source/IntPnts.C

@@ -1,97 +1,97 @@
-//$Id: IntPnts.C,v 1.1 2012/04/03 10:49:42 zjcao Exp $
-
-#include "macrodef.h"
-#ifdef With_AHF
-
-#include <math.h>
-#include <stdio.h>
-
-#include <iostream>
-using namespace std;
-
-#include "myglobal.h"
-
-namespace AHFinderDirect
-{
-  extern struct state state;
-  int globalInterpGFL(double *X, double *Y, double *Z, int Ns,
-                      double *Data)
-  {
-    if (Ns == 0)
-      return 0;
-    int n;
-    double *pox[3];
-    for (int i = 0; i < 3; i++)
-      pox[i] = new double[Ns];
-    for (n = 0; n < Ns; n++)
-    {
-      pox[0][n] = X[n];
-      pox[1][n] = Y[n];
-      pox[2][n] = Z[n];
-    }
-
-    const int InList = 35;
-
-    double *datap;
-    datap = new double[Ns * InList];
-    if (!(state.ADM->AH_Interp_Points(state.AHList, Ns, pox, datap, state.Symmetry)))
-      return 0;
-    // reform data
-    for (int pnt = 0; pnt < Ns; pnt++)
-      for (int ii = 0; ii < InList; ii++)
-      {
-        if (ii == 0 || ii == 12 || ii == 20)
-          Data[pnt + ii * Ns] = datap[ii + pnt * InList] + 1;
-        else if (ii == 24) // from chi-1 to psi
-          Data[pnt + ii * Ns] = pow(datap[ii + pnt * InList] + 1, -0.25);
-        else if (ii == 25 || ii == 26 || ii == 27) // from chi,i to psi,i
-          Data[pnt + ii * Ns] = -pow(datap[24 + pnt * InList] + 1, -1.25) / 4 * datap[ii + pnt * InList];
-        else
-          Data[pnt + ii * Ns] = datap[ii + pnt * InList];
-      }
-    delete[] datap;
-
-    delete[] pox[0];
-    delete[] pox[1];
-    delete[] pox[2];
-
-    return 1;
-  }
-  // inerpolate lapse and shift
-  int globalInterpGFLlash(double *X, double *Y, double *Z, int Ns,
-                          double *Data)
-  {
-    if (Ns == 0)
-      return 0;
-    int n;
-    double *pox[3];
-    for (int i = 0; i < 3; i++)
-      pox[i] = new double[Ns];
-    for (n = 0; n < Ns; n++)
-    {
-      pox[0][n] = X[n];
-      pox[1][n] = Y[n];
-      pox[2][n] = Z[n];
-    }
-
-    double SYM = 1.0, ANT = -1.0;
-    const int InList = 4;
-
-    double *datap;
-    datap = new double[Ns * InList];
-    state.ADM->AH_Interp_Points(state.GaugeList, Ns, pox, datap, state.Symmetry);
-    // reform data
-    for (int pnt = 0; pnt < Ns; pnt++)
-      for (int ii = 0; ii < InList; ii++)
-        Data[pnt + ii * Ns] = datap[ii + pnt * InList];
-
-    delete[] datap;
-    delete[] pox[0];
-    delete[] pox[1];
-    delete[] pox[2];
-
-    return 1;
-  }
-
-} // namespace AHFinderDirect
-#endif
+//$Id: IntPnts.C,v 1.1 2012/04/03 10:49:42 zjcao Exp $
+
+#include "macrodef.h"
+#ifdef With_AHF
+
+#include <math.h>
+#include <stdio.h>
+
+#include <iostream>
+using namespace std;
+
+#include "myglobal.h"
+
+namespace AHFinderDirect
+{
+  extern struct state state;
+  int globalInterpGFL(double *X, double *Y, double *Z, int Ns,
+                      double *Data)
+  {
+    if (Ns == 0)
+      return 0;
+    int n;
+    double *pox[3];
+    for (int i = 0; i < 3; i++)
+      pox[i] = new double[Ns];
+    for (n = 0; n < Ns; n++)
+    {
+      pox[0][n] = X[n];
+      pox[1][n] = Y[n];
+      pox[2][n] = Z[n];
+    }
+
+    const int InList = 35;
+
+    double *datap;
+    datap = new double[Ns * InList];
+    if (!(state.ADM->AH_Interp_Points(state.AHList, Ns, pox, datap, state.Symmetry)))
+      return 0;
+    // reform data
+    for (int pnt = 0; pnt < Ns; pnt++)
+      for (int ii = 0; ii < InList; ii++)
+      {
+        if (ii == 0 || ii == 12 || ii == 20)
+          Data[pnt + ii * Ns] = datap[ii + pnt * InList] + 1;
+        else if (ii == 24) // from chi-1 to psi
+          Data[pnt + ii * Ns] = pow(datap[ii + pnt * InList] + 1, -0.25);
+        else if (ii == 25 || ii == 26 || ii == 27) // from chi,i to psi,i
+          Data[pnt + ii * Ns] = -pow(datap[24 + pnt * InList] + 1, -1.25) / 4 * datap[ii + pnt * InList];
+        else
+          Data[pnt + ii * Ns] = datap[ii + pnt * InList];
+      }
+    delete[] datap;
+
+    delete[] pox[0];
+    delete[] pox[1];
+    delete[] pox[2];
+
+    return 1;
+  }
+  // inerpolate lapse and shift
+  int globalInterpGFLlash(double *X, double *Y, double *Z, int Ns,
+                          double *Data)
+  {
+    if (Ns == 0)
+      return 0;
+    int n;
+    double *pox[3];
+    for (int i = 0; i < 3; i++)
+      pox[i] = new double[Ns];
+    for (n = 0; n < Ns; n++)
+    {
+      pox[0][n] = X[n];
+      pox[1][n] = Y[n];
+      pox[2][n] = Z[n];
+    }
+
+    double SYM = 1.0, ANT = -1.0;
+    const int InList = 4;
+
+    double *datap;
+    datap = new double[Ns * InList];
+    state.ADM->AH_Interp_Points(state.GaugeList, Ns, pox, datap, state.Symmetry);
+    // reform data
+    for (int pnt = 0; pnt < Ns; pnt++)
+      for (int ii = 0; ii < InList; ii++)
+        Data[pnt + ii * Ns] = datap[ii + pnt * InList];
+
+    delete[] datap;
+    delete[] pox[0];
+    delete[] pox[1];
+    delete[] pox[2];
+
+    return 1;
+  }
+
+} // namespace AHFinderDirect
+#endif

AMSS_NCKU_source/IntPnts0.C

@@ -1,43 +1,43 @@
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdarg.h>
-#include <string.h>
-
-#include <mpi.h>
-
-#include "myglobal.h"
-
-int CCTK_VInfo(const char *thorn, const char *format, ...)
-{
-   int myrank;
-   MPI_Comm_rank(MPI_COMM_WORLD,&myrank);
-   if (myrank !=0) return 0;
-   
-   va_list ap;
-   va_start (ap, format);
-   fprintf (stdout, "INFO (%s): ", thorn);
-   vfprintf (stdout, format, ap);
-   fprintf (stdout, "\n");
-   va_end (ap);
-   return 0;
-}
-int CCTK_VWarn (int level,
-                int line,
-                const char *file,
-                const char *thorn,
-                const char *format,
-                ...) 
-{  
-   int myrank;
-   MPI_Comm_rank(MPI_COMM_WORLD,&myrank);
-   if (myrank !=0) return 0;
-   
-   va_list ap;
-   va_start (ap, format);
-   fprintf (stdout, "WARN (%s): ", thorn);
-   vfprintf (stdout, format, ap);
-   fprintf (stdout, "\n");
-   va_end (ap);
-   return 0;
-}
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+#include <mpi.h>
+
+#include "myglobal.h"
+
+int CCTK_VInfo(const char *thorn, const char *format, ...)
+{
+   int myrank;
+   MPI_Comm_rank(MPI_COMM_WORLD,&myrank);
+   if (myrank !=0) return 0;
+   
+   va_list ap;
+   va_start (ap, format);
+   fprintf (stdout, "INFO (%s): ", thorn);
+   vfprintf (stdout, format, ap);
+   fprintf (stdout, "\n");
+   va_end (ap);
+   return 0;
+}
+int CCTK_VWarn (int level,
+                int line,
+                const char *file,
+                const char *thorn,
+                const char *format,
+                ...) 
+{  
+   int myrank;
+   MPI_Comm_rank(MPI_COMM_WORLD,&myrank);
+   if (myrank !=0) return 0;
+   
+   va_list ap;
+   va_start (ap, format);
+   fprintf (stdout, "WARN (%s): ", thorn);
+   vfprintf (stdout, format, ap);
+   fprintf (stdout, "\n");
+   va_end (ap);
+   return 0;
+}

AMSS_NCKU_source/Jacobian.C

@@ -1,270 +1,270 @@
-#include <stdlib.h>
-#include <stdio.h>
-#include <assert.h>
-#include <math.h>
-#include <string.h>
-
-#include "util_Table.h"
-#include "cctk.h"
-
-#include "config.h"
-#include "stdc.h"
-
-#include "util.h"
-#include "array.h"
-#include "cpm_map.h"
-#include "linear_map.h"
-
-#include "coords.h"
-#include "tgrid.h"
-#include "fd_grid.h"
-#include "patch.h"
-#include "patch_edge.h"
-#include "patch_interp.h"
-#include "ghost_zone.h"
-#include "patch_system.h"
-
-#include "Jacobian.h"
-#include "ilucg.h"
-// all the code in this file is inside this namespace
-namespace AHFinderDirect
-{
-	// this represents a single element stored in the matrix for
-	// sort_row_into_column_order()  and  sort_row_into_column_order__cmp()
-	struct matrix_element
-	{
-		int JA;
-		fp A;
-	};
-
-	Jacobian::Jacobian(patch_system &ps)
-		: ps_(ps),
-		  N_rows_(ps.N_grid_points()),
-		  N_nonzeros_(0), current_N_rows_(0), N_nonzeros_allocated_(0),
-		  IA_(new integer[N_rows_ + 1]), JA_(NULL), A_(NULL),
-		  itemp_(NULL), rtemp_(NULL)
-	{
-		IO_ = 1;
-		zero_matrix();
-	}
-
-	Jacobian::~Jacobian()
-	{
-		if (A_)
-			delete[] A_;
-		if (JA_)
-			delete[] JA_;
-		if (IA_)
-			delete[] IA_;
-		if (rtemp_)
-			delete[] rtemp_;
-		if (itemp_)
-			delete[] itemp_;
-	}
-
-	double Jacobian::element(int II, int JJ)
-		const
-	{
-		const int posn = find_element(II, JJ);
-		return (posn >= 0) ? A_[posn] : 0.0;
-	}
-
-	void Jacobian::zero_matrix()
-	{
-
-		N_nonzeros_ = 0;
-		current_N_rows_ = 0;
-		IA_[0] = IO_;
-	}
-
-	void Jacobian::set_element(int II, int JJ, fp value)
-	{
-		const int posn = find_element(II, JJ);
-		if (posn >= 0)
-			then A_[posn] = value;
-		else
-			insert_element(II, JJ, value);
-	}
-
-	void Jacobian::sum_into_element(int II, int JJ, fp value)
-	{
-		const int posn = find_element(II, JJ);
-		if (posn >= 0)
-			then A_[posn] += value;
-		else
-			insert_element(II, JJ, value);
-	}
-
-	int Jacobian::find_element(int II, int JJ)
-		const
-	{
-		if (II >= current_N_rows_)
-			then return -1; // this row not defined yet
-
-		const int start = IA_[II] - IO_;
-		const int stop = IA_[II + 1] - IO_;
-		for (int posn = start; posn < stop; ++posn)
-		{
-			if (JA_[posn] - IO_ == JJ)
-				then return posn; // found
-		}
-
-		return -1; // not found
-	}
-
-	int Jacobian::insert_element(int II, int JJ, double value)
-	{
-		if (!((II == current_N_rows_ - 1) || (II == current_N_rows_)))
-		{
-			printf(
-				"***** row_sparse_Jacobian::insert_element(II=%d, JJ=%d, value=%g):\n"
-				"        attempt to insert element elsewhere than {last row, last row+1}!\n"
-				"        N_rows_=%d   current_N_rows_=%d   IO_=%d\n"
-				"        N_nonzeros_=%d   N_nonzeros_allocated_=%d\n",
-				II, JJ, double(value),
-				N_rows_, current_N_rows_, IO_,
-				N_nonzeros_, N_nonzeros_allocated_);
-			abort();
-		}
-
-		// start a new row if necessary
-		if (II == current_N_rows_)
-			then
-			{
-				assert(current_N_rows_ < N_rows_);
-				IA_[current_N_rows_ + 1] = IA_[current_N_rows_];
-				++current_N_rows_;
-			}
-
-		// insert into current row
-		assert(II == current_N_rows_ - 1);
-		if (IA_[II + 1] - IO_ >= N_nonzeros_allocated_)
-			then grow_arrays();
-		const int posn = IA_[II + 1] - IO_;
-		assert(posn < N_nonzeros_allocated_);
-		JA_[posn] = JJ + IO_;
-		A_[posn] = value;
-		++IA_[II + 1];
-		++N_nonzeros_;
-
-		return posn;
-	}
-
-	void Jacobian::grow_arrays()
-	{
-		N_nonzeros_allocated_ += base_growth_amount + (N_nonzeros_allocated_ >> 1);
-
-		int *const new_JA = new int[N_nonzeros_allocated_];
-		double *const new_A = new double[N_nonzeros_allocated_];
-		for (int posn = 0; posn < N_nonzeros_; ++posn)
-		{
-			new_JA[posn] = JA_[posn];
-			new_A[posn] = A_[posn];
-		}
-		delete[] A_;
-		delete[] JA_;
-		JA_ = new_JA;
-		A_ = new_A;
-	}
-
-	int compare_matrix_elements(const void *x, const void *y)
-	{
-		const struct matrix_element *const px = static_cast<const struct matrix_element *>(x);
-		const struct matrix_element *const py = static_cast<const struct matrix_element *>(y);
-
-		return px->JA - py->JA;
-	}
-
-	void Jacobian::sort_each_row_into_column_order()
-	{
-		// buffer must be big enough to hold the largest row
-		int max_N_in_row = 0;
-		{
-			for (int II = 0; II < N_rows_; ++II)
-			{
-				max_N_in_row = max(max_N_in_row, IA_[II + 1] - IA_[II]);
-			}
-		}
-
-		// contiguous buffer for sorting
-		struct matrix_element *const buffer = new struct matrix_element[max_N_in_row];
-
-		{
-			for (int II = 0; II < N_rows_; ++II)
-			{
-				const int N_in_row = IA_[II + 1] - IA_[II];
-
-				// copy this row's JA_[] and A_[] values to the buffer
-				const int start = IA_[II] - IO_;
-				for (int p = 0; p < N_in_row; ++p)
-				{
-					const int posn = start + p;
-					buffer[p].JA = JA_[posn];
-					buffer[p].A = A_[posn];
-				}
-
-				// sort the buffer
-				qsort(static_cast<void *>(buffer), N_in_row, sizeof(buffer[0]),
-					  &compare_matrix_elements);
-
-				// copy the buffer values back to this row's JA_[] and A_[]
-				for (int p = 0; p < N_in_row; ++p)
-				{
-					const int posn = start + p;
-					JA_[posn] = buffer[p].JA;
-					A_[posn] = buffer[p].A;
-				}
-			}
-		}
-
-		delete[] buffer;
-	}
-
-	double Jacobian::solve_linear_system(int rhs_gfn, int x_gfn, bool print_msg_flag)
-	{
-		assert(IO_ == Fortran_index_origin);
-		assert(current_N_rows_ == N_rows_);
-
-		if (itemp_ == NULL)
-			then
-			{
-				itemp_ = new int[3 * N_rows_ + 3 * N_nonzeros_ + 2];
-				rtemp_ = new double[4 * N_rows_ + N_nonzeros_];
-			}
-
-		// initial guess = all zeros
-		double *x = ps_.gridfn_data(x_gfn);
-		for (int II = 0; II < N_rows_; ++II)
-		{
-			x[II] = 0.0;
-		}
-
-		const int N = N_rows_;
-		const double *rhs = ps_.gridfn_data(rhs_gfn);
-		const double eps = 1e-10;
-		const int max_iterations = N_rows_;
-		int istatus;
-
-		// the actual linear solution
-		f_ilucg(N,
-				IA_, JA_, A_,
-				rhs, x,
-				itemp_, rtemp_,
-				eps, max_iterations,
-				istatus);
-
-		if (istatus < 0)
-		{
-			printf(
-				"***** row_sparse_Jacobian__ILUCG::solve_linear_system(rhs_gfn=%d, x_gfn=%d):\n"
-				"        error return from [sd]ilucg() routine!\n"
-				"        istatus=%d < 0 ==> bad matrix structure, eg. zero diagonal element!\n",
-				rhs_gfn, x_gfn,
-				int(istatus));
-			abort();
-		}
-
-		return -1.0;
-	}
-
-} // namespace AHFinderDirect
+#include <stdlib.h>
+#include <stdio.h>
+#include <assert.h>
+#include <math.h>
+#include <string.h>
+
+#include "util_Table.h"
+#include "cctk.h"
+
+#include "config.h"
+#include "stdc.h"
+
+#include "util.h"
+#include "array.h"
+#include "cpm_map.h"
+#include "linear_map.h"
+
+#include "coords.h"
+#include "tgrid.h"
+#include "fd_grid.h"
+#include "patch.h"
+#include "patch_edge.h"
+#include "patch_interp.h"
+#include "ghost_zone.h"
+#include "patch_system.h"
+
+#include "Jacobian.h"
+#include "ilucg.h"
+// all the code in this file is inside this namespace
+namespace AHFinderDirect
+{
+	// this represents a single element stored in the matrix for
+	// sort_row_into_column_order()  and  sort_row_into_column_order__cmp()
+	struct matrix_element
+	{
+		int JA;
+		fp A;
+	};
+
+	Jacobian::Jacobian(patch_system &ps)
+		: ps_(ps),
+		  N_rows_(ps.N_grid_points()),
+		  N_nonzeros_(0), current_N_rows_(0), N_nonzeros_allocated_(0),
+		  IA_(new integer[N_rows_ + 1]), JA_(NULL), A_(NULL),
+		  itemp_(NULL), rtemp_(NULL)
+	{
+		IO_ = 1;
+		zero_matrix();
+	}
+
+	Jacobian::~Jacobian()
+	{
+		if (A_)
+			delete[] A_;
+		if (JA_)
+			delete[] JA_;
+		if (IA_)
+			delete[] IA_;
+		if (rtemp_)
+			delete[] rtemp_;
+		if (itemp_)
+			delete[] itemp_;
+	}
+
+	double Jacobian::element(int II, int JJ)
+		const
+	{
+		const int posn = find_element(II, JJ);
+		return (posn >= 0) ? A_[posn] : 0.0;
+	}
+
+	void Jacobian::zero_matrix()
+	{
+
+		N_nonzeros_ = 0;
+		current_N_rows_ = 0;
+		IA_[0] = IO_;
+	}
+
+	void Jacobian::set_element(int II, int JJ, fp value)
+	{
+		const int posn = find_element(II, JJ);
+		if (posn >= 0)
+			then A_[posn] = value;
+		else
+			insert_element(II, JJ, value);
+	}
+
+	void Jacobian::sum_into_element(int II, int JJ, fp value)
+	{
+		const int posn = find_element(II, JJ);
+		if (posn >= 0)
+			then A_[posn] += value;
+		else
+			insert_element(II, JJ, value);
+	}
+
+	int Jacobian::find_element(int II, int JJ)
+		const
+	{
+		if (II >= current_N_rows_)
+			then return -1; // this row not defined yet
+
+		const int start = IA_[II] - IO_;
+		const int stop = IA_[II + 1] - IO_;
+		for (int posn = start; posn < stop; ++posn)
+		{
+			if (JA_[posn] - IO_ == JJ)
+				then return posn; // found
+		}
+
+		return -1; // not found
+	}
+
+	int Jacobian::insert_element(int II, int JJ, double value)
+	{
+		if (!((II == current_N_rows_ - 1) || (II == current_N_rows_)))
+		{
+			printf(
+				"***** row_sparse_Jacobian::insert_element(II=%d, JJ=%d, value=%g):\n"
+				"        attempt to insert element elsewhere than {last row, last row+1}!\n"
+				"        N_rows_=%d   current_N_rows_=%d   IO_=%d\n"
+				"        N_nonzeros_=%d   N_nonzeros_allocated_=%d\n",
+				II, JJ, double(value),
+				N_rows_, current_N_rows_, IO_,
+				N_nonzeros_, N_nonzeros_allocated_);
+			abort();
+		}
+
+		// start a new row if necessary
+		if (II == current_N_rows_)
+			then
+			{
+				assert(current_N_rows_ < N_rows_);
+				IA_[current_N_rows_ + 1] = IA_[current_N_rows_];
+				++current_N_rows_;
+			}
+
+		// insert into current row
+		assert(II == current_N_rows_ - 1);
+		if (IA_[II + 1] - IO_ >= N_nonzeros_allocated_)
+			then grow_arrays();
+		const int posn = IA_[II + 1] - IO_;
+		assert(posn < N_nonzeros_allocated_);
+		JA_[posn] = JJ + IO_;
+		A_[posn] = value;
+		++IA_[II + 1];
+		++N_nonzeros_;
+
+		return posn;
+	}
+
+	void Jacobian::grow_arrays()
+	{
+		N_nonzeros_allocated_ += base_growth_amount + (N_nonzeros_allocated_ >> 1);
+
+		int *const new_JA = new int[N_nonzeros_allocated_];
+		double *const new_A = new double[N_nonzeros_allocated_];
+		for (int posn = 0; posn < N_nonzeros_; ++posn)
+		{
+			new_JA[posn] = JA_[posn];
+			new_A[posn] = A_[posn];
+		}
+		delete[] A_;
+		delete[] JA_;
+		JA_ = new_JA;
+		A_ = new_A;
+	}
+
+	int compare_matrix_elements(const void *x, const void *y)
+	{
+		const struct matrix_element *const px = static_cast<const struct matrix_element *>(x);
+		const struct matrix_element *const py = static_cast<const struct matrix_element *>(y);
+
+		return px->JA - py->JA;
+	}
+
+	void Jacobian::sort_each_row_into_column_order()
+	{
+		// buffer must be big enough to hold the largest row
+		int max_N_in_row = 0;
+		{
+			for (int II = 0; II < N_rows_; ++II)
+			{
+				max_N_in_row = max(max_N_in_row, IA_[II + 1] - IA_[II]);
+			}
+		}
+
+		// contiguous buffer for sorting
+		struct matrix_element *const buffer = new struct matrix_element[max_N_in_row];
+
+		{
+			for (int II = 0; II < N_rows_; ++II)
+			{
+				const int N_in_row = IA_[II + 1] - IA_[II];
+
+				// copy this row's JA_[] and A_[] values to the buffer
+				const int start = IA_[II] - IO_;
+				for (int p = 0; p < N_in_row; ++p)
+				{
+					const int posn = start + p;
+					buffer[p].JA = JA_[posn];
+					buffer[p].A = A_[posn];
+				}
+
+				// sort the buffer
+				qsort(static_cast<void *>(buffer), N_in_row, sizeof(buffer[0]),
+					  &compare_matrix_elements);
+
+				// copy the buffer values back to this row's JA_[] and A_[]
+				for (int p = 0; p < N_in_row; ++p)
+				{
+					const int posn = start + p;
+					JA_[posn] = buffer[p].JA;
+					A_[posn] = buffer[p].A;
+				}
+			}
+		}
+
+		delete[] buffer;
+	}
+
+	double Jacobian::solve_linear_system(int rhs_gfn, int x_gfn, bool print_msg_flag)
+	{
+		assert(IO_ == Fortran_index_origin);
+		assert(current_N_rows_ == N_rows_);
+
+		if (itemp_ == NULL)
+			then
+			{
+				itemp_ = new int[3 * N_rows_ + 3 * N_nonzeros_ + 2];
+				rtemp_ = new double[4 * N_rows_ + N_nonzeros_];
+			}
+
+		// initial guess = all zeros
+		double *x = ps_.gridfn_data(x_gfn);
+		for (int II = 0; II < N_rows_; ++II)
+		{
+			x[II] = 0.0;
+		}
+
+		const int N = N_rows_;
+		const double *rhs = ps_.gridfn_data(rhs_gfn);
+		const double eps = 1e-10;
+		const int max_iterations = N_rows_;
+		int istatus;
+
+		// the actual linear solution
+		f_ilucg(N,
+				IA_, JA_, A_,
+				rhs, x,
+				itemp_, rtemp_,
+				eps, max_iterations,
+				istatus);
+
+		if (istatus < 0)
+		{
+			printf(
+				"***** row_sparse_Jacobian__ILUCG::solve_linear_system(rhs_gfn=%d, x_gfn=%d):\n"
+				"        error return from [sd]ilucg() routine!\n"
+				"        istatus=%d < 0 ==> bad matrix structure, eg. zero diagonal element!\n",
+				rhs_gfn, x_gfn,
+				int(istatus));
+			abort();
+		}
+
+		return -1.0;
+	}
+
+} // namespace AHFinderDirect

AMSS_NCKU_source/Jacobian.h

@@ -1,90 +1,90 @@
-#ifndef AHFINDERDIRECT__JACOBIAN_HH
-#define AHFINDERDIRECT__JACOBIAN_HH
-
-namespace AHFinderDirect
-{
-	class Jacobian
-	{
-	public:
-		// basic meta-info
-		patch_system &my_patch_system() const { return ps_; }
-		int N_rows() const { return N_rows_; }
-
-		// convert (patch,irho,isigma) <--> row/column index
-		int II_of_patch_irho_isigma(const patch &p, int irho, int isigma)
-			const
-		{
-			return ps_.gpn_of_patch_irho_isigma(p, irho, isigma);
-		}
-		const patch &patch_irho_isigma_of_II(int II, int &irho, int &isigma)
-			const
-		{
-			return ps_.patch_irho_isigma_of_gpn(II, irho, isigma);
-		}
-
-		double element(int II, int JJ) const;
-
-		// is the matrix element (II,JJ) stored explicitly?
-		bool is_explicitly_stored(int II, int JJ) const
-		{
-			return find_element(II, JJ) > 0;
-		}
-
-		int IO() const { return IO_; }
-		enum
-		{
-			C_index_origin = 0,
-			Fortran_index_origin = 1
-		};
-
-		void zero_matrix();
-
-		void set_element(int II, int JJ, fp value);
-
-		void sum_into_element(int II, int JJ, fp value);
-
-		int find_element(int II, int JJ) const;
-
-		int insert_element(int II, int JJ, fp value);
-
-		void grow_arrays();
-
-		enum
-		{
-			base_growth_amount = 1000
-		};
-
-		void sort_each_row_into_column_order();
-
-		double solve_linear_system(int rhs_gfn, int x_gfn,
-								   bool print_msg_flag);
-
-	public:
-		Jacobian(patch_system &ps);
-		~Jacobian();
-
-	protected:
-		patch_system &ps_;
-		int N_rows_;
-
-		int IO_;
-
-		int N_nonzeros_;
-		int current_N_rows_;
-
-		int N_nonzeros_allocated_;
-
-		int *IA_;
-
-		int *JA_;
-
-		double *A_;
-
-		int *itemp_;
-		double *rtemp_;
-	};
-
-	//******************************************************************************
-
-} // namespace AHFinderDirect
-#endif /* AHFINDERDIRECT__JACOBIAN_HH */
+#ifndef AHFINDERDIRECT__JACOBIAN_HH
+#define AHFINDERDIRECT__JACOBIAN_HH
+
+namespace AHFinderDirect
+{
+	class Jacobian
+	{
+	public:
+		// basic meta-info
+		patch_system &my_patch_system() const { return ps_; }
+		int N_rows() const { return N_rows_; }
+
+		// convert (patch,irho,isigma) <--> row/column index
+		int II_of_patch_irho_isigma(const patch &p, int irho, int isigma)
+			const
+		{
+			return ps_.gpn_of_patch_irho_isigma(p, irho, isigma);
+		}
+		const patch &patch_irho_isigma_of_II(int II, int &irho, int &isigma)
+			const
+		{
+			return ps_.patch_irho_isigma_of_gpn(II, irho, isigma);
+		}
+
+		double element(int II, int JJ) const;
+
+		// is the matrix element (II,JJ) stored explicitly?
+		bool is_explicitly_stored(int II, int JJ) const
+		{
+			return find_element(II, JJ) > 0;
+		}
+
+		int IO() const { return IO_; }
+		enum
+		{
+			C_index_origin = 0,
+			Fortran_index_origin = 1
+		};
+
+		void zero_matrix();
+
+		void set_element(int II, int JJ, fp value);
+
+		void sum_into_element(int II, int JJ, fp value);
+
+		int find_element(int II, int JJ) const;
+
+		int insert_element(int II, int JJ, fp value);
+
+		void grow_arrays();
+
+		enum
+		{
+			base_growth_amount = 1000
+		};
+
+		void sort_each_row_into_column_order();
+
+		double solve_linear_system(int rhs_gfn, int x_gfn,
+								   bool print_msg_flag);
+
+	public:
+		Jacobian(patch_system &ps);
+		~Jacobian();
+
+	protected:
+		patch_system &ps_;
+		int N_rows_;
+
+		int IO_;
+
+		int N_nonzeros_;
+		int current_N_rows_;
+
+		int N_nonzeros_allocated_;
+
+		int *IA_;
+
+		int *JA_;
+
+		double *A_;
+
+		int *itemp_;
+		double *rtemp_;
+	};
+
+	//******************************************************************************
+
+} // namespace AHFinderDirect
+#endif /* AHFINDERDIRECT__JACOBIAN_HH */

AMSS_NCKU_source/KO_dissipation/kodiss_c.C

@@ -1,117 +0,0 @@
-#include "tool.h"
-
-/*
- * C 版 kodis
- *
- * Fortran signature:
- * subroutine kodis(ex,X,Y,Z,f,f_rhs,SoA,Symmetry,eps)
- *
- * 约定：
- *   X: ex1, Y: ex2, Z: ex3
- *   f, f_rhs: ex1*ex2*ex3 按 idx_ex 布局
- *   SoA[3]
- *   eps: double
- */
-void kodis(const int ex[3],
-           const double *X, const double *Y, const double *Z,
-           const double *f, double *f_rhs,
-           const double SoA[3],
-           int Symmetry, double eps)
-{
-    const double ONE = 1.0, SIX = 6.0, FIT = 15.0, TWT = 20.0;
-    const double cof = 64.0;             // 2^6
-    const int NO_SYMM = 0, OCTANT = 2;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    // Fortran: dX = X(2)-X(1) -> C: X[1]-X[0]
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-    (void)ONE; // ONE 在原 Fortran 里只是参数，这里不一定用得上
-
-    // Fortran: imax=ex(1) 等是 1-based 上界
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    // Fortran: imin=jmin=kmin=1，某些对称情况变 -2
-    int iminF = 1, jminF = 1, kminF = 1;
-
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
-    if (Symmetry == OCTANT && fabs(X[0]) < dX) iminF = -2;
-    if (Symmetry == OCTANT && fabs(Y[0]) < dY) jminF = -2;
-
-    // 分配 fh：大小 (ex1+3)*(ex2+3)*(ex3+3)，对应 ord=3
-    const size_t nx = (size_t)ex1 + 3;
-    const size_t ny = (size_t)ex2 + 3;
-    const size_t nz = (size_t)ex3 + 3;
-    const size_t fh_size = nx * ny * nz;
-
-    double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    // Fortran: call symmetry_bd(3,ex,f,fh,SoA)
-    symmetry_bd(3, ex, f, fh, SoA);
-
-    /*
-     * Fortran loops:
-     * do k=1,ex3
-     * do j=1,ex2
-     * do i=1,ex1
-     *
-     * C: k0=0..ex3-1, j0=0..ex2-1, i0=0..ex1-1
-     * 并定义 Fortran index: iF=i0+1, ...
-     */
-    // 收紧循环范围：只遍历满足 iF±3/jF±3/kF±3 条件的内部点
-    // iF-3 >= iminF => iF >= iminF+3 => i0 >= iminF+2 (因为 iF=i0+1)
-    // iF+3 <= imaxF => iF <= imaxF-3 => i0 <= imaxF-4
-    const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
-    const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
-    const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
-    const int i0_hi = imaxF - 4;  // inclusive
-    const int j0_hi = jmaxF - 4;
-    const int k0_hi = kmaxF - 4;
-
-    if (i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi) {
-        free(fh);
-        return;
-    }
-
-    for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
-        const int kF = k0 + 1;
-        for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
-            const int jF = j0 + 1;
-            for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
-                const int iF = i0 + 1;
-
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    // 三个方向各一份同型的 7 点组合（实际上是对称的 6th-order dissipation/filter 核）
-                    const double Dx_term =
-                        ( (fh[idx_fh_F(iF - 3, jF, kF, ex)] + fh[idx_fh_F(iF + 3, jF, kF, ex)]) -
-                          SIX * (fh[idx_fh_F(iF - 2, jF, kF, ex)] + fh[idx_fh_F(iF + 2, jF, kF, ex)]) +
-                          FIT * (fh[idx_fh_F(iF - 1, jF, kF, ex)] + fh[idx_fh_F(iF + 1, jF, kF, ex)]) -
-                          TWT *  fh[idx_fh_F(iF    , jF, kF, ex)] ) / dX;
-
-                    const double Dy_term =
-                        ( (fh[idx_fh_F(iF, jF - 3, kF, ex)] + fh[idx_fh_F(iF, jF + 3, kF, ex)]) -
-                          SIX * (fh[idx_fh_F(iF, jF - 2, kF, ex)] + fh[idx_fh_F(iF, jF + 2, kF, ex)]) +
-                          FIT * (fh[idx_fh_F(iF, jF - 1, kF, ex)] + fh[idx_fh_F(iF, jF + 1, kF, ex)]) -
-                          TWT *  fh[idx_fh_F(iF, jF    , kF, ex)] ) / dY;
-
-                    const double Dz_term =
-                        ( (fh[idx_fh_F(iF, jF, kF - 3, ex)] + fh[idx_fh_F(iF, jF, kF + 3, ex)]) -
-                          SIX * (fh[idx_fh_F(iF, jF, kF - 2, ex)] + fh[idx_fh_F(iF, jF, kF + 2, ex)]) +
-                          FIT * (fh[idx_fh_F(iF, jF, kF - 1, ex)] + fh[idx_fh_F(iF, jF, kF + 1, ex)]) -
-                          TWT *  fh[idx_fh_F(iF, jF, kF    , ex)] ) / dZ;
-
-                    // Fortran:
-                    // f_rhs(i,j,k) = f_rhs(i,j,k) + eps/cof*(Dx_term + Dy_term + Dz_term)
-                    f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
-            }
-        }
-    }
-
-    free(fh);
-}

AMSS_NCKU_source/MPatch.h

@@ -1,55 +1,55 @@
-
-#ifndef PATCH_H
-#define PATCH_H
-
-#include <mpi.h>
-#include "MyList.h"
-#include "Block.h"
-#include "var.h"
-#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
-
-class Patch
-{
-
-public:
-   int lev;
-   int shape[dim];
-   double bbox[2 * dim]; // this bbox includes buffer points
-   MyList<Block> *blb, *ble;
-   int lli[dim], uui[dim]; // denote the buffer points on each boundary
-
-public:
-   Patch() {};
-   Patch(int DIM, int *shapei, double *bboxi, int levi, bool buflog, int Symmetry);
-
-   ~Patch();
-
-   void checkPatch(bool buflog);
-   void checkPatch(bool buflog, const int out_rank);
-   void checkBlock();
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX,
-                      double *Shellf, int Symmetry);
-   bool Interp_ONE_Point(MyList<var> *VarList, double *XX,
-                         double *Shellf, int Symmetry);
-   double getdX(int dir);
-
-   void Find_Maximum(MyList<var> *VarList, double *XX,
-                     double *Shellf);
-
-   bool Find_Point(double *XX);
-
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX,
-                      double *Shellf, int Symmetry,
-                      int Nmin_consumer, int Nmax_consumer);
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX,
-                      double *Shellf, int Symmetry, MPI_Comm Comm_here);
-   bool Interp_ONE_Point(MyList<var> *VarList, double *XX,
-                         double *Shellf, int Symmetry, MPI_Comm Comm_here);
-   void Find_Maximum(MyList<var> *VarList, double *XX,
-                     double *Shellf, MPI_Comm Comm_here);
-};
-
-#endif /* PATCH_H */
+
+#ifndef PATCH_H
+#define PATCH_H
+
+#include <mpi.h>
+#include "MyList.h"
+#include "Block.h"
+#include "var.h"
+#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
+
+class Patch
+{
+
+public:
+   int lev;
+   int shape[dim];
+   double bbox[2 * dim]; // this bbox includes buffer points
+   MyList<Block> *blb, *ble;
+   int lli[dim], uui[dim]; // denote the buffer points on each boundary
+
+public:
+   Patch() {};
+   Patch(int DIM, int *shapei, double *bboxi, int levi, bool buflog, int Symmetry);
+
+   ~Patch();
+
+   void checkPatch(bool buflog);
+   void checkPatch(bool buflog, const int out_rank);
+   void checkBlock();
+   void Interp_Points(MyList<var> *VarList,
+                      int NN, double **XX,
+                      double *Shellf, int Symmetry);
+   bool Interp_ONE_Point(MyList<var> *VarList, double *XX,
+                         double *Shellf, int Symmetry);
+   double getdX(int dir);
+
+   void Find_Maximum(MyList<var> *VarList, double *XX,
+                     double *Shellf);
+
+   bool Find_Point(double *XX);
+
+   void Interp_Points(MyList<var> *VarList,
+                      int NN, double **XX,
+                      double *Shellf, int Symmetry,
+                      int Nmin_consumer, int Nmax_consumer);
+   void Interp_Points(MyList<var> *VarList,
+                      int NN, double **XX,
+                      double *Shellf, int Symmetry, MPI_Comm Comm_here);
+   bool Interp_ONE_Point(MyList<var> *VarList, double *XX,
+                         double *Shellf, int Symmetry, MPI_Comm Comm_here);
+   void Find_Maximum(MyList<var> *VarList, double *XX,
+                     double *Shellf, MPI_Comm Comm_here);
+};
+
+#endif /* PATCH_H */

AMSS_NCKU_source/MyList.h

@@ -1,109 +1,109 @@
-
-#ifndef MYLIST_H
-#define MYLIST_H
-
-// Note: There is never an implementation file (*.C) for a template class
-
-template <class T>
-class MyList
-{
-
-public:
-  MyList *next;
-  T *data;
-
-public:
-  MyList();
-  MyList(T *p);
-  ~MyList();
-  void insert(T *p);
-  void clearList();
-  void destroyList();
-  void catList(MyList<T> *p);
-  void CloneList(MyList<T> *p);
-};
-
-template <class T>
-MyList<T>::MyList()
-{
-  data = 0;
-  next = 0;
-}
-template <class T>
-MyList<T>::MyList(T *p)
-{
-  data = p;
-  next = 0;
-}
-
-template <class T>
-MyList<T>::~MyList()
-{
-}
-template <class T>
-void MyList<T>::insert(T *p)
-{
-  MyList *ct = this;
-  if (data == 0)
-  {
-    data = p;
-  }
-  else
-  {
-    while (ct->next)
-    {
-      ct = ct->next;
-    }
-    ct->next = new MyList(p);
-    ct = ct->next;
-    ct->next = 0;
-  }
-}
-template <class T>
-void MyList<T>::clearList()
-{
-  MyList *ct = this, *n;
-  while (ct)
-  {
-    n = ct->next;
-    delete ct;
-    ct = n;
-  }
-}
-template <class T>
-void MyList<T>::destroyList()
-{
-  MyList *ct = this, *n;
-  while (ct)
-  {
-    n = ct->next;
-    delete ct->data;
-    delete ct;
-    ct = n;
-  }
-}
-template <class T>
-void MyList<T>::catList(MyList<T> *p)
-{
-  MyList *ct = this;
-  while (ct->next)
-  {
-    ct = ct->next;
-  }
-  ct->next = p;
-}
-template <class T>
-void MyList<T>::CloneList(MyList<T> *p)
-{
-  MyList *ct = this;
-  p = 0;
-  while (ct)
-  {
-    if (!p)
-      p = new MyList<T>(ct->data);
-    else
-      p->insert(ct->data);
-    ct = ct->next;
-  }
-}
-#endif /* MyList_H */
+
+#ifndef MYLIST_H
+#define MYLIST_H
+
+// Note: There is never an implementation file (*.C) for a template class
+
+template <class T>
+class MyList
+{
+
+public:
+  MyList *next;
+  T *data;
+
+public:
+  MyList();
+  MyList(T *p);
+  ~MyList();
+  void insert(T *p);
+  void clearList();
+  void destroyList();
+  void catList(MyList<T> *p);
+  void CloneList(MyList<T> *p);
+};
+
+template <class T>
+MyList<T>::MyList()
+{
+  data = 0;
+  next = 0;
+}
+template <class T>
+MyList<T>::MyList(T *p)
+{
+  data = p;
+  next = 0;
+}
+
+template <class T>
+MyList<T>::~MyList()
+{
+}
+template <class T>
+void MyList<T>::insert(T *p)
+{
+  MyList *ct = this;
+  if (data == 0)
+  {
+    data = p;
+  }
+  else
+  {
+    while (ct->next)
+    {
+      ct = ct->next;
+    }
+    ct->next = new MyList(p);
+    ct = ct->next;
+    ct->next = 0;
+  }
+}
+template <class T>
+void MyList<T>::clearList()
+{
+  MyList *ct = this, *n;
+  while (ct)
+  {
+    n = ct->next;
+    delete ct;
+    ct = n;
+  }
+}
+template <class T>
+void MyList<T>::destroyList()
+{
+  MyList *ct = this, *n;
+  while (ct)
+  {
+    n = ct->next;
+    delete ct->data;
+    delete ct;
+    ct = n;
+  }
+}
+template <class T>
+void MyList<T>::catList(MyList<T> *p)
+{
+  MyList *ct = this;
+  while (ct->next)
+  {
+    ct = ct->next;
+  }
+  ct->next = p;
+}
+template <class T>
+void MyList<T>::CloneList(MyList<T> *p)
+{
+  MyList *ct = this;
+  p = 0;
+  while (ct)
+  {
+    if (!p)
+      p = new MyList<T>(ct->data);
+    else
+      p->insert(ct->data);
+    ct = ct->next;
+  }
+}
+#endif /* MyList_H */

AMSS_NCKU_source/NullEvol.h

@@ -1,225 +1,225 @@
-
-#ifndef NULLEVOL_H
-#define NULLEVOL_H
-
-#ifdef fortran1
-#define f_setup_dyad setup_dyad
-#define f_eth_derivs eth_derivs
-#define f_eth_dderivs eth_dderivs
-#define f_fill_symmetric_boundarybuffer fill_symmetric_boundarybuffer
-#define f_fill_symmetric_boundarybuffer2 fill_symmetric_boundarybuffer2
-#define f_calculate_K calculate_k
-#define f_NullEvol_beta nullevol_beta
-#define f_NullEvol_Q nullevol_q
-#define f_NullEvol_U nullevol_u
-#define f_NullEvol_W nullevol_w
-#define f_NullEvol_Theta nullevol_theta
-#define f_NullEvol_Theta_givenx nullevol_theta_givenx
-#define f_Eq_Theta eq_theta
-#define f_Eq_Theta_2 eq_theta_2
-#define f_NullEvol_g01 nullevol_g01
-#define f_NullEvol_pg0A nullevol_pg0a
-#define f_NullEvol_Theta2 nullevol_theta2
-#define f_NullEvol_Thetag00 nullevol_thetag00
-#endif
-#ifdef fortran2
-#define f_setup_dyad SETUP_DYAD
-#define f_eth_derivs ETH_DERIVS
-#define f_eth_dderivs ETH_DDERIVS
-#define f_fill_symmetric_boundarybuffer FILL_SYMMETRIC_BOUNDARYBUFFER
-#define f_fill_symmetric_boundarybuffer2 FILL_SYMMETRIC_BOUNDARYBUFFER2
-#define f_calculate_K CALCULATE_K
-#define f_NullEvol_beta NULLEVOL_BETA
-#define f_NullEvol_Q NULLEVOL_Q
-#define f_NullEvol_U NULLEVOL_U
-#define f_NullEvol_W NULLEVOL_W
-#define f_NullEvol_Theta NULLEVOL_THETA
-#define f_NullEvol_Theta_givenx NULLEVOL_THETA_GIVENX
-#define f_Eq_Theta EQ_THETA
-#define f_Eq_Theta_2 EQ_THETA_2
-#define f_NullEvol_g01 NULLEVOL_G01
-#define f_NullEvol_pg0A NULLEVOL_PG0A
-#define f_NullEvol_Theta2 NULLEVOL_THETA2
-#define f_NullEvol_Thetag00 NULLEVOL_THETAG00
-#endif
-#ifdef fortran3
-#define f_setup_dyad setup_dyad_
-#define f_eth_derivs eth_derivs_
-#define f_eth_dderivs eth_dderivs_
-#define f_fill_symmetric_boundarybuffer fill_symmetric_boundarybuffer_
-#define f_fill_symmetric_boundarybuffer2 fill_symmetric_boundarybuffer2_
-#define f_calculate_K calculate_k_
-#define f_NullEvol_beta nullevol_beta_
-#define f_NullEvol_Q nullevol_q_
-#define f_NullEvol_U nullevol_u_
-#define f_NullEvol_W nullevol_w_
-#define f_NullEvol_Theta nullevol_theta_
-#define f_NullEvol_Theta_givenx nullevol_theta_givenx_
-#define f_Eq_Theta eq_theta_
-#define f_Eq_Theta_2 eq_theta_2_
-#define f_NullEvol_g01 nullevol_g01_
-#define f_NullEvol_pg0A nullevol_pg0a_
-#define f_NullEvol_Theta2 nullevol_theta2_
-#define f_NullEvol_Thetag00 nullevol_thetag00_
-#endif
-
-extern "C"
-{
-	void f_setup_dyad(int *, double *, double *, double *,
-					  double *, double *, double *, double *,
-					  double *, double *, double *, double *,
-					  double *, double *,
-					  double *, double *, double *, double *,
-					  double *, double *, double *, double *,
-					  double *, double *, double *, double *,
-					  double *, double *, double *,
-					  int &, double &);
-}
-
-extern "C"
-{
-	void f_eth_derivs(int *, double *, double *,
-					  double *, double *,
-					  double *, double *,
-					  int &, int &,
-					  double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	void f_eth_dderivs(int *, double *, double *,
-					   double *, double *,
-					   double *, double *,
-					   int &, int &, int &,
-					   double *, double *, double *, double *, double *, double *,
-					   double *, double *, double *, double *,
-					   double *, double *, double *, double *,
-					   double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	void f_fill_symmetric_boundarybuffer(int *, double *, double *, double *,
-										 double &, double &,
-										 double *, double *, double *, double *, double *, double *, double *, double *,
-										 double *, double *, int &, int &, int &);
-}
-
-extern "C"
-{
-	void f_fill_symmetric_boundarybuffer2(int *, double *, double *, double *,
-										  double &, double &,
-										  double *, int &, int &, double *);
-}
-
-extern "C"
-{
-	void f_calculate_K(int *, double *, double *, double *,
-					   double *, double *,
-					   double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_NullEvol_beta(int *, double *, double *, double *,
-						double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_NullEvol_Q(int *, double *, double *, double *,
-					 double *, double *, double *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_NullEvol_U(int *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *, double *,
-					 double *, double *, double &);
-}
-
-extern "C"
-{
-	int f_NullEvol_W(int *, double *, double *, double *,
-					 double *, double *, double *, double *, double *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *, double *, double *, double &,
-					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_NullEvol_Theta(int *, double *, double *, double *,
-						 double *, double *, double *, double *, double *, double *, double *,
-						 double *, double *, double *, double *, double *, double *, double *,
-						 double *, double *, double *, double *,
-						 double &,
-						 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_NullEvol_Theta_givenx(int *, double *, double *, double *,
-								double *, double *, double *, double *, double *, double *, double *,
-								double *, double *, double *, double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double &,
-								double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double &, int &);
-}
-
-extern "C"
-{
-	int f_Eq_Theta(int *, double *, double *, double *,
-				   double *, double *, double *, double *, double *, double *, double *,
-				   double *, double *, double *, double *, double *, double *, double *, double &,
-				   double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	int f_Eq_Theta_2(int *, double *, double *, double *,
-					 double *, double *, double *, double *, double *, double *, double *,
-					 double *, double *, double *, double *, double *, double *, double *, double &,
-					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
-					 double &, int &);
-}
-
-extern "C"
-{
-	int f_NullEvol_g01(int *, double *, double *, double *,
-					   double *, double *, double *, double *,
-					   double &);
-}
-
-extern "C"
-{
-	int f_NullEvol_pg0A(int *, double *, double *, double *,
-						double *, double *, double *, double *,
-						double *, double *, double *, double *,
-						double &);
-}
-
-extern "C"
-{
-	int f_NullEvol_Theta2(int *, double *, double *, double *,
-						  double *, double *, double *, double *, double *, double *, double *, double *, double *,
-						  double *, double *, double *,
-						  double &);
-}
-
-extern "C"
-{
-	int f_NullEvol_Thetag00(int *, double *, double *, double *,
-							double *, double *, double *, double *, double *, double *, double *, double *, double *,
-							double *, double *, double *,
-							double &);
-}
-#endif /* NULLEVOL_H */
+
+#ifndef NULLEVOL_H
+#define NULLEVOL_H
+
+#ifdef fortran1
+#define f_setup_dyad setup_dyad
+#define f_eth_derivs eth_derivs
+#define f_eth_dderivs eth_dderivs
+#define f_fill_symmetric_boundarybuffer fill_symmetric_boundarybuffer
+#define f_fill_symmetric_boundarybuffer2 fill_symmetric_boundarybuffer2
+#define f_calculate_K calculate_k
+#define f_NullEvol_beta nullevol_beta
+#define f_NullEvol_Q nullevol_q
+#define f_NullEvol_U nullevol_u
+#define f_NullEvol_W nullevol_w
+#define f_NullEvol_Theta nullevol_theta
+#define f_NullEvol_Theta_givenx nullevol_theta_givenx
+#define f_Eq_Theta eq_theta
+#define f_Eq_Theta_2 eq_theta_2
+#define f_NullEvol_g01 nullevol_g01
+#define f_NullEvol_pg0A nullevol_pg0a
+#define f_NullEvol_Theta2 nullevol_theta2
+#define f_NullEvol_Thetag00 nullevol_thetag00
+#endif
+#ifdef fortran2
+#define f_setup_dyad SETUP_DYAD
+#define f_eth_derivs ETH_DERIVS
+#define f_eth_dderivs ETH_DDERIVS
+#define f_fill_symmetric_boundarybuffer FILL_SYMMETRIC_BOUNDARYBUFFER
+#define f_fill_symmetric_boundarybuffer2 FILL_SYMMETRIC_BOUNDARYBUFFER2
+#define f_calculate_K CALCULATE_K
+#define f_NullEvol_beta NULLEVOL_BETA
+#define f_NullEvol_Q NULLEVOL_Q
+#define f_NullEvol_U NULLEVOL_U
+#define f_NullEvol_W NULLEVOL_W
+#define f_NullEvol_Theta NULLEVOL_THETA
+#define f_NullEvol_Theta_givenx NULLEVOL_THETA_GIVENX
+#define f_Eq_Theta EQ_THETA
+#define f_Eq_Theta_2 EQ_THETA_2
+#define f_NullEvol_g01 NULLEVOL_G01
+#define f_NullEvol_pg0A NULLEVOL_PG0A
+#define f_NullEvol_Theta2 NULLEVOL_THETA2
+#define f_NullEvol_Thetag00 NULLEVOL_THETAG00
+#endif
+#ifdef fortran3
+#define f_setup_dyad setup_dyad_
+#define f_eth_derivs eth_derivs_
+#define f_eth_dderivs eth_dderivs_
+#define f_fill_symmetric_boundarybuffer fill_symmetric_boundarybuffer_
+#define f_fill_symmetric_boundarybuffer2 fill_symmetric_boundarybuffer2_
+#define f_calculate_K calculate_k_
+#define f_NullEvol_beta nullevol_beta_
+#define f_NullEvol_Q nullevol_q_
+#define f_NullEvol_U nullevol_u_
+#define f_NullEvol_W nullevol_w_
+#define f_NullEvol_Theta nullevol_theta_
+#define f_NullEvol_Theta_givenx nullevol_theta_givenx_
+#define f_Eq_Theta eq_theta_
+#define f_Eq_Theta_2 eq_theta_2_
+#define f_NullEvol_g01 nullevol_g01_
+#define f_NullEvol_pg0A nullevol_pg0a_
+#define f_NullEvol_Theta2 nullevol_theta2_
+#define f_NullEvol_Thetag00 nullevol_thetag00_
+#endif
+
+extern "C"
+{
+	void f_setup_dyad(int *, double *, double *, double *,
+					  double *, double *, double *, double *,
+					  double *, double *, double *, double *,
+					  double *, double *,
+					  double *, double *, double *, double *,
+					  double *, double *, double *, double *,
+					  double *, double *, double *, double *,
+					  double *, double *, double *,
+					  int &, double &);
+}
+
+extern "C"
+{
+	void f_eth_derivs(int *, double *, double *,
+					  double *, double *,
+					  double *, double *,
+					  int &, int &,
+					  double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	void f_eth_dderivs(int *, double *, double *,
+					   double *, double *,
+					   double *, double *,
+					   int &, int &, int &,
+					   double *, double *, double *, double *, double *, double *,
+					   double *, double *, double *, double *,
+					   double *, double *, double *, double *,
+					   double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	void f_fill_symmetric_boundarybuffer(int *, double *, double *, double *,
+										 double &, double &,
+										 double *, double *, double *, double *, double *, double *, double *, double *,
+										 double *, double *, int &, int &, int &);
+}
+
+extern "C"
+{
+	void f_fill_symmetric_boundarybuffer2(int *, double *, double *, double *,
+										  double &, double &,
+										  double *, int &, int &, double *);
+}
+
+extern "C"
+{
+	void f_calculate_K(int *, double *, double *, double *,
+					   double *, double *,
+					   double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_NullEvol_beta(int *, double *, double *, double *,
+						double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_NullEvol_Q(int *, double *, double *, double *,
+					 double *, double *, double *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_NullEvol_U(int *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *, double *,
+					 double *, double *, double &);
+}
+
+extern "C"
+{
+	int f_NullEvol_W(int *, double *, double *, double *,
+					 double *, double *, double *, double *, double *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *, double *, double *, double &,
+					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_NullEvol_Theta(int *, double *, double *, double *,
+						 double *, double *, double *, double *, double *, double *, double *,
+						 double *, double *, double *, double *, double *, double *, double *,
+						 double *, double *, double *, double *,
+						 double &,
+						 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_NullEvol_Theta_givenx(int *, double *, double *, double *,
+								double *, double *, double *, double *, double *, double *, double *,
+								double *, double *, double *, double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double &,
+								double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double &, int &);
+}
+
+extern "C"
+{
+	int f_Eq_Theta(int *, double *, double *, double *,
+				   double *, double *, double *, double *, double *, double *, double *,
+				   double *, double *, double *, double *, double *, double *, double *, double &,
+				   double *, double *, double *, double *, double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	int f_Eq_Theta_2(int *, double *, double *, double *,
+					 double *, double *, double *, double *, double *, double *, double *,
+					 double *, double *, double *, double *, double *, double *, double *, double &,
+					 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
+					 double &, int &);
+}
+
+extern "C"
+{
+	int f_NullEvol_g01(int *, double *, double *, double *,
+					   double *, double *, double *, double *,
+					   double &);
+}
+
+extern "C"
+{
+	int f_NullEvol_pg0A(int *, double *, double *, double *,
+						double *, double *, double *, double *,
+						double *, double *, double *, double *,
+						double &);
+}
+
+extern "C"
+{
+	int f_NullEvol_Theta2(int *, double *, double *, double *,
+						  double *, double *, double *, double *, double *, double *, double *, double *, double *,
+						  double *, double *, double *,
+						  double &);
+}
+
+extern "C"
+{
+	int f_NullEvol_Thetag00(int *, double *, double *, double *,
+							double *, double *, double *, double *, double *, double *, double *, double *, double *,
+							double *, double *, double *,
+							double &);
+}
+#endif /* NULLEVOL_H */

AMSS_NCKU_source/NullNews.h

@@ -1,106 +1,106 @@
-
-#ifndef NULLNEWS_H
-#define NULLNEWS_H
-
-#ifdef fortran1
-#define f_drive_null_news drive_null_news
-#define f_get_null_news2 get_null_news2
-#define f_drive_null_news_diff drive_null_news_diff
-#define f_omega_rhs omega_rhs
-#define f_get_exact_omega get_exact_omega
-#define f_get_omega_and_dtomega_pre get_omega_and_dtomega_pre
-#define f_get_omega_and_dtomega_LN get_omega_and_dtomega_ln
-#define f_get_dtomega get_dtomega
-#endif
-#ifdef fortran2
-#define f_drive_null_news DRIVE_NULL_NEWS
-#define f_get_null_news2 GET_NULL_NEWS2
-#define f_drive_null_news_diff DRIVE_NULL_NEWS_DIFF
-#define f_omega_rhs OMEGA_RHS
-#define f_get_exact_omega GET_EXACT_OMEGA
-#define f_get_omega_and_dtomega_pre GET_OMEGA_AND_DTOMEGA_PRE
-#define f_get_omega_and_dtomega_LN GET_OMEGA_AND_DTOMEGA_LN
-#define f_get_dtomega GET_DTOMEGA
-#endif
-#ifdef fortran3
-#define f_drive_null_news drive_null_news_
-#define f_get_null_news2 get_null_news2_
-#define f_drive_null_news_diff drive_null_news_diff_
-#define f_omega_rhs omega_rhs_
-#define f_get_exact_omega get_exact_omega_
-#define f_get_omega_and_dtomega_pre get_omega_and_dtomega_pre_
-#define f_get_omega_and_dtomega_LN get_omega_and_dtomega_ln_
-#define f_get_dtomega get_dtomega_
-#endif
-
-extern "C"
-{
-	void f_drive_null_news(int *, double *, double *, double *,
-						   double *, double *, double *, double *, double *, double *, double *, double *,
-						   double *, double *, double *, double *,
-						   double *, double *, double *, double *,
-						   double *, double *,
-						   double *, double *, double *, double *,
-						   double *, double *, double *, double *,
-						   double *, double *, double *, double *,
-						   double *, double *, double &, int &);
-}
-
-extern "C"
-{
-	void f_drive_null_news_diff(int *, double *, double *, double *,
-								double *, double *, double *, double *, double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double *, double *,
-								double *, double *, double &, int &, double &);
-}
-
-extern "C"
-{
-	void f_omega_rhs(int *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *, double *, double *,
-					 double *, double *);
-}
-
-extern "C"
-{
-	void f_get_exact_omega(int *, double *, double *, double *,
-						   double *,
-						   int &, double &, double &);
-}
-
-extern "C"
-{
-	void f_get_null_news2(int *, double *, double *, double *,
-						  double *, double *,
-						  double *, double *, double *, double *,
-						  double *, double *, double *,
-						  double *, double *, double *,
-						  double *, double *, double &, int &);
-}
-
-extern "C"
-{
-	void f_get_omega_and_dtomega_pre(int *, double *, double *, double *,
-									 double *, double *, double *,
-									 double *, double *, double &);
-}
-
-extern "C"
-{
-	void f_get_dtomega(int *, double *, double *, double *,
-					   double *, double *, double *,
-					   double *, double *, double &);
-}
-
-extern "C"
-{
-	void f_get_omega_and_dtomega_LN(double &, int *, double *, double *, double *,
-									double *, double *, double &, int &);
-}
-#endif /* NULLNEWS_H */
+
+#ifndef NULLNEWS_H
+#define NULLNEWS_H
+
+#ifdef fortran1
+#define f_drive_null_news drive_null_news
+#define f_get_null_news2 get_null_news2
+#define f_drive_null_news_diff drive_null_news_diff
+#define f_omega_rhs omega_rhs
+#define f_get_exact_omega get_exact_omega
+#define f_get_omega_and_dtomega_pre get_omega_and_dtomega_pre
+#define f_get_omega_and_dtomega_LN get_omega_and_dtomega_ln
+#define f_get_dtomega get_dtomega
+#endif
+#ifdef fortran2
+#define f_drive_null_news DRIVE_NULL_NEWS
+#define f_get_null_news2 GET_NULL_NEWS2
+#define f_drive_null_news_diff DRIVE_NULL_NEWS_DIFF
+#define f_omega_rhs OMEGA_RHS
+#define f_get_exact_omega GET_EXACT_OMEGA
+#define f_get_omega_and_dtomega_pre GET_OMEGA_AND_DTOMEGA_PRE
+#define f_get_omega_and_dtomega_LN GET_OMEGA_AND_DTOMEGA_LN
+#define f_get_dtomega GET_DTOMEGA
+#endif
+#ifdef fortran3
+#define f_drive_null_news drive_null_news_
+#define f_get_null_news2 get_null_news2_
+#define f_drive_null_news_diff drive_null_news_diff_
+#define f_omega_rhs omega_rhs_
+#define f_get_exact_omega get_exact_omega_
+#define f_get_omega_and_dtomega_pre get_omega_and_dtomega_pre_
+#define f_get_omega_and_dtomega_LN get_omega_and_dtomega_ln_
+#define f_get_dtomega get_dtomega_
+#endif
+
+extern "C"
+{
+	void f_drive_null_news(int *, double *, double *, double *,
+						   double *, double *, double *, double *, double *, double *, double *, double *,
+						   double *, double *, double *, double *,
+						   double *, double *, double *, double *,
+						   double *, double *,
+						   double *, double *, double *, double *,
+						   double *, double *, double *, double *,
+						   double *, double *, double *, double *,
+						   double *, double *, double &, int &);
+}
+
+extern "C"
+{
+	void f_drive_null_news_diff(int *, double *, double *, double *,
+								double *, double *, double *, double *, double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double *, double *,
+								double *, double *, double &, int &, double &);
+}
+
+extern "C"
+{
+	void f_omega_rhs(int *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *, double *, double *,
+					 double *, double *);
+}
+
+extern "C"
+{
+	void f_get_exact_omega(int *, double *, double *, double *,
+						   double *,
+						   int &, double &, double &);
+}
+
+extern "C"
+{
+	void f_get_null_news2(int *, double *, double *, double *,
+						  double *, double *,
+						  double *, double *, double *, double *,
+						  double *, double *, double *,
+						  double *, double *, double *,
+						  double *, double *, double &, int &);
+}
+
+extern "C"
+{
+	void f_get_omega_and_dtomega_pre(int *, double *, double *, double *,
+									 double *, double *, double *,
+									 double *, double *, double &);
+}
+
+extern "C"
+{
+	void f_get_dtomega(int *, double *, double *, double *,
+					   double *, double *, double *,
+					   double *, double *, double &);
+}
+
+extern "C"
+{
+	void f_get_omega_and_dtomega_LN(double &, int *, double *, double *, double *,
+									double *, double *, double &, int &);
+}
+#endif /* NULLNEWS_H */

AMSS_NCKU_source/NullShellPatch.h

@@ -1,189 +1,189 @@
-
-#ifndef NULLSHELLPATCH_H
-#define NULLSHELLPATCH_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
-#include <complex>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <math.h>
-#include <complex.h>
-#endif
-
-#include <mpi.h>
-#include "MyList.h"
-#include "Block.h"
-#include "Parallel.h"
-#include "ShellPatch.h"
-#include "var.h"
-#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
-
-#if (dim != 3)
-#error NullShellPatch only supports 3 dimensional stuff yet
-#endif
-
-class xp_npatch : public ss_patch
-{
-public:
-   xp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
-};
-
-class xm_npatch : public ss_patch
-{
-public:
-   xm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
-};
-class yp_npatch : public ss_patch
-{
-public:
-   yp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
-};
-
-class ym_npatch : public ss_patch
-{
-public:
-   ym_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
-};
-class zp_npatch : public ss_patch
-{
-public:
-   zp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
-};
-
-class zm_npatch : public ss_patch
-{
-public:
-   zm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
-};
-
-class NullShellPatch
-{
-
-public:
-   struct pointstru
-   {
-      double gpox[dim]; // global cordinate
-      double lpox[dim]; // local cordinate
-      Block *Bg;
-      int ssst; //-1: cardisian, others as sst of ss_patch source sst
-      int tsst; //-1: cardisian, others as sst of ss_patch target sst
-      double *coef;
-      int *sind;
-      int dumyd;            // the dimension which has common lines, only useful in interdata_packer
-      complex<double> swtf; // exp(i gamma) of Eq.(26) of CQG 24 S327
-   };
-
-   var *FXZEO;
-   var *gx, *gy, *gz;
-   // we always assume the number of VarList = 2* the number of Varwt
-   // so VarList must apear with pairs, either components of complex number or a fake pair
-   var *beta, *W;
-   var *Rnu, *Inu, *Rk, *Ik, *RB, *IB;
-   var *RQ, *IQ, *RU, *IU, *RTheta, *ITheta;
-   var *KK, *HKK, *KKx, *HKKx;
-   var *RJo, *IJo, *omegao;
-   var *RJ0, *IJ0, *omega0;
-   var *RJ, *IJ, *omega;
-   var *RJ1, *IJ1, *omega1;
-   var *RJ_rhs, *IJ_rhs, *omega_rhs;
-
-   var *quR1, *quR2, *quI1, *quI2;
-   var *qlR1, *qlR2, *qlI1, *qlI2;
-   var *gR, *gI;
-   var *dquR1, *dquR2, *dquI1, *dquI2;
-   var *bdquR1, *bdquR2, *bdquI1, *bdquI2;
-   var *dgR, *dgI;
-   var *bdgR, *bdgI;
-
-   var *RNews, *INews;
-
-   MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
-   MyList<var> *OldStateList, *DumpList, *CheckList;
-
-   MyList<var> *betaList, *QUList, *WTheList, *TheList, *JrhsList, *J1List;
-   int betawt[1], QUwt[2], WThewt[2];
-
-   int myrank;
-   int shape[dim]; // for (rho, sigma, X), for rho and sigma means number of points for every pi/2
-   double Rmin, xmin, xmax;
-   int Symmetry;
-   int ingfs, fngfs;
-
-   MyList<ss_patch> *PatL;
-
-   MyList<pointstru> **ss_src, **ss_dst;
-   MyList<pointstru> **cs_src, **cs_dst;
-
-public:
-   NullShellPatch(int *shapei, double Rmini, double xmini, double xmaxi, int Symmetry, int myranki);
-
-   ~NullShellPatch();
-
-   void destroypsuList(MyList<pointstru> *ct);
-   void fill_symmetric_boundarybuffer(MyList<var> *VarList, int *Varwt);
-   MyList<Block> *compose_sh(int cpusize);
-   int getdumydimension(int acsst, int posst);
-   void Setup_dyad();
-   void Setup_Initial_Data(bool checkrun, double PhysTime);
-   void eth_derivs(var *Rv, var *Iv, var *ethRv, var *ethIv, int s, int e);
-   void eth_dderivs(var *Rv, var *Iv, var *ethRv, var *ethIv, int s, int e1, int e2);
-   void getlocalpox_ss(int isst, double ix, double iy, double iz, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpox_fake(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpox(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpoxsst_ss(int isst, double ix, double iy, double iz, int lsst, double &lx, double &ly, double &lz);
-   void getlocalpoxsst(double x, double y, double z, int sst, double &lx, double &ly, double &lz);
-   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
-   complex<double> get_swtf(double *pox, int tsst, int ssst);
-   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPpi, double DH[dim],
-                         MyList<Patch> *Ppi, double CDH[dim], MyList<pointstru> *pss);
-   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
-                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
-   bool prolongpointstru_ss(MyList<pointstru> *&psul, int tsst, MyList<ss_patch> *sPp, double DH[dim],
-                            MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
-   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
-   void checkPatch();
-   void checkBlock(int sst);
-   double getdX(int dir);
-   void shellname(char *sn, int i);
-   void Dump_xyz(char *tag, double time, double dT);
-   void Dump_Data(MyList<var> *DumpListi, char *tag, double time, double dT);
-   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                      int Symmetry, int *Varwt);
-   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
-                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, int *Varwt);
-   void Synch(MyList<var> *VarList, int Symmetry, int *Varwt);
-   void CS_Inter(MyList<var> *VarList, int Symmetry, int *Varwt);
-   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
-   void check_pointstrul2(MyList<pointstru> *pp, int first_last_only);
-   void matchcheck(MyList<Patch> *CPatL);
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX, /*input global Cartesian coordinate*/
-                      double *Shellf, int Symmetry);
-   void Interp_Points_2D(MyList<var> *VarList,
-                         int NN, double **XX, /*input global Cartesian coordinate*/
-                         double *Shellf, int Symmetry);
-   void Step(double dT, double PhysTime, monitor *ErrorMonitor);
-   void Null_Boundary(double PhysTime);
-   void HyperSlice(double dT, double PhysTime, monitor *ErrorMonitor, int RK_count);
-   double News_Error_Check(double PhysTime, double dT, bool dp);
-   double Error_Check(double PhysTime, double dT, bool dp);
-   double EqTheta_Check(double PhysTime, double dT, bool dp);
-   void Compute_News(double PhysTime, double dT, bool dp);
-   void Check_News(double PhysTime, double dT, bool dp);
-};
-
-#endif /* NULLSHELLPATCH_H */
+
+#ifndef NULLSHELLPATCH_H
+#define NULLSHELLPATCH_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
+#include <complex>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <math.h>
+#include <complex.h>
+#endif
+
+#include <mpi.h>
+#include "MyList.h"
+#include "Block.h"
+#include "Parallel.h"
+#include "ShellPatch.h"
+#include "var.h"
+#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
+
+#if (dim != 3)
+#error NullShellPatch only supports 3 dimensional stuff yet
+#endif
+
+class xp_npatch : public ss_patch
+{
+public:
+   xp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
+};
+
+class xm_npatch : public ss_patch
+{
+public:
+   xm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
+};
+class yp_npatch : public ss_patch
+{
+public:
+   yp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
+};
+
+class ym_npatch : public ss_patch
+{
+public:
+   ym_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
+};
+class zp_npatch : public ss_patch
+{
+public:
+   zp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
+};
+
+class zm_npatch : public ss_patch
+{
+public:
+   zm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
+};
+
+class NullShellPatch
+{
+
+public:
+   struct pointstru
+   {
+      double gpox[dim]; // global cordinate
+      double lpox[dim]; // local cordinate
+      Block *Bg;
+      int ssst; //-1: cardisian, others as sst of ss_patch source sst
+      int tsst; //-1: cardisian, others as sst of ss_patch target sst
+      double *coef;
+      int *sind;
+      int dumyd;            // the dimension which has common lines, only useful in interdata_packer
+      complex<double> swtf; // exp(i gamma) of Eq.(26) of CQG 24 S327
+   };
+
+   var *FXZEO;
+   var *gx, *gy, *gz;
+   // we always assume the number of VarList = 2* the number of Varwt
+   // so VarList must apear with pairs, either components of complex number or a fake pair
+   var *beta, *W;
+   var *Rnu, *Inu, *Rk, *Ik, *RB, *IB;
+   var *RQ, *IQ, *RU, *IU, *RTheta, *ITheta;
+   var *KK, *HKK, *KKx, *HKKx;
+   var *RJo, *IJo, *omegao;
+   var *RJ0, *IJ0, *omega0;
+   var *RJ, *IJ, *omega;
+   var *RJ1, *IJ1, *omega1;
+   var *RJ_rhs, *IJ_rhs, *omega_rhs;
+
+   var *quR1, *quR2, *quI1, *quI2;
+   var *qlR1, *qlR2, *qlI1, *qlI2;
+   var *gR, *gI;
+   var *dquR1, *dquR2, *dquI1, *dquI2;
+   var *bdquR1, *bdquR2, *bdquI1, *bdquI2;
+   var *dgR, *dgI;
+   var *bdgR, *bdgI;
+
+   var *RNews, *INews;
+
+   MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
+   MyList<var> *OldStateList, *DumpList, *CheckList;
+
+   MyList<var> *betaList, *QUList, *WTheList, *TheList, *JrhsList, *J1List;
+   int betawt[1], QUwt[2], WThewt[2];
+
+   int myrank;
+   int shape[dim]; // for (rho, sigma, X), for rho and sigma means number of points for every pi/2
+   double Rmin, xmin, xmax;
+   int Symmetry;
+   int ingfs, fngfs;
+
+   MyList<ss_patch> *PatL;
+
+   MyList<pointstru> **ss_src, **ss_dst;
+   MyList<pointstru> **cs_src, **cs_dst;
+
+public:
+   NullShellPatch(int *shapei, double Rmini, double xmini, double xmaxi, int Symmetry, int myranki);
+
+   ~NullShellPatch();
+
+   void destroypsuList(MyList<pointstru> *ct);
+   void fill_symmetric_boundarybuffer(MyList<var> *VarList, int *Varwt);
+   MyList<Block> *compose_sh(int cpusize);
+   int getdumydimension(int acsst, int posst);
+   void Setup_dyad();
+   void Setup_Initial_Data(bool checkrun, double PhysTime);
+   void eth_derivs(var *Rv, var *Iv, var *ethRv, var *ethIv, int s, int e);
+   void eth_dderivs(var *Rv, var *Iv, var *ethRv, var *ethIv, int s, int e1, int e2);
+   void getlocalpox_ss(int isst, double ix, double iy, double iz, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpox_fake(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpox(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpoxsst_ss(int isst, double ix, double iy, double iz, int lsst, double &lx, double &ly, double &lz);
+   void getlocalpoxsst(double x, double y, double z, int sst, double &lx, double &ly, double &lz);
+   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
+   complex<double> get_swtf(double *pox, int tsst, int ssst);
+   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPpi, double DH[dim],
+                         MyList<Patch> *Ppi, double CDH[dim], MyList<pointstru> *pss);
+   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
+   bool prolongpointstru_ss(MyList<pointstru> *&psul, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                            MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
+   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
+   void checkPatch();
+   void checkBlock(int sst);
+   double getdX(int dir);
+   void shellname(char *sn, int i);
+   void Dump_xyz(char *tag, double time, double dT);
+   void Dump_Data(MyList<var> *DumpListi, char *tag, double time, double dT);
+   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                      int Symmetry, int *Varwt);
+   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
+                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, int *Varwt);
+   void Synch(MyList<var> *VarList, int Symmetry, int *Varwt);
+   void CS_Inter(MyList<var> *VarList, int Symmetry, int *Varwt);
+   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
+   void check_pointstrul2(MyList<pointstru> *pp, int first_last_only);
+   void matchcheck(MyList<Patch> *CPatL);
+   void Interp_Points(MyList<var> *VarList,
+                      int NN, double **XX, /*input global Cartesian coordinate*/
+                      double *Shellf, int Symmetry);
+   void Interp_Points_2D(MyList<var> *VarList,
+                         int NN, double **XX, /*input global Cartesian coordinate*/
+                         double *Shellf, int Symmetry);
+   void Step(double dT, double PhysTime, monitor *ErrorMonitor);
+   void Null_Boundary(double PhysTime);
+   void HyperSlice(double dT, double PhysTime, monitor *ErrorMonitor, int RK_count);
+   double News_Error_Check(double PhysTime, double dT, bool dp);
+   double Error_Check(double PhysTime, double dT, bool dp);
+   double EqTheta_Check(double PhysTime, double dT, bool dp);
+   void Compute_News(double PhysTime, double dT, bool dp);
+   void Check_News(double PhysTime, double dT, bool dp);
+};
+
+#endif /* NULLSHELLPATCH_H */

AMSS_NCKU_source/NullShellPatch2.h

@@ -1,183 +1,183 @@
-
-#ifndef NULLSHELLPATCH2_H
-#define NULLSHELLPATCH2_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
-#include <complex>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <math.h>
-#include <complex.h>
-#endif
-
-#include <mpi.h>
-#include "MyList.h"
-#include "Block.h"
-#include "Parallel.h"
-#include "ShellPatch.h"
-#include "var.h"
-#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
-
-#if (dim != 3)
-#error NullShellPatch2 only supports 3 dimensional stuff yet
-#endif
-
-// x   x   x   x   x   o   *
-//             *   o   x   x   x   x   x
-// each side contribute an overlap points
-// so we need half of that
-#define overghost ((ghost_width + 1) / 2 + ghost_width)
-
-class NullShellPatch2
-{
-
-   class xp_npatch : public ss_patch
-   {
-   public:
-      xp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
-   };
-
-   class xm_npatch : public ss_patch
-   {
-   public:
-      xm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
-   };
-   class yp_npatch : public ss_patch
-   {
-   public:
-      yp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
-   };
-
-   class ym_npatch : public ss_patch
-   {
-   public:
-      ym_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
-   };
-   class zp_npatch : public ss_patch
-   {
-   public:
-      zp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
-   };
-
-   class zm_npatch : public ss_patch
-   {
-   public:
-      zm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
-   };
-
-public:
-   struct pointstru
-   {
-      double gpox[dim]; // global cordinate
-      double lpox[dim]; // local cordinate
-      Block *Bg;
-      int ssst; //-1: cardisian, others as sst of ss_patch source sst
-      int tsst; //-1: cardisian, others as sst of ss_patch target sst
-      double *coef;
-      int *sind; // index position, considered dummy dimension already
-      int dumyd; // the dimension which has common lines, only useful in interdata_packer
-      double Jacob[2][2];
-      int indz; // index position of r direction
-   };
-
-   var *gx, *gy, *gz;
-   // surface variable
-   var *g00, *g01, *p02, *p03, *g02, *g03;
-   var *Theta22, *Theta23, *Theta33;
-
-   // evolution variables
-   var *g22o, *g23o, *g33o;
-   var *g220, *g230, *g330;
-   var *g22, *g23, *g33;
-   var *g221, *g231, *g331;
-   var *g22_rhs, *g23_rhs, *g33_rhs;
-
-   var *RNews, *INews;
-   var *omega, *dtomega;
-
-   MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
-   MyList<var> *OldStateList, *DumpList, *CheckList;
-   MyList<var> *NewsList;
-
-   MyList<var> *g01List, *pg0AList, *g00List, *ThetaList;
-
-   double **g01wt, **pg0Awt, **g00wt, **Thetawt;
-
-   int myrank;
-   int shape[dim]; // for (rho, sigma, X), for rho and sigma means number of points for every pi/2
-   double Rmin, xmin, xmax;
-   int Symmetry;
-   int ingfs, fngfs;
-
-   MyList<ss_patch> *PatL;
-
-   MyList<pointstru> **ss_src, **ss_dst;
-   MyList<pointstru> **cs_src, **cs_dst;
-
-public:
-   NullShellPatch2(int *shapei, double Rmini, double xmini, double xmaxi, int Symmetry, int myranki);
-
-   ~NullShellPatch2();
-
-   double getdX(int dir);
-   void shellname(char *sn, int i);
-   void destroypsuList(MyList<pointstru> *ct);
-   MyList<Block> *compose_sh(int cpusize);
-   void Dump_xyz(char *tag, double time, double dT);
-   void Dump_Data(MyList<var> *DumpListi, char *tag, double time, double dT);
-   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
-   void getlocalpox_ss(int isst, double ix, double iy, double iz, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpox_fake(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpox(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
-   void getlocalpoxsst_ss(int isst, double ix, double iy, double iz, int lsst, double &lx, double &ly, double &lz);
-   void getlocalpoxsst(double x, double y, double z, int sst, double &lx, double &ly, double &lz);
-   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
-   int getdumydimension(int acsst, int posst);
-   void get_Jacob(double *pox, int tsst, int ssst, double J[2][2]);
-   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPpi, double DH[dim],
-                         MyList<Patch> *Ppi, double CDH[dim], MyList<pointstru> *pss);
-   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
-                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in, const int iz);
-   bool prolongpointstru_ss(MyList<pointstru> *&psul, int tsst, MyList<ss_patch> *sPp, double DH[dim],
-                            MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in, const int iz);
-   void Setup_Initial_Data(bool checkrun, double PhysTime);
-   void Step(double dT, double PhysTime, monitor *ErrorMonitor);
-   void HyperSlice(double dT, double PhysTime, monitor *ErrorMonitor, int RK_count);
-   void Synch(MyList<var> *VarList, int Symmetry, double **Varwt, const short int svt);
-   void fill_symmetric_boundarybuffer(MyList<var> *VarList, double **Varwt);
-   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                      int Symmetry, double **Varwt, const short int svt);
-   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
-                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
-                        const short int svt);
-   int interdata_packer_pre(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
-                            MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
-                            const short int svt);
-   int interdata_packer_pot(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
-                            MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
-                            const short int svt);
-   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
-   void checkBlock(int sst);
-   void Null_Boundary(double PhysTime);
-   void Compute_News(double PhysTime);
-   void Interp_Points_2D(MyList<var> *VarList,
-                         int NN, double **XX, /*input fake global Cartesian coordinate*/
-                         double *Shellf, int Symmetry);
-   double Error_Check(double PhysTime);
-};
-
-#endif /* NULLSHELLPATCH2_H */
+
+#ifndef NULLSHELLPATCH2_H
+#define NULLSHELLPATCH2_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
+#include <complex>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <math.h>
+#include <complex.h>
+#endif
+
+#include <mpi.h>
+#include "MyList.h"
+#include "Block.h"
+#include "Parallel.h"
+#include "ShellPatch.h"
+#include "var.h"
+#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
+
+#if (dim != 3)
+#error NullShellPatch2 only supports 3 dimensional stuff yet
+#endif
+
+// x   x   x   x   x   o   *
+//             *   o   x   x   x   x   x
+// each side contribute an overlap points
+// so we need half of that
+#define overghost ((ghost_width + 1) / 2 + ghost_width)
+
+class NullShellPatch2
+{
+
+   class xp_npatch : public ss_patch
+   {
+   public:
+      xp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
+   };
+
+   class xm_npatch : public ss_patch
+   {
+   public:
+      xm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
+   };
+   class yp_npatch : public ss_patch
+   {
+   public:
+      yp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
+   };
+
+   class ym_npatch : public ss_patch
+   {
+   public:
+      ym_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
+   };
+   class zp_npatch : public ss_patch
+   {
+   public:
+      zp_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
+   };
+
+   class zm_npatch : public ss_patch
+   {
+   public:
+      zm_npatch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
+   };
+
+public:
+   struct pointstru
+   {
+      double gpox[dim]; // global cordinate
+      double lpox[dim]; // local cordinate
+      Block *Bg;
+      int ssst; //-1: cardisian, others as sst of ss_patch source sst
+      int tsst; //-1: cardisian, others as sst of ss_patch target sst
+      double *coef;
+      int *sind; // index position, considered dummy dimension already
+      int dumyd; // the dimension which has common lines, only useful in interdata_packer
+      double Jacob[2][2];
+      int indz; // index position of r direction
+   };
+
+   var *gx, *gy, *gz;
+   // surface variable
+   var *g00, *g01, *p02, *p03, *g02, *g03;
+   var *Theta22, *Theta23, *Theta33;
+
+   // evolution variables
+   var *g22o, *g23o, *g33o;
+   var *g220, *g230, *g330;
+   var *g22, *g23, *g33;
+   var *g221, *g231, *g331;
+   var *g22_rhs, *g23_rhs, *g33_rhs;
+
+   var *RNews, *INews;
+   var *omega, *dtomega;
+
+   MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
+   MyList<var> *OldStateList, *DumpList, *CheckList;
+   MyList<var> *NewsList;
+
+   MyList<var> *g01List, *pg0AList, *g00List, *ThetaList;
+
+   double **g01wt, **pg0Awt, **g00wt, **Thetawt;
+
+   int myrank;
+   int shape[dim]; // for (rho, sigma, X), for rho and sigma means number of points for every pi/2
+   double Rmin, xmin, xmax;
+   int Symmetry;
+   int ingfs, fngfs;
+
+   MyList<ss_patch> *PatL;
+
+   MyList<pointstru> **ss_src, **ss_dst;
+   MyList<pointstru> **cs_src, **cs_dst;
+
+public:
+   NullShellPatch2(int *shapei, double Rmini, double xmini, double xmaxi, int Symmetry, int myranki);
+
+   ~NullShellPatch2();
+
+   double getdX(int dir);
+   void shellname(char *sn, int i);
+   void destroypsuList(MyList<pointstru> *ct);
+   MyList<Block> *compose_sh(int cpusize);
+   void Dump_xyz(char *tag, double time, double dT);
+   void Dump_Data(MyList<var> *DumpListi, char *tag, double time, double dT);
+   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
+   void getlocalpox_ss(int isst, double ix, double iy, double iz, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpox_fake(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpox(double x, double y, double z, int &sst, double &lx, double &ly, double &lz);
+   void getlocalpoxsst_ss(int isst, double ix, double iy, double iz, int lsst, double &lx, double &ly, double &lz);
+   void getlocalpoxsst(double x, double y, double z, int sst, double &lx, double &ly, double &lz);
+   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
+   int getdumydimension(int acsst, int posst);
+   void get_Jacob(double *pox, int tsst, int ssst, double J[2][2]);
+   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPpi, double DH[dim],
+                         MyList<Patch> *Ppi, double CDH[dim], MyList<pointstru> *pss);
+   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in, const int iz);
+   bool prolongpointstru_ss(MyList<pointstru> *&psul, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                            MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in, const int iz);
+   void Setup_Initial_Data(bool checkrun, double PhysTime);
+   void Step(double dT, double PhysTime, monitor *ErrorMonitor);
+   void HyperSlice(double dT, double PhysTime, monitor *ErrorMonitor, int RK_count);
+   void Synch(MyList<var> *VarList, int Symmetry, double **Varwt, const short int svt);
+   void fill_symmetric_boundarybuffer(MyList<var> *VarList, double **Varwt);
+   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                      int Symmetry, double **Varwt, const short int svt);
+   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
+                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
+                        const short int svt);
+   int interdata_packer_pre(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
+                            MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
+                            const short int svt);
+   int interdata_packer_pot(double *data, MyList<pointstru> *src, MyList<pointstru> *dst, int rank_in, int dir,
+                            MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry, double **Varwt,
+                            const short int svt);
+   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
+   void checkBlock(int sst);
+   void Null_Boundary(double PhysTime);
+   void Compute_News(double PhysTime);
+   void Interp_Points_2D(MyList<var> *VarList,
+                         int NN, double **XX, /*input fake global Cartesian coordinate*/
+                         double *Shellf, int Symmetry);
+   double Error_Check(double PhysTime);
+};
+
+#endif /* NULLSHELLPATCH2_H */

AMSS_NCKU_source/Parallel.h

@@ -1,231 +1,241 @@
-
-#ifndef PARALLEL_H
-#define PARALLEL_H
-
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
-#include <new>
-using namespace std;
-
-#include "Parallel_bam.h"
-#include "var.h"
-#include "MPatch.h"
-#include "Block.h"
-#include "MyList.h"
-#include "macrodef.h" //need dim; ghost_width; CONTRACT
-namespace Parallel
-{
-  struct gridseg
-  {
-    double llb[dim];
-    double uub[dim];
-    int shape[dim];
-    double illb[dim], iuub[dim]; // only use for OutBdLow2Hi
-    Block *Bg;
-  };
-  int partition1(int &nx, int split_size, int min_width, int cpusize, int shape);    // special for 1 diemnsion
-  int partition2(int *nxy, int split_size, int *min_width, int cpusize, int *shape); // special for 2 diemnsions
-  int partition3(int *nxyz, int split_size, int *min_width, int cpusize, int *shape);
-  MyList<Block> *distribute(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0); // produce corresponding Blocks
-  MyList<Block> *distribute_optimize(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0);
-  Block* splitHotspotBlock(MyList<Block>* &BlL, int _dim,
-                           int ib0_orig, int ib3_orig,
-                           int jb1_orig, int jb4_orig,
-                           int kb2_orig, int kb5_orig,
-                           Patch* PP, int r_left, int r_right,
-                           int ingfsi, int fngfsi, bool periodic,
-                           Block* &split_first_block, Block* &split_last_block);
-  Block* createMappedBlock(MyList<Block>* &BlL, int _dim, int* shape, double* bbox,
-                           int block_id, int ingfsi, int fngfsi, int lev);
-  void KillBlocks(MyList<Patch> *PatchLIST);
-
-  void setfunction(MyList<Block> *BlL, var *vn, double func(double x, double y, double z));
-  void setfunction(int rank, MyList<Block> *BlL, var *vn, double func(double x, double y, double z));
-  void writefile(double time, int nx, int ny, int nz, double xmin, double xmax, double ymin, double ymax,
-                 double zmin, double zmax, char *filename, double *data_out);
-  void writefile(double time, int nx, int ny, double xmin, double xmax, double ymin, double ymax,
-                 char *filename, double *datain);
-  void getarrayindex(int DIM, int *shape, int *index, int n);
-  int getarraylocation(int DIM, int *shape, int *index);
-  void copy(int DIM, double *llbout, double *uubout, int *Dshape, double *DD, double *llbin, double *uubin,
-            int *shape, double *datain, double *llb, double *uub);
-  void Dump_CPU_Data(MyList<Block> *BlL, MyList<var> *DumpList, char *tag, double time, double dT);
-  void Dump_Data(MyList<Patch> *PL, MyList<var> *DumpList, char *tag, double time, double dT);
-  void Dump_Data(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT, int grd);
-  double *Collect_Data(Patch *PP, var *VP);
-  void d2Dump_Data(MyList<Patch> *PL, MyList<var> *DumpList, char *tag, double time, double dT);
-  void d2Dump_Data(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT, int grd);
-  void Dump_Data0(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT);
-  double global_interp(int DIM, int *ext, double **CoX, double *datain,
-                       double *poX, int ordn, double *SoA, int Symmetry);
-  double global_interp(int DIM, int *ext, double **CoX, double *datain,
-                       double *poX, int ordn);
-  double Lagrangian_Int(double x, int npts, double *xpts, double *funcvals);
-  double LagrangePoly(double x, int pt, int npts, double *xpts);
-  MyList<gridseg> *build_complete_gsl(Patch *Pat);
-  MyList<gridseg> *build_complete_gsl(MyList<Patch> *PatL);
-  MyList<gridseg> *build_complete_gsl_virtual(MyList<Patch> *PatL);
-  MyList<gridseg> *build_complete_gsl_virtual2(MyList<Patch> *PatL);        // - buffer
-  MyList<gridseg> *build_owned_gsl0(Patch *Pat, int rank_in);               // - ghost without extension, special for Sync usage
-  MyList<gridseg> *build_owned_gsl1(Patch *Pat, int rank_in);               // - ghost, similar to build_owned_gsl0 but extend one point on left side for vertex grid
-  MyList<gridseg> *build_owned_gsl2(Patch *Pat, int rank_in);               // - buffer - ghost
-  MyList<gridseg> *build_owned_gsl3(Patch *Pat, int rank_in, int Symmetry); // - ghost - BD ghost
-  MyList<gridseg> *build_owned_gsl4(Patch *Pat, int rank_in, int Symmetry); // - buffer - ghost - BD ghost
-  MyList<gridseg> *build_owned_gsl5(Patch *Pat, int rank_in);               // similar to build_owned_gsl2 but no extension
-  MyList<gridseg> *build_owned_gsl(MyList<Patch> *PatL, int rank_in, int type, int Symmetry);
-  void build_gstl(MyList<gridseg> *srci, MyList<gridseg> *dsti, MyList<gridseg> **out_src, MyList<gridseg> **out_dst);
-  int data_packer(double *data, MyList<gridseg> *src, MyList<gridseg> *dst, int rank_in, int dir,
-                  MyList<var> *VarLists, MyList<var> *VarListd, int Symmetry);
-  void transfer(MyList<gridseg> **src, MyList<gridseg> **dst,
-                MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                int Symmetry);
-  int data_packermix(double *data, MyList<gridseg> *src, MyList<gridseg> *dst, int rank_in, int dir,
-                     MyList<var> *VarLists, MyList<var> *VarListd, int Symmetry);
-  void transfermix(MyList<gridseg> **src, MyList<gridseg> **dst,
-                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                   int Symmetry);
-  void Sync(Patch *Pat, MyList<var> *VarList, int Symmetry);
-  void Sync(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
-  void Sync_merged(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
-
-  struct SyncCache {
-    bool valid;
-    int cpusize;
-    MyList<gridseg> **combined_src;
-    MyList<gridseg> **combined_dst;
-    int *send_lengths;
-    int *recv_lengths;
-    double **send_bufs;
-    double **recv_bufs;
-    int *send_buf_caps;
-    int *recv_buf_caps;
-    MPI_Request *reqs;
-    MPI_Status *stats;
-    int max_reqs;
-    bool lengths_valid;
-    int *tc_req_node;
-    int *tc_req_is_recv;
-    int *tc_completed;
-    SyncCache();
-    void invalidate();
-    void destroy();
-  };
-
-  void Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry, SyncCache &cache);
-  void transfer_cached(MyList<gridseg> **src, MyList<gridseg> **dst,
-                       MyList<var> *VarList1, MyList<var> *VarList2,
-                       int Symmetry, SyncCache &cache);
-
-  struct AsyncSyncState {
-    int req_no;
-    bool active;
-    int *req_node;
-    int *req_is_recv;
-    int pending_recv;
-    AsyncSyncState() : req_no(0), active(false), req_node(0), req_is_recv(0), pending_recv(0) {}
-  };
-
-  void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
-                  SyncCache &cache, AsyncSyncState &state);
-  void Sync_finish(SyncCache &cache, AsyncSyncState &state,
-                   MyList<var> *VarList, int Symmetry);
-  void OutBdLow2Hi(Patch *Patc, Patch *Patf,
-                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                   int Symmetry);
-  void OutBdLow2Hi(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                   int Symmetry);
-  void OutBdLow2Himix(Patch *Patc, Patch *Patf,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                      int Symmetry);
-  void OutBdLow2Himix(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                      int Symmetry);
-  void Restrict_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                       MyList<var> *VarList1, MyList<var> *VarList2,
-                       int Symmetry, SyncCache &cache);
-  void OutBdLow2Hi_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                          MyList<var> *VarList1, MyList<var> *VarList2,
-                          int Symmetry, SyncCache &cache);
-  void OutBdLow2Himix_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                             MyList<var> *VarList1, MyList<var> *VarList2,
-                             int Symmetry, SyncCache &cache);
-  void Prolong(Patch *Patc, Patch *Patf,
-               MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-               int Symmetry);
-  void Prolongint(Patch *Patc, Patch *Patf,
-                  MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                  int Symmetry);
-  void Restrict(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                int Symmetry);
-  void Restrict_after(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                      int Symmetry); // for -ghost - BDghost
-  MyList<Parallel::gridseg> *build_PhysBD_gsl(Patch *Pat);
-  MyList<Parallel::gridseg> *build_ghost_gsl(MyList<Patch> *PatL);
-  MyList<Parallel::gridseg> *build_ghost_gsl(Patch *Pat);
-  MyList<Parallel::gridseg> *build_buffer_gsl(Patch *Pat);
-  MyList<Parallel::gridseg> *build_buffer_gsl(MyList<Patch> *PatL);
-  MyList<Parallel::gridseg> *gsl_subtract(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
-  MyList<Parallel::gridseg> *gs_subtract(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
-  MyList<Parallel::gridseg> *gsl_and(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
-  MyList<Parallel::gridseg> *gs_and(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
-  MyList<Parallel::gridseg> *clone_gsl(MyList<Parallel::gridseg> *p, bool first_only);
-  MyList<Parallel::gridseg> *build_bulk_gsl(Patch *Pat); // similar to build_owned_gsl0 but does not care rank issue
-  MyList<Parallel::gridseg> *build_bulk_gsl(Block *bp, Patch *Pat);
-  void build_PhysBD_gstl(Patch *Pat, MyList<Parallel::gridseg> *srci, MyList<Parallel::gridseg> *dsti,
-                         MyList<Parallel::gridseg> **out_src, MyList<Parallel::gridseg> **out_dst);
-  void PeriodicBD(Patch *Pat, MyList<var> *VarList, int Symmetry);
-  double L2Norm(Patch *Pat, var *vf);
-  void L2Norm7(Patch *Pat, var **vf, double *norms);
-  void checkgsl(MyList<Parallel::gridseg> *pp, bool first_only);
-  void checkvarl(MyList<var> *pp, bool first_only);
-  MyList<Parallel::gridseg> *divide_gsl(MyList<Parallel::gridseg> *p, Patch *Pat);
-  MyList<Parallel::gridseg> *divide_gs(MyList<Parallel::gridseg> *p, Patch *Pat);
-  void prepare_inter_time_level(Patch *Pat,
-                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
-                                MyList<var> *VarList3 /* target (t+a*dt) */, int tindex);
-  void prepare_inter_time_level(Patch *Pat,
-                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
-                                MyList<var> *VarList3 /* source (t-dt) */, MyList<var> *VarList4 /* target (t+a*dt) */, int tindex);
-  void prepare_inter_time_level(MyList<Patch> *PatL,
-                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
-                                MyList<var> *VarList3 /* target (t+a*dt) */, int tindex);
-  void prepare_inter_time_level(MyList<Patch> *Pat,
-                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
-                                MyList<var> *VarList3 /* source (t-dt) */, MyList<var> *VarList4 /* target (t+a*dt) */, int tindex);
-  void merge_gsl(MyList<gridseg> *&A, const double ratio);
-  bool merge_gs(MyList<gridseg> *D, MyList<gridseg> *B, MyList<gridseg> *&C, const double ratio);
-  // Add ghost region to tangent plane
-  // we assume the grids have the same resolution
-  void add_ghost_touch(MyList<gridseg> *&A);
-  void cut_gsl(MyList<gridseg> *&A);
-  bool cut_gs(MyList<gridseg> *D, MyList<gridseg> *B, MyList<gridseg> *&C);
-  MyList<Parallel::gridseg> *gs_subtract_virtual(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
-  void fill_level_data(MyList<Patch> *PatLd, MyList<Patch> *PatLs, MyList<Patch> *PatcL,
-                       MyList<var> *OldList, MyList<var> *StateList, MyList<var> *FutureList,
-                       MyList<var> *tmList, int Symmetry, bool BB, bool CC);
-  bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
-                             int NN, double **XX,
-                             double *Shellf, int Symmetry);
-  void aligncheck(double *bbox0, double *bboxl, int lev, double *DH0, int *shape);
-  bool point_locat_gsl(double *pox, MyList<Parallel::gridseg> *gsl);
-  void checkpatchlist(MyList<Patch> *PatL, bool buflog);
-
-  double L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here);
-  void L2Norm7(Patch *Pat, var **vf, double *norms, MPI_Comm Comm_here);
-  bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
-                             int NN, double **XX,
-                             double *Shellf, int Symmetry, MPI_Comm Comm_here);
-#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
-  MyList<Block> *distribute(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfsi,
-                            bool periodic, int start_rank, int end_rank, int nodes = 0);
-#endif
-}
-#endif /*PARALLEL_H */
+
+#ifndef PARALLEL_H
+#define PARALLEL_H
+
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
+#include <new>
+using namespace std;
+
+#include "Parallel_bam.h"
+#include "var.h"
+#include "MPatch.h"
+#include "Block.h"
+#include "MyList.h"
+#include "macrodef.h" //need dim; ghost_width; CONTRACT
+namespace Parallel
+{
+  struct gridseg
+  {
+    double llb[dim];
+    double uub[dim];
+    int shape[dim];
+    double illb[dim], iuub[dim]; // only use for OutBdLow2Hi
+    Block *Bg;
+  };
+  int partition1(int &nx, int split_size, int min_width, int cpusize, int shape);    // special for 1 diemnsion
+  int partition2(int *nxy, int split_size, int *min_width, int cpusize, int *shape); // special for 2 diemnsions
+  int partition3(int *nxyz, int split_size, int *min_width, int cpusize, int *shape);
+  MyList<Block> *distribute(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0); // produce corresponding Blocks
+  MyList<Block> *distribute_optimize(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0);
+  Block* splitHotspotBlock(MyList<Block>* &BlL, int _dim,
+                           int ib0_orig, int ib3_orig,
+                           int jb1_orig, int jb4_orig,
+                           int kb2_orig, int kb5_orig,
+                           Patch* PP, int r_left, int r_right,
+                           int ingfsi, int fngfsi, bool periodic,
+                           Block* &split_first_block, Block* &split_last_block);
+  Block* createMappedBlock(MyList<Block>* &BlL, int _dim, int* shape, double* bbox,
+                           int block_id, int ingfsi, int fngfsi, int lev);
+  void KillBlocks(MyList<Patch> *PatchLIST);
+
+  void setfunction(MyList<Block> *BlL, var *vn, double func(double x, double y, double z));
+  void setfunction(int rank, MyList<Block> *BlL, var *vn, double func(double x, double y, double z));
+  void writefile(double time, int nx, int ny, int nz, double xmin, double xmax, double ymin, double ymax,
+                 double zmin, double zmax, char *filename, double *data_out);
+  void writefile(double time, int nx, int ny, double xmin, double xmax, double ymin, double ymax,
+                 char *filename, double *datain);
+  void getarrayindex(int DIM, int *shape, int *index, int n);
+  int getarraylocation(int DIM, int *shape, int *index);
+  void copy(int DIM, double *llbout, double *uubout, int *Dshape, double *DD, double *llbin, double *uubin,
+            int *shape, double *datain, double *llb, double *uub);
+  void Dump_CPU_Data(MyList<Block> *BlL, MyList<var> *DumpList, char *tag, double time, double dT);
+  void Dump_Data(MyList<Patch> *PL, MyList<var> *DumpList, char *tag, double time, double dT);
+  void Dump_Data(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT, int grd);
+  double *Collect_Data(Patch *PP, var *VP);
+  void d2Dump_Data(MyList<Patch> *PL, MyList<var> *DumpList, char *tag, double time, double dT);
+  void d2Dump_Data(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT, int grd);
+  void Dump_Data0(Patch *PP, MyList<var> *DumpList, char *tag, double time, double dT);
+  double global_interp(int DIM, int *ext, double **CoX, double *datain,
+                       double *poX, int ordn, double *SoA, int Symmetry);
+  double global_interp(int DIM, int *ext, double **CoX, double *datain,
+                       double *poX, int ordn);
+  double Lagrangian_Int(double x, int npts, double *xpts, double *funcvals);
+  double LagrangePoly(double x, int pt, int npts, double *xpts);
+  MyList<gridseg> *build_complete_gsl(Patch *Pat);
+  MyList<gridseg> *build_complete_gsl(MyList<Patch> *PatL);
+  MyList<gridseg> *build_complete_gsl_virtual(MyList<Patch> *PatL);
+  MyList<gridseg> *build_complete_gsl_virtual2(MyList<Patch> *PatL);        // - buffer
+  MyList<gridseg> *build_owned_gsl0(Patch *Pat, int rank_in);               // - ghost without extension, special for Sync usage
+  MyList<gridseg> *build_owned_gsl1(Patch *Pat, int rank_in);               // - ghost, similar to build_owned_gsl0 but extend one point on left side for vertex grid
+  MyList<gridseg> *build_owned_gsl2(Patch *Pat, int rank_in);               // - buffer - ghost
+  MyList<gridseg> *build_owned_gsl3(Patch *Pat, int rank_in, int Symmetry); // - ghost - BD ghost
+  MyList<gridseg> *build_owned_gsl4(Patch *Pat, int rank_in, int Symmetry); // - buffer - ghost - BD ghost
+  MyList<gridseg> *build_owned_gsl5(Patch *Pat, int rank_in);               // similar to build_owned_gsl2 but no extension
+  MyList<gridseg> *build_owned_gsl(MyList<Patch> *PatL, int rank_in, int type, int Symmetry);
+  void build_gstl(MyList<gridseg> *srci, MyList<gridseg> *dsti, MyList<gridseg> **out_src, MyList<gridseg> **out_dst);
+  int data_packer(double *data, MyList<gridseg> *src, MyList<gridseg> *dst, int rank_in, int dir,
+                  MyList<var> *VarLists, MyList<var> *VarListd, int Symmetry);
+  void transfer(MyList<gridseg> **src, MyList<gridseg> **dst,
+                MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                int Symmetry);
+  int data_packermix(double *data, MyList<gridseg> *src, MyList<gridseg> *dst, int rank_in, int dir,
+                     MyList<var> *VarLists, MyList<var> *VarListd, int Symmetry);
+  void transfermix(MyList<gridseg> **src, MyList<gridseg> **dst,
+                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                   int Symmetry);
+  void Sync(Patch *Pat, MyList<var> *VarList, int Symmetry);
+  void Sync(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
+  void Sync_merged(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
+
+  struct SyncCache {
+    bool valid;
+    int cpusize;
+    MyList<gridseg> **combined_src;
+    MyList<gridseg> **combined_dst;
+    int *send_lengths;
+    int *recv_lengths;
+    double **send_bufs;
+    double **recv_bufs;
+    int *send_buf_caps;
+    int *recv_buf_caps;
+    unsigned char *send_buf_pinned;
+    unsigned char *recv_buf_pinned;
+    unsigned char *send_buf_is_dev;
+    unsigned char *recv_buf_is_dev;
+    int *send_buf_caps_dev;
+    int *recv_buf_caps_dev;
+    double **send_bufs_dev;
+    double **recv_bufs_dev;
+    MPI_Request *reqs;
+    MPI_Status *stats;
+    int max_reqs;
+    bool lengths_valid;
+    int *tc_req_node;
+    int *tc_req_is_recv;
+    int *tc_completed;
+    bool cuda_aware_mode;
+    SyncCache();
+    void invalidate();
+    void destroy();
+  };
+
+  void Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry, SyncCache &cache);
+  void Sync_ensure_cache(MyList<Patch> *PatL, int Symmetry, SyncCache &cache);
+  void transfer_cached(MyList<gridseg> **src, MyList<gridseg> **dst,
+                       MyList<var> *VarList1, MyList<var> *VarList2,
+                       int Symmetry, SyncCache &cache);
+
+  struct AsyncSyncState {
+    int req_no;
+    bool active;
+    int *req_node;
+    int *req_is_recv;
+    int pending_recv;
+    AsyncSyncState() : req_no(0), active(false), req_node(0), req_is_recv(0), pending_recv(0) {}
+  };
+
+  void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
+                  SyncCache &cache, AsyncSyncState &state);
+  void Sync_finish(SyncCache &cache, AsyncSyncState &state,
+                   MyList<var> *VarList, int Symmetry);
+  void OutBdLow2Hi(Patch *Patc, Patch *Patf,
+                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                   int Symmetry);
+  void OutBdLow2Hi(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                   MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                   int Symmetry);
+  void OutBdLow2Himix(Patch *Patc, Patch *Patf,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                      int Symmetry);
+  void OutBdLow2Himix(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                      int Symmetry);
+  void Restrict_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                       MyList<var> *VarList1, MyList<var> *VarList2,
+                       int Symmetry, SyncCache &cache);
+  void OutBdLow2Hi_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                          MyList<var> *VarList1, MyList<var> *VarList2,
+                          int Symmetry, SyncCache &cache);
+  void OutBdLow2Himix_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                             MyList<var> *VarList1, MyList<var> *VarList2,
+                             int Symmetry, SyncCache &cache);
+  void Prolong(Patch *Patc, Patch *Patf,
+               MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+               int Symmetry);
+  void Prolongint(Patch *Patc, Patch *Patf,
+                  MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                  int Symmetry);
+  void Restrict(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                int Symmetry);
+  void Restrict_after(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                      int Symmetry); // for -ghost - BDghost
+  MyList<Parallel::gridseg> *build_PhysBD_gsl(Patch *Pat);
+  MyList<Parallel::gridseg> *build_ghost_gsl(MyList<Patch> *PatL);
+  MyList<Parallel::gridseg> *build_ghost_gsl(Patch *Pat);
+  MyList<Parallel::gridseg> *build_buffer_gsl(Patch *Pat);
+  MyList<Parallel::gridseg> *build_buffer_gsl(MyList<Patch> *PatL);
+  MyList<Parallel::gridseg> *gsl_subtract(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
+  MyList<Parallel::gridseg> *gs_subtract(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
+  MyList<Parallel::gridseg> *gsl_and(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
+  MyList<Parallel::gridseg> *gs_and(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
+  MyList<Parallel::gridseg> *clone_gsl(MyList<Parallel::gridseg> *p, bool first_only);
+  MyList<Parallel::gridseg> *build_bulk_gsl(Patch *Pat); // similar to build_owned_gsl0 but does not care rank issue
+  MyList<Parallel::gridseg> *build_bulk_gsl(Block *bp, Patch *Pat);
+  void build_PhysBD_gstl(Patch *Pat, MyList<Parallel::gridseg> *srci, MyList<Parallel::gridseg> *dsti,
+                         MyList<Parallel::gridseg> **out_src, MyList<Parallel::gridseg> **out_dst);
+  void PeriodicBD(Patch *Pat, MyList<var> *VarList, int Symmetry);
+  double L2Norm(Patch *Pat, var *vf);
+  void L2Norm7(Patch *Pat, var **vf, double *norms);
+  void checkgsl(MyList<Parallel::gridseg> *pp, bool first_only);
+  void checkvarl(MyList<var> *pp, bool first_only);
+  MyList<Parallel::gridseg> *divide_gsl(MyList<Parallel::gridseg> *p, Patch *Pat);
+  MyList<Parallel::gridseg> *divide_gs(MyList<Parallel::gridseg> *p, Patch *Pat);
+  void prepare_inter_time_level(Patch *Pat,
+                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
+                                MyList<var> *VarList3 /* target (t+a*dt) */, int tindex);
+  void prepare_inter_time_level(Patch *Pat,
+                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
+                                MyList<var> *VarList3 /* source (t-dt) */, MyList<var> *VarList4 /* target (t+a*dt) */, int tindex);
+  void prepare_inter_time_level(MyList<Patch> *PatL,
+                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
+                                MyList<var> *VarList3 /* target (t+a*dt) */, int tindex);
+  void prepare_inter_time_level(MyList<Patch> *Pat,
+                                MyList<var> *VarList1 /* source (t+dt) */, MyList<var> *VarList2 /* source (t) */,
+                                MyList<var> *VarList3 /* source (t-dt) */, MyList<var> *VarList4 /* target (t+a*dt) */, int tindex);
+  void merge_gsl(MyList<gridseg> *&A, const double ratio);
+  bool merge_gs(MyList<gridseg> *D, MyList<gridseg> *B, MyList<gridseg> *&C, const double ratio);
+  // Add ghost region to tangent plane
+  // we assume the grids have the same resolution
+  void add_ghost_touch(MyList<gridseg> *&A);
+  void cut_gsl(MyList<gridseg> *&A);
+  bool cut_gs(MyList<gridseg> *D, MyList<gridseg> *B, MyList<gridseg> *&C);
+  MyList<Parallel::gridseg> *gs_subtract_virtual(MyList<Parallel::gridseg> *A, MyList<Parallel::gridseg> *B);
+  void fill_level_data(MyList<Patch> *PatLd, MyList<Patch> *PatLs, MyList<Patch> *PatcL,
+                       MyList<var> *OldList, MyList<var> *StateList, MyList<var> *FutureList,
+                       MyList<var> *tmList, int Symmetry, bool BB, bool CC);
+  bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
+                             int NN, double **XX,
+                             double *Shellf, int Symmetry);
+  void aligncheck(double *bbox0, double *bboxl, int lev, double *DH0, int *shape);
+  bool point_locat_gsl(double *pox, MyList<Parallel::gridseg> *gsl);
+  void checkpatchlist(MyList<Patch> *PatL, bool buflog);
+
+  double L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here);
+  void L2Norm7(Patch *Pat, var **vf, double *norms, MPI_Comm Comm_here);
+  bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
+                             int NN, double **XX,
+                             double *Shellf, int Symmetry, MPI_Comm Comm_here);
+#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
+  MyList<Block> *distribute(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfsi,
+                            bool periodic, int start_rank, int end_rank, int nodes = 0);
+#endif
+}
+#endif /*PARALLEL_H */

AMSS_NCKU_source/Parallel_bam.h

@@ -1,53 +1,53 @@
-
-#ifndef PARALLEL_BAM_H
-#define PARALLEL_BAM_H
-
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
-#include <new>
-using namespace std;
-
-#include "var.h"
-#include "MPatch.h"
-#include "Block.h"
-#include "MyList.h"
-#include "macrodef.h"
-namespace Parallel
-{
-  struct pointstru_bam
-  {
-    double pox[dim]; // cordinate
-    Block *Bgs;      // interplate from
-    Block *Bgd;      // interplate for
-    double *coef;    // interpolation coefficients
-    int sind[dim];   // interpolation starting array index
-  };
-  void destroypsuList_bam(MyList<pointstru_bam> *ct);
-  void OutBdLow2Hi_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
-                       MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                       int Symmetry);
-  void OutBdLow2Hi_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
-                       MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                       MyList<Parallel::pointstru_bam> *bdsul, int Symmetry);
-  void Constr_pointstr_OutBdLow2Hi(MyList<Patch> *PLf, MyList<Patch> *PLc,
-                                   MyList<Parallel::pointstru_bam> *&bdsul);
-  void Restrict_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
-                    MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                    int Symmetry);
-  void Restrict_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
-                    MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
-                    MyList<Parallel::pointstru_bam> *rsul, int Symmetry);
-  void Constr_pointstr_Restrict(MyList<Patch> *PLf, MyList<Patch> *PLc,
-                                MyList<Parallel::pointstru_bam> *&rsul);
-  void intertransfer(MyList<Parallel::pointstru_bam> *&sul,
-                     MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                     int Symmetry);
-  int interdata_packer(double *data, MyList<Parallel::pointstru_bam> *sul, int myrank, int node, int dir,
-                       MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry);
-}
-#endif /*PARALLEL_BAM_H */
+
+#ifndef PARALLEL_BAM_H
+#define PARALLEL_BAM_H
+
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
+#include <new>
+using namespace std;
+
+#include "var.h"
+#include "MPatch.h"
+#include "Block.h"
+#include "MyList.h"
+#include "macrodef.h"
+namespace Parallel
+{
+  struct pointstru_bam
+  {
+    double pox[dim]; // cordinate
+    Block *Bgs;      // interplate from
+    Block *Bgd;      // interplate for
+    double *coef;    // interpolation coefficients
+    int sind[dim];   // interpolation starting array index
+  };
+  void destroypsuList_bam(MyList<pointstru_bam> *ct);
+  void OutBdLow2Hi_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
+                       MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                       int Symmetry);
+  void OutBdLow2Hi_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
+                       MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                       MyList<Parallel::pointstru_bam> *bdsul, int Symmetry);
+  void Constr_pointstr_OutBdLow2Hi(MyList<Patch> *PLf, MyList<Patch> *PLc,
+                                   MyList<Parallel::pointstru_bam> *&bdsul);
+  void Restrict_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
+                    MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                    int Symmetry);
+  void Restrict_bam(MyList<Patch> *PLc, MyList<Patch> *PLf,
+                    MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
+                    MyList<Parallel::pointstru_bam> *rsul, int Symmetry);
+  void Constr_pointstr_Restrict(MyList<Patch> *PLf, MyList<Patch> *PLc,
+                                MyList<Parallel::pointstru_bam> *&rsul);
+  void intertransfer(MyList<Parallel::pointstru_bam> *&sul,
+                     MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                     int Symmetry);
+  int interdata_packer(double *data, MyList<Parallel::pointstru_bam> *sul, int myrank, int node, int dir,
+                       MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */, int Symmetry);
+}
+#endif /*PARALLEL_BAM_H */

AMSS_NCKU_source/Set_Rho_ADM.f90

@@ -1,271 +1,271 @@
-
-! define scalar field distribution and potential in F(R) scalar-tensor theory
-! 1: Case C of 1112.3928, V=0
-! 2: shell with a2^2*phi0/(1+a2^2), f(R) = R+a2*R^2 induced V
-! 3: ground state of Schrodinger-Newton system, f(R) = R+a2*R^2 induced V
-! 4: a2 = oo and \phi = \phi_0*0.5*(tanh((r+r_0)/\sigma)-tanh((r-r_0)/\sigma))
-! 5: shell with phi0*dexp(-(r-r0)**2/sigma), V = 0
-
-! original way, manually define the preprocessor macro
-! #define CC 2
-! the new way, define according to the preprocessor macro in "macrodef.fh"
-#include "macrodef.fh"
-#define CC EScalar_CC
-
-subroutine setparameters(a2,r0,phi0,sigma,l2)
-implicit none
-real*8,intent(out) :: a2,r0,phi0,sigma,l2
-
-! original way: read in parameters one by one
-! call seta2(a2)
-! call setphi0(phi0)
-
-! new way: read in all parameters at once
-call set_escalar_parameter(a2, phi0, r0, sigma, l2)
-
-! r0=120.d0
-! sigma=8.d0
-! l2=1.d4
-
-! write(*,*)
-! write(*,*) " Set_Rho_ADM.f90 a2     = ", a2
-! write(*,*) " Set_Rho_ADM.f90 phi0   = ", phi0
-! write(*,*) " Set_Rho_ADM.f90 r0     = ", r0
-! write(*,*) " Set_Rho_ADM.f90 sigma0 = ", sigma
-! write(*,*) " Set_Rho_ADM.f90 l2     = ", l2
-! write(*,*)
-
-return
-
-end subroutine setparameters
-!===================================================================
-function phi(X,Y,Z) result(gont)
-implicit none
-
-double precision,intent(in)::X
-double precision,intent(in)::Y
-double precision,intent(in)::Z
-real*8 :: gont
-
-real*8 ::r
-real*8 :: a2,r0,phi0,sigma,l2
-
-  call setparameters(a2,r0,phi0,sigma,l2)
-  r=dsqrt(X*X+Y*Y+Z*Z)
-#if  ( CC == 1)  
-! configuration 1  
-  gont = phi0*dtanh((r-r0)/sigma)
-#elif ( CC == 2)
-! configuration 2  
-  phi0 = a2**2*phi0/(1+a2**2)
-  gont = phi0*dexp(-(r-r0)**2/sigma)
-#elif ( CC == 3)
-  gont =  (0.0481646d0*dexp(-0.0581545d0*(r-1.8039d-8)*(r-1.8039d-8)/l2) &
-           +0.298408d0*dexp(-0.111412d0*(r+9.6741d-9)*(r+9.6741d-9)/l2)+   &
-             0.42755d0*dexp(-0.207156d0*(r-1.09822d-8)*(r-1.09822d-8)/l2)+   &
-            0.204229d0*dexp(-0.37742d0*(r+2.13778d-8)*(r+2.13778d-8)/l2)+   &
-            0.021649d0*dexp(-0.68406d0*(r-8.78608d-8)*(r-8.78608d-8)/l2))/l2
-#elif ( CC == 4)
-! configuration 4, a2 = oo
-  phi0 = 0.5d0*phi0
-  gont = phi0*(dtanh((r+r0)/sigma)-dtanh((r-r0)/sigma))
-#elif ( CC == 5)
-! configuration 5  
-  gont = phi0*dexp(-(r-r0)**2/sigma)
-#endif
-
-return
-
-end function phi
-
-! d phi/dr
-function dphi(X,Y,Z) result(gont)
-implicit none
-
-double precision,intent(in)::X
-double precision,intent(in)::Y
-double precision,intent(in)::Z
-real*8 :: gont
-
-real*8 ::r
-real*8 :: a2,r0,phi0,sigma,l2
-
-  call setparameters(a2,r0,phi0,sigma,l2)
-  r=dsqrt(X*X+Y*Y+Z*Z)
-#if  ( CC == 1)  
-! configuration 1  
-  gont = phi0/sigma*(1-(dtanh((r-r0)/sigma))**2)
-#elif ( CC == 2)
-! configuration 2
-  phi0 = a2**2*phi0/(1+a2**2)
-  gont = -2.d0*phi0*(r-r0)/sigma*exp(-(r-r0)**2/sigma)
-#elif ( CC == 3)
-  gont = (-0.5601976461d-2*(r-0.18039d-7)/l2*dexp(-0.581545d-1*(r-0.18039d-7)**2/l2) &
-          -0.6649246419d-1*(r+0.96741d-8)/l2*dexp(-0.111412d0*(r+.96741e-8)**2/l2)    &
-          -0.1771390956d0*(r-0.109822d-7)/l2*dexp(-0.207156d0*(r-0.109822d-7)**2/l2)  &
-          -0.1541602184d0*(r+0.213778d-7)/l2*dexp(-0.37742d0*(r+0.213778d-7)**2/l2)   &
-          -0.2961842988d-1*(r-0.878608d-7)/l2*dexp(-0.68406*(r-0.878608d-7)**2/l2))/l2
-#elif ( CC == 4)
-! configuration 4, a2 = oo
-  phi0 = 0.5d0*phi0
-  gont = phi0*((1-dtanh((r+r0)/sigma)**2)/sigma- &
-               (1-dtanh((r-r0)/sigma)**2)/sigma)
-#elif ( CC == 5)
-! configuration 5
-  gont = -2.d0*phi0*(r-r0)/sigma*exp(-(r-r0)**2/sigma)
-#endif
-
-return
-
-end function dphi
-!==================================================================
-function potential(X,Y,Z) result(gont)
-implicit none
-
-double precision,intent(in)::X
-double precision,intent(in)::Y
-double precision,intent(in)::Z
-real*8 :: gont
-
-real*8 :: phi
-real*8 :: PI,v
-
-real*8 :: a2,r0,phi0,sigma,l2
-
-#if  ( CC == 1 || CC == 4 || CC == 5)  
-  gont = 0.d0
-
-#elif ( CC == 2 || CC == 3)
-  call setparameters(a2,r0,phi0,sigma,l2)
-  PI = dacos(-1.d0)
-
-  v = phi(X,Y,Z)
-
-  gont = dexp(-8.d0*dsqrt(PI/3)*v)*(1-dexp(4*dsqrt(PI/3)*v))**2/32/PI/a2
-#endif
-
-return
-
-end function potential
-!==================================================================
-!Note this part is for evolution 
-!not just for initial configuration
-
-!f(R) potential F=R+a_2R^2
-subroutine frpotential(ex,Sphi,V,dVdSphi)
-
-implicit none
-
-integer,intent(in ):: ex(1:3)
-real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Sphi
-real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: V,dVdSphi
-
-real*8 :: a2,r0,phi0,sigma,l2
-real*8, parameter :: Four = 4.d0, TWO = 2.d0,ONE = 1.d0,ZEO=0.d0
-real*8 :: PI
-
-  PI = dacos(-ONE)
-
-#if  ( CC == 1 || CC == 4 || CC == 5)  
-  V = ZEO
-  dVdSphi = ZEO
-#elif ( CC == 2 || CC == 3)
-  call setparameters(a2,r0,phi0,sigma,l2)
-  V = dexp(-8.d0*dsqrt(PI/3)*Sphi)*(1-dexp(4*dsqrt(PI/3)*Sphi))**2/32/PI/a2
-  dVdSphi = 1.d0/a2/1.2d1*dsqrt(3.d0/PI)*dexp(-8.d0*dsqrt(PI/3.d0)*Sphi)*(-1+dexp(4*dsqrt(Pi/3)*Sphi))
-#endif
-
-return
-
-end subroutine frpotential
-!==================================================================
-!f(R) potential F=R+a_2R^2
-!fprim(R) = 1+2*a_2*R
-subroutine frfprim(ex,RR,fprim)
-
-implicit none
-
-integer,intent(in ):: ex(1:3)
-real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: RR
-real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: fprim
-
-real*8 :: a2,r0,phi0,sigma,l2
-real*8, parameter :: ONE=1.d0, TWO = 2.d0
-
-#if  ( CC == 1 || CC == 4 || CC == 5)  
-  fprim = ONE
-#elif ( CC == 2 || CC == 3)
-  call setparameters(a2,r0,phi0,sigma,l2)
-  fprim = ONE+TWO*a2*RR
-#endif
-
-return
-
-end subroutine frfprim
-!==================================================================
-subroutine set_rho_adm2(ex,rho,X,Y,Z)
-
-implicit none
-! argument variables
-integer,intent(in)::ex
-double precision,intent(in),dimension(ex)::X
-double precision,intent(in),dimension(ex)::Y
-double precision,intent(in),dimension(ex)::Z
-double precision,intent(out),dimension(ex)::rho
-
-integer :: i
-real*8 :: dphi
-
-  do i=1,ex
-    ! rho(i) = dphi(X,Y,Z)
-    rho(i) = dphi(X(i),Y(i),Z(i))
-    rho(i) = rho(i)*rho(i)
-  enddo
-
-  return
-
-end subroutine set_rho_adm2
-
-subroutine set_rho_adm1(ex,rho,X,Y,Z)
-
-implicit none
-! argument variables
-integer,intent(in)::ex
-double precision,intent(in),dimension(ex)::X
-double precision,intent(in),dimension(ex)::Y
-double precision,intent(in),dimension(ex)::Z
-double precision,intent(out),dimension(ex)::rho
-
-real*8 :: potential
-integer :: i
-
-  do i=1,ex
-    rho(i) = potential(X(i),Y(i),Z(i))
-  enddo
-
-  return
-
-end subroutine set_rho_adm1
-
-subroutine set_rho_adm(ex,rho,X,Y,Z)
-
-implicit none
-! argument variables
-integer,intent(in)::ex
-double precision,intent(in),dimension(ex)::X
-double precision,intent(in),dimension(ex)::Y
-double precision,intent(in),dimension(ex)::Z
-! in psivac, out rho_adm
-double precision,intent(inout),dimension(ex)::rho
-
-double precision,dimension(ex)::rho1,rho2
-
-  call set_rho_adm1(ex,rho1,X,Y,Z)
-  call set_rho_adm2(ex,rho2,X,Y,Z)
-
-  rho = rho**4
-  rho = rho**2*rho1+rho*rho2
-
-  return
-
-end subroutine set_rho_adm
+
+! define scalar field distribution and potential in F(R) scalar-tensor theory
+! 1: Case C of 1112.3928, V=0
+! 2: shell with a2^2*phi0/(1+a2^2), f(R) = R+a2*R^2 induced V
+! 3: ground state of Schrodinger-Newton system, f(R) = R+a2*R^2 induced V
+! 4: a2 = oo and \phi = \phi_0*0.5*(tanh((r+r_0)/\sigma)-tanh((r-r_0)/\sigma))
+! 5: shell with phi0*dexp(-(r-r0)**2/sigma), V = 0
+
+! original way, manually define the preprocessor macro
+! #define CC 2
+! the new way, define according to the preprocessor macro in "macrodef.fh"
+#include "macrodef.fh"
+#define CC EScalar_CC
+
+subroutine setparameters(a2,r0,phi0,sigma,l2)
+implicit none
+real*8,intent(out) :: a2,r0,phi0,sigma,l2
+
+! original way: read in parameters one by one
+! call seta2(a2)
+! call setphi0(phi0)
+
+! new way: read in all parameters at once
+call set_escalar_parameter(a2, phi0, r0, sigma, l2)
+
+! r0=120.d0
+! sigma=8.d0
+! l2=1.d4
+
+! write(*,*)
+! write(*,*) " Set_Rho_ADM.f90 a2     = ", a2
+! write(*,*) " Set_Rho_ADM.f90 phi0   = ", phi0
+! write(*,*) " Set_Rho_ADM.f90 r0     = ", r0
+! write(*,*) " Set_Rho_ADM.f90 sigma0 = ", sigma
+! write(*,*) " Set_Rho_ADM.f90 l2     = ", l2
+! write(*,*)
+
+return
+
+end subroutine setparameters
+!===================================================================
+function phi(X,Y,Z) result(gont)
+implicit none
+
+double precision,intent(in)::X
+double precision,intent(in)::Y
+double precision,intent(in)::Z
+real*8 :: gont
+
+real*8 ::r
+real*8 :: a2,r0,phi0,sigma,l2
+
+  call setparameters(a2,r0,phi0,sigma,l2)
+  r=dsqrt(X*X+Y*Y+Z*Z)
+#if  ( CC == 1)  
+! configuration 1  
+  gont = phi0*dtanh((r-r0)/sigma)
+#elif ( CC == 2)
+! configuration 2  
+  phi0 = a2**2*phi0/(1+a2**2)
+  gont = phi0*dexp(-(r-r0)**2/sigma)
+#elif ( CC == 3)
+  gont =  (0.0481646d0*dexp(-0.0581545d0*(r-1.8039d-8)*(r-1.8039d-8)/l2) &
+           +0.298408d0*dexp(-0.111412d0*(r+9.6741d-9)*(r+9.6741d-9)/l2)+   &
+             0.42755d0*dexp(-0.207156d0*(r-1.09822d-8)*(r-1.09822d-8)/l2)+   &
+            0.204229d0*dexp(-0.37742d0*(r+2.13778d-8)*(r+2.13778d-8)/l2)+   &
+            0.021649d0*dexp(-0.68406d0*(r-8.78608d-8)*(r-8.78608d-8)/l2))/l2
+#elif ( CC == 4)
+! configuration 4, a2 = oo
+  phi0 = 0.5d0*phi0
+  gont = phi0*(dtanh((r+r0)/sigma)-dtanh((r-r0)/sigma))
+#elif ( CC == 5)
+! configuration 5  
+  gont = phi0*dexp(-(r-r0)**2/sigma)
+#endif
+
+return
+
+end function phi
+
+! d phi/dr
+function dphi(X,Y,Z) result(gont)
+implicit none
+
+double precision,intent(in)::X
+double precision,intent(in)::Y
+double precision,intent(in)::Z
+real*8 :: gont
+
+real*8 ::r
+real*8 :: a2,r0,phi0,sigma,l2
+
+  call setparameters(a2,r0,phi0,sigma,l2)
+  r=dsqrt(X*X+Y*Y+Z*Z)
+#if  ( CC == 1)  
+! configuration 1  
+  gont = phi0/sigma*(1-(dtanh((r-r0)/sigma))**2)
+#elif ( CC == 2)
+! configuration 2
+  phi0 = a2**2*phi0/(1+a2**2)
+  gont = -2.d0*phi0*(r-r0)/sigma*exp(-(r-r0)**2/sigma)
+#elif ( CC == 3)
+  gont = (-0.5601976461d-2*(r-0.18039d-7)/l2*dexp(-0.581545d-1*(r-0.18039d-7)**2/l2) &
+          -0.6649246419d-1*(r+0.96741d-8)/l2*dexp(-0.111412d0*(r+.96741e-8)**2/l2)    &
+          -0.1771390956d0*(r-0.109822d-7)/l2*dexp(-0.207156d0*(r-0.109822d-7)**2/l2)  &
+          -0.1541602184d0*(r+0.213778d-7)/l2*dexp(-0.37742d0*(r+0.213778d-7)**2/l2)   &
+          -0.2961842988d-1*(r-0.878608d-7)/l2*dexp(-0.68406*(r-0.878608d-7)**2/l2))/l2
+#elif ( CC == 4)
+! configuration 4, a2 = oo
+  phi0 = 0.5d0*phi0
+  gont = phi0*((1-dtanh((r+r0)/sigma)**2)/sigma- &
+               (1-dtanh((r-r0)/sigma)**2)/sigma)
+#elif ( CC == 5)
+! configuration 5
+  gont = -2.d0*phi0*(r-r0)/sigma*exp(-(r-r0)**2/sigma)
+#endif
+
+return
+
+end function dphi
+!==================================================================
+function potential(X,Y,Z) result(gont)
+implicit none
+
+double precision,intent(in)::X
+double precision,intent(in)::Y
+double precision,intent(in)::Z
+real*8 :: gont
+
+real*8 :: phi
+real*8 :: PI,v
+
+real*8 :: a2,r0,phi0,sigma,l2
+
+#if  ( CC == 1 || CC == 4 || CC == 5)  
+  gont = 0.d0
+
+#elif ( CC == 2 || CC == 3)
+  call setparameters(a2,r0,phi0,sigma,l2)
+  PI = dacos(-1.d0)
+
+  v = phi(X,Y,Z)
+
+  gont = dexp(-8.d0*dsqrt(PI/3)*v)*(1-dexp(4*dsqrt(PI/3)*v))**2/32/PI/a2
+#endif
+
+return
+
+end function potential
+!==================================================================
+!Note this part is for evolution 
+!not just for initial configuration
+
+!f(R) potential F=R+a_2R^2
+subroutine frpotential(ex,Sphi,V,dVdSphi)
+
+implicit none
+
+integer,intent(in ):: ex(1:3)
+real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Sphi
+real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: V,dVdSphi
+
+real*8 :: a2,r0,phi0,sigma,l2
+real*8, parameter :: Four = 4.d0, TWO = 2.d0,ONE = 1.d0,ZEO=0.d0
+real*8 :: PI
+
+  PI = dacos(-ONE)
+
+#if  ( CC == 1 || CC == 4 || CC == 5)  
+  V = ZEO
+  dVdSphi = ZEO
+#elif ( CC == 2 || CC == 3)
+  call setparameters(a2,r0,phi0,sigma,l2)
+  V = dexp(-8.d0*dsqrt(PI/3)*Sphi)*(1-dexp(4*dsqrt(PI/3)*Sphi))**2/32/PI/a2
+  dVdSphi = 1.d0/a2/1.2d1*dsqrt(3.d0/PI)*dexp(-8.d0*dsqrt(PI/3.d0)*Sphi)*(-1+dexp(4*dsqrt(Pi/3)*Sphi))
+#endif
+
+return
+
+end subroutine frpotential
+!==================================================================
+!f(R) potential F=R+a_2R^2
+!fprim(R) = 1+2*a_2*R
+subroutine frfprim(ex,RR,fprim)
+
+implicit none
+
+integer,intent(in ):: ex(1:3)
+real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: RR
+real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: fprim
+
+real*8 :: a2,r0,phi0,sigma,l2
+real*8, parameter :: ONE=1.d0, TWO = 2.d0
+
+#if  ( CC == 1 || CC == 4 || CC == 5)  
+  fprim = ONE
+#elif ( CC == 2 || CC == 3)
+  call setparameters(a2,r0,phi0,sigma,l2)
+  fprim = ONE+TWO*a2*RR
+#endif
+
+return
+
+end subroutine frfprim
+!==================================================================
+subroutine set_rho_adm2(ex,rho,X,Y,Z)
+
+implicit none
+! argument variables
+integer,intent(in)::ex
+double precision,intent(in),dimension(ex)::X
+double precision,intent(in),dimension(ex)::Y
+double precision,intent(in),dimension(ex)::Z
+double precision,intent(out),dimension(ex)::rho
+
+integer :: i
+real*8 :: dphi
+
+  do i=1,ex
+    ! rho(i) = dphi(X,Y,Z)
+    rho(i) = dphi(X(i),Y(i),Z(i))
+    rho(i) = rho(i)*rho(i)
+  enddo
+
+  return
+
+end subroutine set_rho_adm2
+
+subroutine set_rho_adm1(ex,rho,X,Y,Z)
+
+implicit none
+! argument variables
+integer,intent(in)::ex
+double precision,intent(in),dimension(ex)::X
+double precision,intent(in),dimension(ex)::Y
+double precision,intent(in),dimension(ex)::Z
+double precision,intent(out),dimension(ex)::rho
+
+real*8 :: potential
+integer :: i
+
+  do i=1,ex
+    rho(i) = potential(X(i),Y(i),Z(i))
+  enddo
+
+  return
+
+end subroutine set_rho_adm1
+
+subroutine set_rho_adm(ex,rho,X,Y,Z)
+
+implicit none
+! argument variables
+integer,intent(in)::ex
+double precision,intent(in),dimension(ex)::X
+double precision,intent(in),dimension(ex)::Y
+double precision,intent(in),dimension(ex)::Z
+! in psivac, out rho_adm
+double precision,intent(inout),dimension(ex)::rho
+
+double precision,dimension(ex)::rho1,rho2
+
+  call set_rho_adm1(ex,rho1,X,Y,Z)
+  call set_rho_adm2(ex,rho2,X,Y,Z)
+
+  rho = rho**4
+  rho = rho**2*rho1+rho*rho2
+
+  return
+
+end subroutine set_rho_adm

AMSS_NCKU_source/ShellPatch.h

@@ -1,205 +1,221 @@
-
-#ifndef SHELLPATCH_H
-#define SHELLPATCH_H
-
-#include <mpi.h>
-#include "MyList.h"
-#include "Block.h"
-#include "Parallel.h"
-#include "var.h"
-#include "monitor.h"
-#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
-
-#if (dim != 3)
-#error shellpatch only supports 3 dimensional stuff yet
-#endif
-
-class ss_patch
-{
-
-public:
-   int sst; // ss_patch type: 0:zp, 1:zm, 2:xp, 3:xm, 4:yp, 5:ym
-   int myrank;
-   int shape[dim];
-   double bbox[2 * dim]; // this bbox includes nominal points and overlap points
-   MyList<Block> *blb, *ble;
-   int ingfs, fngfs;
-
-   ss_patch() {};
-   ss_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki);
-
-   ~ss_patch();
-
-   virtual void setupcordtrans() {};
-   void Sync(MyList<var> *VarList, int Symmetry);
-   MyList<Parallel::gridseg> *build_bulk_gsl(Block *bp);
-   MyList<Parallel::gridseg> *build_ghost_gsl();
-   MyList<Parallel::gridseg> *build_owned_gsl0(int rank_in);
-};
-
-class xp_patch : public ss_patch
-{
-public:
-   xp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
-   void setupcordtrans();
-};
-
-class xm_patch : public ss_patch
-{
-public:
-   xm_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
-   void setupcordtrans();
-};
-class yp_patch : public ss_patch
-{
-public:
-   yp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
-   void setupcordtrans();
-};
-
-class ym_patch : public ss_patch
-{
-public:
-   ym_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
-   void setupcordtrans();
-};
-class zp_patch : public ss_patch
-{
-public:
-   zp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
-   void setupcordtrans();
-};
-
-class zm_patch : public ss_patch
-{
-public:
-   zm_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
-   void setupcordtrans();
-};
-// Shell Patch system
-// for derivatives usage we ask 27 more double type grid functions
-// here we use **sngfs corresponding to fngfs to store them:
-//                    drho/dx, drho/dy, drho/dz
-//                    dsigma/dx, dsigma/dy, dsigma/dz
-//                    dR/dx, dR/dy, dR/dz
-//                    drho/dxdx, drho/dxdy, drho/dxdz, drho/dydy, drho/dydz, drho/dzdz
-//                    dsigma/dxdx, dsigma/dxdy, dsigma/dxdz, dsigma/dydy, dsigma/dydz, dsigma/dzdz
-//                    dR/dxdx, dR/dxdy, dR/dxdz, dR/dydy, dR/dydz, dR/dzdz
-class ShellPatch
-{
-
-public:
-   struct pointstru
-   {
-      double gpox[dim]; // global cordinate
-      double lpox[dim]; // local cordinate
-      Block *Bg;
-      int ssst; //-1: cardisian, others as sst of ss_patch source sst
-      int tsst; //-1: cardisian, others as sst of ss_patch target sst
-      double *coef;
-      int *sind;
-      int dumyd; // the dimension which has common lines, only useful in interdata_packer
-                 //-1: means no dumy dimension at all; 0: means rho; 1: means sigma
-   };
-
-   int myrank;
-   int shape[dim];   // for (rho, sigma, R), for rho and sigma means number of points for every pi/2
-   double Rrange[2]; // for Rmin and Rmax
-   int Symmetry;
-   int ingfs, fngfs;
-
-   MyList<ss_patch> *PatL;
-
-   // we use fngfs+v to reference the variable
-   enum
-   {
-      gx = 0,
-      gy,
-      gz,
-      drhodx,
-      drhody,
-      drhodz,
-      dsigmadx,
-      dsigmady,
-      dsigmadz,
-      dRdx,
-      dRdy,
-      dRdz,
-      drhodxx,
-      drhodxy,
-      drhodxz,
-      drhodyy,
-      drhodyz,
-      drhodzz,
-      dsigmadxx,
-      dsigmadxy,
-      dsigmadxz,
-      dsigmadyy,
-      dsigmadyz,
-      dsigmadzz,
-      dRdxx,
-      dRdxy,
-      dRdxz,
-      dRdyy,
-      dRdyz,
-      dRdzz
-   };
-
-   MyList<pointstru> **ss_src, **ss_dst;
-   // at means target
-   MyList<pointstru> **csatc_src, **csatc_dst;
-   MyList<pointstru> **csats_src, **csats_dst;
-
-public:
-   ShellPatch(int ingfsi, int fngfsi, char *filename, int Symmetry, int myranki, monitor *ErrorMonitor);
-
-   ~ShellPatch();
-
-   MyList<Block> *compose_sh(int cpusize, int nodes = 0);
-   MyList<Block> *compose_shr(int cpusize, int nodes = 0);
-   void setupcordtrans();
-   double getR(double r);
-   double getsr(double R);
-   void checkPatch();
-   void checkBlock(int sst);
-   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
-   void check_pointstrul2(MyList<pointstru> *pp, int first_last_only);
-   double getdX(int dir); //(rho, sigma, R)
-   void Dump_xyz(char *tag, double time, double dT);
-   void Dump_Data(MyList<var> *DumpList, char *tag, double time, double dT);
-   double *Collect_Data(ss_patch *PP, var *VP);
-   void getlocalpoxsst(double gx, double gy, double gz, int sst, double &lx, double &ly, double &lz);
-   void getlocalpox(double gx, double gy, double gz, int &sst, double &lx, double &ly, double &lz);
-   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
-   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPp, double DH[dim],
-                         MyList<Patch> *Pp, double CDH[dim], MyList<pointstru> *pss);
-   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
-                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
-   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
-   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
-                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
-                      int Symmetry);
-   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst,
-                        int rank_in, int dir,
-                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */,
-                        int Symmetry);
-   void Synch(MyList<var> *VarList, int Symmetry);
-   void CS_Inter(MyList<var> *VarList, int Symmetry);
-   void destroypsuList(MyList<pointstru> *ct);
-   int getdumydimension(int acsst, int posst); // -1 means no dumy dimension
-   void matchcheck(MyList<Patch> *CPatL);
-   void shellname(char *sn, int i);
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX, /*input global Cartesian coordinate*/
-                      double *Shellf, int Symmetry);
-   bool Interp_One_Point(MyList<var> *VarList,
-                         double *XX, /*input global Cartesian coordinate*/
-                         double *Shellf, int Symmetry);
-   void write_Pablo_file_ss(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
-                            char *filename, int sst);
-   double L2Norm(var *vf);
-   void L2Norm7(var **vf, double *norms);
-   void Find_Maximum(MyList<var> *VarList, double *XX, double *Shellf);
-};
-
-#endif /* SHELLPATCH_H */
+
+#ifndef SHELLPATCH_H
+#define SHELLPATCH_H
+
+#include <mpi.h>
+#include "MyList.h"
+#include "Block.h"
+#include "Parallel.h"
+#include "var.h"
+#include "monitor.h"
+#include "macrodef.h" //need dim here; Vertex or Cell; ghost_width
+
+#if (dim != 3)
+#error shellpatch only supports 3 dimensional stuff yet
+#endif
+
+class ss_patch
+{
+
+public:
+   int sst; // ss_patch type: 0:zp, 1:zm, 2:xp, 3:xm, 4:yp, 5:ym
+   int myrank;
+   int shape[dim];
+   double bbox[2 * dim]; // this bbox includes nominal points and overlap points
+   MyList<Block> *blb, *ble;
+   int ingfs, fngfs;
+
+   ss_patch() {};
+   ss_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki);
+
+   ~ss_patch();
+
+   virtual void setupcordtrans() {};
+   void Sync(MyList<var> *VarList, int Symmetry);
+   MyList<Parallel::gridseg> *build_bulk_gsl(Block *bp);
+   MyList<Parallel::gridseg> *build_ghost_gsl();
+   MyList<Parallel::gridseg> *build_owned_gsl0(int rank_in);
+};
+
+class xp_patch : public ss_patch
+{
+public:
+   xp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 2; };
+   void setupcordtrans();
+};
+
+class xm_patch : public ss_patch
+{
+public:
+   xm_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 3; };
+   void setupcordtrans();
+};
+class yp_patch : public ss_patch
+{
+public:
+   yp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 4; };
+   void setupcordtrans();
+};
+
+class ym_patch : public ss_patch
+{
+public:
+   ym_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 5; };
+   void setupcordtrans();
+};
+class zp_patch : public ss_patch
+{
+public:
+   zp_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 0; };
+   void setupcordtrans();
+};
+
+class zm_patch : public ss_patch
+{
+public:
+   zm_patch(int ingfsi, int fngfsi, int *shapei, double *bboxi, int myranki) : ss_patch(ingfsi, fngfsi, shapei, bboxi, myranki) { sst = 1; };
+   void setupcordtrans();
+};
+// Shell Patch system
+// for derivatives usage we ask 27 more double type grid functions
+// here we use **sngfs corresponding to fngfs to store them:
+//                    drho/dx, drho/dy, drho/dz
+//                    dsigma/dx, dsigma/dy, dsigma/dz
+//                    dR/dx, dR/dy, dR/dz
+//                    drho/dxdx, drho/dxdy, drho/dxdz, drho/dydy, drho/dydz, drho/dzdz
+//                    dsigma/dxdx, dsigma/dxdy, dsigma/dxdz, dsigma/dydy, dsigma/dydz, dsigma/dzdz
+//                    dR/dxdx, dR/dxdy, dR/dxdz, dR/dydy, dR/dydz, dR/dzdz
+class ShellPatch
+{
+
+public:
+   struct pointstru
+   {
+      double gpox[dim]; // global cordinate
+      double lpox[dim]; // local cordinate
+      Block *Bg;
+      int ssst; //-1: cardisian, others as sst of ss_patch source sst
+      int tsst; //-1: cardisian, others as sst of ss_patch target sst
+      double *coef;
+      int *sind;
+      int dumyd; // the dimension which has common lines, only useful in interdata_packer
+                 //-1: means no dumy dimension at all; 0: means rho; 1: means sigma
+   };
+
+   // Thread-safe search result (no pointers to shared mutable state)
+   struct PointSearchResult
+   {
+      bool found;
+      Block *Bg;
+      double gx, gy, gz; // global Cartesian coordinates
+      double lx, ly, lz; // local coordinates within the found block
+      int ssst;          // source shell-patch type (-1 = Cartesian)
+   };
+
+   int myrank;
+   int shape[dim];   // for (rho, sigma, R), for rho and sigma means number of points for every pi/2
+   double Rrange[2]; // for Rmin and Rmax
+   int Symmetry;
+   int ingfs, fngfs;
+
+   MyList<ss_patch> *PatL;
+
+   // we use fngfs+v to reference the variable
+   enum
+   {
+      gx = 0,
+      gy,
+      gz,
+      drhodx,
+      drhody,
+      drhodz,
+      dsigmadx,
+      dsigmady,
+      dsigmadz,
+      dRdx,
+      dRdy,
+      dRdz,
+      drhodxx,
+      drhodxy,
+      drhodxz,
+      drhodyy,
+      drhodyz,
+      drhodzz,
+      dsigmadxx,
+      dsigmadxy,
+      dsigmadxz,
+      dsigmadyy,
+      dsigmadyz,
+      dsigmadzz,
+      dRdxx,
+      dRdxy,
+      dRdxz,
+      dRdyy,
+      dRdyz,
+      dRdzz
+   };
+
+   MyList<pointstru> **ss_src, **ss_dst;
+   // at means target
+   MyList<pointstru> **csatc_src, **csatc_dst;
+   MyList<pointstru> **csats_src, **csats_dst;
+
+public:
+   ShellPatch(int ingfsi, int fngfsi, char *filename, int Symmetry, int myranki, monitor *ErrorMonitor);
+
+   ~ShellPatch();
+
+   MyList<Block> *compose_sh(int cpusize, int nodes = 0);
+   MyList<Block> *compose_shr(int cpusize, int nodes = 0);
+   void setupcordtrans();
+   double getR(double r);
+   double getsr(double R);
+   void checkPatch();
+   void checkBlock(int sst);
+   void check_pointstrul(MyList<pointstru> *pp, bool first_only);
+   void check_pointstrul2(MyList<pointstru> *pp, int first_last_only);
+   double getdX(int dir); //(rho, sigma, R)
+   void Dump_xyz(char *tag, double time, double dT);
+   void Dump_Data(MyList<var> *DumpList, char *tag, double time, double dT);
+   double *Collect_Data(ss_patch *PP, var *VP);
+   void getlocalpoxsst(double gx, double gy, double gz, int sst, double &lx, double &ly, double &lz);
+   void getlocalpox(double gx, double gy, double gz, int &sst, double &lx, double &ly, double &lz);
+   void getglobalpox(double &x, double &y, double &z, int sst, double lx, double ly, double lz);
+   void prolongpointstru(MyList<pointstru> *&psul, MyList<ss_patch> *sPp, double DH[dim],
+                         MyList<Patch> *Pp, double CDH[dim], MyList<pointstru> *pss);
+   bool prolongpointstru(MyList<pointstru> *&psul, bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                         MyList<Patch> *Pp, double CDH[dim], double x, double y, double z, int Symmetry, int rank_in);
+   // Read-only point search — thread-safe (no shared mutable state modified)
+   PointSearchResult prolongpointstru_search(bool ssyn, int tsst, MyList<ss_patch> *sPp, double DH[dim],
+                                             MyList<Patch> *Pp, double CDH[dim], double x, double y, double z,
+                                             int Symmetry, int rank_in);
+   // Append a search result to a linked list — use inside omp critical section
+   void prolongpointstru_append(MyList<pointstru> *&psul, const PointSearchResult &sr, int tsst);
+   void setupintintstuff(int cpusize, MyList<Patch> *CPatL, int Symmetry);
+   void intertransfer(MyList<pointstru> **src, MyList<pointstru> **dst,
+                      MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /*target */,
+                      int Symmetry);
+   int interdata_packer(double *data, MyList<pointstru> *src, MyList<pointstru> *dst,
+                        int rank_in, int dir,
+                        MyList<var> *VarLists /* source */, MyList<var> *VarListd /* target */,
+                        int Symmetry);
+   void Synch(MyList<var> *VarList, int Symmetry);
+   void CS_Inter(MyList<var> *VarList, int Symmetry);
+   void destroypsuList(MyList<pointstru> *ct);
+   int getdumydimension(int acsst, int posst); // -1 means no dumy dimension
+   void matchcheck(MyList<Patch> *CPatL);
+   void shellname(char *sn, int i);
+   void Interp_Points(MyList<var> *VarList,
+                      int NN, double **XX, /*input global Cartesian coordinate*/
+                      double *Shellf, int Symmetry);
+   bool Interp_One_Point(MyList<var> *VarList,
+                         double *XX, /*input global Cartesian coordinate*/
+                         double *Shellf, int Symmetry);
+   void write_Pablo_file_ss(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
+                            char *filename, int sst);
+   double L2Norm(var *vf);
+   void L2Norm7(var **vf, double *norms);
+   void Find_Maximum(MyList<var> *VarList, double *XX, double *Shellf);
+};
+
+#endif /* SHELLPATCH_H */

AMSS_NCKU_source/TwoPunctureABE.C

@@ -1,221 +1,221 @@
-
-#ifdef newc
-#include <algorithm>
-#include <functional>
-#include <vector>
-#include <cstring>
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <cstdio>
-#include <string>
-#include <cmath>
-#include <strstream>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include "TwoPunctures.h"
-
-inline string &lTrim(string &ss)
-{
-  string::iterator p = find_if(ss.begin(), ss.end(), not1(ptr_fun<int, int>(isspace)));
-  ss.erase(ss.begin(), p);
-  return ss;
-}
-inline string &rTrim(string &ss)
-{
-  string::reverse_iterator p = find_if(ss.rbegin(), ss.rend(), not1(ptr_fun<int, int>(isspace)));
-  ss.erase(p.base(), ss.end());
-  return ss;
-}
-inline string &Trim(string &st)
-{
-  lTrim(rTrim(st));
-  return st;
-}
-
-int parse_parts(string str, string &sgrp, string &skey, string &sval, int &ind)
-{
-  int pos1, pos2;
-  string s0;
-
-  ind = 0;
-
-  // remove comments
-  str = str.substr(0, str.find("#"));
-  if (rTrim(str).empty())
-    return 0; // continue;
-
-  // parse {group, key, val}
-  pos1 = str.find("::");
-  pos2 = str.find("=");
-  if (pos1 == string::npos || pos2 == string::npos)
-    return -1;
-
-  s0 = str.substr(0, pos1);
-  sgrp = lTrim(s0);
-  s0 = str.substr(pos1 + 2, pos2 - pos1 - 2);
-  skey = rTrim(s0);
-  s0 = str.substr(pos2 + 1);
-  sval = Trim(s0);
-
-  pos1 = sval.find("\"");
-  pos2 = sval.rfind("\"");
-  if (pos1 != string::npos)
-  {
-    sval = sval.substr(1, pos2 - 1);
-  }
-
-  pos1 = skey.find("[");
-  pos2 = skey.find("]");
-  if (pos1 != string::npos)
-  {
-    s0 = skey.substr(0, pos1);
-    ind = atoi(skey.substr(pos1 + 1, pos2 - pos1 - 1).c_str());
-    skey = s0;
-  }
-
-  return 1;
-}
-//=======================================
-int main(int argc, char *argv[])
-{
-  double mp, mm, b, Mp, Mm, admtol, Newtontol;
-  int nA, nB, nphi, Newtonmaxit;
-  double P_plusx, P_plusy, P_plusz;
-  double P_minusx, P_minusy, P_minusz;
-  double S_plusx, S_plusy, S_plusz;
-  double S_minusx, S_minusy, S_minusz;
-  // read parameter from file
-  {
-    const int LEN = 256;
-    char pline[LEN];
-    string str, sgrp, skey, sval;
-    int sind;
-    const char pname[] = "TwoPunctureinput.par";
-    ifstream inf(pname, ifstream::in);
-    if (!inf.good())
-    {
-      cout << "Can not open parameter file " << pname << endl;
-      exit(0);
-    }
-
-    for (int i = 1; inf.good(); i++)
-    {
-      inf.getline(pline, LEN);
-      str = pline;
-
-      int status = parse_parts(str, sgrp, skey, sval, sind);
-      if (status == -1)
-      {
-        cout << "error reading parameter file " << pname << " in line " << i << endl;
-        exit(0);
-      }
-      else if (status == 0)
-        continue;
-      // we assume input in Brugmann's convention
-      if (sgrp == "ABE")
-      {
-        if (skey == "mm")
-          mm = atof(sval.c_str());
-        else if (skey == "mp")
-          mp = atof(sval.c_str());
-        else if (skey == "b")
-          b = atof(sval.c_str());
-        else if (skey == "P_plusx")
-          P_plusy = -atof(sval.c_str());
-        else if (skey == "P_plusy")
-          P_plusx = atof(sval.c_str());
-        else if (skey == "P_plusz")
-          P_plusz = atof(sval.c_str());
-        else if (skey == "P_minusx")
-          P_minusy = -atof(sval.c_str());
-        else if (skey == "P_minusy")
-          P_minusx = atof(sval.c_str());
-        else if (skey == "P_minusz")
-          P_minusz = atof(sval.c_str());
-        else if (skey == "S_plusx")
-          S_plusy = -atof(sval.c_str());
-        else if (skey == "S_plusy")
-          S_plusx = atof(sval.c_str());
-        else if (skey == "S_plusz")
-          S_plusz = atof(sval.c_str());
-        else if (skey == "S_minusx")
-          S_minusy = -atof(sval.c_str());
-        else if (skey == "S_minusy")
-          S_minusx = atof(sval.c_str());
-        else if (skey == "S_minusz")
-          S_minusz = atof(sval.c_str());
-        else if (skey == "Mp")
-          Mp = atof(sval.c_str());
-        else if (skey == "Mm")
-          Mm = atof(sval.c_str());
-        else if (skey == "admtol")
-          admtol = atof(sval.c_str());
-        else if (skey == "Newtontol")
-          Newtontol = atof(sval.c_str());
-        else if (skey == "nA")
-          nA = atoi(sval.c_str());
-        else if (skey == "nB")
-          nB = atoi(sval.c_str());
-        else if (skey == "nphi")
-          nphi = atoi(sval.c_str());
-        else if (skey == "Newtonmaxit")
-          Newtonmaxit = atoi(sval.c_str());
-      }
-    }
-    inf.close();
-  }
-  // echo parameters
-  {
-    cout << "///////////////////////////////////////////////////////////////" << endl;
-    cout << "     mp     = " << mp << endl;
-    cout << "     mm     = " << mm << endl;
-    cout << "     b      = " << b << endl;
-    cout << "  P_plusx   = " << P_plusx << endl;
-    cout << "  P_plusy   = " << P_plusy << endl;
-    cout << "  P_plusz   = " << P_plusz << endl;
-    cout << "  P_minusx  = " << P_minusx << endl;
-    cout << "  P_minusy  = " << P_minusy << endl;
-    cout << "  P_minusz  = " << P_minusz << endl;
-    cout << "  S_plusx   = " << S_plusx << endl;
-    cout << "  S_plusy   = " << S_plusy << endl;
-    cout << "  S_plusz   = " << S_plusz << endl;
-    cout << "  S_minusx  = " << S_minusx << endl;
-    cout << "  S_minusy  = " << S_minusy << endl;
-    cout << "  S_minusz  = " << S_minusz << endl;
-    cout << "     Mp     = " << Mp << endl;
-    cout << "     Mm     = " << Mm << endl;
-    cout << "   admtol   = " << admtol << endl;
-    cout << " Newtontol  = " << Newtontol << endl;
-    cout << "    nA      = " << nA << endl;
-    cout << "    nB      = " << nB << endl;
-    cout << "   nphi     = " << nphi << endl;
-    cout << "Newtonmaxit = " << Newtonmaxit << endl;
-    cout << "///////////////////////////////////////////////////////////////" << endl;
-  }
-  //===========================the computation body====================================================
-  TwoPunctures *ADM;
-
-  ADM = new TwoPunctures(mp, mm, b, P_plusx, P_plusy, P_plusz, S_plusx, S_plusy, S_plusz,
-                         P_minusx, P_minusy, P_minusz, S_minusx, S_minusy, S_minusz,
-                         nA, nB, nphi, Mp, Mm, admtol, Newtontol, Newtonmaxit);
-  ADM->Solve();
-  ADM->Save("Ansorg.psid");
-
-  delete ADM;
-  //=======================caculation done=============================================================
-  cout << "===============================================================" << endl;
-  cout << "Initial data is successfully producede!!" << endl;
-
-  exit(0);
-}
+
+#ifdef newc
+#include <algorithm>
+#include <functional>
+#include <vector>
+#include <cstring>
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <cstdio>
+#include <string>
+#include <cmath>
+#include <strstream>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include "TwoPunctures.h"
+
+inline string &lTrim(string &ss)
+{
+  string::iterator p = find_if(ss.begin(), ss.end(), not1(ptr_fun<int, int>(isspace)));
+  ss.erase(ss.begin(), p);
+  return ss;
+}
+inline string &rTrim(string &ss)
+{
+  string::reverse_iterator p = find_if(ss.rbegin(), ss.rend(), not1(ptr_fun<int, int>(isspace)));
+  ss.erase(p.base(), ss.end());
+  return ss;
+}
+inline string &Trim(string &st)
+{
+  lTrim(rTrim(st));
+  return st;
+}
+
+int parse_parts(string str, string &sgrp, string &skey, string &sval, int &ind)
+{
+  int pos1, pos2;
+  string s0;
+
+  ind = 0;
+
+  // remove comments
+  str = str.substr(0, str.find("#"));
+  if (rTrim(str).empty())
+    return 0; // continue;
+
+  // parse {group, key, val}
+  pos1 = str.find("::");
+  pos2 = str.find("=");
+  if (pos1 == string::npos || pos2 == string::npos)
+    return -1;
+
+  s0 = str.substr(0, pos1);
+  sgrp = lTrim(s0);
+  s0 = str.substr(pos1 + 2, pos2 - pos1 - 2);
+  skey = rTrim(s0);
+  s0 = str.substr(pos2 + 1);
+  sval = Trim(s0);
+
+  pos1 = sval.find("\"");
+  pos2 = sval.rfind("\"");
+  if (pos1 != string::npos)
+  {
+    sval = sval.substr(1, pos2 - 1);
+  }
+
+  pos1 = skey.find("[");
+  pos2 = skey.find("]");
+  if (pos1 != string::npos)
+  {
+    s0 = skey.substr(0, pos1);
+    ind = atoi(skey.substr(pos1 + 1, pos2 - pos1 - 1).c_str());
+    skey = s0;
+  }
+
+  return 1;
+}
+//=======================================
+int main(int argc, char *argv[])
+{
+  double mp, mm, b, Mp, Mm, admtol, Newtontol;
+  int nA, nB, nphi, Newtonmaxit;
+  double P_plusx, P_plusy, P_plusz;
+  double P_minusx, P_minusy, P_minusz;
+  double S_plusx, S_plusy, S_plusz;
+  double S_minusx, S_minusy, S_minusz;
+  // read parameter from file
+  {
+    const int LEN = 256;
+    char pline[LEN];
+    string str, sgrp, skey, sval;
+    int sind;
+    const char pname[] = "TwoPunctureinput.par";
+    ifstream inf(pname, ifstream::in);
+    if (!inf.good())
+    {
+      cout << "Can not open parameter file " << pname << endl;
+      exit(0);
+    }
+
+    for (int i = 1; inf.good(); i++)
+    {
+      inf.getline(pline, LEN);
+      str = pline;
+
+      int status = parse_parts(str, sgrp, skey, sval, sind);
+      if (status == -1)
+      {
+        cout << "error reading parameter file " << pname << " in line " << i << endl;
+        exit(0);
+      }
+      else if (status == 0)
+        continue;
+      // we assume input in Brugmann's convention
+      if (sgrp == "ABE")
+      {
+        if (skey == "mm")
+          mm = atof(sval.c_str());
+        else if (skey == "mp")
+          mp = atof(sval.c_str());
+        else if (skey == "b")
+          b = atof(sval.c_str());
+        else if (skey == "P_plusx")
+          P_plusy = -atof(sval.c_str());
+        else if (skey == "P_plusy")
+          P_plusx = atof(sval.c_str());
+        else if (skey == "P_plusz")
+          P_plusz = atof(sval.c_str());
+        else if (skey == "P_minusx")
+          P_minusy = -atof(sval.c_str());
+        else if (skey == "P_minusy")
+          P_minusx = atof(sval.c_str());
+        else if (skey == "P_minusz")
+          P_minusz = atof(sval.c_str());
+        else if (skey == "S_plusx")
+          S_plusy = -atof(sval.c_str());
+        else if (skey == "S_plusy")
+          S_plusx = atof(sval.c_str());
+        else if (skey == "S_plusz")
+          S_plusz = atof(sval.c_str());
+        else if (skey == "S_minusx")
+          S_minusy = -atof(sval.c_str());
+        else if (skey == "S_minusy")
+          S_minusx = atof(sval.c_str());
+        else if (skey == "S_minusz")
+          S_minusz = atof(sval.c_str());
+        else if (skey == "Mp")
+          Mp = atof(sval.c_str());
+        else if (skey == "Mm")
+          Mm = atof(sval.c_str());
+        else if (skey == "admtol")
+          admtol = atof(sval.c_str());
+        else if (skey == "Newtontol")
+          Newtontol = atof(sval.c_str());
+        else if (skey == "nA")
+          nA = atoi(sval.c_str());
+        else if (skey == "nB")
+          nB = atoi(sval.c_str());
+        else if (skey == "nphi")
+          nphi = atoi(sval.c_str());
+        else if (skey == "Newtonmaxit")
+          Newtonmaxit = atoi(sval.c_str());
+      }
+    }
+    inf.close();
+  }
+  // echo parameters
+  {
+    cout << "///////////////////////////////////////////////////////////////" << endl;
+    cout << "     mp     = " << mp << endl;
+    cout << "     mm     = " << mm << endl;
+    cout << "     b      = " << b << endl;
+    cout << "  P_plusx   = " << P_plusx << endl;
+    cout << "  P_plusy   = " << P_plusy << endl;
+    cout << "  P_plusz   = " << P_plusz << endl;
+    cout << "  P_minusx  = " << P_minusx << endl;
+    cout << "  P_minusy  = " << P_minusy << endl;
+    cout << "  P_minusz  = " << P_minusz << endl;
+    cout << "  S_plusx   = " << S_plusx << endl;
+    cout << "  S_plusy   = " << S_plusy << endl;
+    cout << "  S_plusz   = " << S_plusz << endl;
+    cout << "  S_minusx  = " << S_minusx << endl;
+    cout << "  S_minusy  = " << S_minusy << endl;
+    cout << "  S_minusz  = " << S_minusz << endl;
+    cout << "     Mp     = " << Mp << endl;
+    cout << "     Mm     = " << Mm << endl;
+    cout << "   admtol   = " << admtol << endl;
+    cout << " Newtontol  = " << Newtontol << endl;
+    cout << "    nA      = " << nA << endl;
+    cout << "    nB      = " << nB << endl;
+    cout << "   nphi     = " << nphi << endl;
+    cout << "Newtonmaxit = " << Newtonmaxit << endl;
+    cout << "///////////////////////////////////////////////////////////////" << endl;
+  }
+  //===========================the computation body====================================================
+  TwoPunctures *ADM;
+
+  ADM = new TwoPunctures(mp, mm, b, P_plusx, P_plusy, P_plusz, S_plusx, S_plusy, S_plusz,
+                         P_minusx, P_minusy, P_minusz, S_minusx, S_minusy, S_minusz,
+                         nA, nB, nphi, Mp, Mm, admtol, Newtontol, Newtonmaxit);
+  ADM->Solve();
+  ADM->Save("Ansorg.psid");
+
+  delete ADM;
+  //=======================caculation done=============================================================
+  cout << "===============================================================" << endl;
+  cout << "Initial data is successfully producede!!" << endl;
+
+  exit(0);
+}

AMSS_NCKU_source/TwoPunctures.h

@@ -1,167 +1,167 @@
-#ifndef TWO_PUNCTURES_H
-#define TWO_PUNCTURES_H
-
-#include <omp.h>
-
-#define StencilSize 19
-#define N_PlaneRelax 1
-#define NRELAX 200
-#define Step_Relax 1
-
-#define Pi 3.14159265358979323846264338328
-#define Pih 1.57079632679489661923132169164 /* Pi/2*/
-#define Piq 0.78539816339744830961566084582 /* Pi/4*/
-
-#define TINY 1.0e-20
-
-class TwoPunctures
-{
-public:
-       typedef struct DERIVS
-       {
-              double *d0, *d1, *d2, *d3, *d11, *d12, *d13, *d22, *d23, *d33;
-       } derivs;
-
-       double *F;
-       derivs u, v;
-
-private:
-       double par_m_plus, par_m_minus, par_b;
-       double par_P_plus[3], par_P_minus[3];
-       double par_S_plus[3], par_S_minus[3];
-
-       int npoints_A, npoints_B, npoints_phi;
-
-       double target_M_plus, target_M_minus;
-
-       double admMass;
-
-       double adm_tol;
-
-       double Newton_tol;
-       int Newton_maxit;
-
-       int ntotal;
-
-       // ===== Precomputed spectral derivative matrices =====
-       double *D1_A, *D2_A;
-       double *D1_B, *D2_B;
-       double *DF1_phi, *DF2_phi;
-
-       // ===== Pre-allocated workspace for LineRelax (per-thread) =====
-       int max_threads;
-       double **ws_diag_be, **ws_e_be, **ws_f_be, **ws_b_be, **ws_x_be;
-       double **ws_l_be, **ws_u_be, **ws_d_be, **ws_y_be;
-       double **ws_diag_al, **ws_e_al, **ws_f_al, **ws_b_al, **ws_x_al;
-       double **ws_l_al, **ws_u_al, **ws_d_al, **ws_y_al;
-
-       struct parameters
-       {
-              int nvar, n1, n2, n3;
-              double b;
-       };
-
-public:
-       TwoPunctures(double mp, double mm, double b, double P_plusx, double P_plusy, double P_plusz,
-                    double S_plusx, double S_plusy, double S_plusz,
-                    double P_minusx, double P_minusy, double P_minusz,
-                    double S_minusx, double S_minusy, double S_minusz,
-                    int nA, int nB, int nphi,
-                    double Mp, double Mm, double admtol, double Newtontol,
-                    int Newtonmaxit);
-       ~TwoPunctures();
-
-       // 02/07: New/modified methods
-       void allocate_workspace();
-       void free_workspace();
-       void precompute_derivative_matrices();
-       void build_cheb_deriv_matrices(int n, double *D1, double *D2);
-       void build_fourier_deriv_matrices(int N, double *DF1, double *DF2);
-       void Derivatives_AB3_MatMul(int nvar, int n1, int n2, int n3, derivs v);
-       void ThomasAlgorithm_ws(int N, double *b, double *a, double *c, double *x, double *q,
-                                double *l, double *u_ws, double *d, double *y);
-       void LineRelax_be_omp(double *dv,
-                         int const i, int const k, int const nvar,
-                         int const n1, int const n2, int const n3,
-                         double const *rhs, int const *ncols, int **cols,
-                         double **JFD, int tid);
-       void LineRelax_al_omp(double *dv,
-                         int const j, int const k, int const nvar,
-                         int const n1, int const n2, int const n3,
-                         double const *rhs, int const *ncols,
-                         int **cols, double **JFD, int tid);
-       void relax_omp(double *dv, int const nvar, int const n1, int const n2, int const n3,
-                  double const *rhs, int const *ncols, int **cols, double **JFD);
-
-       void Solve();
-       void set_initial_guess(derivs v);
-       int index(int i, int j, int k, int l, int a, int b, int c, int d);
-       int *ivector(long nl, long nh);
-       double *dvector(long nl, long nh);
-       int **imatrix(long nrl, long nrh, long ncl, long nch);
-       double **dmatrix(long nrl, long nrh, long ncl, long nch);
-       double ***d3tensor(long nrl, long nrh, long ncl, long nch, long ndl, long ndh);
-       void free_ivector(int *v, long nl, long nh);
-       void free_dvector(double *v, long nl, long nh);
-       void free_imatrix(int **m, long nrl, long nrh, long ncl, long nch);
-       void free_dmatrix(double **m, long nrl, long nrh, long ncl, long nch);
-       void free_d3tensor(double ***t, long nrl, long nrh, long ncl, long nch,
-                          long ndl, long ndh);
-       int minimum2(int i, int j);
-       int minimum3(int i, int j, int k);
-       int maximum2(int i, int j);
-       int maximum3(int i, int j, int k);
-       int pow_int(int mantisse, int exponent);
-       void chebft_Zeros(double u[], int n, int inv);
-       void chebft_Extremes(double u[], int n, int inv);
-       void chder(double *c, double *cder, int n);
-       double chebev(double a, double b, double c[], int m, double x);
-       void fourft(double *u, int N, int inv);
-       void fourder(double u[], double du[], int N);
-       void fourder2(double u[], double d2u[], int N);
-       double fourev(double *u, int N, double x);
-       double norm1(double *v, int n);
-       double norm2(double *v, int n);
-       double scalarproduct(double *v, double *w, int n);
-       double PunctIntPolAtArbitPosition(int ivar, int nvar, int n1,
-                                         int n2, int n3, derivs v, double x, double y,
-                                         double z);
-       double PunctEvalAtArbitPosition(double *v, int ivar, double A, double B, double phi,
-                                       int nvar, int n1, int n2, int n3);
-       void AB_To_XR(int nvar, double A, double B, double *X, double *R,
-                     derivs U);
-       void C_To_c(int nvar, double X, double R, double *x, double *r,
-                   derivs U);
-       void rx3_To_xyz(int nvar, double x, double r, double phi,
-                       double *y, double *z, derivs U);
-       void Derivatives_AB3(int nvar, int n1, int n2, int n3, derivs v);
-       void Newton(int const nvar, int const n1, int const n2, int const n3,
-                   derivs v, double const tol, int const itmax);
-       void F_of_v(int nvar, int n1, int n2, int n3, derivs v, double *F,
-                   derivs u);
-       double norm_inf(double const *F, int const ntotal);
-       int bicgstab(int const nvar, int const n1, int const n2, int const n3,
-                    derivs v, derivs dv, int const itmax, double const tol,
-                    double *normres);
-       void allocate_derivs(derivs *v, int n);
-       void free_derivs(derivs *v, int n);
-       int Index(int ivar, int i, int j, int k, int nvar, int n1, int n2, int n3);
-       void NonLinEquations(double rho_adm, double A, double B, double X, double R, double x, double r, double phi,
-                            double y, double z, derivs U, double *values);
-       double BY_KKofxyz(double x, double y, double z);
-       void SetMatrix_JFD(int nvar, int n1, int n2, int n3, derivs u, int *ncols, int **cols, double **Matrix);
-       void J_times_dv(int nvar, int n1, int n2, int n3, derivs dv, double *Jdv, derivs u);
-       void JFD_times_dv(int i, int j, int k, int nvar, int n1, int n2,
-                         int n3, derivs dv, derivs u, double *values);
-       void LinEquations(double A, double B, double X, double R,
-                         double x, double r, double phi,
-                         double y, double z, derivs dU, derivs U, double *values);
-       void ThomasAlgorithm(int N, double *b, double *a, double *c, double *x, double *q);
-       void Save(char *fname);
-       // provided by Vasileios Paschalidis (vpaschal@illinois.edu)
-       double Spec_IntPolABphiFast(parameters par, double *v, int ivar, double A, double B, double phi);
-       double Spec_IntPolFast(parameters par, int ivar, double *v, double x, double y, double z);
-       void SpecCoef(parameters par, int ivar, double *v, double *cf);
-};
-
+#ifndef TWO_PUNCTURES_H
+#define TWO_PUNCTURES_H
+
+#include <omp.h>
+
+#define StencilSize 19
+#define N_PlaneRelax 1
+#define NRELAX 200
+#define Step_Relax 1
+
+#define Pi 3.14159265358979323846264338328
+#define Pih 1.57079632679489661923132169164 /* Pi/2*/
+#define Piq 0.78539816339744830961566084582 /* Pi/4*/
+
+#define TINY 1.0e-20
+
+class TwoPunctures
+{
+public:
+       typedef struct DERIVS
+       {
+              double *d0, *d1, *d2, *d3, *d11, *d12, *d13, *d22, *d23, *d33;
+       } derivs;
+
+       double *F;
+       derivs u, v;
+
+private:
+       double par_m_plus, par_m_minus, par_b;
+       double par_P_plus[3], par_P_minus[3];
+       double par_S_plus[3], par_S_minus[3];
+
+       int npoints_A, npoints_B, npoints_phi;
+
+       double target_M_plus, target_M_minus;
+
+       double admMass;
+
+       double adm_tol;
+
+       double Newton_tol;
+       int Newton_maxit;
+
+       int ntotal;
+
+       // ===== Precomputed spectral derivative matrices =====
+       double *D1_A, *D2_A;
+       double *D1_B, *D2_B;
+       double *DF1_phi, *DF2_phi;
+
+       // ===== Pre-allocated workspace for LineRelax (per-thread) =====
+       int max_threads;
+       double **ws_diag_be, **ws_e_be, **ws_f_be, **ws_b_be, **ws_x_be;
+       double **ws_l_be, **ws_u_be, **ws_d_be, **ws_y_be;
+       double **ws_diag_al, **ws_e_al, **ws_f_al, **ws_b_al, **ws_x_al;
+       double **ws_l_al, **ws_u_al, **ws_d_al, **ws_y_al;
+
+       struct parameters
+       {
+              int nvar, n1, n2, n3;
+              double b;
+       };
+
+public:
+       TwoPunctures(double mp, double mm, double b, double P_plusx, double P_plusy, double P_plusz,
+                    double S_plusx, double S_plusy, double S_plusz,
+                    double P_minusx, double P_minusy, double P_minusz,
+                    double S_minusx, double S_minusy, double S_minusz,
+                    int nA, int nB, int nphi,
+                    double Mp, double Mm, double admtol, double Newtontol,
+                    int Newtonmaxit);
+       ~TwoPunctures();
+
+       // 02/07: New/modified methods
+       void allocate_workspace();
+       void free_workspace();
+       void precompute_derivative_matrices();
+       void build_cheb_deriv_matrices(int n, double *D1, double *D2);
+       void build_fourier_deriv_matrices(int N, double *DF1, double *DF2);
+       void Derivatives_AB3_MatMul(int nvar, int n1, int n2, int n3, derivs v);
+       void ThomasAlgorithm_ws(int N, double *b, double *a, double *c, double *x, double *q,
+                                double *l, double *u_ws, double *d, double *y);
+       void LineRelax_be_omp(double *dv,
+                         int const i, int const k, int const nvar,
+                         int const n1, int const n2, int const n3,
+                         double const *rhs, int const *ncols, int **cols,
+                         double **JFD, int tid);
+       void LineRelax_al_omp(double *dv,
+                         int const j, int const k, int const nvar,
+                         int const n1, int const n2, int const n3,
+                         double const *rhs, int const *ncols,
+                         int **cols, double **JFD, int tid);
+       void relax_omp(double *dv, int const nvar, int const n1, int const n2, int const n3,
+                  double const *rhs, int const *ncols, int **cols, double **JFD);
+
+       void Solve();
+       void set_initial_guess(derivs v);
+       int index(int i, int j, int k, int l, int a, int b, int c, int d);
+       int *ivector(long nl, long nh);
+       double *dvector(long nl, long nh);
+       int **imatrix(long nrl, long nrh, long ncl, long nch);
+       double **dmatrix(long nrl, long nrh, long ncl, long nch);
+       double ***d3tensor(long nrl, long nrh, long ncl, long nch, long ndl, long ndh);
+       void free_ivector(int *v, long nl, long nh);
+       void free_dvector(double *v, long nl, long nh);
+       void free_imatrix(int **m, long nrl, long nrh, long ncl, long nch);
+       void free_dmatrix(double **m, long nrl, long nrh, long ncl, long nch);
+       void free_d3tensor(double ***t, long nrl, long nrh, long ncl, long nch,
+                          long ndl, long ndh);
+       int minimum2(int i, int j);
+       int minimum3(int i, int j, int k);
+       int maximum2(int i, int j);
+       int maximum3(int i, int j, int k);
+       int pow_int(int mantisse, int exponent);
+       void chebft_Zeros(double u[], int n, int inv);
+       void chebft_Extremes(double u[], int n, int inv);
+       void chder(double *c, double *cder, int n);
+       double chebev(double a, double b, double c[], int m, double x);
+       void fourft(double *u, int N, int inv);
+       void fourder(double u[], double du[], int N);
+       void fourder2(double u[], double d2u[], int N);
+       double fourev(double *u, int N, double x);
+       double norm1(double *v, int n);
+       double norm2(double *v, int n);
+       double scalarproduct(double *v, double *w, int n);
+       double PunctIntPolAtArbitPosition(int ivar, int nvar, int n1,
+                                         int n2, int n3, derivs v, double x, double y,
+                                         double z);
+       double PunctEvalAtArbitPosition(double *v, int ivar, double A, double B, double phi,
+                                       int nvar, int n1, int n2, int n3);
+       void AB_To_XR(int nvar, double A, double B, double *X, double *R,
+                     derivs U);
+       void C_To_c(int nvar, double X, double R, double *x, double *r,
+                   derivs U);
+       void rx3_To_xyz(int nvar, double x, double r, double phi,
+                       double *y, double *z, derivs U);
+       void Derivatives_AB3(int nvar, int n1, int n2, int n3, derivs v);
+       void Newton(int const nvar, int const n1, int const n2, int const n3,
+                   derivs v, double const tol, int const itmax);
+       void F_of_v(int nvar, int n1, int n2, int n3, derivs v, double *F,
+                   derivs u);
+       double norm_inf(double const *F, int const ntotal);
+       int bicgstab(int const nvar, int const n1, int const n2, int const n3,
+                    derivs v, derivs dv, int const itmax, double const tol,
+                    double *normres);
+       void allocate_derivs(derivs *v, int n);
+       void free_derivs(derivs *v, int n);
+       int Index(int ivar, int i, int j, int k, int nvar, int n1, int n2, int n3);
+       void NonLinEquations(double rho_adm, double A, double B, double X, double R, double x, double r, double phi,
+                            double y, double z, derivs U, double *values);
+       double BY_KKofxyz(double x, double y, double z);
+       void SetMatrix_JFD(int nvar, int n1, int n2, int n3, derivs u, int *ncols, int **cols, double **Matrix);
+       void J_times_dv(int nvar, int n1, int n2, int n3, derivs dv, double *Jdv, derivs u);
+       void JFD_times_dv(int i, int j, int k, int nvar, int n1, int n2,
+                         int n3, derivs dv, derivs u, double *values);
+       void LinEquations(double A, double B, double X, double R,
+                         double x, double r, double phi,
+                         double y, double z, derivs dU, derivs U, double *values);
+       void ThomasAlgorithm(int N, double *b, double *a, double *c, double *x, double *q);
+       void Save(char *fname);
+       // provided by Vasileios Paschalidis (vpaschal@illinois.edu)
+       double Spec_IntPolABphiFast(parameters par, double *v, int ivar, double A, double B, double phi);
+       double Spec_IntPolFast(parameters par, int ivar, double *v, double x, double y, double z);
+       void SpecCoef(parameters par, int ivar, double *v, double *cf);
+};
+
 #endif /* TWO_PUNCTURES_H */

AMSS_NCKU_source/Z4c_class.h

@@ -1,64 +1,64 @@
-
-#ifndef Z4c_CLASS_H
-#define Z4c_CLASS_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#include "cgh.h"
-#include "ShellPatch.h"
-#include "misc.h"
-#include "var.h"
-#include "MyList.h"
-#include "monitor.h"
-#include "surface_integral.h"
-
-#include "macrodef.h"
-
-#ifdef USE_GPU
-#include "bssn_gpu_class.h"
-#else
-#include "bssn_class.h"
-#endif
-
-class Z4c_class : public bssn_class
-{
-public:
-     Z4c_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
-               int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
-               int a_levi, int maxli, int decni, double maxrexi, double drexi);
-     ~Z4c_class();
-
-     void Initialize();
-     void Check_extrop();
-     // Since we have set zero to variables at very begining
-     // we can neglect TZ for initial data setting
-     void Step(int lev, int YN);
-     void Interp_Constraint();
-     void Constraint_Out();
-     void Compute_Constraint();
-
-protected:
-     var *TZo;
-     var *TZ0;
-     var *TZ;
-     var *TZ1;
-     var *TZ_rhs;
-};
-#endif /* Z4c_CLASS_H */
+
+#ifndef Z4c_CLASS_H
+#define Z4c_CLASS_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <string>
+#include <cmath>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include <mpi.h>
+
+#include "cgh.h"
+#include "ShellPatch.h"
+#include "misc.h"
+#include "var.h"
+#include "MyList.h"
+#include "monitor.h"
+#include "surface_integral.h"
+
+#include "macrodef.h"
+
+#ifdef USE_GPU
+#include "bssn_gpu_class.h"
+#else
+#include "bssn_class.h"
+#endif
+
+class Z4c_class : public bssn_class
+{
+public:
+     Z4c_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
+               int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
+               int a_levi, int maxli, int decni, double maxrexi, double drexi);
+     ~Z4c_class();
+
+     void Initialize();
+     void Check_extrop();
+     // Since we have set zero to variables at very begining
+     // we can neglect TZ for initial data setting
+     void Step(int lev, int YN);
+     void Interp_Constraint();
+     void Constraint_Out();
+     void Compute_Constraint();
+
+protected:
+     var *TZo;
+     var *TZ0;
+     var *TZ;
+     var *TZ1;
+     var *TZ_rhs;
+};
+#endif /* Z4c_CLASS_H */

AMSS_NCKU_source/adm_constraint.f90

@@ -1,382 +1,382 @@
-
-!-------------------------------------------------------------------------------!
-! computed constraint for ADM formalism                                         !
-!-------------------------------------------------------------------------------!
-  subroutine constraint_adm(ex, X, Y, Z,&
-               dxx,gxy,gxz,dyy,gyz,dzz, &
-               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz, &
-               Lap,Sfx,Sfy,Sfz,rho,Sx,Sy,Sz,&
-               ham_Res, movx_Res, movy_Res, movz_Res, &
-               Symmetry)
-
-  implicit none
-!~~~~~~> Input parameters:
-
-  integer,intent(in ):: ex(1:3),symmetry
-  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3))
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Lap,Sfx,Sfy,Sfz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: rho,Sx,Sy,Sz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: ham_Res, movx_Res, movy_Res, movz_Res
-!~~~~~~> Other variables:
-!  inverse metric
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
-! first order derivative of metric, @_k g_ij
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyx,gyzx,gzzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyy,gyzy,gzzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyz,gyzz,gzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz,trK,fx,fy,fz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamxxx, Gamxxy, Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamxyy, Gamxyz, Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamyxx, Gamyxy, Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamyyy, Gamyyz, Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamzxx, Gamzxy, Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamzyy, Gamzyz, Gamzzz
-
-  integer, parameter :: NO_SYMM = 0, EQUATORIAL = 1, OCTANT = 2
-  real*8, parameter :: ZERO = 0.D0, HALF = 0.5d0, ONE = 1.d0, TWO = 2.d0, FOUR = 4.d0
-  real*8, parameter :: F2o3 = 2.d0/3.d0, F8 = 8.d0, F16 = 1.6d1, SIX = 6.d0
-  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
-  real*8            :: PI
-
-  call adm_ricci_gamma(ex, X, Y, Z,                        &
-               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
-               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
-               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
-               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
-               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
-               Symmetry)
-
-  PI = dacos(-ONE)
-
-  gxx = dxx + ONE
-  gyy = dyy + ONE
-  gzz = dzz + ONE
-! invert 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
-
-  trK =          gupxx * Kxx + gupyy * Kyy + gupzz * Kzz &
-        + TWO * (gupxy * Kxy + gupxz * Kxz + gupyz * Kyz)
-
-! ham_Res = trR + K^2 - K_ij * K^ij - 16 * PI * rho
-  ham_Res =   gupxx * Rxx + gupyy * Ryy + gupzz * Rzz + &
-        TWO* ( gupxy * Rxy + gupxz * Rxz + gupyz * Ryz )
-
-  ham_Res = ham_Res + trK * trK -(&
-       gupxx * ( &
-       gupxx * Kxx * Kxx + gupyy * Kxy * Kxy + gupzz * Kxz * Kxz + &
-       TWO * (gupxy * Kxx * Kxy + gupxz * Kxx * Kxz + gupyz * Kxy * Kxz) ) + &
-       gupyy * ( &
-       gupxx * Kxy * Kxy + gupyy * Kyy * Kyy + gupzz * Kyz * Kyz + &
-       TWO * (gupxy * Kxy * Kyy + gupxz * Kxy * Kyz + gupyz * Kyy * Kyz) ) + &
-       gupzz * ( &
-       gupxx * Kxz * Kxz + gupyy * Kyz * Kyz + gupzz * Kzz * Kzz + &
-       TWO * (gupxy * Kxz * Kyz + gupxz * Kxz * Kzz + gupyz * Kyz * Kzz) ) + &
-       TWO * ( &
-       gupxy * ( &
-       gupxx * Kxx * Kxy + gupyy * Kxy * Kyy + gupzz * Kxz * Kyz + &
-       gupxy * (Kxx * Kyy + Kxy * Kxy) + &
-       gupxz * (Kxx * Kyz + Kxz * Kxy) + &
-       gupyz * (Kxy * Kyz + Kxz * Kyy) ) + &
-       gupxz * ( &
-       gupxx * Kxx * Kxz + gupyy * Kxy * Kyz + gupzz * Kxz * Kzz + &
-       gupxy * (Kxx * Kyz + Kxy * Kxz) + &
-       gupxz * (Kxx * Kzz + Kxz * Kxz) + &
-       gupyz * (Kxy * Kzz + Kxz * Kyz) ) + &
-       gupyz * ( &
-       gupxx * Kxy * Kxz + gupyy * Kyy * Kyz + gupzz * Kyz * Kzz + &
-       gupxy * (Kxy * Kyz + Kyy * Kxz) + &
-       gupxz * (Kxy * Kzz + Kyz * Kxz) + &
-       gupyz * (Kyy * Kzz + Kyz * Kyz) ) ))- F16 * PI * rho
-
-! mov_Res_j = gupkj*D_k K_ij - d_j trK - 8 PI s_j where D respect to physical metric
-! store D_i K_jk
-  call fderivs(ex,Kxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,Kxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
-  call fderivs(ex,Kxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
-  call fderivs(ex,Kyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,Kyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
-  call fderivs(ex,Kzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-
-  gxxx = gxxx - (  Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz &
-                 + Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz)
-  gxyx = gxyx - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
-                 + Gamxxx * Kxy + Gamyxx * Kyy + Gamzxx * Kyz)
-  gxzx = gxzx - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
-                 + Gamxxx * Kxz + Gamyxx * Kyz + Gamzxx * Kzz)
-  gyyx = gyyx - (  Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz &
-                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
-  gyzx = gyzx - (  Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz &
-                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
-  gzzx = gzzx - (  Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz &
-                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
-  gxxy = gxxy - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
-                 + Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz)
-  gxyy = gxyy - (  Gamxyy * Kxx + Gamyyy * Kxy + Gamzyy * Kxz &
-                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
-  gxzy = gxzy - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
-                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
-  gyyy = gyyy - (  Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz &
-                 + Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz)
-  gyzy = gyzy - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
-                 + Gamxyy * Kxz + Gamyyy * Kyz + Gamzyy * Kzz)
-  gzzy = gzzy - (  Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz &
-                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
-  gxxz = gxxz - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
-                 + Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz)
-  gxyz = gxyz - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
-                 + Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz)
-  gxzz = gxzz - (  Gamxzz * Kxx + Gamyzz * Kxy + Gamzzz * Kxz &
-                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
-  gyyz = gyyz - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
-                 + Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz)
-  gyzz = gyzz - (  Gamxzz * Kxy + Gamyzz * Kyy + Gamzzz * Kyz &
-                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
-  gzzz = gzzz - (  Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz &
-                 + Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz)
-movx_Res = gupxx*gxxx + gupyy*gxyy + gupzz*gxzz &
-          +gupxy*gxyx + gupxz*gxzx + gupyz*gxzy &
-          +gupxy*gxxy + gupxz*gxxz + gupyz*gxyz
-movy_Res = gupxx*gxyx + gupyy*gyyy + gupzz*gyzz &
-          +gupxy*gyyx + gupxz*gyzx + gupyz*gyzy &
-          +gupxy*gxyy + gupxz*gxyz + gupyz*gyyz
-movz_Res = gupxx*gxzx + gupyy*gyzy + gupzz*gzzz &
-          +gupxy*gyzx + gupxz*gzzx + gupyz*gzzy &
-          +gupxy*gxzy + gupxz*gxzz + gupyz*gyzz
-
-  call fderivs(ex,trK,fx,fy,fz,X,Y,Z,SYM,SYM,SYM,Symmetry,0)
-
-movx_Res = movx_Res - fx - F8*PI*sx
-movy_Res = movy_Res - fy - F8*PI*sy
-movz_Res = movz_Res - fz - F8*PI*sz
-
-  return
-
-  end subroutine constraint_adm
-!-------------------------------------------------------------------------------!
-! computed constraint for ADM formalism for shell                              !
-!-------------------------------------------------------------------------------!
-  subroutine constraint_adm_ss(ex,crho,sigma,R, X, Y, Z,&
-               drhodx, drhody, drhodz,                                         &
-               dsigmadx,dsigmady,dsigmadz,                                     &
-               dRdx,dRdy,dRdz,                                                 &
-               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
-               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
-               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
-               dxx,gxy,gxz,dyy,gyz,dzz, &
-               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz, &
-               Lap,Sfx,Sfy,Sfz,rho,Sx,Sy,Sz,&
-               Gamxxx, Gamxxy, Gamxxz,Gamxyy, Gamxyz, Gamxzz, &
-               Gamyxx, Gamyxy, Gamyxz,Gamyyy, Gamyyz, Gamyzz, &
-               Gamzxx, Gamzxy, Gamzxz,Gamzyy, Gamzyz, Gamzzz, &
-               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz, &
-               ham_Res, movx_Res, movy_Res, movz_Res, &
-               Symmetry,Lev,sst)
-
-  implicit none
-!~~~~~~> Input parameters:
-
-  integer,intent(in ):: ex(1:3),symmetry,Lev,sst
-  double precision,intent(in),dimension(ex(1))::crho
-  double precision,intent(in),dimension(ex(2))::sigma
-  double precision,intent(in),dimension(ex(3))::R
-  real*8, intent(in ),dimension(ex(1),ex(2),ex(3)):: X,Y,Z
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodx, drhody, drhodz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadx,dsigmady,dsigmadz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdx,dRdy,dRdz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Lap,Sfx,Sfy,Sfz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: rho,Sx,Sy,Sz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
-! second kind of Christofel symble Gamma^i_jk respect to physical metric
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: ham_Res, movx_Res, movy_Res, movz_Res
-!~~~~~~> Other variables:
-!  inverse metric
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
-! first order derivative of metric, @_k g_ij
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyx,gyzx,gzzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyy,gyzy,gzzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyz,gyzz,gzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz,trK,fx,fy,fz
-
-  integer, parameter :: NO_SYMM = 0, EQUATORIAL = 1, OCTANT = 2
-  real*8, parameter :: ZERO = 0.D0, HALF = 0.5d0, ONE = 1.d0, TWO = 2.d0, FOUR = 4.d0
-  real*8, parameter :: F2o3 = 2.d0/3.d0, F8 = 8.d0, F16 = 1.6d1, SIX = 6.d0
-  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
-  real*8            :: PI
-
-  call adm_ricci_gamma_ss(ex,crho,sigma,R,X, Y, Z,                      &
-               drhodx, drhody, drhodz,                                         &
-               dsigmadx,dsigmady,dsigmadz,                                     &
-               dRdx,dRdy,dRdz,                                                 &
-               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
-               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
-               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
-               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
-               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
-               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
-               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
-               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
-               Symmetry,Lev,sst)
-
-  PI = dacos(-ONE)
-
-  gxx = dxx + ONE
-  gyy = dyy + ONE
-  gzz = dzz + ONE
-! invert 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
-
-  trK =          gupxx * Kxx + gupyy * Kyy + gupzz * Kzz &
-        + TWO * (gupxy * Kxy + gupxz * Kxz + gupyz * Kyz)
-
-! ham_Res = trR + K^2 - K_ij * K^ij - 16 * PI * rho
-  ham_Res =   gupxx * Rxx + gupyy * Ryy + gupzz * Rzz + &
-        TWO* ( gupxy * Rxy + gupxz * Rxz + gupyz * Ryz )
-
-  ham_Res = ham_Res + trK * trK -(&
-       gupxx * ( &
-       gupxx * Kxx * Kxx + gupyy * Kxy * Kxy + gupzz * Kxz * Kxz + &
-       TWO * (gupxy * Kxx * Kxy + gupxz * Kxx * Kxz + gupyz * Kxy * Kxz) ) + &
-       gupyy * ( &
-       gupxx * Kxy * Kxy + gupyy * Kyy * Kyy + gupzz * Kyz * Kyz + &
-       TWO * (gupxy * Kxy * Kyy + gupxz * Kxy * Kyz + gupyz * Kyy * Kyz) ) + &
-       gupzz * ( &
-       gupxx * Kxz * Kxz + gupyy * Kyz * Kyz + gupzz * Kzz * Kzz + &
-       TWO * (gupxy * Kxz * Kyz + gupxz * Kxz * Kzz + gupyz * Kyz * Kzz) ) + &
-       TWO * ( &
-       gupxy * ( &
-       gupxx * Kxx * Kxy + gupyy * Kxy * Kyy + gupzz * Kxz * Kyz + &
-       gupxy * (Kxx * Kyy + Kxy * Kxy) + &
-       gupxz * (Kxx * Kyz + Kxz * Kxy) + &
-       gupyz * (Kxy * Kyz + Kxz * Kyy) ) + &
-       gupxz * ( &
-       gupxx * Kxx * Kxz + gupyy * Kxy * Kyz + gupzz * Kxz * Kzz + &
-       gupxy * (Kxx * Kyz + Kxy * Kxz) + &
-       gupxz * (Kxx * Kzz + Kxz * Kxz) + &
-       gupyz * (Kxy * Kzz + Kxz * Kyz) ) + &
-       gupyz * ( &
-       gupxx * Kxy * Kxz + gupyy * Kyy * Kyz + gupzz * Kyz * Kzz + &
-       gupxy * (Kxy * Kyz + Kyy * Kxz) + &
-       gupxz * (Kxy * Kzz + Kyz * Kxz) + &
-       gupyz * (Kyy * Kzz + Kyz * Kyz) ) ))- F16 * PI * rho
-
-! mov_Res_j = gupkj*D_k K_ij - d_j trK - 8 PI s_j where D respect to physical metric
-! store D_i K_jk
-  call fderivs_shc(ex,Kxx,gxxx,gxxy,gxxz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,Kxy,gxyx,gxyy,gxyz,crho,sigma,R,ANTI,ANTI,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,Kxz,gxzx,gxzy,gxzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,         &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,Kyy,gyyx,gyyy,gyyz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,Kyz,gyzx,gyzy,gyzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,         &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,Kzz,gzzx,gzzy,gzzz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-
-  gxxx = gxxx - (  Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz &
-                 + Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz)
-  gxyx = gxyx - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
-                 + Gamxxx * Kxy + Gamyxx * Kyy + Gamzxx * Kyz)
-  gxzx = gxzx - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
-                 + Gamxxx * Kxz + Gamyxx * Kyz + Gamzxx * Kzz)
-  gyyx = gyyx - (  Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz &
-                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
-  gyzx = gyzx - (  Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz &
-                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
-  gzzx = gzzx - (  Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz &
-                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
-  gxxy = gxxy - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
-                 + Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz)
-  gxyy = gxyy - (  Gamxyy * Kxx + Gamyyy * Kxy + Gamzyy * Kxz &
-                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
-  gxzy = gxzy - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
-                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
-  gyyy = gyyy - (  Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz &
-                 + Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz)
-  gyzy = gyzy - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
-                 + Gamxyy * Kxz + Gamyyy * Kyz + Gamzyy * Kzz)
-  gzzy = gzzy - (  Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz &
-                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
-  gxxz = gxxz - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
-                 + Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz)
-  gxyz = gxyz - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
-                 + Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz)
-  gxzz = gxzz - (  Gamxzz * Kxx + Gamyzz * Kxy + Gamzzz * Kxz &
-                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
-  gyyz = gyyz - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
-                 + Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz)
-  gyzz = gyzz - (  Gamxzz * Kxy + Gamyzz * Kyy + Gamzzz * Kyz &
-                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
-  gzzz = gzzz - (  Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz &
-                 + Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz)
-movx_Res = gupxx*gxxx + gupyy*gxyy + gupzz*gxzz &
-          +gupxy*gxyx + gupxz*gxzx + gupyz*gxzy &
-          +gupxy*gxxy + gupxz*gxxz + gupyz*gxyz
-movy_Res = gupxx*gxyx + gupyy*gyyy + gupzz*gyzz &
-          +gupxy*gyyx + gupxz*gyzx + gupyz*gyzy &
-          +gupxy*gxyy + gupxz*gxyz + gupyz*gyyz
-movz_Res = gupxx*gxzx + gupyy*gyzy + gupzz*gzzz &
-          +gupxy*gyzx + gupxz*gzzx + gupyz*gzzy &
-          +gupxy*gxzy + gupxz*gxzz + gupyz*gyzz
-
-  call fderivs_shc(ex,trK,fx,fy,fz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,                &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-
-movx_Res = movx_Res - fx - F8*PI*sx
-movy_Res = movy_Res - fy - F8*PI*sy
-movz_Res = movz_Res - fz - F8*PI*sz
-
-  return
-
-  end subroutine constraint_adm_ss
+
+!-------------------------------------------------------------------------------!
+! computed constraint for ADM formalism                                         !
+!-------------------------------------------------------------------------------!
+  subroutine constraint_adm(ex, X, Y, Z,&
+               dxx,gxy,gxz,dyy,gyz,dzz, &
+               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz, &
+               Lap,Sfx,Sfy,Sfz,rho,Sx,Sy,Sz,&
+               ham_Res, movx_Res, movy_Res, movz_Res, &
+               Symmetry)
+
+  implicit none
+!~~~~~~> Input parameters:
+
+  integer,intent(in ):: ex(1:3),symmetry
+  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3))
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Lap,Sfx,Sfy,Sfz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: rho,Sx,Sy,Sz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: ham_Res, movx_Res, movy_Res, movz_Res
+!~~~~~~> Other variables:
+!  inverse metric
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
+! first order derivative of metric, @_k g_ij
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyx,gyzx,gzzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyy,gyzy,gzzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyz,gyzz,gzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz,trK,fx,fy,fz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamxxx, Gamxxy, Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamxyy, Gamxyz, Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamyxx, Gamyxy, Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamyyy, Gamyyz, Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamzxx, Gamzxy, Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Gamzyy, Gamzyz, Gamzzz
+
+  integer, parameter :: NO_SYMM = 0, EQUATORIAL = 1, OCTANT = 2
+  real*8, parameter :: ZERO = 0.D0, HALF = 0.5d0, ONE = 1.d0, TWO = 2.d0, FOUR = 4.d0
+  real*8, parameter :: F2o3 = 2.d0/3.d0, F8 = 8.d0, F16 = 1.6d1, SIX = 6.d0
+  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
+  real*8            :: PI
+
+  call adm_ricci_gamma(ex, X, Y, Z,                        &
+               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
+               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
+               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
+               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
+               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
+               Symmetry)
+
+  PI = dacos(-ONE)
+
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
+! invert 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
+
+  trK =          gupxx * Kxx + gupyy * Kyy + gupzz * Kzz &
+        + TWO * (gupxy * Kxy + gupxz * Kxz + gupyz * Kyz)
+
+! ham_Res = trR + K^2 - K_ij * K^ij - 16 * PI * rho
+  ham_Res =   gupxx * Rxx + gupyy * Ryy + gupzz * Rzz + &
+        TWO* ( gupxy * Rxy + gupxz * Rxz + gupyz * Ryz )
+
+  ham_Res = ham_Res + trK * trK -(&
+       gupxx * ( &
+       gupxx * Kxx * Kxx + gupyy * Kxy * Kxy + gupzz * Kxz * Kxz + &
+       TWO * (gupxy * Kxx * Kxy + gupxz * Kxx * Kxz + gupyz * Kxy * Kxz) ) + &
+       gupyy * ( &
+       gupxx * Kxy * Kxy + gupyy * Kyy * Kyy + gupzz * Kyz * Kyz + &
+       TWO * (gupxy * Kxy * Kyy + gupxz * Kxy * Kyz + gupyz * Kyy * Kyz) ) + &
+       gupzz * ( &
+       gupxx * Kxz * Kxz + gupyy * Kyz * Kyz + gupzz * Kzz * Kzz + &
+       TWO * (gupxy * Kxz * Kyz + gupxz * Kxz * Kzz + gupyz * Kyz * Kzz) ) + &
+       TWO * ( &
+       gupxy * ( &
+       gupxx * Kxx * Kxy + gupyy * Kxy * Kyy + gupzz * Kxz * Kyz + &
+       gupxy * (Kxx * Kyy + Kxy * Kxy) + &
+       gupxz * (Kxx * Kyz + Kxz * Kxy) + &
+       gupyz * (Kxy * Kyz + Kxz * Kyy) ) + &
+       gupxz * ( &
+       gupxx * Kxx * Kxz + gupyy * Kxy * Kyz + gupzz * Kxz * Kzz + &
+       gupxy * (Kxx * Kyz + Kxy * Kxz) + &
+       gupxz * (Kxx * Kzz + Kxz * Kxz) + &
+       gupyz * (Kxy * Kzz + Kxz * Kyz) ) + &
+       gupyz * ( &
+       gupxx * Kxy * Kxz + gupyy * Kyy * Kyz + gupzz * Kyz * Kzz + &
+       gupxy * (Kxy * Kyz + Kyy * Kxz) + &
+       gupxz * (Kxy * Kzz + Kyz * Kxz) + &
+       gupyz * (Kyy * Kzz + Kyz * Kyz) ) ))- F16 * PI * rho
+
+! mov_Res_j = gupkj*D_k K_ij - d_j trK - 8 PI s_j where D respect to physical metric
+! store D_i K_jk
+  call fderivs(ex,Kxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+  call fderivs(ex,Kxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
+  call fderivs(ex,Kxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
+  call fderivs(ex,Kyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+  call fderivs(ex,Kyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
+  call fderivs(ex,Kzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+
+  gxxx = gxxx - (  Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz &
+                 + Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz)
+  gxyx = gxyx - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
+                 + Gamxxx * Kxy + Gamyxx * Kyy + Gamzxx * Kyz)
+  gxzx = gxzx - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
+                 + Gamxxx * Kxz + Gamyxx * Kyz + Gamzxx * Kzz)
+  gyyx = gyyx - (  Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz &
+                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
+  gyzx = gyzx - (  Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz &
+                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
+  gzzx = gzzx - (  Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz &
+                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
+  gxxy = gxxy - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
+                 + Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz)
+  gxyy = gxyy - (  Gamxyy * Kxx + Gamyyy * Kxy + Gamzyy * Kxz &
+                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
+  gxzy = gxzy - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
+                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
+  gyyy = gyyy - (  Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz &
+                 + Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz)
+  gyzy = gyzy - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
+                 + Gamxyy * Kxz + Gamyyy * Kyz + Gamzyy * Kzz)
+  gzzy = gzzy - (  Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz &
+                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
+  gxxz = gxxz - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
+                 + Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz)
+  gxyz = gxyz - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
+                 + Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz)
+  gxzz = gxzz - (  Gamxzz * Kxx + Gamyzz * Kxy + Gamzzz * Kxz &
+                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
+  gyyz = gyyz - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
+                 + Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz)
+  gyzz = gyzz - (  Gamxzz * Kxy + Gamyzz * Kyy + Gamzzz * Kyz &
+                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
+  gzzz = gzzz - (  Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz &
+                 + Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz)
+movx_Res = gupxx*gxxx + gupyy*gxyy + gupzz*gxzz &
+          +gupxy*gxyx + gupxz*gxzx + gupyz*gxzy &
+          +gupxy*gxxy + gupxz*gxxz + gupyz*gxyz
+movy_Res = gupxx*gxyx + gupyy*gyyy + gupzz*gyzz &
+          +gupxy*gyyx + gupxz*gyzx + gupyz*gyzy &
+          +gupxy*gxyy + gupxz*gxyz + gupyz*gyyz
+movz_Res = gupxx*gxzx + gupyy*gyzy + gupzz*gzzz &
+          +gupxy*gyzx + gupxz*gzzx + gupyz*gzzy &
+          +gupxy*gxzy + gupxz*gxzz + gupyz*gyzz
+
+  call fderivs(ex,trK,fx,fy,fz,X,Y,Z,SYM,SYM,SYM,Symmetry,0)
+
+movx_Res = movx_Res - fx - F8*PI*sx
+movy_Res = movy_Res - fy - F8*PI*sy
+movz_Res = movz_Res - fz - F8*PI*sz
+
+  return
+
+  end subroutine constraint_adm
+!-------------------------------------------------------------------------------!
+! computed constraint for ADM formalism for shell                              !
+!-------------------------------------------------------------------------------!
+  subroutine constraint_adm_ss(ex,crho,sigma,R, X, Y, Z,&
+               drhodx, drhody, drhodz,                                         &
+               dsigmadx,dsigmady,dsigmadz,                                     &
+               dRdx,dRdy,dRdz,                                                 &
+               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
+               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
+               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
+               dxx,gxy,gxz,dyy,gyz,dzz, &
+               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz, &
+               Lap,Sfx,Sfy,Sfz,rho,Sx,Sy,Sz,&
+               Gamxxx, Gamxxy, Gamxxz,Gamxyy, Gamxyz, Gamxzz, &
+               Gamyxx, Gamyxy, Gamyxz,Gamyyy, Gamyyz, Gamyzz, &
+               Gamzxx, Gamzxy, Gamzxz,Gamzyy, Gamzyz, Gamzzz, &
+               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz, &
+               ham_Res, movx_Res, movy_Res, movz_Res, &
+               Symmetry,Lev,sst)
+
+  implicit none
+!~~~~~~> Input parameters:
+
+  integer,intent(in ):: ex(1:3),symmetry,Lev,sst
+  double precision,intent(in),dimension(ex(1))::crho
+  double precision,intent(in),dimension(ex(2))::sigma
+  double precision,intent(in),dimension(ex(3))::R
+  real*8, intent(in ),dimension(ex(1),ex(2),ex(3)):: X,Y,Z
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodx, drhody, drhodz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadx,dsigmady,dsigmadz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdx,dRdy,dRdz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: Lap,Sfx,Sfy,Sfz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: rho,Sx,Sy,Sz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
+! second kind of Christofel symble Gamma^i_jk respect to physical metric
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: ham_Res, movx_Res, movy_Res, movz_Res
+!~~~~~~> Other variables:
+!  inverse metric
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
+! first order derivative of metric, @_k g_ij
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyx,gyzx,gzzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyy,gyzy,gzzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyz,gyzz,gzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz,trK,fx,fy,fz
+
+  integer, parameter :: NO_SYMM = 0, EQUATORIAL = 1, OCTANT = 2
+  real*8, parameter :: ZERO = 0.D0, HALF = 0.5d0, ONE = 1.d0, TWO = 2.d0, FOUR = 4.d0
+  real*8, parameter :: F2o3 = 2.d0/3.d0, F8 = 8.d0, F16 = 1.6d1, SIX = 6.d0
+  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
+  real*8            :: PI
+
+  call adm_ricci_gamma_ss(ex,crho,sigma,R,X, Y, Z,                      &
+               drhodx, drhody, drhodz,                                         &
+               dsigmadx,dsigmady,dsigmadz,                                     &
+               dRdx,dRdy,dRdz,                                                 &
+               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
+               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
+               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
+               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
+               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
+               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
+               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
+               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
+               Symmetry,Lev,sst)
+
+  PI = dacos(-ONE)
+
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
+! invert 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
+
+  trK =          gupxx * Kxx + gupyy * Kyy + gupzz * Kzz &
+        + TWO * (gupxy * Kxy + gupxz * Kxz + gupyz * Kyz)
+
+! ham_Res = trR + K^2 - K_ij * K^ij - 16 * PI * rho
+  ham_Res =   gupxx * Rxx + gupyy * Ryy + gupzz * Rzz + &
+        TWO* ( gupxy * Rxy + gupxz * Rxz + gupyz * Ryz )
+
+  ham_Res = ham_Res + trK * trK -(&
+       gupxx * ( &
+       gupxx * Kxx * Kxx + gupyy * Kxy * Kxy + gupzz * Kxz * Kxz + &
+       TWO * (gupxy * Kxx * Kxy + gupxz * Kxx * Kxz + gupyz * Kxy * Kxz) ) + &
+       gupyy * ( &
+       gupxx * Kxy * Kxy + gupyy * Kyy * Kyy + gupzz * Kyz * Kyz + &
+       TWO * (gupxy * Kxy * Kyy + gupxz * Kxy * Kyz + gupyz * Kyy * Kyz) ) + &
+       gupzz * ( &
+       gupxx * Kxz * Kxz + gupyy * Kyz * Kyz + gupzz * Kzz * Kzz + &
+       TWO * (gupxy * Kxz * Kyz + gupxz * Kxz * Kzz + gupyz * Kyz * Kzz) ) + &
+       TWO * ( &
+       gupxy * ( &
+       gupxx * Kxx * Kxy + gupyy * Kxy * Kyy + gupzz * Kxz * Kyz + &
+       gupxy * (Kxx * Kyy + Kxy * Kxy) + &
+       gupxz * (Kxx * Kyz + Kxz * Kxy) + &
+       gupyz * (Kxy * Kyz + Kxz * Kyy) ) + &
+       gupxz * ( &
+       gupxx * Kxx * Kxz + gupyy * Kxy * Kyz + gupzz * Kxz * Kzz + &
+       gupxy * (Kxx * Kyz + Kxy * Kxz) + &
+       gupxz * (Kxx * Kzz + Kxz * Kxz) + &
+       gupyz * (Kxy * Kzz + Kxz * Kyz) ) + &
+       gupyz * ( &
+       gupxx * Kxy * Kxz + gupyy * Kyy * Kyz + gupzz * Kyz * Kzz + &
+       gupxy * (Kxy * Kyz + Kyy * Kxz) + &
+       gupxz * (Kxy * Kzz + Kyz * Kxz) + &
+       gupyz * (Kyy * Kzz + Kyz * Kyz) ) ))- F16 * PI * rho
+
+! mov_Res_j = gupkj*D_k K_ij - d_j trK - 8 PI s_j where D respect to physical metric
+! store D_i K_jk
+  call fderivs_shc(ex,Kxx,gxxx,gxxy,gxxz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,Kxy,gxyx,gxyy,gxyz,crho,sigma,R,ANTI,ANTI,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,Kxz,gxzx,gxzy,gxzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,         &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,Kyy,gyyx,gyyy,gyyz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,Kyz,gyzx,gyzy,gyzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,         &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,Kzz,gzzx,gzzy,gzzz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+
+  gxxx = gxxx - (  Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz &
+                 + Gamxxx * Kxx + Gamyxx * Kxy + Gamzxx * Kxz)
+  gxyx = gxyx - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
+                 + Gamxxx * Kxy + Gamyxx * Kyy + Gamzxx * Kyz)
+  gxzx = gxzx - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
+                 + Gamxxx * Kxz + Gamyxx * Kyz + Gamzxx * Kzz)
+  gyyx = gyyx - (  Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz &
+                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
+  gyzx = gyzx - (  Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz &
+                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
+  gzzx = gzzx - (  Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz &
+                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
+  gxxy = gxxy - (  Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz &
+                 + Gamxxy * Kxx + Gamyxy * Kxy + Gamzxy * Kxz)
+  gxyy = gxyy - (  Gamxyy * Kxx + Gamyyy * Kxy + Gamzyy * Kxz &
+                 + Gamxxy * Kxy + Gamyxy * Kyy + Gamzxy * Kyz)
+  gxzy = gxzy - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
+                 + Gamxxy * Kxz + Gamyxy * Kyz + Gamzxy * Kzz)
+  gyyy = gyyy - (  Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz &
+                 + Gamxyy * Kxy + Gamyyy * Kyy + Gamzyy * Kyz)
+  gyzy = gyzy - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
+                 + Gamxyy * Kxz + Gamyyy * Kyz + Gamzyy * Kzz)
+  gzzy = gzzy - (  Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz &
+                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
+  gxxz = gxxz - (  Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz &
+                 + Gamxxz * Kxx + Gamyxz * Kxy + Gamzxz * Kxz)
+  gxyz = gxyz - (  Gamxyz * Kxx + Gamyyz * Kxy + Gamzyz * Kxz &
+                 + Gamxxz * Kxy + Gamyxz * Kyy + Gamzxz * Kyz)
+  gxzz = gxzz - (  Gamxzz * Kxx + Gamyzz * Kxy + Gamzzz * Kxz &
+                 + Gamxxz * Kxz + Gamyxz * Kyz + Gamzxz * Kzz)
+  gyyz = gyyz - (  Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz &
+                 + Gamxyz * Kxy + Gamyyz * Kyy + Gamzyz * Kyz)
+  gyzz = gyzz - (  Gamxzz * Kxy + Gamyzz * Kyy + Gamzzz * Kyz &
+                 + Gamxyz * Kxz + Gamyyz * Kyz + Gamzyz * Kzz)
+  gzzz = gzzz - (  Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz &
+                 + Gamxzz * Kxz + Gamyzz * Kyz + Gamzzz * Kzz)
+movx_Res = gupxx*gxxx + gupyy*gxyy + gupzz*gxzz &
+          +gupxy*gxyx + gupxz*gxzx + gupyz*gxzy &
+          +gupxy*gxxy + gupxz*gxxz + gupyz*gxyz
+movy_Res = gupxx*gxyx + gupyy*gyyy + gupzz*gyzz &
+          +gupxy*gyyx + gupxz*gyzx + gupyz*gyzy &
+          +gupxy*gxyy + gupxz*gxyz + gupyz*gyyz
+movz_Res = gupxx*gxzx + gupyy*gyzy + gupzz*gzzz &
+          +gupxy*gyzx + gupxz*gzzx + gupyz*gzzy &
+          +gupxy*gxzy + gupxz*gxzz + gupyz*gyzz
+
+  call fderivs_shc(ex,trK,fx,fy,fz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,                &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+
+movx_Res = movx_Res - fx - F8*PI*sx
+movy_Res = movy_Res - fy - F8*PI*sy
+movz_Res = movz_Res - fz - F8*PI*sz
+
+  return
+
+  end subroutine constraint_adm_ss

AMSS_NCKU_source/adm_ricci_gamma.f90

@@ -1,306 +1,306 @@
-
-! for ADM variables
-  subroutine adm_ricci_gamma(ex, X, Y, Z,                        &
-               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
-               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
-               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
-               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
-               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
-               Symmetry)
-  implicit none
-
-!~~~~~~> Input parameters:
-
-  integer,intent(in ):: ex(1:3), Symmetry
-  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3))
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
-! when out, physical second kind of connection  
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
-! when out, physical Ricci tensor  
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
-
-!~~~~~~> Other variables:
-
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx,gyyx,gyzx,gzzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy,gyyy,gyzy,gzzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz,gyyz,gyzz,gzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxxx,ass_Gamxxy,ass_Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxyy,ass_Gamxyz,ass_Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyxx,ass_Gamyxy,ass_Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyyy,ass_Gamyyz,ass_Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzxx,ass_Gamzxy,ass_Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzyy,ass_Gamzyz,ass_Gamzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxyxy,  Rxyxz,  Rxyyz,  Rxzxz,  Rxzyz,  Ryzyz
-
-  real*8, parameter :: ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
-  real*8, parameter :: HALF = 0.5D0, F2o3 = 2.d0/3.d0, F3o2 = 1.5d0
-  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
-
-  gxx = dxx + ONE
-  gyy = dyy + ONE
-  gzz = dzz + ONE
- 
-  call fderivs(ex,dxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,gxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
-  call fderivs(ex,gxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
-  call fderivs(ex,dyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fderivs(ex,gyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
-  call fderivs(ex,dzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-
-  call kind1_connection(ex,                      &
-                        gxxx,gxyx,gxzx,gyyx,gyzx,gzzx, &
-                        gxxy,gxyy,gxzy,gyyy,gyzy,gzzy, &
-                        gxxz,gxyz,gxzz,gyyz,gyzz,gzzz, &
-                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
-                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
-                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz)
-! invert 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
-
-  call kind2_connection(ex,                      &
-                        gupxx,gupxy,gupxz,gupyy,gupyz,gupzz, &
-                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
-                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
-                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz, &
-                        Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
-                        Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
-                        Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz)                        
-
-  call fdderivs(ex,dxx,gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-  call fdderivs(ex,gxy,gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
-  call fdderivs(ex,gxz,gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
-  call fdderivs(ex,dyy,gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz,X,Y,Z,SYM, SYM ,SYM ,Symmetry,0)
-  call fdderivs(ex,gyz,gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
-  call fdderivs(ex,dzz,gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
-
-  call adm_riemann(ex, &
-               gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz, &
-               gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz, &
-               gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz, &
-               gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz, &
-               gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz, &
-               gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz, &
-               Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
-               Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
-               Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz, &
-               ass_Gamxxx,ass_Gamxxy,ass_Gamxxz, ass_Gamxyy,ass_Gamxyz,ass_Gamxzz, &
-               ass_Gamyxx,ass_Gamyxy,ass_Gamyxz, ass_Gamyyy,ass_Gamyyz,ass_Gamyzz, &
-               ass_Gamzxx,ass_Gamzxy,ass_Gamzxz, ass_Gamzyy,ass_Gamzyz,ass_Gamzzz, &
-               Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz)
-
-  call adm_ricci(ex,                          &
-                   gupxx , gupxy , gupxz , gupyy , gupyz , gupzz , &
-                   Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz, &
-                   Rxx ,   Rxy ,   Rxz ,   Ryy ,   Ryz ,   Rzz)
-
-  return
-
-  end subroutine adm_ricci_gamma
-!----------------------------------------------------------------------------
-  subroutine adm_ricci_gamma_ss(ex,crho,sigma,R,X, Y, Z,                      &
-               drhodx, drhody, drhodz,                                         &
-               dsigmadx,dsigmady,dsigmadz,                                     &
-               dRdx,dRdy,dRdz,                                                 &
-               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
-               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
-               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
-               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
-               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
-               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
-               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
-               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
-               Symmetry,Lev,sst)
-  implicit none
-
-!~~~~~~> Input parameters:
-
-  integer,intent(in ):: ex(1:3), Symmetry,Lev,sst
-  double precision,intent(in),dimension(ex(1))::crho
-  double precision,intent(in),dimension(ex(2))::sigma
-  double precision,intent(in),dimension(ex(3))::R
-  real*8, intent(in ),dimension(ex(1),ex(2),ex(3)):: X,Y,Z
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodx, drhody, drhodz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadx,dsigmady,dsigmadz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdx,dRdy,dRdz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
-! when out, physical second kind of connection  
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
-! when out, physical Ricci tensor  
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
-
-!~~~~~~> Other variables:
-
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx,gyyx,gyzx,gzzx
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy,gyyy,gyzy,gzzy
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz,gyyz,gyzz,gzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxxx,ass_Gamxxy,ass_Gamxxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxyy,ass_Gamxyz,ass_Gamxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyxx,ass_Gamyxy,ass_Gamyxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyyy,ass_Gamyyz,ass_Gamyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzxx,ass_Gamzxy,ass_Gamzxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzyy,ass_Gamzyz,ass_Gamzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz
-  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxyxy,  Rxyxz,  Rxyyz,  Rxzxz,  Rxzyz,  Ryzyz
-
-  real*8, parameter :: ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
-  real*8, parameter :: HALF = 0.5D0, F2o3 = 2.d0/3.d0, F3o2 = 1.5d0
-  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
-
-  gxx = dxx + ONE
-  gyy = dyy + ONE
-  gzz = dzz + ONE
- 
-  call fderivs_shc(ex,dxx,gxxx,gxxy,gxxz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,gxy,gxyx,gxyy,gxyz,crho,sigma,R,ANTI,ANTI,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,gxz,gxzx,gxzy,gxzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,         &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,dyy,gyyx,gyyy,gyyz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,gyz,gyzx,gyzy,gyzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,         &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-  call fderivs_shc(ex,dzz,gzzx,gzzy,gzzz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
-                       drhodx, drhody, drhodz,                                                 &
-                       dsigmadx,dsigmady,dsigmadz,                                             &
-                       dRdx,dRdy,dRdz)
-
-  call kind1_connection(ex,                      &
-                        gxxx,gxyx,gxzx,gyyx,gyzx,gzzx, &
-                        gxxy,gxyy,gxzy,gyyy,gyzy,gzzy, &
-                        gxxz,gxyz,gxzz,gyyz,gyzz,gzzz, &
-                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
-                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
-                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz)
-! invert 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
-
-  call kind2_connection(ex,                      &
-                        gupxx,gupxy,gupxz,gupyy,gupyz,gupzz, &
-                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
-                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
-                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz, &
-                        Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
-                        Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
-                        Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz)                        
-
-  call fdderivs_shc(ex,dxx,gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-  call fdderivs_shc(ex,dyy,gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-  call fdderivs_shc(ex,dzz,gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-  call fdderivs_shc(ex,gxy,gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz,crho,sigma,R,ANTI,ANTI,SYM ,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-  call fdderivs_shc(ex,gxz,gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-  call fdderivs_shc(ex,gyz,gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,  &
-                       drhodx, drhody, drhodz,                                                    &
-                       dsigmadx,dsigmady,dsigmadz,                                                &
-                       dRdx,dRdy,dRdz,                                                            &
-                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
-                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
-                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
-
-  call adm_riemann(ex, &
-               gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz, &
-               gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz, &
-               gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz, &
-               gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz, &
-               gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz, &
-               gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz, &
-               Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
-               Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
-               Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz, &
-               ass_Gamxxx,ass_Gamxxy,ass_Gamxxz, ass_Gamxyy,ass_Gamxyz,ass_Gamxzz, &
-               ass_Gamyxx,ass_Gamyxy,ass_Gamyxz, ass_Gamyyy,ass_Gamyyz,ass_Gamyzz, &
-               ass_Gamzxx,ass_Gamzxy,ass_Gamzxz, ass_Gamzyy,ass_Gamzyz,ass_Gamzzz, &
-               Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz)
-
-  call adm_ricci(ex,                          &
-                   gupxx , gupxy , gupxz , gupyy , gupyz , gupzz , &
-                   Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz, &
-                   Rxx ,   Rxy ,   Rxz ,   Ryy ,   Ryz ,   Rzz)
-
-  return
-
-  end subroutine adm_ricci_gamma_ss
+
+! for ADM variables
+  subroutine adm_ricci_gamma(ex, X, Y, Z,                        &
+               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
+               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
+               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
+               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
+               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
+               Symmetry)
+  implicit none
+
+!~~~~~~> Input parameters:
+
+  integer,intent(in ):: ex(1:3), Symmetry
+  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3))
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
+! when out, physical second kind of connection  
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
+! when out, physical Ricci tensor  
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
+
+!~~~~~~> Other variables:
+
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx,gyyx,gyzx,gzzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy,gyyy,gyzy,gzzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz,gyyz,gyzz,gzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxxx,ass_Gamxxy,ass_Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxyy,ass_Gamxyz,ass_Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyxx,ass_Gamyxy,ass_Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyyy,ass_Gamyyz,ass_Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzxx,ass_Gamzxy,ass_Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzyy,ass_Gamzyz,ass_Gamzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxyxy,  Rxyxz,  Rxyyz,  Rxzxz,  Rxzyz,  Ryzyz
+
+  real*8, parameter :: ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
+  real*8, parameter :: HALF = 0.5D0, F2o3 = 2.d0/3.d0, F3o2 = 1.5d0
+  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
+
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
+ 
+  call fderivs(ex,dxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+  call fderivs(ex,gxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
+  call fderivs(ex,gxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
+  call fderivs(ex,dyy,gyyx,gyyy,gyyz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+  call fderivs(ex,gyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
+  call fderivs(ex,dzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+
+  call kind1_connection(ex,                      &
+                        gxxx,gxyx,gxzx,gyyx,gyzx,gzzx, &
+                        gxxy,gxyy,gxzy,gyyy,gyzy,gzzy, &
+                        gxxz,gxyz,gxzz,gyyz,gyzz,gzzz, &
+                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
+                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
+                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz)
+! invert 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
+
+  call kind2_connection(ex,                      &
+                        gupxx,gupxy,gupxz,gupyy,gupyz,gupzz, &
+                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
+                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
+                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz, &
+                        Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
+                        Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
+                        Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz)                        
+
+  call fdderivs(ex,dxx,gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+  call fdderivs(ex,gxy,gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,0)
+  call fdderivs(ex,gxz,gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,0)
+  call fdderivs(ex,dyy,gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz,X,Y,Z,SYM, SYM ,SYM ,Symmetry,0)
+  call fdderivs(ex,gyz,gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,0)
+  call fdderivs(ex,dzz,gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,0)
+
+  call adm_riemann(ex, &
+               gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz, &
+               gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz, &
+               gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz, &
+               gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz, &
+               gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz, &
+               gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz, &
+               Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
+               Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
+               Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz, &
+               ass_Gamxxx,ass_Gamxxy,ass_Gamxxz, ass_Gamxyy,ass_Gamxyz,ass_Gamxzz, &
+               ass_Gamyxx,ass_Gamyxy,ass_Gamyxz, ass_Gamyyy,ass_Gamyyz,ass_Gamyzz, &
+               ass_Gamzxx,ass_Gamzxy,ass_Gamzxz, ass_Gamzyy,ass_Gamzyz,ass_Gamzzz, &
+               Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz)
+
+  call adm_ricci(ex,                          &
+                   gupxx , gupxy , gupxz , gupyy , gupyz , gupzz , &
+                   Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz, &
+                   Rxx ,   Rxy ,   Rxz ,   Ryy ,   Ryz ,   Rzz)
+
+  return
+
+  end subroutine adm_ricci_gamma
+!----------------------------------------------------------------------------
+  subroutine adm_ricci_gamma_ss(ex,crho,sigma,R,X, Y, Z,                      &
+               drhodx, drhody, drhodz,                                         &
+               dsigmadx,dsigmady,dsigmadz,                                     &
+               dRdx,dRdy,dRdz,                                                 &
+               drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                &
+               dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,    &
+               dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz,                            &
+               dxx    ,   gxy    ,   gxz    ,   dyy    ,   gyz    ,   dzz,&
+               Gamxxx,Gamxxy,Gamxxz,Gamxyy,Gamxyz,Gamxzz,&
+               Gamyxx,Gamyxy,Gamyxz,Gamyyy,Gamyyz,Gamyzz,&
+               Gamzxx,Gamzxy,Gamzxz,Gamzyy,Gamzyz,Gamzzz,&
+               Rxx,Rxy,Rxz,Ryy,Ryz,Rzz,&
+               Symmetry,Lev,sst)
+  implicit none
+
+!~~~~~~> Input parameters:
+
+  integer,intent(in ):: ex(1:3), Symmetry,Lev,sst
+  double precision,intent(in),dimension(ex(1))::crho
+  double precision,intent(in),dimension(ex(2))::sigma
+  double precision,intent(in),dimension(ex(3))::R
+  real*8, intent(in ),dimension(ex(1),ex(2),ex(3)):: X,Y,Z
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodx, drhody, drhodz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadx,dsigmady,dsigmadz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdx,dRdy,dRdz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in ) :: dxx,gxy,gxz,dyy,gyz,dzz
+! when out, physical second kind of connection  
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxxx, Gamxxy, Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamxyy, Gamxyz, Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyxx, Gamyxy, Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamyyy, Gamyyz, Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzxx, Gamzxy, Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Gamzyy, Gamzyz, Gamzzz
+! when out, physical Ricci tensor  
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Rxx,Rxy,Rxz,Ryy,Ryz,Rzz
+
+!~~~~~~> Other variables:
+
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxx,gxyx,gxzx,gyyx,gyzx,gzzx
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxy,gxyy,gxzy,gyyy,gyzy,gzzy
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxz,gxyz,gxzz,gyyz,gyzz,gzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxxx,ass_Gamxxy,ass_Gamxxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamxyy,ass_Gamxyz,ass_Gamxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyxx,ass_Gamyxy,ass_Gamyxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamyyy,ass_Gamyyz,ass_Gamyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzxx,ass_Gamzxy,ass_Gamzxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: ass_Gamzyy,ass_Gamzyz,ass_Gamzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupyy,gupyz,gupzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz
+  real*8, dimension(ex(1),ex(2),ex(3)) :: Rxyxy,  Rxyxz,  Rxyyz,  Rxzxz,  Rxzyz,  Ryzyz
+
+  real*8, parameter :: ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
+  real*8, parameter :: HALF = 0.5D0, F2o3 = 2.d0/3.d0, F3o2 = 1.5d0
+  real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
+
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
+ 
+  call fderivs_shc(ex,dxx,gxxx,gxxy,gxxz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,gxy,gxyx,gxyy,gxyz,crho,sigma,R,ANTI,ANTI,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,gxz,gxzx,gxzy,gxzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,         &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,dyy,gyyx,gyyy,gyyz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,gyz,gyzx,gyzy,gyzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,         &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+  call fderivs_shc(ex,dzz,gzzx,gzzy,gzzz,crho,sigma,R, SYM, SYM,SYM,Symmetry,Lev,sst,          &
+                       drhodx, drhody, drhodz,                                                 &
+                       dsigmadx,dsigmady,dsigmadz,                                             &
+                       dRdx,dRdy,dRdz)
+
+  call kind1_connection(ex,                      &
+                        gxxx,gxyx,gxzx,gyyx,gyzx,gzzx, &
+                        gxxy,gxyy,gxzy,gyyy,gyzy,gzzy, &
+                        gxxz,gxyz,gxzz,gyyz,gyzz,gzzz, &
+                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
+                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
+                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz)
+! invert 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
+
+  call kind2_connection(ex,                      &
+                        gupxx,gupxy,gupxz,gupyy,gupyz,gupzz, &
+                        ass_Gamxxx, ass_Gamxxy, ass_Gamxxz, ass_Gamxyy, ass_Gamxyz, ass_Gamxzz, &
+                        ass_Gamyxx, ass_Gamyxy, ass_Gamyxz, ass_Gamyyy, ass_Gamyyz, ass_Gamyzz, &
+                        ass_Gamzxx, ass_Gamzxy, ass_Gamzxz, ass_Gamzyy, ass_Gamzyz, ass_Gamzzz, &
+                        Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
+                        Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
+                        Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz)                        
+
+  call fdderivs_shc(ex,dxx,gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+  call fdderivs_shc(ex,dyy,gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+  call fdderivs_shc(ex,dzz,gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz,crho,sigma,R, SYM, SYM,SYM ,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+  call fdderivs_shc(ex,gxy,gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz,crho,sigma,R,ANTI,ANTI,SYM ,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+  call fdderivs_shc(ex,gxz,gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz,crho,sigma,R,ANTI,SYM ,ANTI,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+  call fdderivs_shc(ex,gyz,gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz,crho,sigma,R,SYM ,ANTI,ANTI,Symmetry,Lev,sst,  &
+                       drhodx, drhody, drhodz,                                                    &
+                       dsigmadx,dsigmady,dsigmadz,                                                &
+                       dRdx,dRdy,dRdz,                                                            &
+                       drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz,                           &
+                       dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz,               &
+                       dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz)
+
+  call adm_riemann(ex, &
+               gxxxx,gxxxy,gxxxz,gxxyy,gxxyz,gxxzz, &
+               gxyxx,gxyxy,gxyxz,gxyyy,gxyyz,gxyzz, &
+               gxzxx,gxzxy,gxzxz,gxzyy,gxzyz,gxzzz, &
+               gyyxx,gyyxy,gyyxz,gyyyy,gyyyz,gyyzz, &
+               gyzxx,gyzxy,gyzxz,gyzyy,gyzyz,gyzzz, &
+               gzzxx,gzzxy,gzzxz,gzzyy,gzzyz,gzzzz, &
+               Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz, &
+               Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz, &
+               Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz, &
+               ass_Gamxxx,ass_Gamxxy,ass_Gamxxz, ass_Gamxyy,ass_Gamxyz,ass_Gamxzz, &
+               ass_Gamyxx,ass_Gamyxy,ass_Gamyxz, ass_Gamyyy,ass_Gamyyz,ass_Gamyzz, &
+               ass_Gamzxx,ass_Gamzxy,ass_Gamzxz, ass_Gamzyy,ass_Gamzyz,ass_Gamzzz, &
+               Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz)
+
+  call adm_ricci(ex,                          &
+                   gupxx , gupxy , gupxz , gupyy , gupyz , gupzz , &
+                   Rxyxy, Rxyxz, Rxyyz, Rxzxz, Rxzyz, Ryzyz, &
+                   Rxx ,   Rxy ,   Rxz ,   Ryy ,   Ryz ,   Rzz)
+
+  return
+
+  end subroutine adm_ricci_gamma_ss

AMSS_NCKU_source/array.C

@@ -1,186 +1,186 @@
-#include <assert.h>
-#include <stddef.h> // NULL
-#include <stdlib.h> // size_t
-
-#include "cctk.h"
-
-#include "stdc.h"
-#include "util.h"
-#include "array.h"
-
-namespace AHFinderDirect
-{
-	namespace jtutil
-	{
-
-		template <typename T>
-		array1d<T>::array1d(int min_i_in, int max_i_in,
-							T *array_in /* = NULL */,
-							int stride_i_in /* = 0 */)
-			: array_(array_in),
-			  offset_(0), // temp value, changed below
-			  stride_i_(stride_i_in),
-			  min_i_(min_i_in), max_i_(max_i_in),
-			  we_own_array_(array_in == NULL)
-		{
-			if (stride_i_ == 0)
-				then stride_i_ = 1;
-
-			// must use unchecked subscripting here since setup isn't done yet
-			offset_ = -subscript_unchecked(min_i_); // RHS uses offset_ = 0
-			assert(subscript_unchecked(min_i_) == 0);
-			max_subscript_ = subscript_unchecked(max_i_);
-
-			if (we_own_array_)
-				then
-				{
-					// allocate it
-					const int N_allocate = N_i();
-					array_ = new T[N_allocate];
-				}
-
-			// explicitly initialize array (new[] *doesn't* do this automagically)
-			for (int i = min_i(); i <= max_i(); ++i)
-			{
-				operator()(i) = T(0);
-			}
-		}
-
-		//
-		// This function destroys an  array1d  object.
-		//
-		template <typename T>
-		array1d<T>::~array1d()
-		{
-			if (we_own_array_)
-				then delete[] array_;
-		}
-
-		//
-		// This function constructs an  array2d  object.
-		//
-		template <typename T>
-		array2d<T>::array2d(int min_i_in, int max_i_in,
-							int min_j_in, int max_j_in,
-							T *array_in /* = NULL */,
-							int stride_i_in /* = 0 */, int stride_j_in /* = 0 */)
-			: array_(array_in),
-			  offset_(0), // temp value, changed below
-			  stride_i_(stride_i_in), stride_j_(stride_j_in),
-			  min_i_(min_i_in), max_i_(max_i_in),
-			  min_j_(min_j_in), max_j_(max_j_in),
-			  we_own_array_(array_in == NULL)
-		{
-			if (stride_j_ == 0)
-				then stride_j_ = 1;
-			if (stride_i_ == 0)
-				then stride_i_ = N_j();
-
-			// must use unchecked subscripting here since setup isn't done yet
-			offset_ = -subscript_unchecked(min_i_, min_j_); // RHS uses offset_ = 0
-			assert(subscript_unchecked(min_i_, min_j_) == 0);
-			max_subscript_ = subscript_unchecked(max_i_, max_j_);
-
-			if (we_own_array_)
-				then
-				{
-					// allocate it
-					const int N_allocate = N_i() * N_j();
-					array_ = new T[N_allocate];
-				}
-
-			// explicitly initialize array (new[] *doesn't* do this automagically)
-			for (int i = min_i(); i <= max_i(); ++i)
-			{
-				for (int j = min_j(); j <= max_j(); ++j)
-				{
-					operator()(i, j) = T(0);
-				}
-			}
-		}
-
-		//
-		// This function destroys an  array2d  object.
-		//
-		template <typename T>
-		array2d<T>::~array2d()
-		{
-			if (we_own_array_)
-				then delete[] array_;
-		}
-
-		//
-		// This function constructs an  array3d  object.
-		//
-		template <typename T>
-		array3d<T>::array3d(int min_i_in, int max_i_in,
-							int min_j_in, int max_j_in,
-							int min_k_in, int max_k_in,
-							T *array_in /* = NULL */,
-							int stride_i_in /* = 0 */, int stride_j_in /* = 0 */,
-							int stride_k_in /* = 0 */)
-			: array_(array_in),
-			  offset_(0), // temp value, changed below
-			  stride_i_(stride_i_in), stride_j_(stride_j_in),
-			  stride_k_(stride_k_in),
-			  min_i_(min_i_in), max_i_(max_i_in),
-			  min_j_(min_j_in), max_j_(max_j_in),
-			  min_k_(min_k_in), max_k_(max_k_in),
-			  we_own_array_(array_in == NULL)
-		{
-			if (stride_k_ == 0)
-				then stride_k_ = 1;
-			if (stride_j_ == 0)
-				then stride_j_ = N_k();
-			if (stride_i_ == 0)
-				then stride_i_ = N_j() * N_k();
-
-			// must use unchecked subscripting here since setup isn't done yet
-			offset_ = -subscript_unchecked(min_i_, min_j_, min_k_); // RHS uses offset_ = 0
-			assert(subscript_unchecked(min_i_, min_j_, min_k_) == 0);
-			max_subscript_ = subscript_unchecked(max_i_, max_j_, max_k_);
-
-			if (we_own_array_)
-				then
-				{
-					// allocate it
-					const int N_allocate = N_i() * N_j() * N_k();
-					array_ = new T[N_allocate];
-				}
-
-			// explicitly initialize array (new[] *doesn't* do this automagically)
-			for (int i = min_i(); i <= max_i(); ++i)
-			{
-				for (int j = min_j(); j <= max_j(); ++j)
-				{
-					for (int k = min_k(); k <= max_k(); ++k)
-					{
-						operator()(i, j, k) = T(0);
-					}
-				}
-			}
-		}
-		//
-		// This function destroys an  array3d  object.
-		//
-		template <typename T>
-		array3d<T>::~array3d()
-		{
-			if (we_own_array_)
-				then delete[] array_;
-		}
-
-		template class array1d<int>;
-
-		// FIXME: we shouldn't have to instantiate these both, the const one
-		//	  is actually trivially derivable from the non-const one. :(
-		template class array1d<void *>;
-		template class array1d<const void *>;
-
-		template class array1d<CCTK_REAL>;
-		template class array2d<CCTK_INT>;
-		template class array2d<CCTK_REAL>;
-		template class array3d<CCTK_REAL>;
-
-	} // namespace jtutil
-} // namespace AHFinderDirect
+#include <assert.h>
+#include <stddef.h> // NULL
+#include <stdlib.h> // size_t
+
+#include "cctk.h"
+
+#include "stdc.h"
+#include "util.h"
+#include "array.h"
+
+namespace AHFinderDirect
+{
+	namespace jtutil
+	{
+
+		template <typename T>
+		array1d<T>::array1d(int min_i_in, int max_i_in,
+							T *array_in /* = NULL */,
+							int stride_i_in /* = 0 */)
+			: array_(array_in),
+			  offset_(0), // temp value, changed below
+			  stride_i_(stride_i_in),
+			  min_i_(min_i_in), max_i_(max_i_in),
+			  we_own_array_(array_in == NULL)
+		{
+			if (stride_i_ == 0)
+				then stride_i_ = 1;
+
+			// must use unchecked subscripting here since setup isn't done yet
+			offset_ = -subscript_unchecked(min_i_); // RHS uses offset_ = 0
+			assert(subscript_unchecked(min_i_) == 0);
+			max_subscript_ = subscript_unchecked(max_i_);
+
+			if (we_own_array_)
+				then
+				{
+					// allocate it
+					const int N_allocate = N_i();
+					array_ = new T[N_allocate];
+				}
+
+			// explicitly initialize array (new[] *doesn't* do this automagically)
+			for (int i = min_i(); i <= max_i(); ++i)
+			{
+				operator()(i) = T(0);
+			}
+		}
+
+		//
+		// This function destroys an  array1d  object.
+		//
+		template <typename T>
+		array1d<T>::~array1d()
+		{
+			if (we_own_array_)
+				then delete[] array_;
+		}
+
+		//
+		// This function constructs an  array2d  object.
+		//
+		template <typename T>
+		array2d<T>::array2d(int min_i_in, int max_i_in,
+							int min_j_in, int max_j_in,
+							T *array_in /* = NULL */,
+							int stride_i_in /* = 0 */, int stride_j_in /* = 0 */)
+			: array_(array_in),
+			  offset_(0), // temp value, changed below
+			  stride_i_(stride_i_in), stride_j_(stride_j_in),
+			  min_i_(min_i_in), max_i_(max_i_in),
+			  min_j_(min_j_in), max_j_(max_j_in),
+			  we_own_array_(array_in == NULL)
+		{
+			if (stride_j_ == 0)
+				then stride_j_ = 1;
+			if (stride_i_ == 0)
+				then stride_i_ = N_j();
+
+			// must use unchecked subscripting here since setup isn't done yet
+			offset_ = -subscript_unchecked(min_i_, min_j_); // RHS uses offset_ = 0
+			assert(subscript_unchecked(min_i_, min_j_) == 0);
+			max_subscript_ = subscript_unchecked(max_i_, max_j_);
+
+			if (we_own_array_)
+				then
+				{
+					// allocate it
+					const int N_allocate = N_i() * N_j();
+					array_ = new T[N_allocate];
+				}
+
+			// explicitly initialize array (new[] *doesn't* do this automagically)
+			for (int i = min_i(); i <= max_i(); ++i)
+			{
+				for (int j = min_j(); j <= max_j(); ++j)
+				{
+					operator()(i, j) = T(0);
+				}
+			}
+		}
+
+		//
+		// This function destroys an  array2d  object.
+		//
+		template <typename T>
+		array2d<T>::~array2d()
+		{
+			if (we_own_array_)
+				then delete[] array_;
+		}
+
+		//
+		// This function constructs an  array3d  object.
+		//
+		template <typename T>
+		array3d<T>::array3d(int min_i_in, int max_i_in,
+							int min_j_in, int max_j_in,
+							int min_k_in, int max_k_in,
+							T *array_in /* = NULL */,
+							int stride_i_in /* = 0 */, int stride_j_in /* = 0 */,
+							int stride_k_in /* = 0 */)
+			: array_(array_in),
+			  offset_(0), // temp value, changed below
+			  stride_i_(stride_i_in), stride_j_(stride_j_in),
+			  stride_k_(stride_k_in),
+			  min_i_(min_i_in), max_i_(max_i_in),
+			  min_j_(min_j_in), max_j_(max_j_in),
+			  min_k_(min_k_in), max_k_(max_k_in),
+			  we_own_array_(array_in == NULL)
+		{
+			if (stride_k_ == 0)
+				then stride_k_ = 1;
+			if (stride_j_ == 0)
+				then stride_j_ = N_k();
+			if (stride_i_ == 0)
+				then stride_i_ = N_j() * N_k();
+
+			// must use unchecked subscripting here since setup isn't done yet
+			offset_ = -subscript_unchecked(min_i_, min_j_, min_k_); // RHS uses offset_ = 0
+			assert(subscript_unchecked(min_i_, min_j_, min_k_) == 0);
+			max_subscript_ = subscript_unchecked(max_i_, max_j_, max_k_);
+
+			if (we_own_array_)
+				then
+				{
+					// allocate it
+					const int N_allocate = N_i() * N_j() * N_k();
+					array_ = new T[N_allocate];
+				}
+
+			// explicitly initialize array (new[] *doesn't* do this automagically)
+			for (int i = min_i(); i <= max_i(); ++i)
+			{
+				for (int j = min_j(); j <= max_j(); ++j)
+				{
+					for (int k = min_k(); k <= max_k(); ++k)
+					{
+						operator()(i, j, k) = T(0);
+					}
+				}
+			}
+		}
+		//
+		// This function destroys an  array3d  object.
+		//
+		template <typename T>
+		array3d<T>::~array3d()
+		{
+			if (we_own_array_)
+				then delete[] array_;
+		}
+
+		template class array1d<int>;
+
+		// FIXME: we shouldn't have to instantiate these both, the const one
+		//	  is actually trivially derivable from the non-const one. :(
+		template class array1d<void *>;
+		template class array1d<const void *>;
+
+		template class array1d<CCTK_REAL>;
+		template class array2d<CCTK_INT>;
+		template class array2d<CCTK_REAL>;
+		template class array3d<CCTK_REAL>;
+
+	} // namespace jtutil
+} // namespace AHFinderDirect

AMSS_NCKU_source/array.h

@@ -1,292 +1,292 @@
-#ifndef AHFINDERDIRECT__ARRAY_HH
-#define AHFINDERDIRECT__ARRAY_HH
-
-namespace AHFinderDirect
-{
-	namespace jtutil
-	{
-
-		//******************************************************************************
-
-		template <typename T>
-		class array1d
-		{
-		public:
-			int min_i() const { return min_i_; }
-			int max_i() const { return max_i_; }
-			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
-			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
-
-			int subscript_unchecked(int i) const
-			{
-				return offset_ + stride_i_ * i;
-			}
-			int subscript(int i) const
-			{
-				assert(is_valid_i(i));
-				const int posn = subscript_unchecked(i);
-				assert(posn >= 0);
-				assert(posn <= max_subscript_);
-				return posn;
-			}
-			int subscript_offset() const { return offset_; }
-			int subscript_stride_i() const { return stride_i_; }
-
-			// normal-use access functions
-			// ... rvalue
-			const T &operator()(int i) const { return array_[subscript(i)]; }
-			// ... lvalue
-			T &operator()(int i) { return array_[subscript(i)]; }
-
-			// get access to internal 0-origin 1D storage array
-			// (low-level, dangerous, use with caution!)
-			// ... semantics of N_array() may not be what you want
-			//     if strides specify noncontiguous storage
-			int N_array() const { return max_subscript_ + stride_i_; }
-			const T *data_array() const { return const_cast<const T *>(array_); }
-			T *data_array() { return array_; }
-
-			// constructor, destructor
-			// ... constructor initializes all array elements to T(0.0)
-			// ... omitted strides default to C storage order
-			array1d(int min_i_in, int max_i_in,
-					T *array_in = NULL, // caller-provided storage array
-										// if non-NULL
-					int stride_i_in = 0);
-			~array1d();
-
-		private:
-			// we forbid copying and passing by value
-			// by declaring the copy constructor and assignment operator
-			// private, but never defining them
-			array1d(const array1d<T> &rhs);
-			array1d<T> &operator=(const array1d<T> &rhs);
-
-		private:
-			// n.b. we declare the array pointer first in the class
-			// ==> it's probably at 0 offset
-			// ==> we may get slightly faster array access
-			T *array_; // --> new-allocated 1D storage array
-
-			// subscripting info
-			// n.b. put this next in class so it should be in the same
-			//	cpu cache line as  array_  ==> faster array access
-			int offset_, stride_i_;
-
-			// min/max array bounds
-			const int min_i_, max_i_;
-			int max_subscript_;
-
-			// n.b. put this at end of class since performance doesn't matter
-			bool we_own_array_; // true ==> array_ --> new[] array which we own
-								// false ==> array_ --> client-owned storage
-		};
-
-		//******************************************************************************
-
-		template <typename T>
-		class array2d
-		{
-		public:
-			// array info
-			int min_i() const { return min_i_; }
-			int max_i() const { return max_i_; }
-			int min_j() const { return min_j_; }
-			int max_j() const { return max_j_; }
-			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
-			int N_j() const { return jtutil::how_many_in_range(min_j_, max_j_); }
-			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
-			bool is_valid_j(int j) const { return (j >= min_j_) && (j <= max_j_); }
-			bool is_valid_ij(int i, int j) const
-			{
-				return is_valid_i(i) && is_valid_j(j);
-			}
-
-			int subscript_unchecked(int i, int j) const
-			{
-				return offset_ + stride_i_ * i + stride_j_ * j;
-			}
-			int subscript(int i, int j) const
-			{
-				// n.b. we want each assert() here to be on a separate
-				//	source line, so an assert() failure message can
-				//	pinpoint *which* index is bad
-				assert(is_valid_i(i));
-				assert(is_valid_j(j));
-				const int posn = subscript_unchecked(i, j);
-				assert(posn >= 0);
-				assert(posn <= max_subscript_);
-				return posn;
-			}
-			int subscript_offset() const { return offset_; }
-			int subscript_stride_i() const { return stride_i_; }
-			int subscript_stride_j() const { return stride_j_; }
-
-			// normal-use access functions
-			// ... rvalue
-			const T &operator()(int i, int j) const
-			{
-				return array_[subscript(i, j)];
-			}
-			// ... lvalue
-			T &operator()(int i, int j)
-			{
-				return array_[subscript(i, j)];
-			}
-
-			// get access to internal 0-origin 1D storage array
-			// (low-level, dangerous, use with caution!)
-			// ... semantics of N_array() may not be what you want
-			//     if strides specify noncontiguous storage
-			int N_array() const { return max_subscript_ + stride_j_; }
-			const T *data_array() const { return const_cast<const T *>(array_); }
-			T *data_array() { return array_; }
-
-			// constructor, destructor
-			// ... constructor initializes all array elements to T(0.0)
-			// ... omitted strides default to C storage order
-			array2d(int min_i_in, int max_i_in,
-					int min_j_in, int max_j_in,
-					T *array_in = NULL, // caller-provided storage array
-										// if non-NULL
-					int stride_i_in = 0, int stride_j_in = 0);
-			~array2d();
-
-		private:
-			// we forbid copying and passing by value
-			// by declaring the copy constructor and assignment operator
-			// private, but never defining them
-			array2d(const array2d<T> &rhs);
-			array2d<T> &operator=(const array2d<T> &rhs);
-
-		private:
-			// n.b. we declare the array pointer first in the class
-			// ==> it's probably at 0 offset
-			// ==> we may get slightly faster array access
-			T *array_; // --> new-allocated 1D storage array
-
-			// subscripting info
-			// n.b. put this next in class so it should be in the same
-			//	cpu cache line as  array_  ==> faster array access
-			int offset_, stride_i_, stride_j_;
-
-			// min/max array bounds
-			const int min_i_, max_i_;
-			const int min_j_, max_j_;
-			int max_subscript_;
-
-			// n.b. put this at end of class since performance doesn't matter
-			bool we_own_array_; // true ==> array_ --> new[] array which we own
-								// false ==> array_ --> client-owned storage
-		};
-
-		//******************************************************************************
-
-		template <typename T>
-		class array3d
-		{
-		public:
-			// array info
-			int min_i() const { return min_i_; }
-			int max_i() const { return max_i_; }
-			int min_j() const { return min_j_; }
-			int max_j() const { return max_j_; }
-			int min_k() const { return min_k_; }
-			int max_k() const { return max_k_; }
-			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
-			int N_j() const { return jtutil::how_many_in_range(min_j_, max_j_); }
-			int N_k() const { return jtutil::how_many_in_range(min_k_, max_k_); }
-			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
-			bool is_valid_j(int j) const { return (j >= min_j_) && (j <= max_j_); }
-			bool is_valid_k(int k) const { return (k >= min_k_) && (k <= max_k_); }
-			bool is_valid_ijk(int i, int j, int k) const
-			{
-				return is_valid_i(i) && is_valid_j(j) && is_valid_k(k);
-			}
-
-			int subscript_unchecked(int i, int j, int k) const
-			{
-				return offset_ + stride_i_ * i + stride_j_ * j + stride_k_ * k;
-			}
-			int subscript(int i, int j, int k) const
-			{
-				// n.b. we want each assert() here to be on a separate
-				//	source line, so an assert() failure message can
-				//	pinpoint *which* index is bad
-				assert(is_valid_i(i));
-				assert(is_valid_j(j));
-				assert(is_valid_k(k));
-				const int posn = subscript_unchecked(i, j, k);
-				assert(posn >= 0);
-				assert(posn <= max_subscript_);
-				return posn;
-			}
-			int subscript_offset() const { return offset_; }
-			int subscript_stride_i() const { return stride_i_; }
-			int subscript_stride_j() const { return stride_j_; }
-			int subscript_stride_k() const { return stride_k_; }
-
-			// normal-use access functions
-			// ... rvalue
-			const T &operator()(int i, int j, int k) const
-			{
-				return array_[subscript(i, j, k)];
-			}
-			// ... lvalue
-			T &operator()(int i, int j, int k)
-			{
-				return array_[subscript(i, j, k)];
-			}
-
-			// get access to internal 0-origin 1D storage array
-			// (low-level, dangerous, use with caution!)
-			// ... semantics of N_array() may not be what you want
-			//     if strides specify noncontiguous storage
-			int N_array() const { return max_subscript_ + stride_k_; }
-			const T *data_array() const { return const_cast<const T *>(array_); }
-			T *data_array() { return array_; }
-
-			// constructor, destructor
-			// ... constructor initializes all array elements to T(0.0)
-			// ... omitted strides default to C storage order
-			array3d(int min_i_in, int max_i_in,
-					int min_j_in, int max_j_in,
-					int min_k_in, int max_k_in,
-					T *array_in = NULL, // caller-provided storage array
-										// if non-NULL
-					int stride_i_in = 0, int stride_j_in = 0, int stride_k_in = 0);
-			~array3d();
-
-		private:
-			// we forbid copying and passing by value
-			// by declaring the copy constructor and assignment operator
-			// private, but never defining them
-			array3d(const array3d<T> &rhs);
-			array3d<T> &operator=(const array3d<T> &rhs);
-
-		private:
-			// n.b. we declare the array pointer first in the class
-			// ==> it's probably at 0 offset
-			// ==> we may get slightly faster array access
-			T *array_; // --> new-allocated 1D storage array
-
-			// subscripting info
-			// n.b. put this next in class so it should be in the same
-			//	cpu cache line as  array_  ==> faster array access
-			int offset_, stride_i_, stride_j_, stride_k_;
-
-			// min/max array bounds
-			const int min_i_, max_i_;
-			const int min_j_, max_j_;
-			const int min_k_, max_k_;
-			int max_subscript_;
-
-			// n.b. put this at end of class since performance doesn't matter
-			bool we_own_array_; // true ==> array_ --> new[] array which we own
-								// false ==> array_ --> client-owned storage
-		};
-
-	} // namespace jtutil
-} // namespace AHFinderDirect
-
-#endif /* AHFINDERDIRECT__ARRAY_HH */
+#ifndef AHFINDERDIRECT__ARRAY_HH
+#define AHFINDERDIRECT__ARRAY_HH
+
+namespace AHFinderDirect
+{
+	namespace jtutil
+	{
+
+		//******************************************************************************
+
+		template <typename T>
+		class array1d
+		{
+		public:
+			int min_i() const { return min_i_; }
+			int max_i() const { return max_i_; }
+			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
+			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
+
+			int subscript_unchecked(int i) const
+			{
+				return offset_ + stride_i_ * i;
+			}
+			int subscript(int i) const
+			{
+				assert(is_valid_i(i));
+				const int posn = subscript_unchecked(i);
+				assert(posn >= 0);
+				assert(posn <= max_subscript_);
+				return posn;
+			}
+			int subscript_offset() const { return offset_; }
+			int subscript_stride_i() const { return stride_i_; }
+
+			// normal-use access functions
+			// ... rvalue
+			const T &operator()(int i) const { return array_[subscript(i)]; }
+			// ... lvalue
+			T &operator()(int i) { return array_[subscript(i)]; }
+
+			// get access to internal 0-origin 1D storage array
+			// (low-level, dangerous, use with caution!)
+			// ... semantics of N_array() may not be what you want
+			//     if strides specify noncontiguous storage
+			int N_array() const { return max_subscript_ + stride_i_; }
+			const T *data_array() const { return const_cast<const T *>(array_); }
+			T *data_array() { return array_; }
+
+			// constructor, destructor
+			// ... constructor initializes all array elements to T(0.0)
+			// ... omitted strides default to C storage order
+			array1d(int min_i_in, int max_i_in,
+					T *array_in = NULL, // caller-provided storage array
+										// if non-NULL
+					int stride_i_in = 0);
+			~array1d();
+
+		private:
+			// we forbid copying and passing by value
+			// by declaring the copy constructor and assignment operator
+			// private, but never defining them
+			array1d(const array1d<T> &rhs);
+			array1d<T> &operator=(const array1d<T> &rhs);
+
+		private:
+			// n.b. we declare the array pointer first in the class
+			// ==> it's probably at 0 offset
+			// ==> we may get slightly faster array access
+			T *array_; // --> new-allocated 1D storage array
+
+			// subscripting info
+			// n.b. put this next in class so it should be in the same
+			//	cpu cache line as  array_  ==> faster array access
+			int offset_, stride_i_;
+
+			// min/max array bounds
+			const int min_i_, max_i_;
+			int max_subscript_;
+
+			// n.b. put this at end of class since performance doesn't matter
+			bool we_own_array_; // true ==> array_ --> new[] array which we own
+								// false ==> array_ --> client-owned storage
+		};
+
+		//******************************************************************************
+
+		template <typename T>
+		class array2d
+		{
+		public:
+			// array info
+			int min_i() const { return min_i_; }
+			int max_i() const { return max_i_; }
+			int min_j() const { return min_j_; }
+			int max_j() const { return max_j_; }
+			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
+			int N_j() const { return jtutil::how_many_in_range(min_j_, max_j_); }
+			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
+			bool is_valid_j(int j) const { return (j >= min_j_) && (j <= max_j_); }
+			bool is_valid_ij(int i, int j) const
+			{
+				return is_valid_i(i) && is_valid_j(j);
+			}
+
+			int subscript_unchecked(int i, int j) const
+			{
+				return offset_ + stride_i_ * i + stride_j_ * j;
+			}
+			int subscript(int i, int j) const
+			{
+				// n.b. we want each assert() here to be on a separate
+				//	source line, so an assert() failure message can
+				//	pinpoint *which* index is bad
+				assert(is_valid_i(i));
+				assert(is_valid_j(j));
+				const int posn = subscript_unchecked(i, j);
+				assert(posn >= 0);
+				assert(posn <= max_subscript_);
+				return posn;
+			}
+			int subscript_offset() const { return offset_; }
+			int subscript_stride_i() const { return stride_i_; }
+			int subscript_stride_j() const { return stride_j_; }
+
+			// normal-use access functions
+			// ... rvalue
+			const T &operator()(int i, int j) const
+			{
+				return array_[subscript(i, j)];
+			}
+			// ... lvalue
+			T &operator()(int i, int j)
+			{
+				return array_[subscript(i, j)];
+			}
+
+			// get access to internal 0-origin 1D storage array
+			// (low-level, dangerous, use with caution!)
+			// ... semantics of N_array() may not be what you want
+			//     if strides specify noncontiguous storage
+			int N_array() const { return max_subscript_ + stride_j_; }
+			const T *data_array() const { return const_cast<const T *>(array_); }
+			T *data_array() { return array_; }
+
+			// constructor, destructor
+			// ... constructor initializes all array elements to T(0.0)
+			// ... omitted strides default to C storage order
+			array2d(int min_i_in, int max_i_in,
+					int min_j_in, int max_j_in,
+					T *array_in = NULL, // caller-provided storage array
+										// if non-NULL
+					int stride_i_in = 0, int stride_j_in = 0);
+			~array2d();
+
+		private:
+			// we forbid copying and passing by value
+			// by declaring the copy constructor and assignment operator
+			// private, but never defining them
+			array2d(const array2d<T> &rhs);
+			array2d<T> &operator=(const array2d<T> &rhs);
+
+		private:
+			// n.b. we declare the array pointer first in the class
+			// ==> it's probably at 0 offset
+			// ==> we may get slightly faster array access
+			T *array_; // --> new-allocated 1D storage array
+
+			// subscripting info
+			// n.b. put this next in class so it should be in the same
+			//	cpu cache line as  array_  ==> faster array access
+			int offset_, stride_i_, stride_j_;
+
+			// min/max array bounds
+			const int min_i_, max_i_;
+			const int min_j_, max_j_;
+			int max_subscript_;
+
+			// n.b. put this at end of class since performance doesn't matter
+			bool we_own_array_; // true ==> array_ --> new[] array which we own
+								// false ==> array_ --> client-owned storage
+		};
+
+		//******************************************************************************
+
+		template <typename T>
+		class array3d
+		{
+		public:
+			// array info
+			int min_i() const { return min_i_; }
+			int max_i() const { return max_i_; }
+			int min_j() const { return min_j_; }
+			int max_j() const { return max_j_; }
+			int min_k() const { return min_k_; }
+			int max_k() const { return max_k_; }
+			int N_i() const { return jtutil::how_many_in_range(min_i_, max_i_); }
+			int N_j() const { return jtutil::how_many_in_range(min_j_, max_j_); }
+			int N_k() const { return jtutil::how_many_in_range(min_k_, max_k_); }
+			bool is_valid_i(int i) const { return (i >= min_i_) && (i <= max_i_); }
+			bool is_valid_j(int j) const { return (j >= min_j_) && (j <= max_j_); }
+			bool is_valid_k(int k) const { return (k >= min_k_) && (k <= max_k_); }
+			bool is_valid_ijk(int i, int j, int k) const
+			{
+				return is_valid_i(i) && is_valid_j(j) && is_valid_k(k);
+			}
+
+			int subscript_unchecked(int i, int j, int k) const
+			{
+				return offset_ + stride_i_ * i + stride_j_ * j + stride_k_ * k;
+			}
+			int subscript(int i, int j, int k) const
+			{
+				// n.b. we want each assert() here to be on a separate
+				//	source line, so an assert() failure message can
+				//	pinpoint *which* index is bad
+				assert(is_valid_i(i));
+				assert(is_valid_j(j));
+				assert(is_valid_k(k));
+				const int posn = subscript_unchecked(i, j, k);
+				assert(posn >= 0);
+				assert(posn <= max_subscript_);
+				return posn;
+			}
+			int subscript_offset() const { return offset_; }
+			int subscript_stride_i() const { return stride_i_; }
+			int subscript_stride_j() const { return stride_j_; }
+			int subscript_stride_k() const { return stride_k_; }
+
+			// normal-use access functions
+			// ... rvalue
+			const T &operator()(int i, int j, int k) const
+			{
+				return array_[subscript(i, j, k)];
+			}
+			// ... lvalue
+			T &operator()(int i, int j, int k)
+			{
+				return array_[subscript(i, j, k)];
+			}
+
+			// get access to internal 0-origin 1D storage array
+			// (low-level, dangerous, use with caution!)
+			// ... semantics of N_array() may not be what you want
+			//     if strides specify noncontiguous storage
+			int N_array() const { return max_subscript_ + stride_k_; }
+			const T *data_array() const { return const_cast<const T *>(array_); }
+			T *data_array() { return array_; }
+
+			// constructor, destructor
+			// ... constructor initializes all array elements to T(0.0)
+			// ... omitted strides default to C storage order
+			array3d(int min_i_in, int max_i_in,
+					int min_j_in, int max_j_in,
+					int min_k_in, int max_k_in,
+					T *array_in = NULL, // caller-provided storage array
+										// if non-NULL
+					int stride_i_in = 0, int stride_j_in = 0, int stride_k_in = 0);
+			~array3d();
+
+		private:
+			// we forbid copying and passing by value
+			// by declaring the copy constructor and assignment operator
+			// private, but never defining them
+			array3d(const array3d<T> &rhs);
+			array3d<T> &operator=(const array3d<T> &rhs);
+
+		private:
+			// n.b. we declare the array pointer first in the class
+			// ==> it's probably at 0 offset
+			// ==> we may get slightly faster array access
+			T *array_; // --> new-allocated 1D storage array
+
+			// subscripting info
+			// n.b. put this next in class so it should be in the same
+			//	cpu cache line as  array_  ==> faster array access
+			int offset_, stride_i_, stride_j_, stride_k_;
+
+			// min/max array bounds
+			const int min_i_, max_i_;
+			const int min_j_, max_j_;
+			const int min_k_, max_k_;
+			int max_subscript_;
+
+			// n.b. put this at end of class since performance doesn't matter
+			bool we_own_array_; // true ==> array_ --> new[] array which we own
+								// false ==> array_ --> client-owned storage
+		};
+
+	} // namespace jtutil
+} // namespace AHFinderDirect
+
+#endif /* AHFINDERDIRECT__ARRAY_HH */

AMSS_NCKU_source/bssn2adm.f90

@@ -1,40 +1,40 @@
-
-!-------------------------------------------------------------------------------!
-! convert bssn variables to ADM variables                                       !
-!-------------------------------------------------------------------------------!
-  subroutine bssn2adm(ex,chi,trK, &
-               gxx,gxy,gxz,gyy,gyz,gzz, &
-               Axx,Axy,Axz,Ayy,Ayz,Azz, &
-               adm_gxx,adm_gxy,adm_gxz,adm_gyy,adm_gyz,adm_gzz, &
-               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz)
-
-  implicit none
-!~~~~~~> Input parameters:
-
-  integer,intent(in ):: ex(1:3)
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::chi,trK
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::gxx,gxy,gxz,gyy,gyz,gzz
-  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::Axx,Axy,Axz,Ayy,Ayz,Azz
-
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: adm_gxx,adm_gxy,adm_gxz,adm_gyy,adm_gyz,adm_gzz
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
-
-  real*8, parameter :: F1o3=1.d0/3.d0
-
-  adm_gxx = gxx/chi
-  adm_gxy = gxy/chi
-  adm_gxz = gxz/chi
-  adm_gyy = gyy/chi
-  adm_gyz = gyz/chi
-  adm_gzz = gzz/chi
-
-  Kxx = Axx/chi+F1o3*trK*adm_gxx
-  Kxy = Axy/chi+F1o3*trK*adm_gxy
-  Kxz = Axz/chi+F1o3*trK*adm_gxz
-  Kyy = Ayy/chi+F1o3*trK*adm_gyy
-  Kyz = Ayz/chi+F1o3*trK*adm_gyz
-  Kzz = Azz/chi+F1o3*trK*adm_gzz
-
-  return
-
-  end subroutine bssn2adm
+
+!-------------------------------------------------------------------------------!
+! convert bssn variables to ADM variables                                       !
+!-------------------------------------------------------------------------------!
+  subroutine bssn2adm(ex,chi,trK, &
+               gxx,gxy,gxz,gyy,gyz,gzz, &
+               Axx,Axy,Axz,Ayy,Ayz,Azz, &
+               adm_gxx,adm_gxy,adm_gxz,adm_gyy,adm_gyz,adm_gzz, &
+               Kxx,Kxy,Kxz,Kyy,Kyz,Kzz)
+
+  implicit none
+!~~~~~~> Input parameters:
+
+  integer,intent(in ):: ex(1:3)
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::chi,trK
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::gxx,gxy,gxz,gyy,gyz,gzz
+  double precision,intent(in),dimension(ex(1),ex(2),ex(3))::Axx,Axy,Axz,Ayy,Ayz,Azz
+
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: adm_gxx,adm_gxy,adm_gxz,adm_gyy,adm_gyz,adm_gzz
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(out) :: Kxx,Kxy,Kxz,Kyy,Kyz,Kzz
+
+  real*8, parameter :: F1o3=1.d0/3.d0
+
+  adm_gxx = gxx/chi
+  adm_gxy = gxy/chi
+  adm_gxz = gxz/chi
+  adm_gyy = gyy/chi
+  adm_gyz = gyz/chi
+  adm_gzz = gzz/chi
+
+  Kxx = Axx/chi+F1o3*trK*adm_gxx
+  Kxy = Axy/chi+F1o3*trK*adm_gxy
+  Kxz = Axz/chi+F1o3*trK*adm_gxz
+  Kyy = Ayy/chi+F1o3*trK*adm_gyy
+  Kyz = Ayz/chi+F1o3*trK*adm_gyz
+  Kzz = Azz/chi+F1o3*trK*adm_gzz
+
+  return
+
+  end subroutine bssn2adm

AMSS_NCKU_source/bssnEM_class.h

@@ -1,69 +1,69 @@
-
-#ifndef BSSNEM_CLASS_H
-#define BSSNEM_CLASS_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#include "cgh.h"
-#include "ShellPatch.h"
-#include "misc.h"
-#include "var.h"
-#include "MyList.h"
-#include "monitor.h"
-#include "surface_integral.h"
-
-#include "macrodef.h"
-
-#ifdef USE_GPU
-#include "bssn_gpu_class.h"
-#else
-#include "bssn_class.h"
-#endif
-
-class bssnEM_class : public bssn_class
-{
-public:
-     bssnEM_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
-                  int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
-                  int a_levi, int maxli, int decni, double maxrexi, double drexi);
-     ~bssnEM_class();
-
-     void Initialize();
-     void Read_Ansorg();
-     void Setup_Initial_Data();
-     void Step(int lev, int YN);
-     void Compute_Phi2(int lev);
-     void AnalysisStuff_EM(int lev, double dT_lev);
-     void Interp_Constraint();
-
-protected:
-     var *Exo, *Eyo, *Ezo, *Bxo, *Byo, *Bzo, *Kpsio, *Kphio;
-     var *Ex0, *Ey0, *Ez0, *Bx0, *By0, *Bz0, *Kpsi0, *Kphi0;
-     var *Ex, *Ey, *Ez, *Bx, *By, *Bz, *Kpsi, *Kphi;
-     var *Ex1, *Ey1, *Ez1, *Bx1, *By1, *Bz1, *Kpsi1, *Kphi1;
-     var *Ex_rhs, *Ey_rhs, *Ez_rhs, *Bx_rhs, *By_rhs, *Bz_rhs, *Kpsi_rhs, *Kphi_rhs;
-     var *Jx, *Jy, *Jz, *qchar;
-     var *Rphi2, *Iphi2;
-     var *Rphi1, *Iphi1;
-
-     monitor *Phi2Monitor;
-     monitor *Phi1Monitor;
-};
-#endif /* BSSNEM_CLASS_H */
+
+#ifndef BSSNEM_CLASS_H
+#define BSSNEM_CLASS_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <string>
+#include <cmath>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include <mpi.h>
+
+#include "cgh.h"
+#include "ShellPatch.h"
+#include "misc.h"
+#include "var.h"
+#include "MyList.h"
+#include "monitor.h"
+#include "surface_integral.h"
+
+#include "macrodef.h"
+
+#ifdef USE_GPU
+#include "bssn_gpu_class.h"
+#else
+#include "bssn_class.h"
+#endif
+
+class bssnEM_class : public bssn_class
+{
+public:
+     bssnEM_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
+                  int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
+                  int a_levi, int maxli, int decni, double maxrexi, double drexi);
+     ~bssnEM_class();
+
+     void Initialize();
+     void Read_Ansorg();
+     void Setup_Initial_Data();
+     void Step(int lev, int YN);
+     void Compute_Phi2(int lev);
+     void AnalysisStuff_EM(int lev, double dT_lev);
+     void Interp_Constraint();
+
+protected:
+     var *Exo, *Eyo, *Ezo, *Bxo, *Byo, *Bzo, *Kpsio, *Kphio;
+     var *Ex0, *Ey0, *Ez0, *Bx0, *By0, *Bz0, *Kpsi0, *Kphi0;
+     var *Ex, *Ey, *Ez, *Bx, *By, *Bz, *Kpsi, *Kphi;
+     var *Ex1, *Ey1, *Ez1, *Bx1, *By1, *Bz1, *Kpsi1, *Kphi1;
+     var *Ex_rhs, *Ey_rhs, *Ez_rhs, *Bx_rhs, *By_rhs, *Bz_rhs, *Kpsi_rhs, *Kphi_rhs;
+     var *Jx, *Jy, *Jz, *qchar;
+     var *Rphi2, *Iphi2;
+     var *Rphi1, *Iphi1;
+
+     monitor *Phi2Monitor;
+     monitor *Phi1Monitor;
+};
+#endif /* BSSNEM_CLASS_H */

AMSS_NCKU_source/bssnEScalar_class.h

@@ -1,70 +1,70 @@
-
-#ifndef BSSNESCALAR_CLASS_H
-#define BSSNESCALAR_CLASS_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#include "cgh.h"
-#include "ShellPatch.h"
-#include "misc.h"
-#include "var.h"
-#include "MyList.h"
-#include "monitor.h"
-#include "surface_integral.h"
-
-#include "macrodef.h"
-
-#ifdef USE_GPU
-#include "bssn_gpu_class.h"
-#else
-#include "bssn_class.h"
-#endif
-
-class bssnEScalar_class : public bssn_class
-{
-public:
-     bssnEScalar_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
-                       int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
-                       int a_levi, int maxli, int decni, double maxrexi, double drexi);
-     ~bssnEScalar_class();
-
-     void Initialize();
-     void Read_Ansorg();
-     void Read_Pablo();
-     void Compute_Psi4(int lev);
-     void Step(int lev, int YN);
-     void AnalysisStuff_EScalar(int lev, double dT_lev);
-     void Interp_Constraint();
-     void Constraint_Out(); 
-
-protected:
-     var *Sphio, *Spio;
-     var *Sphi0, *Spi0;
-     var *Sphi,  *Spi;
-     var *Sphi1, *Spi1;
-     var *Sphi_rhs, *Spi_rhs;
-
-     var *Cons_fR;
-
-     monitor *MaxScalar_Monitor;
-};
-
-#endif /* BSSNESCALAR_CLASS_H */
-
+
+#ifndef BSSNESCALAR_CLASS_H
+#define BSSNESCALAR_CLASS_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <string>
+#include <cmath>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include <mpi.h>
+
+#include "cgh.h"
+#include "ShellPatch.h"
+#include "misc.h"
+#include "var.h"
+#include "MyList.h"
+#include "monitor.h"
+#include "surface_integral.h"
+
+#include "macrodef.h"
+
+#ifdef USE_GPU
+#include "bssn_gpu_class.h"
+#else
+#include "bssn_class.h"
+#endif
+
+class bssnEScalar_class : public bssn_class
+{
+public:
+     bssnEScalar_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
+                       int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
+                       int a_levi, int maxli, int decni, double maxrexi, double drexi);
+     ~bssnEScalar_class();
+
+     void Initialize();
+     void Read_Ansorg();
+     void Read_Pablo();
+     void Compute_Psi4(int lev);
+     void Step(int lev, int YN);
+     void AnalysisStuff_EScalar(int lev, double dT_lev);
+     void Interp_Constraint();
+     void Constraint_Out(); 
+
+protected:
+     var *Sphio, *Spio;
+     var *Sphi0, *Spi0;
+     var *Sphi,  *Spi;
+     var *Sphi1, *Spi1;
+     var *Sphi_rhs, *Spi_rhs;
+
+     var *Cons_fR;
+
+     monitor *MaxScalar_Monitor;
+};
+
+#endif /* BSSNESCALAR_CLASS_H */
+

AMSS_NCKU_source/bssn_class.h

@@ -1,206 +1,207 @@
-
-#ifndef BSSN_CLASS_H
-#define BSSN_CLASS_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <fstream>
-#include <cstdlib>
-#include <string>
-#include <cmath>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <fstream.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#endif
-
-#include <mpi.h>
-
-#include "macrodef.h"
-#include "cgh.h"
-#include "ShellPatch.h"
-#include "misc.h"
-#include "var.h"
-#include "MyList.h"
-#include "monitor.h"
-#include "surface_integral.h"
-#include "checkpoint.h"
-
-extern void setpbh(int iBHN, double **iPBH, double *iMass, int rBHN);
-
-class bssn_class
-{
-public:
-       int ngfs;
-       int nprocs, myrank;
-       cgh *GH;
-       ShellPatch *SH;
-       double PhysTime;
-
-       int checkrun;
-       char checkfilename[50];
-       int Steps;
+
+#ifndef BSSN_CLASS_H
+#define BSSN_CLASS_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <fstream>
+#include <cstdlib>
+#include <string>
+#include <cmath>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <fstream.h>
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#endif
+
+#include <mpi.h>
+
+#include "macrodef.h"
+#include "cgh.h"
+#include "ShellPatch.h"
+#include "misc.h"
+#include "var.h"
+#include "MyList.h"
+#include "monitor.h"
+#include "surface_integral.h"
+#include "checkpoint.h"
+
+extern void setpbh(int iBHN, double **iPBH, double *iMass, int rBHN);
+
+class bssn_class
+{
+public:
+       int ngfs;
+       int nprocs, myrank;
+       cgh *GH;
+       ShellPatch *SH;
+       double PhysTime;
+
+       int checkrun;
+       char checkfilename[50];
+       int Steps;
        double StartTime, TotalTime;
        double AnasTime, DumpTime, d2DumpTime, CheckTime;
        double LastAnas, LastConsOut;
+       bool cuda_level0_constraint_cache_valid;
        int *ConstraintRefreshLevels;
        double Courant;
-       double numepss, numepsb, numepsh;
-       int Symmetry;
-       int maxl, decn;
-       double maxrex, drex;
-       int trfls, a_lev;
-
-       double dT;
-       double chitiny;
-
-       double **Porg0, **Porgbr, **Porg, **Porg1, **Porg_rhs;
-       int BH_num, BH_num_input;
-       double *Mass, *Pmom, *Spin;
-       double ADMMass;
-
-       var *phio, *trKo;
-       var *gxxo, *gxyo, *gxzo, *gyyo, *gyzo, *gzzo;
-       var *Axxo, *Axyo, *Axzo, *Ayyo, *Ayzo, *Azzo;
-       var *Gmxo, *Gmyo, *Gmzo;
-       var *Lapo, *Sfxo, *Sfyo, *Sfzo;
-       var *dtSfxo, *dtSfyo, *dtSfzo;
-
-       var *phi0, *trK0;
-       var *gxx0, *gxy0, *gxz0, *gyy0, *gyz0, *gzz0;
-       var *Axx0, *Axy0, *Axz0, *Ayy0, *Ayz0, *Azz0;
-       var *Gmx0, *Gmy0, *Gmz0;
-       var *Lap0, *Sfx0, *Sfy0, *Sfz0;
-       var *dtSfx0, *dtSfy0, *dtSfz0;
-
-       var *phi, *trK;
-       var *gxx, *gxy, *gxz, *gyy, *gyz, *gzz;
-       var *Axx, *Axy, *Axz, *Ayy, *Ayz, *Azz;
-       var *Gmx, *Gmy, *Gmz;
-       var *Lap, *Sfx, *Sfy, *Sfz;
-       var *dtSfx, *dtSfy, *dtSfz;
-
-       var *phi1, *trK1;
-       var *gxx1, *gxy1, *gxz1, *gyy1, *gyz1, *gzz1;
-       var *Axx1, *Axy1, *Axz1, *Ayy1, *Ayz1, *Azz1;
-       var *Gmx1, *Gmy1, *Gmz1;
-       var *Lap1, *Sfx1, *Sfy1, *Sfz1;
-       var *dtSfx1, *dtSfy1, *dtSfz1;
-
-       var *phi_rhs, *trK_rhs;
-       var *gxx_rhs, *gxy_rhs, *gxz_rhs, *gyy_rhs, *gyz_rhs, *gzz_rhs;
-       var *Axx_rhs, *Axy_rhs, *Axz_rhs, *Ayy_rhs, *Ayz_rhs, *Azz_rhs;
-       var *Gmx_rhs, *Gmy_rhs, *Gmz_rhs;
-       var *Lap_rhs, *Sfx_rhs, *Sfy_rhs, *Sfz_rhs;
-       var *dtSfx_rhs, *dtSfy_rhs, *dtSfz_rhs;
-
-       var *rho, *Sx, *Sy, *Sz, *Sxx, *Sxy, *Sxz, *Syy, *Syz, *Szz;
-
-       var *Gamxxx, *Gamxxy, *Gamxxz, *Gamxyy, *Gamxyz, *Gamxzz;
-       var *Gamyxx, *Gamyxy, *Gamyxz, *Gamyyy, *Gamyyz, *Gamyzz;
-       var *Gamzxx, *Gamzxy, *Gamzxz, *Gamzyy, *Gamzyz, *Gamzzz;
-
-       var *Rxx, *Rxy, *Rxz, *Ryy, *Ryz, *Rzz;
-
-       var *Rpsi4, *Ipsi4;
-       var *t1Rpsi4, *t1Ipsi4, *t2Rpsi4, *t2Ipsi4;
-
-       var *Cons_Ham, *Cons_Px, *Cons_Py, *Cons_Pz, *Cons_Gx, *Cons_Gy, *Cons_Gz;
-
-#ifdef Point_Psi4
-       var *phix, *phiy, *phiz;
-       var *trKx, *trKy, *trKz;
-       var *Axxx, *Axxy, *Axxz;
-       var *Axyx, *Axyy, *Axyz;
-       var *Axzx, *Axzy, *Axzz;
-       var *Ayyx, *Ayyy, *Ayyz;
-       var *Ayzx, *Ayzy, *Ayzz;
-       var *Azzx, *Azzy, *Azzz;
-#endif
-       // FIXME: uc = StateList, up = OldStateList, upp = SynchList_cor; so never touch these three data
-       MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
-       MyList<var> *OldStateList, *DumpList;
-       MyList<var> *ConstraintList;
-
-       Parallel::SyncCache *sync_cache_pre;  // per-level cache for predictor sync
-       Parallel::SyncCache *sync_cache_cor;  // per-level cache for corrector sync
-       Parallel::SyncCache *sync_cache_rp_coarse;  // RestrictProlong sync on PatL[lev-1]
-       Parallel::SyncCache *sync_cache_rp_fine;    // RestrictProlong sync on PatL[lev]
-       Parallel::SyncCache *sync_cache_restrict;   // cached Restrict in RestrictProlong
-       Parallel::SyncCache *sync_cache_outbd;      // cached OutBdLow2Hi in RestrictProlong
-
+       double numepss, numepsb, numepsh;
+       int Symmetry;
+       int maxl, decn;
+       double maxrex, drex;
+       int trfls, a_lev;
+
+       double dT;
+       double chitiny;
+
+       double **Porg0, **Porgbr, **Porg, **Porg1, **Porg_rhs;
+       int BH_num, BH_num_input;
+       double *Mass, *Pmom, *Spin;
+       double ADMMass;
+
+       var *phio, *trKo;
+       var *gxxo, *gxyo, *gxzo, *gyyo, *gyzo, *gzzo;
+       var *Axxo, *Axyo, *Axzo, *Ayyo, *Ayzo, *Azzo;
+       var *Gmxo, *Gmyo, *Gmzo;
+       var *Lapo, *Sfxo, *Sfyo, *Sfzo;
+       var *dtSfxo, *dtSfyo, *dtSfzo;
+
+       var *phi0, *trK0;
+       var *gxx0, *gxy0, *gxz0, *gyy0, *gyz0, *gzz0;
+       var *Axx0, *Axy0, *Axz0, *Ayy0, *Ayz0, *Azz0;
+       var *Gmx0, *Gmy0, *Gmz0;
+       var *Lap0, *Sfx0, *Sfy0, *Sfz0;
+       var *dtSfx0, *dtSfy0, *dtSfz0;
+
+       var *phi, *trK;
+       var *gxx, *gxy, *gxz, *gyy, *gyz, *gzz;
+       var *Axx, *Axy, *Axz, *Ayy, *Ayz, *Azz;
+       var *Gmx, *Gmy, *Gmz;
+       var *Lap, *Sfx, *Sfy, *Sfz;
+       var *dtSfx, *dtSfy, *dtSfz;
+
+       var *phi1, *trK1;
+       var *gxx1, *gxy1, *gxz1, *gyy1, *gyz1, *gzz1;
+       var *Axx1, *Axy1, *Axz1, *Ayy1, *Ayz1, *Azz1;
+       var *Gmx1, *Gmy1, *Gmz1;
+       var *Lap1, *Sfx1, *Sfy1, *Sfz1;
+       var *dtSfx1, *dtSfy1, *dtSfz1;
+
+       var *phi_rhs, *trK_rhs;
+       var *gxx_rhs, *gxy_rhs, *gxz_rhs, *gyy_rhs, *gyz_rhs, *gzz_rhs;
+       var *Axx_rhs, *Axy_rhs, *Axz_rhs, *Ayy_rhs, *Ayz_rhs, *Azz_rhs;
+       var *Gmx_rhs, *Gmy_rhs, *Gmz_rhs;
+       var *Lap_rhs, *Sfx_rhs, *Sfy_rhs, *Sfz_rhs;
+       var *dtSfx_rhs, *dtSfy_rhs, *dtSfz_rhs;
+
+       var *rho, *Sx, *Sy, *Sz, *Sxx, *Sxy, *Sxz, *Syy, *Syz, *Szz;
+
+       var *Gamxxx, *Gamxxy, *Gamxxz, *Gamxyy, *Gamxyz, *Gamxzz;
+       var *Gamyxx, *Gamyxy, *Gamyxz, *Gamyyy, *Gamyyz, *Gamyzz;
+       var *Gamzxx, *Gamzxy, *Gamzxz, *Gamzyy, *Gamzyz, *Gamzzz;
+
+       var *Rxx, *Rxy, *Rxz, *Ryy, *Ryz, *Rzz;
+
+       var *Rpsi4, *Ipsi4;
+       var *t1Rpsi4, *t1Ipsi4, *t2Rpsi4, *t2Ipsi4;
+
+       var *Cons_Ham, *Cons_Px, *Cons_Py, *Cons_Pz, *Cons_Gx, *Cons_Gy, *Cons_Gz;
+
+#ifdef Point_Psi4
+       var *phix, *phiy, *phiz;
+       var *trKx, *trKy, *trKz;
+       var *Axxx, *Axxy, *Axxz;
+       var *Axyx, *Axyy, *Axyz;
+       var *Axzx, *Axzy, *Axzz;
+       var *Ayyx, *Ayyy, *Ayyz;
+       var *Ayzx, *Ayzy, *Ayzz;
+       var *Azzx, *Azzy, *Azzz;
+#endif
+       // FIXME: uc = StateList, up = OldStateList, upp = SynchList_cor; so never touch these three data
+       MyList<var> *StateList, *SynchList_pre, *SynchList_cor, *RHSList;
+       MyList<var> *OldStateList, *DumpList;
+       MyList<var> *ConstraintList;
+
+       Parallel::SyncCache *sync_cache_pre;  // per-level cache for predictor sync
+       Parallel::SyncCache *sync_cache_cor;  // per-level cache for corrector sync
+       Parallel::SyncCache *sync_cache_rp_coarse;  // RestrictProlong sync on PatL[lev-1]
+       Parallel::SyncCache *sync_cache_rp_fine;    // RestrictProlong sync on PatL[lev]
+       Parallel::SyncCache *sync_cache_restrict;   // cached Restrict in RestrictProlong
+       Parallel::SyncCache *sync_cache_outbd;      // cached OutBdLow2Hi in RestrictProlong
+
        monitor *ErrorMonitor, *Psi4Monitor, *BHMonitor, *MAPMonitor;
        monitor *ConVMonitor, *TimingMonitor;
        surface_integral *Waveshell;
-       checkpoint *CheckPoint;
-
-public:
-       bssn_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
-                  int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
-                  int a_levi, int maxli, int decni, double maxrexi, double drexi);
-       ~bssn_class();
-
-       void Evolve(int Steps);
-       void RecursiveStep(int lev);
-#if (PSTR == 3)
-       void RecursiveStep(int lev, int num);
-#endif
-#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
-       void ParallelStep();
-       void SHStep();
-#endif
-       void RestrictProlong(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
-       void RestrictProlong_aux(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
-       void RestrictProlong(int lev, int YN, bool BB);
-       void ProlongRestrict(int lev, int YN, bool BB);
-       void Setup_Black_Hole_position();
-       void compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, var *fory, var *forz, int lev);
-       bool read_Pablo_file(int *ext, double *datain, char *filename);
-       void write_Pablo_file(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
-                             char *filename);
-       void AnalysisStuff(int lev, double dT_lev);
-       void Setup_KerrSchild();
-       void Enforce_algcon(int lev, int fg);
-
-       void testRestrict();
-       void testOutBd();
-       
-       bool check_Stdin_Abort(); 
-
-       virtual void Setup_Initial_Data_Cao();
-       virtual void Setup_Initial_Data_Lousto();
-       virtual void Initialize();
-       virtual void Read_Ansorg();
-       virtual void Read_Pablo() {};
-       virtual void Compute_Psi4(int lev);
-       virtual void Step(int lev, int YN);
-       virtual void Interp_Constraint(bool infg);
-       virtual void Constraint_Out();
-       virtual void Compute_Constraint();
-
-#ifdef With_AHF
-protected:
-       MyList<var> *AHList, *AHDList, *GaugeList;
-       int AHfindevery;
-       double AHdumptime;
-       int *lastahdumpid, HN_num; // number of possible horizons
-       int *findeveryl;
-       double *xc, *yc, *zc, *xr, *yr, *zr;
-       bool *trigger;
-       double *dTT;
-       int *dumpid;
-
-public:
-       void AH_Prepare_derivatives();
-       bool AH_Interp_Points(MyList<var> *VarList,
-                             int NN, double **XX,
-                             double *Shellf, int Symmetryi);
-       void AH_Step_Find(int lev, double dT_lev);
-#endif
-};
-#endif /* BSSN_CLASS_H */
+       checkpoint *CheckPoint;
+
+public:
+       bssn_class(double Couranti, double StartTimei, double TotalTimei, double DumpTimei, double d2DumpTimei, double CheckTimei, double AnasTimei,
+                  int Symmetryi, int checkruni, char *checkfilenamei, double numepssi, double numepsbi, double numepshi,
+                  int a_levi, int maxli, int decni, double maxrexi, double drexi);
+       virtual ~bssn_class();
+
+       void Evolve(int Steps);
+       void RecursiveStep(int lev);
+#if (PSTR == 3)
+       void RecursiveStep(int lev, int num);
+#endif
+#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
+       void ParallelStep();
+       void SHStep();
+#endif
+       void RestrictProlong(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
+       void RestrictProlong_aux(int lev, int YN, bool BB, MyList<var> *SL, MyList<var> *OL, MyList<var> *corL);
+       void RestrictProlong(int lev, int YN, bool BB);
+       void ProlongRestrict(int lev, int YN, bool BB);
+       void Setup_Black_Hole_position();
+       void compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, var *fory, var *forz, int lev);
+       bool read_Pablo_file(int *ext, double *datain, char *filename);
+       void write_Pablo_file(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
+                             char *filename);
+       void AnalysisStuff(int lev, double dT_lev);
+       void Setup_KerrSchild();
+       void Enforce_algcon(int lev, int fg);
+
+       void testRestrict();
+       void testOutBd();
+       
+       bool check_Stdin_Abort(); 
+
+       virtual void Setup_Initial_Data_Cao();
+       virtual void Setup_Initial_Data_Lousto();
+       virtual void Initialize();
+       virtual void Read_Ansorg();
+       virtual void Read_Pablo() {};
+       virtual void Compute_Psi4(int lev);
+       virtual void Step(int lev, int YN);
+       virtual void Interp_Constraint(bool infg);
+       virtual void Constraint_Out();
+       virtual void Compute_Constraint();
+
+#ifdef With_AHF
+protected:
+       MyList<var> *AHList, *AHDList, *GaugeList;
+       int AHfindevery;
+       double AHdumptime;
+       int *lastahdumpid, HN_num; // number of possible horizons
+       int *findeveryl;
+       double *xc, *yc, *zc, *xr, *yr, *zr;
+       bool *trigger;
+       double *dTT;
+       int *dumpid;
+
+public:
+       void AH_Prepare_derivatives();
+       bool AH_Interp_Points(MyList<var> *VarList,
+                             int NN, double **XX,
+                             double *Shellf, int Symmetryi);
+       void AH_Step_Find(int lev, double dT_lev);
+#endif
+};
+#endif /* BSSN_CLASS_H */

AMSS_NCKU_source/bssn_em_rhs_c.C

@@ -0,0 +1,323 @@
+#include "macrodef.h"
+#include "bssn_rhs.h"
+#include "share_func.h"
+#include "tool.h"
+#include <cstddef>
+
+/*
+ * C 版 BSSN-EM RHS kernel — replaces empart.f90 + bssn_rhs.f90 for BSSN+Maxwell.
+ *
+ * Computes:
+ *   1. All metric and EM field derivatives
+ *   2. Physical metric, Christoffel-like terms
+ *   3. EM field RHS (E, B, Kpsi, Kphi)
+ *   4. Stress-energy tensor (rho, Si, Sij)
+ *   5. Calls f_compute_rhs_bssn (C BSSN RHS) with stress-energy
+ *   6. Advection + KO dissipation for EM fields
+ *   7. NaN check
+ */
+int f_compute_rhs_bssn_em_c(int *ex, double &T,
+                            double *X, double *Y, double *Z,
+                            double *chi, double *trK,
+                            double *dxx, double *gxy, double *gxz, double *dyy, double *gyz, double *dzz,
+                            double *Axx, double *Axy, double *Axz, double *Ayy, double *Ayz, double *Azz,
+                            double *Gamx, double *Gamy, double *Gamz,
+                            double *Lap, double *betax, double *betay, double *betaz,
+                            double *dtSfx, double *dtSfy, double *dtSfz,
+                            double *Ex,  double *Ey,  double *Ez,
+                            double *Bx,  double *By,  double *Bz,
+                            double *Kpsi, double *Kphi,
+                            double *Jx, double *Jy, double *Jz, double *qchar,
+                            double *chi_rhs, double *trK_rhs,
+                            double *gxx_rhs, double *gxy_rhs, double *gxz_rhs,
+                            double *gyy_rhs, double *gyz_rhs, double *gzz_rhs,
+                            double *Axx_rhs, double *Axy_rhs, double *Axz_rhs,
+                            double *Ayy_rhs, double *Ayz_rhs, double *Azz_rhs,
+                            double *Gamx_rhs, double *Gamy_rhs, double *Gamz_rhs,
+                            double *Lap_rhs, double *betax_rhs, double *betay_rhs, double *betaz_rhs,
+                            double *dtSfx_rhs, double *dtSfy_rhs, double *dtSfz_rhs,
+                            double *Ex_rhs,  double *Ey_rhs,  double *Ez_rhs,
+                            double *Bx_rhs,  double *By_rhs,  double *Bz_rhs,
+                            double *Kpsi_rhs, double *Kphi_rhs,
+                            double *rho, double *Sx, double *Sy, double *Sz,
+                            double *Sxx, double *Sxy, double *Sxz,
+                            double *Syy, double *Syz, double *Szz,
+                            double *Gamxxx, double *Gamxxy, double *Gamxxz,
+                            double *Gamxyy, double *Gamxyz, double *Gamxzz,
+                            double *Gamyxx, double *Gamyxy, double *Gamyxz,
+                            double *Gamyyy, double *Gamyyz, double *Gamyzz,
+                            double *Gamzxx, double *Gamzxy, double *Gamzxz,
+                            double *Gamzyy, double *Gamzyz, double *Gamzzz,
+                            double *Rxx, double *Rxy, double *Rxz,
+                            double *Ryy, double *Ryz, double *Rzz,
+                            double *ham_Res, double *movx_Res, double *movy_Res, double *movz_Res,
+                            double *Gmx_Res, double *Gmy_Res, double *Gmz_Res,
+                            int &Symmetry, int &Lev, double &eps, int &co)
+{
+    (void)T;
+    int gont = 0;
+    const int nx = ex[0], ny = ex[1], nz = ex[2];
+    const int all = nx * ny * nz;
+    const size_t n = (size_t)all;
+
+    const double ZEO = 0.0, ONE = 1.0, TWO = 2.0, FOUR = 4.0, EIT = 8.0;
+    const double HALF = 0.5, THR = 3.0, F3o2 = 1.5, PI = 3.14159265358979323846;
+    const double SYM = 1.0, ANTI = -1.0;
+    const double kappa = 1.0;
+    const double SSS[3]={SYM,SYM,SYM},   AAS[3]={ANTI,ANTI,SYM};
+    const double ASA[3]={ANTI,SYM,ANTI}, SAA[3]={SYM,ANTI,ANTI};
+    const double ASS[3]={ANTI,SYM,SYM},   SAS[3]={SYM,ANTI,SYM};
+    const double SSA[3]={SYM,SYM,ANTI};
+
+    /* ---- allocate temporary arrays ---- */
+    double *chix = (double*)malloc(n*sizeof(double));
+    double *chiy = (double*)malloc(n*sizeof(double));
+    double *chiz = (double*)malloc(n*sizeof(double));
+    double *Exx=(double*)malloc(n*sizeof(double)),*Exy=(double*)malloc(n*sizeof(double)),*Exz=(double*)malloc(n*sizeof(double));
+    double *Eyx=(double*)malloc(n*sizeof(double)),*Eyy=(double*)malloc(n*sizeof(double)),*Eyz=(double*)malloc(n*sizeof(double));
+    double *Ezx=(double*)malloc(n*sizeof(double)),*Ezy=(double*)malloc(n*sizeof(double)),*Ezz=(double*)malloc(n*sizeof(double));
+    double *Bxx=(double*)malloc(n*sizeof(double)),*Bxy=(double*)malloc(n*sizeof(double)),*Bxz=(double*)malloc(n*sizeof(double));
+    double *Byx=(double*)malloc(n*sizeof(double)),*Byy=(double*)malloc(n*sizeof(double)),*Byz=(double*)malloc(n*sizeof(double));
+    double *Bzx=(double*)malloc(n*sizeof(double)),*Bzy=(double*)malloc(n*sizeof(double)),*Bzz=(double*)malloc(n*sizeof(double));
+    double *Kpsix=(double*)malloc(n*sizeof(double)),*Kpsiy=(double*)malloc(n*sizeof(double)),*Kpsiz=(double*)malloc(n*sizeof(double));
+    double *Kphix=(double*)malloc(n*sizeof(double)),*Kphiy=(double*)malloc(n*sizeof(double)),*Kphiz=(double*)malloc(n*sizeof(double));
+    double *Lapx=(double*)malloc(n*sizeof(double)),*Lapy=(double*)malloc(n*sizeof(double)),*Lapz=(double*)malloc(n*sizeof(double));
+    double *betaxx=(double*)malloc(n*sizeof(double)),*betaxy=(double*)malloc(n*sizeof(double)),*betaxz=(double*)malloc(n*sizeof(double));
+    double *betayx=(double*)malloc(n*sizeof(double)),*betayy=(double*)malloc(n*sizeof(double)),*betayz=(double*)malloc(n*sizeof(double));
+    double *betazx=(double*)malloc(n*sizeof(double)),*betazy=(double*)malloc(n*sizeof(double)),*betazz=(double*)malloc(n*sizeof(double));
+    double *gxxx=(double*)malloc(n*sizeof(double)),*gxxy=(double*)malloc(n*sizeof(double)),*gxxz=(double*)malloc(n*sizeof(double));
+    double *gxyx=(double*)malloc(n*sizeof(double)),*gxyy=(double*)malloc(n*sizeof(double)),*gxyz=(double*)malloc(n*sizeof(double));
+    double *gxzx=(double*)malloc(n*sizeof(double)),*gxzy=(double*)malloc(n*sizeof(double)),*gxzz=(double*)malloc(n*sizeof(double));
+    double *gyyx=(double*)malloc(n*sizeof(double)),*gyyy=(double*)malloc(n*sizeof(double)),*gyyz=(double*)malloc(n*sizeof(double));
+    double *gyzx=(double*)malloc(n*sizeof(double)),*gyzy=(double*)malloc(n*sizeof(double)),*gyzz=(double*)malloc(n*sizeof(double));
+    double *gzzx=(double*)malloc(n*sizeof(double)),*gzzy=(double*)malloc(n*sizeof(double)),*gzzz=(double*)malloc(n*sizeof(double));
+    double *gupxx=(double*)malloc(n*sizeof(double)),*gupxy=(double*)malloc(n*sizeof(double)),*gupxz=(double*)malloc(n*sizeof(double));
+    double *gupyy=(double*)malloc(n*sizeof(double)),*gupyz=(double*)malloc(n*sizeof(double)),*gupzz=(double*)malloc(n*sizeof(double));
+
+    if (!chix||!chiy||!chiz||!Exx||!Exy||!Exz||!Eyx||!Eyy||!Eyz||!Ezx||!Ezy||!Ezz||
+        !Bxx||!Bxy||!Bxz||!Byx||!Byy||!Byz||!Bzx||!Bzy||!Bzz||
+        !Kpsix||!Kpsiy||!Kpsiz||!Kphix||!Kphiy||!Kphiz||
+        !Lapx||!Lapy||!Lapz||
+        !betaxx||!betaxy||!betaxz||!betayx||!betayy||!betayz||!betazx||!betazy||!betazz||
+        !gxxx||!gxxy||!gxxz||!gxyx||!gxyy||!gxyz||!gxzx||!gxzy||!gxzz||
+        !gyyx||!gyyy||!gyyz||!gyzx||!gyzy||!gyzz||!gzzx||!gzzy||!gzzz||
+        !gupxx||!gupxy||!gupxz||!gupyy||!gupyz||!gupzz) {
+        gont = 1;
+    }
+
+    /* ==== 1. Compute all derivatives ==== */
+    if (!gont) {
+
+    /* metric derivatives */
+    fderivs(ex, Lap, Lapx, Lapy, Lapz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, betax, betaxx, betaxy, betaxz, X, Y, Z, ANTI, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, betay, betayx, betayy, betayz, X, Y, Z, SYM, ANTI, SYM, Symmetry, Lev);
+    fderivs(ex, betaz, betazx, betazy, betazz, X, Y, Z, SYM, SYM, ANTI, Symmetry, Lev);
+    fderivs(ex, chi, chix, chiy, chiz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, dxx, gxxx, gxxy, gxxz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, gxy, gxyx, gxyy, gxyz, X, Y, Z, ANTI, ANTI, SYM, Symmetry, Lev);
+    fderivs(ex, gxz, gxzx, gxzy, gxzz, X, Y, Z, ANTI, SYM, ANTI, Symmetry, Lev);
+    fderivs(ex, dyy, gyyx, gyyy, gyyz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, gyz, gyzx, gyzy, gyzz, X, Y, Z, SYM, ANTI, ANTI, Symmetry, Lev);
+    fderivs(ex, dzz, gzzx, gzzy, gzzz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+
+    /* EM field derivatives */
+    fderivs(ex, Kpsi, Kpsix, Kpsiy, Kpsiz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, Kphi, Kphix, Kphiy, Kphiz, X, Y, Z, SYM, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, Ex, Exx, Exy, Exz, X, Y, Z, ANTI, SYM, SYM, Symmetry, Lev);
+    fderivs(ex, Ey, Eyx, Eyy, Eyz, X, Y, Z, SYM, ANTI, SYM, Symmetry, Lev);
+    fderivs(ex, Ez, Ezx, Ezy, Ezz, X, Y, Z, SYM, SYM, ANTI, Symmetry, Lev);
+    fderivs(ex, Bx, Bxx, Bxy, Bxz, X, Y, Z, SYM, ANTI, ANTI, Symmetry, Lev);
+    fderivs(ex, By, Byx, Byy, Byz, X, Y, Z, ANTI, SYM, ANTI, Symmetry, Lev);
+    fderivs(ex, Bz, Bzx, Bzy, Bzz, X, Y, Z, ANTI, ANTI, SYM, Symmetry, Lev);
+
+    /* ==== 2. Compute EM RHS and stress-energy ==== */
+    const double F1o4PI = ONE / (FOUR * PI);
+    for (size_t i = 0; i < n; ++i) {
+        const double alpn1 = Lap[i] + ONE;
+        const double chin1 = chi[i] + ONE;
+        const double chi3o2 = sqrt(chin1) * chin1;  // chi^{3/2}
+        const double ichi = ONE / chin1;
+
+        /* physical metric */
+        const double pgxx = (dxx[i] + ONE) * ichi;
+        const double pgyy = (dyy[i] + ONE) * ichi;
+        const double pgzz = (dzz[i] + ONE) * ichi;
+        const double pgxy = gxy[i] * ichi;
+        const double pgxz = gxz[i] * ichi;
+        const double pgyz = gyz[i] * ichi;
+
+        /* inverse physical metric */
+        const double det = pgxx * pgyy * pgzz + pgxy * pgyz * pgxz + pgxz * pgxy * pgyz
+                         - pgxz * pgyy * pgxz - pgxy * pgxy * pgzz - pgxx * pgyz * pgyz;
+        const double idet = ONE / det;
+        const double upxx = (pgyy * pgzz - pgyz * pgyz) * idet;
+        const double upxy = -(pgxy * pgzz - pgyz * pgxz) * idet;
+        const double upxz = (pgxy * pgyz - pgyy * pgxz) * idet;
+        const double upyy = (pgxx * pgzz - pgxz * pgxz) * idet;
+        const double upyz = -(pgxx * pgyz - pgxy * pgxz) * idet;
+        const double upzz = (pgxx * pgyy - pgxy * pgxy) * idet;
+        gupxx[i]=upxx; gupxy[i]=upxy; gupxz[i]=upxz;
+        gupyy[i]=upyy; gupyz[i]=upyz; gupzz[i]=upzz;
+
+        /* E-field RHS */
+        /* curl(B) part: epsilon^{ijk} ∂_j (alpha * B_k) in coordinate basis */
+        /* Using lower-index B fields: B_i_lower = pg_{ij} * B^j */
+        const double BxL = pgxx*Bx[i] + pgxy*By[i] + pgxz*Bz[i];
+        const double ByL = pgxy*Bx[i] + pgyy*By[i] + pgyz*Bz[i];
+        const double BzL = pgxz*Bx[i] + pgyz*By[i] + pgzz*Bz[i];
+
+        /* Physical metric derivatives (chain rule from conformal) */
+        const double pgxx_x = (gxxx[i] - pgxx*chix[i]) * ichi;
+        /* const double pgxx_y = (gxxy[i] - pgxx*chiy[i]) * ichi; */
+        const double pgxy_x = (gxyx[i] - pgxy*chix[i]) * ichi;
+        const double pgxy_y = (gxyy[i] - pgxy*chiy[i]) * ichi;
+        const double pgxz_x = (gxzx[i] - pgxz*chix[i]) * ichi;
+        const double pgxz_z = (gxzz[i] - pgxz*chiz[i]) * ichi;
+        const double pgyy_y = (gyyy[i] - pgyy*chiy[i]) * ichi;
+        const double pgyz_y = (gyzy[i] - pgyz*chiy[i]) * ichi;
+        const double pgyz_z = (gyzz[i] - pgyz*chiz[i]) * ichi;
+        const double pgzz_z = (gzzz[i] - pgzz*chiz[i]) * ichi;
+
+        /* Curl_x(B) = ∂_y (alpha*BzL) - ∂_z (alpha*ByL) */
+        const double aBx = alpn1*BxL, aBy = alpn1*ByL, aBz = alpn1*BzL;
+        const double curlBx = (aBz*Lapy[i] + alpn1*(pgxz*Bxy[i]+pgyz*Byy[i]+pgzz*Bzy[i]) + alpn1*(Bx[i]*gxzy[i]+By[i]*gyzy[i]+Bz[i]*gzzy[i]))
+                            - (aBy*Lapz[i] + alpn1*(pgxy*Bxz[i]+pgyy*Byz[i]+pgyz*Bzz[i]) + alpn1*(Bx[i]*gxyz[i]+By[i]*gyyz[i]+Bz[i]*gyzz[i]));
+        double curlBy = (aBx*Lapz[i] + alpn1*(pgxx*Bxz[i]+pgxy*Byz[i]+pgxz*Bzz[i]) + alpn1*(Bx[i]*gxxz[i]+By[i]*gxyz[i]+Bz[i]*gxzz[i]))
+                      - (aBz*Lapx[i] + alpn1*(pgxz*Bxx[i]+pgyz*Byx[i]+pgzz*Bzx[i]) + alpn1*(Bx[i]*gxzx[i]+By[i]*gyzx[i]+Bz[i]*gzzx[i]));
+        double curlBz = (aBy*Lapx[i] + alpn1*(pgxy*Bxx[i]+pgyy*Byx[i]+pgyz*Bzx[i]) + alpn1*(Bx[i]*gxyx[i]+By[i]*gyyx[i]+Bz[i]*gyzx[i]))
+                      - (aBx*Lapy[i] + alpn1*(pgxx*Bxy[i]+pgxy*Byy[i]+pgxz*Bzy[i]) + alpn1*(Bx[i]*gxxy[i]+By[i]*gxyy[i]+Bz[i]*gxzy[i]));
+
+        /* Advection part: -beta^j * ∂_j E^i */
+        const double advEx = Ex[i]*betaxx[i] + Ey[i]*betaxy[i] + Ez[i]*betaxz[i];
+        const double advEy = Ex[i]*betayx[i] + Ey[i]*betayy[i] + Ez[i]*betayz[i];
+        const double advEz = Ex[i]*betazx[i] + Ey[i]*betazy[i] + Ez[i]*betazz[i];
+
+        /* grad(Kpsi) contracted with inverse metric */
+        const double gupKx = upxx*Kpsix[i] + upxy*Kpsiy[i] + upxz*Kpsiz[i];
+        const double gupKy = upxy*Kpsix[i] + upyy*Kpsiy[i] + upyz*Kpsiz[i];
+        const double gupKz = upxz*Kpsix[i] + upyz*Kpsiy[i] + upzz*Kpsiz[i];
+
+        Ex_rhs[i] = alpn1*trK[i]*Ex[i] - advEx - FOUR*PI*alpn1*Jx[i] - alpn1*gupKx + chi3o2*curlBx;
+        Ey_rhs[i] = alpn1*trK[i]*Ey[i] - advEy - FOUR*PI*alpn1*Jy[i] - alpn1*gupKy + chi3o2*curlBy;
+        Ez_rhs[i] = alpn1*trK[i]*Ez[i] - advEz - FOUR*PI*alpn1*Jz[i] - alpn1*gupKz + chi3o2*curlBz;
+
+        /* B-field RHS: similar but with -chi^{3/2} * curl(E) and grad(Kphi) */
+        const double ExL = pgxx*Ex[i] + pgxy*Ey[i] + pgxz*Ez[i];
+        const double EyL = pgxy*Ex[i] + pgyy*Ey[i] + pgyz*Ez[i];
+        const double EzL = pgxz*Ex[i] + pgyz*Ey[i] + pgzz*Ez[i];
+
+        const double aEx = alpn1*ExL, aEy = alpn1*EyL, aEz = alpn1*EzL;
+        const double curlEx = (aEz*Lapy[i] + alpn1*(pgxz*Exy[i]+pgyz*Eyy[i]+pgzz*Ezy[i]) + alpn1*(Ex[i]*gxzy[i]+Ey[i]*gyzy[i]+Ez[i]*gzzy[i]))
+                            - (aEy*Lapz[i] + alpn1*(pgxy*Exz[i]+pgyy*Eyz[i]+pgyz*Ezz[i]) + alpn1*(Ex[i]*gxyz[i]+Ey[i]*gyyz[i]+Ez[i]*gyzz[i]));
+        double curlEy = (aEx*Lapz[i] + alpn1*(pgxx*Exz[i]+pgxy*Eyz[i]+pgxz*Ezz[i]) + alpn1*(Ex[i]*gxxz[i]+Ey[i]*gxyz[i]+Ez[i]*gxzz[i]))
+                      - (aEz*Lapx[i] + alpn1*(pgxz*Exx[i]+pgyz*Eyx[i]+pgzz*Ezx[i]) + alpn1*(Ex[i]*gxzx[i]+Ey[i]*gyzx[i]+Ez[i]*gzzx[i]));
+        double curlEz = (aEy*Lapx[i] + alpn1*(pgxy*Exx[i]+pgyy*Eyx[i]+pgyz*Ezx[i]) + alpn1*(Ex[i]*gxyx[i]+Ey[i]*gyyx[i]+Ez[i]*gyzx[i]))
+                      - (aEx*Lapy[i] + alpn1*(pgxx*Exy[i]+pgxy*Eyy[i]+pgxz*Ezy[i]) + alpn1*(Ex[i]*gxxy[i]+Ey[i]*gxyy[i]+Ez[i]*gxzy[i]));
+
+        const double advBx = Bx[i]*betaxx[i] + By[i]*betaxy[i] + Bz[i]*betaxz[i];
+        const double advBy = Bx[i]*betayx[i] + By[i]*betayy[i] + Bz[i]*betayz[i];
+        const double advBz = Bx[i]*betazx[i] + By[i]*betazy[i] + Bz[i]*betazz[i];
+
+        const double gupKphix = upxx*Kphix[i] + upxy*Kphiy[i] + upxz*Kphiz[i];
+        const double gupKphiy = upxy*Kphix[i] + upyy*Kphiy[i] + upyz*Kphiz[i];
+        const double gupKphiz = upxz*Kphix[i] + upyz*Kphiy[i] + upzz*Kphiz[i];
+
+        Bx_rhs[i] = alpn1*trK[i]*Bx[i] - advBx - alpn1*gupKphix - chi3o2*curlEx;
+        By_rhs[i] = alpn1*trK[i]*By[i] - advBy - alpn1*gupKphiy - chi3o2*curlEy;
+        Bz_rhs[i] = alpn1*trK[i]*Bz[i] - advBz - alpn1*gupKphiz - chi3o2*curlEz;
+
+        /* Scalar potential RHS */
+        const double divE = Exx[i] + Eyy[i] + Ezz[i];
+        const double divB = Bxx[i] + Byy[i] + Bzz[i];
+        const double chiCont = F3o2 * ichi * (chix[i]*Ex[i] + chiy[i]*Ey[i] + chiz[i]*Ez[i]);
+        Kpsi_rhs[i] = FOUR*PI*alpn1*qchar[i] - alpn1*kappa*Kpsi[i] - alpn1*(divE - chiCont);
+        Kphi_rhs[i] = -alpn1*kappa*Kphi[i] - alpn1*(divB - F3o2*ichi*(chix[i]*Bx[i] + chiy[i]*By[i] + chiz[i]*Bz[i]));
+
+        /* Stress-energy tensor */
+        const double E2 = pgxx*Ex[i]*Ex[i] + pgyy*Ey[i]*Ey[i] + pgzz*Ez[i]*Ez[i]
+                        + TWO*(pgxy*Ex[i]*Ey[i] + pgxz*Ex[i]*Ez[i] + pgyz*Ey[i]*Ez[i]);
+        const double B2 = pgxx*Bx[i]*Bx[i] + pgyy*By[i]*By[i] + pgzz*Bz[i]*Bz[i]
+                        + TWO*(pgxy*Bx[i]*By[i] + pgxz*Bx[i]*Bz[i] + pgyz*By[i]*Bz[i]);
+        rho[i] = (E2 + B2) / (EIT * PI);
+        const double ichi3o2 = ONE / chi3o2;
+        Sx[i] = (Ey[i]*Bz[i] - Ez[i]*By[i]) * F1o4PI * ichi3o2;
+        Sy[i] = (Ez[i]*Bx[i] - Ex[i]*Bz[i]) * F1o4PI * ichi3o2;
+        Sz[i] = (Ex[i]*By[i] - Ey[i]*Bx[i]) * F1o4PI * ichi3o2;
+        const double lExi = pgxx*Ex[i] + pgxy*Ey[i] + pgxz*Ez[i];
+        const double lEyi = pgxy*Ex[i] + pgyy*Ey[i] + pgyz*Ez[i];
+        const double lEzi = pgxz*Ex[i] + pgyz*Ey[i] + pgzz*Ez[i];
+        const double lBxi = pgxx*Bx[i] + pgxy*By[i] + pgxz*Bz[i];
+        const double lByi = pgxy*Bx[i] + pgyy*By[i] + pgyz*Bz[i];
+        const double lBzi = pgxz*Bx[i] + pgyz*By[i] + pgzz*Bz[i];
+        Sxx[i] = rho[i]*pgxx - (lExi*lExi + lBxi*lBxi) * F1o4PI;
+        Sxy[i] = rho[i]*pgxy - (lExi*lEyi + lBxi*lByi) * F1o4PI;
+        Sxz[i] = rho[i]*pgxz - (lExi*lEzi + lBxi*lBzi) * F1o4PI;
+        Syy[i] = rho[i]*pgyy - (lEyi*lEyi + lByi*lByi) * F1o4PI;
+        Syz[i] = rho[i]*pgyz - (lEyi*lEzi + lByi*lBzi) * F1o4PI;
+        Szz[i] = rho[i]*pgzz - (lEzi*lEzi + lBzi*lBzi) * F1o4PI;
+    }
+
+    /* ==== 3. Call BSSN RHS with EM stress-energy ==== */
+    gont = f_compute_rhs_bssn(ex, T, X, Y, Z,
+        chi, trK, dxx, gxy, gxz, dyy, gyz, dzz,
+        Axx, Axy, Axz, Ayy, Ayz, Azz,
+        Gamx, Gamy, Gamz, Lap, betax, betay, betaz, dtSfx, dtSfy, dtSfz,
+        chi_rhs, trK_rhs,
+        gxx_rhs, gxy_rhs, gxz_rhs, gyy_rhs, gyz_rhs, gzz_rhs,
+        Axx_rhs, Axy_rhs, Axz_rhs, Ayy_rhs, Ayz_rhs, Azz_rhs,
+        Gamx_rhs, Gamy_rhs, Gamz_rhs, Lap_rhs, betax_rhs, betay_rhs, betaz_rhs,
+        dtSfx_rhs, dtSfy_rhs, dtSfz_rhs,
+        rho, Sx, Sy, Sz, Sxx, Sxy, Sxz, Syy, Syz, Szz,
+        Gamxxx, Gamxxy, Gamxxz, Gamxyy, Gamxyz, Gamxzz,
+        Gamyxx, Gamyxy, Gamyxz, Gamyyy, Gamyyz, Gamyzz,
+        Gamzxx, Gamzxy, Gamzxz, Gamzyy, Gamzyz, Gamzzz,
+        Rxx, Rxy, Rxz, Ryy, Ryz, Rzz,
+        ham_Res, movx_Res, movy_Res, movz_Res,
+        Gmx_Res, Gmy_Res, Gmz_Res,
+        Symmetry, Lev, eps, co);
+    if (!gont) {
+
+    /* ==== 4. Advection terms for EM fields ==== */
+    lopsided(ex, X, Y, Z, Kpsi, Kpsi_rhs, betax, betay, betaz, Symmetry, SSS);
+    lopsided(ex, X, Y, Z, Kphi, Kphi_rhs, betax, betay, betaz, Symmetry, SSS);
+    lopsided(ex, X, Y, Z, Ex,   Ex_rhs,   betax, betay, betaz, Symmetry, ASS);
+    lopsided(ex, X, Y, Z, Ey,   Ey_rhs,   betax, betay, betaz, Symmetry, SAS);
+    lopsided(ex, X, Y, Z, Ez,   Ez_rhs,   betax, betay, betaz, Symmetry, SSA);
+    lopsided(ex, X, Y, Z, Bx,   Bx_rhs,   betax, betay, betaz, Symmetry, SAA);
+    lopsided(ex, X, Y, Z, By,   By_rhs,   betax, betay, betaz, Symmetry, ASA);
+    lopsided(ex, X, Y, Z, Bz,   Bz_rhs,   betax, betay, betaz, Symmetry, AAS);
+
+    /* ==== 5. KO dissipation for EM fields ==== */
+    if (eps > ZEO) {
+        kodis(ex, X, Y, Z, Kpsi, Kpsi_rhs, SSS, Symmetry, eps);
+        kodis(ex, X, Y, Z, Kphi, Kphi_rhs, SSS, Symmetry, eps);
+        kodis(ex, X, Y, Z, Ex,   Ex_rhs,   ASS, Symmetry, eps);
+        kodis(ex, X, Y, Z, Ey,   Ey_rhs,   SAS, Symmetry, eps);
+        kodis(ex, X, Y, Z, Ez,   Ez_rhs,   SSA, Symmetry, eps);
+        kodis(ex, X, Y, Z, Bx,   Bx_rhs,   SAA, Symmetry, eps);
+        kodis(ex, X, Y, Z, By,   By_rhs,   ASA, Symmetry, eps);
+        kodis(ex, X, Y, Z, Bz,   Bz_rhs,   AAS, Symmetry, eps);
+    }
+
+    /* ==== 6. NaN check ==== */
+        for (int i = 0; i < all; ++i) {
+            if (!isfinite(Ex_rhs[i]+Ey_rhs[i]+Ez_rhs[i]+Bx_rhs[i]+By_rhs[i]+Bz_rhs[i]+Kpsi_rhs[i]+Kphi_rhs[i])) {
+                gont = 1; break;
+            }
+        }
+        } /* inner if (!gont) */
+    } /* outer if (!gont) */
+
+    free(chix);free(chiy);free(chiz);
+    free(Exx);free(Exy);free(Exz);free(Eyx);free(Eyy);free(Eyz);free(Ezx);free(Ezy);free(Ezz);
+    free(Bxx);free(Bxy);free(Bxz);free(Byx);free(Byy);free(Byz);free(Bzx);free(Bzy);free(Bzz);
+    free(Kpsix);free(Kpsiy);free(Kpsiz);
+    free(Kphix);free(Kphiy);free(Kphiz);
+    free(Lapx);free(Lapy);free(Lapz);
+    free(betaxx);free(betaxy);free(betaxz);free(betayx);free(betayy);free(betayz);free(betazx);free(betazy);free(betazz);
+    free(gxxx);free(gxxy);free(gxxz);free(gxyx);free(gxyy);free(gxyz);free(gxzx);free(gxzy);free(gxzz);
+    free(gyyx);free(gyyy);free(gyyz);free(gyzx);free(gyzy);free(gyzz);free(gzzx);free(gzzy);free(gzzz);
+    free(gupxx);free(gupxy);free(gupxz);free(gupyy);free(gupyz);free(gupzz);
+    return gont;
+}

AMSS_NCKU_source/bssn_gpu.h

@@ -2,7 +2,7 @@
 #ifndef BSSN_GPU_H_
 #define BSSN_GPU_H_
 #include "bssn_macro.h"
-#include "macrodef.fh"
+#include "macrodef.h"
 
 #define DEVICE_ID 0
 // #define DEVICE_ID_BY_MPI_RANK
@@ -25,49 +25,32 @@
 /**  main function */
 int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,
             double *X, double *Y, double *Z,
-
             double *chi, double *trK,
-
             double *dxx, double *gxy, double *gxz, double *dyy, double *gyz, double *dzz,
-
             double *Axx, double *Axy, double *Axz, double *Ayy, double *Ayz, double *Azz,
-
             double *Gamx, double *Gamy, double *Gamz,
-
             double *Lap, double *betax, double *betay, double *betaz,
-
             double *dtSfx, double *dtSfy, double *dtSfz,
-
             double *chi_rhs, double *trK_rhs,
-
             double *gxx_rhs, double *gxy_rhs, double *gxz_rhs, double *gyy_rhs, double *gyz_rhs, double *gzz_rhs,
-
             double *Axx_rhs, double *Axy_rhs, double *Axz_rhs, double *Ayy_rhs, double *Ayz_rhs, double *Azz_rhs,
-
             double *Gamx_rhs, double *Gamy_rhs, double *Gamz_rhs,
-
             double *Lap_rhs, double *betax_rhs, double *betay_rhs, double *betaz_rhs,
-
             double *dtSfx_rhs, double *dtSfy_rhs, double *dtSfz_rhs,
-
             double *rho, double *Sx, double *Sy, double *Sz, double *Sxx,
             double *Sxy, double *Sxz, double *Syy, double *Syz, double *Szz,
-
             double *Gamxxx, double *Gamxxy, double *Gamxxz, double *Gamxyy, double *Gamxyz, double *Gamxzz,
-
             double *Gamyxx, double *Gamyxy, double *Gamyxz, double *Gamyyy, double *Gamyyz, double *Gamyzz,
-
             double *Gamzxx, double *Gamzxy, double *Gamzxz, double *Gamzyy, double *Gamzyz, double *Gamzzz,
-
             double *Rxx, double *Rxy, double *Rxz, double *Ryy, double *Ryz, double *Rzz,
-
             double *ham_Res, double *movx_Res, double *movy_Res, double *movz_Res,
             double *Gmx_Res, double *Gmy_Res, double *Gmz_Res,
             int &Symmetry, int &Lev, double &eps, int &co);
 
 int gpu_rhs_ss(RHS_SS_PARA);
 
-/** Init GPU side data in GPUMeta. */
-// void init_fluid_meta_gpu(GPUMeta *gpu_meta);
+#define Z4C_SS_PARA int calledby, int mpi_rank, int *ex, double &T, double *crho, double *sigma, double *R, double *X, double *Y, double *Z, double *drhodx, double *drhody, double *drhodz, double *dsigmadx, double *dsigmady, double *dsigmadz, double *dRdx, double *dRdy, double *dRdz, double *drhodxx, double *drhodxy, double *drhodxz, double *drhodyy, double *drhodyz, double *drhodzz, double *dsigmadxx, double *dsigmadxy, double *dsigmadxz, double *dsigmadyy, double *dsigmadyz, double *dsigmadzz, double *dRdxx, double *dRdxy, double *dRdxz, double *dRdyy, double *dRdyz, double *dRdzz, double *chi, double *trK, double *dxx, double *gxy, double *gxz, double *dyy, double *gyz, double *dzz, double *Axx, double *Axy, double *Axz, double *Ayy, double *Ayz, double *Azz, double *Gamx, double *Gamy, double *Gamz, double *Lap, double *betax, double *betay, double *betaz, double *dtSfx, double *dtSfy, double *dtSfz, double *TZ, double *chi_rhs, double *trK_rhs, double *gxx_rhs, double *gxy_rhs, double *gxz_rhs, double *gyy_rhs, double *gyz_rhs, double *gzz_rhs, double *Axx_rhs, double *Axy_rhs, double *Axz_rhs, double *Ayy_rhs, double *Ayz_rhs, double *Azz_rhs, double *Gamx_rhs, double *Gamy_rhs, double *Gamz_rhs, double *Lap_rhs, double *betax_rhs, double *betay_rhs, double *betaz_rhs, double *dtSfx_rhs, double *dtSfy_rhs, double *dtSfz_rhs, double *TZ_rhs, double *rho, double *Sx, double *Sy, double *Sz, double *Sxx, double *Sxy, double *Sxz, double *Syy, double *Syz, double *Szz, double *Gamxxx, double *Gamxxy, double *Gamxxz, double *Gamxyy, double *Gamxyz, double *Gamxzz, double *Gamyxx, double *Gamyxy, double *Gamyxz, double *Gamyyy, double *Gamyyz, double *Gamyzz, double *Gamzxx, double *Gamzxy, double *Gamzxz, double *Gamzyy, double *Gamzyz, double *Gamzzz, double *Rxx, double *Rxy, double *Rxz, double *Ryy, double *Ryz, double *Rzz, double *ham_Res, double *movx_Res, double *movy_Res, double *movz_Res, double *Gmx_Res, double *Gmy_Res, double *Gmz_Res, int &Symmetry, int &Lev, double &eps, int &sst, int &co
+
+int gpu_rhs_z4c_ss(Z4C_SS_PARA);
 
 #endif

AMSS_NCKU_source/bssn_macro.C

@@ -1,124 +1,124 @@
-#include "bssn_macro.h"
-#include <iostream>
-#include <fstream>
-#include <cstring>
-using namespace std;
-
-int compare_two_file(char *fname1, char *fname2, int data_num)
-{
-	// read file
-	fstream file1(fname1, ios_base::in);
-	fstream file2(fname2, ios_base::in);
-	double *d1, *d2;
-	d1 = (double *)malloc(sizeof(double) * data_num);
-	d2 = (double *)malloc(sizeof(double) * data_num);
-
-	for (int i = 0; i < data_num; ++i)
-	{
-		file1.read((char *)(d1 + i), sizeof(double));
-		file2.read((char *)(d2 + i), sizeof(double));
-	}
-
-	// compare data
-	bool is_match = true;
-	for (int i = 0; i < data_num; ++i)
-	{
-		if (d1[i] != d2[i])
-		{
-			is_match = false;
-			cout << "miss match at position " << i << endl;
-			break;
-		}
-	}
-	if (is_match)
-		cout << "Result is right." << endl;
-
-	free(d1);
-	free(d2);
-	file1.close();
-	file2.close();
-	return 0;
-}
-void printMatrix(int ftag1, int ftag2, double *d1, double *d2, int ord)
-{
-	char fname1[32];
-	char fname2[32];
-	// char ftag1[32]; char ftag2[32];
-	// sprintf(ftag1,"%d",ftag1);
-	strcpy(fname1, "matrix_f.show");
-	// strcat(fname1,ftag1);
-
-	// sprintf(ftag2,"%d",ftag2);
-	strcpy(fname2, "matrix_g.show");
-	// strcat(fname2,ftag2);
-
-	ofstream fout0, fout1, fout2;
-	fout1.open(fname1);
-	fout2.open(fname2);
-
-	for (int k = 0; k < 65; k++)
-	{
-		fout1 << "---------square " << k << " ----------" << endl;
-		fout2 << "---------square " << k << " ----------" << endl;
-		for (int j = 0; j < 67 + ord * 2; j++)
-		{
-			for (int i = 0; i < 67 + ord * 2; i++)
-			{
-				fout1 << d1[i + j * (67 + ord * 2) + k * ((67 + ord * 2) * (67 + ord * 2))] << ' ';
-				fout2 << d2[i + j * (67 + ord * 2) + k * ((67 + ord * 2) * (67 + ord * 2))] << ' ';
-				// fout1<<test_output_g[i+j*(cg->shape[0]) + k*(_2d_size)] <<' ';
-				// fout2<<test_fh_f    [i+j*(cg->shape[0]) + k*(_2d_size)] <<' ';
-			}
-			fout1 << endl;
-			fout2 << endl;
-		}
-	}
-}
-
-int compare_result(int ftag1, double *d2, int data_num)
-{
-	// read file
-	char fname1[32];
-	char ftag[32];
-	// itoa(filetag,ftag,10);
-	sprintf(ftag, "%d", ftag1);
-	strcpy(fname1, "matrix_f.out");
-	strcat(fname1, ftag);
-
-	fstream file1(fname1, ios_base::in);
-	double *d1;
-	d1 = (double *)malloc(sizeof(double) * data_num);
-
-	for (int i = 0; i < data_num; ++i)
-	{
-		file1.read((char *)(d1 + i), sizeof(double));
-	}
-
-	// compare data
-	bool is_match = true;
-	double delta;
-	for (int i = 0; i < data_num; ++i)
-	{
-		delta = d1[i] - d2[i];
-		if (delta < 0)
-			delta = -delta;
-		if (delta > 1e-14)
-		{
-			is_match = false;
-			cout << fname1 << "::miss match at position " << i << endl;
-			break;
-		}
-		// if(i<100 && i>50)
-		//	cout<<d1[i]<<" "<<d2[i]<<endl;
-	}
-	if (is_match)
-		cout << ftag1 << "::matched." << endl;
-
-	if (ftag1 == 0)
-	{
-		printMatrix(1, 2, d1, d2, 3);
-	}
-	free(d1);
-	file1.close();
-	return 0;
-}
+#include "bssn_macro.h"
+#include <iostream>
+#include <fstream>
+#include <cstring>
+using namespace std;
+
+int compare_two_file(char *fname1, char *fname2, int data_num)
+{
+	// read file
+	fstream file1(fname1, ios_base::in);
+	fstream file2(fname2, ios_base::in);
+	double *d1, *d2;
+	d1 = (double *)malloc(sizeof(double) * data_num);
+	d2 = (double *)malloc(sizeof(double) * data_num);
+
+	for (int i = 0; i < data_num; ++i)
+	{
+		file1.read((char *)(d1 + i), sizeof(double));
+		file2.read((char *)(d2 + i), sizeof(double));
+	}
+
+	// compare data
+	bool is_match = true;
+	for (int i = 0; i < data_num; ++i)
+	{
+		if (d1[i] != d2[i])
+		{
+			is_match = false;
+			cout << "miss match at position " << i << endl;
+			break;
+		}
+	}
+	if (is_match)
+		cout << "Result is right." << endl;
+
+	free(d1);
+	free(d2);
+	file1.close();
+	file2.close();
+	return 0;
+}
+void printMatrix(int ftag1, int ftag2, double *d1, double *d2, int ord)
+{
+	char fname1[32];
+	char fname2[32];
+	// char ftag1[32]; char ftag2[32];
+	// sprintf(ftag1,"%d",ftag1);
+	strcpy(fname1, "matrix_f.show");
+	// strcat(fname1,ftag1);
+
+	// sprintf(ftag2,"%d",ftag2);
+	strcpy(fname2, "matrix_g.show");
+	// strcat(fname2,ftag2);
+
+	ofstream fout0, fout1, fout2;
+	fout1.open(fname1);
+	fout2.open(fname2);
+
+	for (int k = 0; k < 65; k++)
+	{
+		fout1 << "---------square " << k << " ----------" << endl;
+		fout2 << "---------square " << k << " ----------" << endl;
+		for (int j = 0; j < 67 + ord * 2; j++)
+		{
+			for (int i = 0; i < 67 + ord * 2; i++)
+			{
+				fout1 << d1[i + j * (67 + ord * 2) + k * ((67 + ord * 2) * (67 + ord * 2))] << ' ';
+				fout2 << d2[i + j * (67 + ord * 2) + k * ((67 + ord * 2) * (67 + ord * 2))] << ' ';
+				// fout1<<test_output_g[i+j*(cg->shape[0]) + k*(_2d_size)] <<' ';
+				// fout2<<test_fh_f    [i+j*(cg->shape[0]) + k*(_2d_size)] <<' ';
+			}
+			fout1 << endl;
+			fout2 << endl;
+		}
+	}
+}
+
+int compare_result(int ftag1, double *d2, int data_num)
+{
+	// read file
+	char fname1[32];
+	char ftag[32];
+	// itoa(filetag,ftag,10);
+	sprintf(ftag, "%d", ftag1);
+	strcpy(fname1, "matrix_f.out");
+	strcat(fname1, ftag);
+
+	fstream file1(fname1, ios_base::in);
+	double *d1;
+	d1 = (double *)malloc(sizeof(double) * data_num);
+
+	for (int i = 0; i < data_num; ++i)
+	{
+		file1.read((char *)(d1 + i), sizeof(double));
+	}
+
+	// compare data
+	bool is_match = true;
+	double delta;
+	for (int i = 0; i < data_num; ++i)
+	{
+		delta = d1[i] - d2[i];
+		if (delta < 0)
+			delta = -delta;
+		if (delta > 1e-14)
+		{
+			is_match = false;
+			cout << fname1 << "::miss match at position " << i << endl;
+			break;
+		}
+		// if(i<100 && i>50)
+		//	cout<<d1[i]<<" "<<d2[i]<<endl;
+	}
+	if (is_match)
+		cout << ftag1 << "::matched." << endl;
+
+	if (ftag1 == 0)
+	{
+		printMatrix(1, 2, d1, d2, 3);
+	}
+	free(d1);
+	file1.close();
+	return 0;
+}

AMSS_NCKU_source/bssn_macro.h

@@ -1,94 +1,94 @@
-#ifndef BSSN_STEP_H
-#define BSSN_STEP_H
-//1---------------------FLAGS---------------------
-
-#define USE_GPU
-#define MAX_GPU_PROCESS_NUM 1
-#define COUNT_CPU_RHS_TIME
-
-
-//2---------------------TIMER---------------------
-//2.1 TIMER_INIT
-//2.2 TIMER_TIC_WITHOUT_OUTPUT
-//2.3 TIMER_TIC(tag,order,label)
-//2.4 TIMER_TIC_TAIL_OF_FUNC(tag,label)
-
-#define TIME_COUNT_EACH_RANK 0
-
-#define TIMER_INIT \
-double clock_prev,clock_curr,step_begin_clock;\
-if(1 == 1){\
-	clock_curr =MPI_Wtime();\
-	step_begin_clock = MPI_Wtime();\
-}else{\
-if(myrank == 0){\
-	clock_curr= MPI_Wtime();\
-	step_begin_clock = MPI_Wtime();\
-}\
-}
-      
-#define TIMER_TIC(tag,order,label) \
-if(TIME_COUNT_EACH_RANK == 1){\
-	  clock_prev= clock_curr;\
-      clock_curr = MPI_Wtime();\
-      cout<<#tag <<order <<":MPI Rank: "<<myrank<<" "<<#label <<" "<<(clock_curr-clock_prev)<<endl;\
-}else{\
-  if(myrank==0){\
-      clock_prev= clock_curr;\
-      clock_curr = MPI_Wtime();\
-      cout<<#tag <<order <<" "<<#label " "<<(clock_curr-clock_prev)<<endl;\
-  }\
-}
-
-#define TIMER_TIC_EACH_PROC(tag,order,label) \
-	  clock_prev= clock_curr;\
-      clock_curr = MPI_Wtime();\
-      cout<<#tag <<order <<":MPI Rank: "<<myrank<<" "<<#label <<" "<<(clock_curr-clock_prev)<<endl;\
-}
-
-#define TIMER_TIC_WITHOUT_OUTPUT \
-if(TIME_COUNT_EACH_RANK == 1){\
-      clock_curr = MPI_Wtime();\
-}else{\
-  if(myrank==0){\
-      clock_curr = MPI_Wtime();\
-  }\
-}
-
-#define TIMER_TIC_TAIL_OF_FUNC(tag,label) \
-if(TIME_COUNT_EACH_RANK == 1){\
-	 cout<<#tag <<"MPI Rank: "<<myrank<<" "<<#label <<" "<<(MPI_Wtime()-step_begin_clock)<<" seconds!"<<endl;\
-}else{\
-     if(myrank==0)\
-     {\
-      cout<<#tag <<#label <<" "<<(MPI_Wtime()-step_begin_clock)<<" seconds!"<<endl;\
-     }\
-}
-
-//3---------------------GPU---------------------
-#define CALLED_BY_STEP 0
-#define CALLED_BY_CONSTRAINT 1
-
-#define RHS_PARA_CALLED_FIRST_TIME cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
-
-#define RHS_PARA_CALLED_THEN cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi->sgfn],cg->fgfs[trK->sgfn],cg->fgfs[gxx->sgfn],cg->fgfs[gxy->sgfn],cg->fgfs[gxz->sgfn],cg->fgfs[gyy->sgfn],cg->fgfs[gyz->sgfn],cg->fgfs[gzz->sgfn],cg->fgfs[Axx->sgfn],cg->fgfs[Axy->sgfn],cg->fgfs[Axz->sgfn],cg->fgfs[Ayy->sgfn],cg->fgfs[Ayz->sgfn],cg->fgfs[Azz->sgfn],cg->fgfs[Gmx->sgfn],cg->fgfs[Gmy->sgfn],cg->fgfs[Gmz->sgfn],cg->fgfs[Lap->sgfn],cg->fgfs[Sfx->sgfn],cg->fgfs[Sfy->sgfn],cg->fgfs[Sfz->sgfn],cg->fgfs[dtSfx->sgfn],cg->fgfs[dtSfy->sgfn],cg->fgfs[dtSfz->sgfn],cg->fgfs[phi1->sgfn],cg->fgfs[trK1->sgfn],cg->fgfs[gxx1->sgfn],cg->fgfs[gxy1->sgfn],cg->fgfs[gxz1->sgfn],cg->fgfs[gyy1->sgfn],cg->fgfs[gyz1->sgfn],cg->fgfs[gzz1->sgfn],cg->fgfs[Axx1->sgfn],cg->fgfs[Axy1->sgfn],cg->fgfs[Axz1->sgfn],cg->fgfs[Ayy1->sgfn],cg->fgfs[Ayz1->sgfn],cg->fgfs[Azz1->sgfn],cg->fgfs[Gmx1->sgfn],cg->fgfs[Gmy1->sgfn],cg->fgfs[Gmz1->sgfn],cg->fgfs[Lap1->sgfn],cg->fgfs[Sfx1->sgfn],cg->fgfs[Sfy1->sgfn],cg->fgfs[Sfz1->sgfn],cg->fgfs[dtSfx1->sgfn],cg->fgfs[dtSfy1->sgfn],cg->fgfs[dtSfz1->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,cor
-
-#define RHS_PARA_CALLED_Constraint_Out cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
-
-
-#define RHS_PARA_CALLED_Interp_Constraint cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
-
-#define RHS_SS_PARA_CALLED_FIRST_TIME cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
-
-#define RHS_SS_PARA_CALLED_THEN cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi->sgfn],cg->fgfs[trK->sgfn],cg->fgfs[gxx->sgfn],cg->fgfs[gxy->sgfn],cg->fgfs[gxz->sgfn],cg->fgfs[gyy->sgfn],cg->fgfs[gyz->sgfn],cg->fgfs[gzz->sgfn],cg->fgfs[Axx->sgfn],cg->fgfs[Axy->sgfn],cg->fgfs[Axz->sgfn],cg->fgfs[Ayy->sgfn],cg->fgfs[Ayz->sgfn],cg->fgfs[Azz->sgfn],cg->fgfs[Gmx->sgfn],cg->fgfs[Gmy->sgfn],cg->fgfs[Gmz->sgfn],cg->fgfs[Lap->sgfn],cg->fgfs[Sfx->sgfn],cg->fgfs[Sfy->sgfn],cg->fgfs[Sfz->sgfn],cg->fgfs[dtSfx->sgfn],cg->fgfs[dtSfy->sgfn],cg->fgfs[dtSfz->sgfn],cg->fgfs[phi1->sgfn],cg->fgfs[trK1->sgfn],cg->fgfs[gxx1->sgfn],cg->fgfs[gxy1->sgfn],cg->fgfs[gxz1->sgfn],cg->fgfs[gyy1->sgfn],cg->fgfs[gyz1->sgfn],cg->fgfs[gzz1->sgfn],cg->fgfs[Axx1->sgfn],cg->fgfs[Axy1->sgfn],cg->fgfs[Axz1->sgfn],cg->fgfs[Ayy1->sgfn],cg->fgfs[Ayz1->sgfn],cg->fgfs[Azz1->sgfn],cg->fgfs[Gmx1->sgfn],cg->fgfs[Gmy1->sgfn],cg->fgfs[Gmz1->sgfn],cg->fgfs[Lap1->sgfn],cg->fgfs[Sfx1->sgfn],cg->fgfs[Sfy1->sgfn],cg->fgfs[Sfz1->sgfn],cg->fgfs[dtSfx1->sgfn],cg->fgfs[dtSfy1->sgfn],cg->fgfs[dtSfz1->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,cor
-
-
-#define RHS_PARA_CALLED_Constraint_Out_SS cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
-
-#define RHS_PARA_CALLED_Intrp_Constraint_Out_SS cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
-//4------------tool------------------------------
-int compare_result(int ftag1,double * d2,int data_num);
-
-
-
-#endif
+#ifndef BSSN_STEP_H
+#define BSSN_STEP_H
+//1---------------------FLAGS---------------------
+
+#define USE_GPU
+#define MAX_GPU_PROCESS_NUM 1
+#define COUNT_CPU_RHS_TIME
+
+
+//2---------------------TIMER---------------------
+//2.1 TIMER_INIT
+//2.2 TIMER_TIC_WITHOUT_OUTPUT
+//2.3 TIMER_TIC(tag,order,label)
+//2.4 TIMER_TIC_TAIL_OF_FUNC(tag,label)
+
+#define TIME_COUNT_EACH_RANK 0
+
+#define TIMER_INIT \
+double clock_prev,clock_curr,step_begin_clock;\
+if(1 == 1){\
+	clock_curr =MPI_Wtime();\
+	step_begin_clock = MPI_Wtime();\
+}else{\
+if(myrank == 0){\
+	clock_curr= MPI_Wtime();\
+	step_begin_clock = MPI_Wtime();\
+}\
+}
+      
+#define TIMER_TIC(tag,order,label) \
+if(TIME_COUNT_EACH_RANK == 1){\
+	  clock_prev= clock_curr;\
+      clock_curr = MPI_Wtime();\
+      cout<<#tag <<order <<":MPI Rank: "<<myrank<<" "<<#label <<" "<<(clock_curr-clock_prev)<<endl;\
+}else{\
+  if(myrank==0){\
+      clock_prev= clock_curr;\
+      clock_curr = MPI_Wtime();\
+      cout<<#tag <<order <<" "<<#label " "<<(clock_curr-clock_prev)<<endl;\
+  }\
+}
+
+#define TIMER_TIC_EACH_PROC(tag,order,label) \
+	  clock_prev= clock_curr;\
+      clock_curr = MPI_Wtime();\
+      cout<<#tag <<order <<":MPI Rank: "<<myrank<<" "<<#label <<" "<<(clock_curr-clock_prev)<<endl;\
+}
+
+#define TIMER_TIC_WITHOUT_OUTPUT \
+if(TIME_COUNT_EACH_RANK == 1){\
+      clock_curr = MPI_Wtime();\
+}else{\
+  if(myrank==0){\
+      clock_curr = MPI_Wtime();\
+  }\
+}
+
+#define TIMER_TIC_TAIL_OF_FUNC(tag,label) \
+if(TIME_COUNT_EACH_RANK == 1){\
+	 cout<<#tag <<"MPI Rank: "<<myrank<<" "<<#label <<" "<<(MPI_Wtime()-step_begin_clock)<<" seconds!"<<endl;\
+}else{\
+     if(myrank==0)\
+     {\
+      cout<<#tag <<#label <<" "<<(MPI_Wtime()-step_begin_clock)<<" seconds!"<<endl;\
+     }\
+}
+
+//3---------------------GPU---------------------
+#define CALLED_BY_STEP 0
+#define CALLED_BY_CONSTRAINT 1
+
+#define RHS_PARA_CALLED_FIRST_TIME cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
+
+#define RHS_PARA_CALLED_THEN cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi->sgfn],cg->fgfs[trK->sgfn],cg->fgfs[gxx->sgfn],cg->fgfs[gxy->sgfn],cg->fgfs[gxz->sgfn],cg->fgfs[gyy->sgfn],cg->fgfs[gyz->sgfn],cg->fgfs[gzz->sgfn],cg->fgfs[Axx->sgfn],cg->fgfs[Axy->sgfn],cg->fgfs[Axz->sgfn],cg->fgfs[Ayy->sgfn],cg->fgfs[Ayz->sgfn],cg->fgfs[Azz->sgfn],cg->fgfs[Gmx->sgfn],cg->fgfs[Gmy->sgfn],cg->fgfs[Gmz->sgfn],cg->fgfs[Lap->sgfn],cg->fgfs[Sfx->sgfn],cg->fgfs[Sfy->sgfn],cg->fgfs[Sfz->sgfn],cg->fgfs[dtSfx->sgfn],cg->fgfs[dtSfy->sgfn],cg->fgfs[dtSfz->sgfn],cg->fgfs[phi1->sgfn],cg->fgfs[trK1->sgfn],cg->fgfs[gxx1->sgfn],cg->fgfs[gxy1->sgfn],cg->fgfs[gxz1->sgfn],cg->fgfs[gyy1->sgfn],cg->fgfs[gyz1->sgfn],cg->fgfs[gzz1->sgfn],cg->fgfs[Axx1->sgfn],cg->fgfs[Axy1->sgfn],cg->fgfs[Axz1->sgfn],cg->fgfs[Ayy1->sgfn],cg->fgfs[Ayz1->sgfn],cg->fgfs[Azz1->sgfn],cg->fgfs[Gmx1->sgfn],cg->fgfs[Gmy1->sgfn],cg->fgfs[Gmz1->sgfn],cg->fgfs[Lap1->sgfn],cg->fgfs[Sfx1->sgfn],cg->fgfs[Sfy1->sgfn],cg->fgfs[Sfz1->sgfn],cg->fgfs[dtSfx1->sgfn],cg->fgfs[dtSfy1->sgfn],cg->fgfs[dtSfz1->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,cor
+
+#define RHS_PARA_CALLED_Constraint_Out cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
+
+
+#define RHS_PARA_CALLED_Interp_Constraint cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,ndeps,pre
+
+#define RHS_SS_PARA_CALLED_FIRST_TIME cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
+
+#define RHS_SS_PARA_CALLED_THEN cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi->sgfn],cg->fgfs[trK->sgfn],cg->fgfs[gxx->sgfn],cg->fgfs[gxy->sgfn],cg->fgfs[gxz->sgfn],cg->fgfs[gyy->sgfn],cg->fgfs[gyz->sgfn],cg->fgfs[gzz->sgfn],cg->fgfs[Axx->sgfn],cg->fgfs[Axy->sgfn],cg->fgfs[Axz->sgfn],cg->fgfs[Ayy->sgfn],cg->fgfs[Ayz->sgfn],cg->fgfs[Azz->sgfn],cg->fgfs[Gmx->sgfn],cg->fgfs[Gmy->sgfn],cg->fgfs[Gmz->sgfn],cg->fgfs[Lap->sgfn],cg->fgfs[Sfx->sgfn],cg->fgfs[Sfy->sgfn],cg->fgfs[Sfz->sgfn],cg->fgfs[dtSfx->sgfn],cg->fgfs[dtSfy->sgfn],cg->fgfs[dtSfz->sgfn],cg->fgfs[phi1->sgfn],cg->fgfs[trK1->sgfn],cg->fgfs[gxx1->sgfn],cg->fgfs[gxy1->sgfn],cg->fgfs[gxz1->sgfn],cg->fgfs[gyy1->sgfn],cg->fgfs[gyz1->sgfn],cg->fgfs[gzz1->sgfn],cg->fgfs[Axx1->sgfn],cg->fgfs[Axy1->sgfn],cg->fgfs[Axz1->sgfn],cg->fgfs[Ayy1->sgfn],cg->fgfs[Ayz1->sgfn],cg->fgfs[Azz1->sgfn],cg->fgfs[Gmx1->sgfn],cg->fgfs[Gmy1->sgfn],cg->fgfs[Gmz1->sgfn],cg->fgfs[Lap1->sgfn],cg->fgfs[Sfx1->sgfn],cg->fgfs[Sfy1->sgfn],cg->fgfs[Sfz1->sgfn],cg->fgfs[dtSfx1->sgfn],cg->fgfs[dtSfy1->sgfn],cg->fgfs[dtSfz1->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,cor
+
+
+#define RHS_PARA_CALLED_Constraint_Out_SS cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
+
+#define RHS_PARA_CALLED_Intrp_Constraint_Out_SS cg->shape,TRK4,cg->X[0],cg->X[1],cg->X[2],cg->fgfs[fngfs+ShellPatch::gx],cg->fgfs[fngfs+ShellPatch::gy],cg->fgfs[fngfs+ShellPatch::gz],cg->fgfs[fngfs+ShellPatch::drhodx],cg->fgfs[fngfs+ShellPatch::drhody],cg->fgfs[fngfs+ShellPatch::drhodz],cg->fgfs[fngfs+ShellPatch::dsigmadx],cg->fgfs[fngfs+ShellPatch::dsigmady],cg->fgfs[fngfs+ShellPatch::dsigmadz],cg->fgfs[fngfs+ShellPatch::dRdx],cg->fgfs[fngfs+ShellPatch::dRdy],cg->fgfs[fngfs+ShellPatch::dRdz],cg->fgfs[fngfs+ShellPatch::drhodxx],cg->fgfs[fngfs+ShellPatch::drhodxy],cg->fgfs[fngfs+ShellPatch::drhodxz],cg->fgfs[fngfs+ShellPatch::drhodyy],cg->fgfs[fngfs+ShellPatch::drhodyz],cg->fgfs[fngfs+ShellPatch::drhodzz],cg->fgfs[fngfs+ShellPatch::dsigmadxx],cg->fgfs[fngfs+ShellPatch::dsigmadxy],cg->fgfs[fngfs+ShellPatch::dsigmadxz],cg->fgfs[fngfs+ShellPatch::dsigmadyy],cg->fgfs[fngfs+ShellPatch::dsigmadyz],cg->fgfs[fngfs+ShellPatch::dsigmadzz],cg->fgfs[fngfs+ShellPatch::dRdxx],cg->fgfs[fngfs+ShellPatch::dRdxy],cg->fgfs[fngfs+ShellPatch::dRdxz],cg->fgfs[fngfs+ShellPatch::dRdyy],cg->fgfs[fngfs+ShellPatch::dRdyz],cg->fgfs[fngfs+ShellPatch::dRdzz],cg->fgfs[phi0->sgfn],cg->fgfs[trK0->sgfn],cg->fgfs[gxx0->sgfn],cg->fgfs[gxy0->sgfn],cg->fgfs[gxz0->sgfn],cg->fgfs[gyy0->sgfn],cg->fgfs[gyz0->sgfn],cg->fgfs[gzz0->sgfn],cg->fgfs[Axx0->sgfn],cg->fgfs[Axy0->sgfn],cg->fgfs[Axz0->sgfn],cg->fgfs[Ayy0->sgfn],cg->fgfs[Ayz0->sgfn],cg->fgfs[Azz0->sgfn],cg->fgfs[Gmx0->sgfn],cg->fgfs[Gmy0->sgfn],cg->fgfs[Gmz0->sgfn],cg->fgfs[Lap0->sgfn],cg->fgfs[Sfx0->sgfn],cg->fgfs[Sfy0->sgfn],cg->fgfs[Sfz0->sgfn],cg->fgfs[dtSfx0->sgfn],cg->fgfs[dtSfy0->sgfn],cg->fgfs[dtSfz0->sgfn],cg->fgfs[phi_rhs->sgfn],cg->fgfs[trK_rhs->sgfn],cg->fgfs[gxx_rhs->sgfn],cg->fgfs[gxy_rhs->sgfn],cg->fgfs[gxz_rhs->sgfn],cg->fgfs[gyy_rhs->sgfn],cg->fgfs[gyz_rhs->sgfn],cg->fgfs[gzz_rhs->sgfn],cg->fgfs[Axx_rhs->sgfn],cg->fgfs[Axy_rhs->sgfn],cg->fgfs[Axz_rhs->sgfn],cg->fgfs[Ayy_rhs->sgfn],cg->fgfs[Ayz_rhs->sgfn],cg->fgfs[Azz_rhs->sgfn],cg->fgfs[Gmx_rhs->sgfn],cg->fgfs[Gmy_rhs->sgfn],cg->fgfs[Gmz_rhs->sgfn],cg->fgfs[Lap_rhs->sgfn],cg->fgfs[Sfx_rhs->sgfn],cg->fgfs[Sfy_rhs->sgfn],cg->fgfs[Sfz_rhs->sgfn],cg->fgfs[dtSfx_rhs->sgfn],cg->fgfs[dtSfy_rhs->sgfn],cg->fgfs[dtSfz_rhs->sgfn],cg->fgfs[rho->sgfn],cg->fgfs[Sx->sgfn],cg->fgfs[Sy->sgfn],cg->fgfs[Sz->sgfn],cg->fgfs[Sxx->sgfn],cg->fgfs[Sxy->sgfn],cg->fgfs[Sxz->sgfn],cg->fgfs[Syy->sgfn],cg->fgfs[Syz->sgfn],cg->fgfs[Szz->sgfn],cg->fgfs[Gamxxx->sgfn],cg->fgfs[Gamxxy->sgfn],cg->fgfs[Gamxxz->sgfn],cg->fgfs[Gamxyy->sgfn],cg->fgfs[Gamxyz->sgfn],cg->fgfs[Gamxzz->sgfn],cg->fgfs[Gamyxx->sgfn],cg->fgfs[Gamyxy->sgfn],cg->fgfs[Gamyxz->sgfn],cg->fgfs[Gamyyy->sgfn],cg->fgfs[Gamyyz->sgfn],cg->fgfs[Gamyzz->sgfn],cg->fgfs[Gamzxx->sgfn],cg->fgfs[Gamzxy->sgfn],cg->fgfs[Gamzxz->sgfn],cg->fgfs[Gamzyy->sgfn],cg->fgfs[Gamzyz->sgfn],cg->fgfs[Gamzzz->sgfn],cg->fgfs[Rxx->sgfn],cg->fgfs[Rxy->sgfn],cg->fgfs[Rxz->sgfn],cg->fgfs[Ryy->sgfn],cg->fgfs[Ryz->sgfn],cg->fgfs[Rzz->sgfn],cg->fgfs[Cons_Ham->sgfn],cg->fgfs[Cons_Px->sgfn],cg->fgfs[Cons_Py->sgfn],cg->fgfs[Cons_Pz->sgfn],cg->fgfs[Cons_Gx->sgfn],cg->fgfs[Cons_Gy->sgfn],cg->fgfs[Cons_Gz->sgfn],Symmetry,lev,numepsh,sPp->data->sst,pre
+//4------------tool------------------------------
+int compare_result(int ftag1,double * d2,int data_num);
+
+
+
+#endif

AMSS_NCKU_source/bssn_rhs.h

@@ -1,244 +1,292 @@
-
-#ifndef BSSN_H
-#define BSSN_H
-
-#ifdef fortran1
-#define f_compute_rhs_bssn compute_rhs_bssn
-#define f_compute_rhs_bssn_ss compute_rhs_bssn_ss
-#define f_compute_rhs_bssn_escalar compute_rhs_bssn_escalar
-#define f_compute_rhs_bssn_escalar_ss compute_rhs_bssn_escalar_ss
-#define f_compute_rhs_Z4c compute_rhs_z4c
-#define f_compute_rhs_Z4cnot compute_rhs_z4cnot
-#define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss
-#define f_compute_constraint_fr compute_constraint_fr
-#endif
-#ifdef fortran2
-#define f_compute_rhs_bssn COMPUTE_RHS_BSSN
-#define f_compute_rhs_bssn_ss COMPUTE_RHS_BSSN_SS
-#define f_compute_rhs_bssn_escalar COMPUTE_RHS_BSSN_ESCALAR
-#define f_compute_rhs_bssn_escalar_ss COMPUTE_RHS_BSSN_ESCALAR_SS
-#define f_compute_rhs_Z4c COMPUTE_RHS_Z4C
-#define f_compute_rhs_Z4cnot COMPUTE_RHS_Z4CNOT
-#define f_compute_rhs_Z4c_ss COMPUTE_RHS_Z4C_SS
-#define f_compute_constraint_fr COMPUTE_CONSTRAINT_FR
-#endif
-#ifdef fortran3
-#define f_compute_rhs_bssn compute_rhs_bssn_
-#define f_compute_rhs_bssn_ss compute_rhs_bssn_ss_
-#define f_compute_rhs_bssn_escalar compute_rhs_bssn_escalar_
-#define f_compute_rhs_bssn_escalar_ss compute_rhs_bssn_escalar_ss_
-#define f_compute_rhs_Z4c compute_rhs_z4c_
-#define f_compute_rhs_Z4cnot compute_rhs_z4cnot_
-#define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss_
-#define f_compute_constraint_fr compute_constraint_fr_
-#endif
-
-#ifdef __cplusplus
-extern "C"
-{
-#endif
-        void f_bssn_rhs_kernel_timing_reset();
-        int f_bssn_rhs_kernel_timing_bucket_count();
-        const double *f_bssn_rhs_kernel_timing_local_seconds();
-        const char *f_bssn_rhs_kernel_timing_label(int);
-#ifdef __cplusplus
-}
-#endif
-
-extern "C"
-{
-        int f_compute_rhs_bssn(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z
-                               double *, double *,                                                                                 // chi, trK
-                               double *, double *, double *, double *, double *, double *,                                         // gij
-                               double *, double *, double *, double *, double *, double *,                                         // Aij
-                               double *, double *, double *,                                                                       // Gam
-                               double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                               double *, double *,                                                                                 // chi, trK
-                               double *, double *, double *, double *, double *, double *,                                         // gij
-                               double *, double *, double *, double *, double *, double *,                                         // Aij
-                               double *, double *, double *,                                                                       // Gam
-                               double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                               double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
-                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                               double *, double *, double *, double *, double *, double *,                                         // Ricci
-                               double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
-                               int &, int &, double &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_bssn_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
-                                  double *, double *, double *,                                                                       // X,Y,Z
-                                  double *, double *, double *,                                                                       // drhodx,drhody,drhodz
-                                  double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
-                                  double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
-                                  double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-                                  double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-                                  double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-                                  double *, double *,                                                                                 // chi, trK
-                                  double *, double *, double *, double *, double *, double *,                                         // gij
-                                  double *, double *, double *, double *, double *, double *,                                         // Aij
-                                  double *, double *, double *,                                                                       // Gam
-                                  double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                  double *, double *,                                                                                 // chi, trK
-                                  double *, double *, double *, double *, double *, double *,                                         // gij
-                                  double *, double *, double *, double *, double *, double *,                                         // Aij
-                                  double *, double *, double *,                                                                       // Gam
-                                  double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                  double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
-                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                  double *, double *, double *, double *, double *, double *,                                         // Ricci
-                                  double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
-                                  int &, int &, double &, int &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_bssn_escalar(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z
-                                       double *, double *,                                                                                 // chi, trK
-                                       double *, double *, double *, double *, double *, double *,                                         // gij
-                                       double *, double *, double *, double *, double *, double *,                                         // Aij
-                                       double *, double *, double *,                                                                       // Gam
-                                       double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                       double *, double *,                                                                                 // Sphi, Spi
-                                       double *, double *,                                                                                 // chi, trK
-                                       double *, double *, double *, double *, double *, double *,                                         // gij
-                                       double *, double *, double *, double *, double *, double *,                                         // Aij
-                                       double *, double *, double *,                                                                       // Gam
-                                       double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                       double *, double *,                                                                                 // Sphi, Spi
-                                       double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
-                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                       double *, double *, double *, double *, double *, double *,                                         // Ricci
-                                       double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
-                                       int &, int &, double &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_bssn_escalar_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
-                                          double *, double *, double *,                                                                       // X,Y,Z
-                                          double *, double *, double *,                                                                       // drhodx,drhody,drhodz
-                                          double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
-                                          double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
-                                          double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-                                          double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-                                          double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-                                          double *, double *,                                                                                 // chi, trK
-                                          double *, double *, double *, double *, double *, double *,                                         // gij
-                                          double *, double *, double *, double *, double *, double *,                                         // Aij
-                                          double *, double *, double *,                                                                       // Gam
-                                          double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                          double *, double *,                                                                                 // Sphi,Spi
-                                          double *, double *,                                                                                 // chi, trK
-                                          double *, double *, double *, double *, double *, double *,                                         // gij
-                                          double *, double *, double *, double *, double *, double *,                                         // Aij
-                                          double *, double *, double *,                                                                       // Gam
-                                          double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                          double *, double *,                                                                                 // Sphi,Spi
-                                          double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
-                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                          double *, double *, double *, double *, double *, double *,                                         // Ricci
-                                          double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
-                                          int &, int &, double &, int &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_Z4c(int *, double &, double *, double *, double *,                        // ex,T,X,Y,Z
-                              double *, double *,                                                   // chi, trK
-                              double *, double *, double *, double *, double *, double *,           // gij
-                              double *, double *, double *, double *, double *, double *,           // Aij
-                              double *, double *, double *,                                         // Gam
-                              double *, double *, double *, double *, double *, double *, double *, // Gauge
-                              double *,                                                             // Z4
-                              double *, double *,                                                   // chi, trK
-                              double *, double *, double *, double *, double *, double *,           // gij
-                              double *, double *, double *, double *, double *, double *,           // Aij
-                              double *, double *, double *,                                         // Gam
-                              double *, double *, double *, double *, double *, double *, double *, // Gauge
-                              double *,                                                             // Z4
-                              double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
-                              double *, double *, double *, double *, double *, double *,
-                              double *, double *, double *, double *, double *, double *,
-                              double *, double *, double *, double *, double *, double *,
-                              double *, double *, double *, double *, double *, double *,
-                              double *, double *, double *, double *, double *, double *, double *,
-                              int &, int &, double &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_Z4c_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
-                                 double *, double *, double *,                                                                       // X,Y,Z
-                                 double *, double *, double *,                                                                       // drhodx,drhody,drhodz
-                                 double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
-                                 double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
-                                 double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-                                 double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-                                 double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-                                 double *, double *,                                                                                 // chi, trK
-                                 double *, double *, double *, double *, double *, double *,                                         // gij
-                                 double *, double *, double *, double *, double *, double *,                                         // Aij
-                                 double *, double *, double *,                                                                       // Gam
-                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                 double *,                                                                                           // TZ
-                                 double *, double *,                                                                                 // chi, trK
-                                 double *, double *, double *, double *, double *, double *,                                         // gij
-                                 double *, double *, double *, double *, double *, double *,                                         // Aij
-                                 double *, double *, double *,                                                                       // Gam
-                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
-                                 double *,                                                                                           // TZ
-                                 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
-                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
-                                 double *, double *, double *, double *, double *, double *,                                         // Ricci
-                                 double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
-                                 int &, int &, double &, int &, int &);
-}
-
-extern "C"
-{
-        int f_compute_rhs_Z4cnot(int *, double &, double *, double *, double *,                        // ex,T,X,Y,Z
-                                 double *, double *,                                                   // chi, trK
-                                 double *, double *, double *, double *, double *, double *,           // gij
-                                 double *, double *, double *, double *, double *, double *,           // Aij
-                                 double *, double *, double *,                                         // Gam
-                                 double *, double *, double *, double *, double *, double *, double *, // Gauge
-                                 double *,                                                             // Z4
-                                 double *, double *,                                                   // chi, trK
-                                 double *, double *, double *, double *, double *, double *,           // gij
-                                 double *, double *, double *, double *, double *, double *,           // Aij
-                                 double *, double *, double *,                                         // Gam
-                                 double *, double *, double *, double *, double *, double *, double *, // Gauge
-                                 double *,                                                             // Z4
-                                 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
-                                 double *, double *, double *, double *, double *, double *,
-                                 double *, double *, double *, double *, double *, double *,
-                                 double *, double *, double *, double *, double *, double *,
-                                 double *, double *, double *, double *, double *, double *,
-                                 double *, double *, double *, double *, double *, double *, double *,
-                                 int &, int &, double &, int &, double &);
-}
-
-extern "C"
-{
-        void f_compute_constraint_fr(int *, double *, double *, double *,                        // ex,X,Y,Z
-                                     double *, double *, double *, double *,                     // chi, trK,rho,Sphi
-                                     double *, double *, double *, double *, double *, double *, // gij
-                                     double *, double *, double *, double *, double *, double *, // Aij
-                                     double *, double *, double *, double *, double *, double *, // Rij
-                                     double *, double *, double *, double *, double *, double *, // Sij
-                                     double *);
-} // FR_cons
-
-#endif /* BSSN_H */
+
+#ifndef BSSN_H
+#define BSSN_H
+
+#ifdef fortran1
+#define f_compute_rhs_bssn compute_rhs_bssn
+#define f_compute_rhs_bssn_ss compute_rhs_bssn_ss
+#define f_compute_rhs_bssn_escalar compute_rhs_bssn_escalar
+#define f_compute_rhs_bssn_escalar_ss compute_rhs_bssn_escalar_ss
+#define f_compute_rhs_Z4c compute_rhs_z4c
+#define f_compute_rhs_Z4cnot compute_rhs_z4cnot
+#define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss
+#define f_compute_constraint_fr compute_constraint_fr
+#endif
+#ifdef fortran2
+#define f_compute_rhs_bssn COMPUTE_RHS_BSSN
+#define f_compute_rhs_bssn_ss COMPUTE_RHS_BSSN_SS
+#define f_compute_rhs_bssn_escalar COMPUTE_RHS_BSSN_ESCALAR
+#define f_compute_rhs_bssn_escalar_ss COMPUTE_RHS_BSSN_ESCALAR_SS
+#define f_compute_rhs_Z4c COMPUTE_RHS_Z4C
+#define f_compute_rhs_Z4cnot COMPUTE_RHS_Z4CNOT
+#define f_compute_rhs_Z4c_ss COMPUTE_RHS_Z4C_SS
+#define f_compute_constraint_fr COMPUTE_CONSTRAINT_FR
+#endif
+#ifdef fortran3
+#define f_compute_rhs_bssn compute_rhs_bssn_
+#define f_compute_rhs_bssn_ss compute_rhs_bssn_ss_
+#define f_compute_rhs_bssn_escalar compute_rhs_bssn_escalar_
+#define f_compute_rhs_bssn_escalar_ss compute_rhs_bssn_escalar_ss_
+#define f_compute_rhs_Z4c compute_rhs_z4c_
+#define f_compute_rhs_Z4cnot compute_rhs_z4cnot_
+#define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss_
+#define f_compute_constraint_fr compute_constraint_fr_
+#endif
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+        void f_bssn_rhs_kernel_timing_reset();
+        int f_bssn_rhs_kernel_timing_bucket_count();
+        const double *f_bssn_rhs_kernel_timing_local_seconds();
+        const char *f_bssn_rhs_kernel_timing_label(int);
+#ifdef __cplusplus
+}
+#endif
+
+extern "C"
+{
+        int f_compute_rhs_bssn(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z
+                               double *, double *,                                                                                 // chi, trK
+                               double *, double *, double *, double *, double *, double *,                                         // gij
+                               double *, double *, double *, double *, double *, double *,                                         // Aij
+                               double *, double *, double *,                                                                       // Gam
+                               double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                               double *, double *,                                                                                 // chi, trK
+                               double *, double *, double *, double *, double *, double *,                                         // gij
+                               double *, double *, double *, double *, double *, double *,                                         // Aij
+                               double *, double *, double *,                                                                       // Gam
+                               double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                               double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                               double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                               double *, double *, double *, double *, double *, double *,                                         // Ricci
+                               double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                               int &, int &, double &, int &);
+}
+
+int f_compute_rhs_bssn_escalar_c(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z
+                                 double *, double *,                                                                                 // chi, trK
+                                 double *, double *, double *, double *, double *, double *,                                         // gij
+                                 double *, double *, double *, double *, double *, double *,                                         // Aij
+                                 double *, double *, double *,                                                                       // Gam
+                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                 double *, double *,                                                                                 // Sphi, Spi
+                                 double *, double *,                                                                                 // chi, trK
+                                 double *, double *, double *, double *, double *, double *,                                         // gij
+                                 double *, double *, double *, double *, double *, double *,                                         // Aij
+                                 double *, double *, double *,                                                                       // Gam
+                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                 double *, double *,                                                                                 // Sphi, Spi
+                                 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Ricci
+                                 double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                                 int &, int &, double &, int &);
+
+extern "C"
+{
+        int f_compute_rhs_bssn_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
+                                  double *, double *, double *,                                                                       // X,Y,Z
+                                  double *, double *, double *,                                                                       // drhodx,drhody,drhodz
+                                  double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
+                                  double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
+                                  double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+                                  double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+                                  double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+                                  double *, double *,                                                                                 // chi, trK
+                                  double *, double *, double *, double *, double *, double *,                                         // gij
+                                  double *, double *, double *, double *, double *, double *,                                         // Aij
+                                  double *, double *, double *,                                                                       // Gam
+                                  double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                  double *, double *,                                                                                 // chi, trK
+                                  double *, double *, double *, double *, double *, double *,                                         // gij
+                                  double *, double *, double *, double *, double *, double *,                                         // Aij
+                                  double *, double *, double *,                                                                       // Gam
+                                  double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                  double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                  double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                  double *, double *, double *, double *, double *, double *,                                         // Ricci
+                                  double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                                  int &, int &, double &, int &, int &);
+}
+
+extern "C"
+{
+        int f_compute_rhs_bssn_escalar(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z
+                                       double *, double *,                                                                                 // chi, trK
+                                       double *, double *, double *, double *, double *, double *,                                         // gij
+                                       double *, double *, double *, double *, double *, double *,                                         // Aij
+                                       double *, double *, double *,                                                                       // Gam
+                                       double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                       double *, double *,                                                                                 // Sphi, Spi
+                                       double *, double *,                                                                                 // chi, trK
+                                       double *, double *, double *, double *, double *, double *,                                         // gij
+                                       double *, double *, double *, double *, double *, double *,                                         // Aij
+                                       double *, double *, double *,                                                                       // Gam
+                                       double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                       double *, double *,                                                                                 // Sphi, Spi
+                                       double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                       double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                       double *, double *, double *, double *, double *, double *,                                         // Ricci
+                                       double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                                       int &, int &, double &, int &);
+}
+
+extern "C"
+{
+        int f_compute_rhs_bssn_escalar_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
+                                          double *, double *, double *,                                                                       // X,Y,Z
+                                          double *, double *, double *,                                                                       // drhodx,drhody,drhodz
+                                          double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
+                                          double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
+                                          double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+                                          double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+                                          double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+                                          double *, double *,                                                                                 // chi, trK
+                                          double *, double *, double *, double *, double *, double *,                                         // gij
+                                          double *, double *, double *, double *, double *, double *,                                         // Aij
+                                          double *, double *, double *,                                                                       // Gam
+                                          double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                          double *, double *,                                                                                 // Sphi,Spi
+                                          double *, double *,                                                                                 // chi, trK
+                                          double *, double *, double *, double *, double *, double *,                                         // gij
+                                          double *, double *, double *, double *, double *, double *,                                         // Aij
+                                          double *, double *, double *,                                                                       // Gam
+                                          double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                          double *, double *,                                                                                 // Sphi,Spi
+                                          double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                          double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                          double *, double *, double *, double *, double *, double *,                                         // Ricci
+                                          double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                                          int &, int &, double &, int &, int &);
+}
+
+extern "C"
+{
+        int f_compute_rhs_Z4c(int *, double &, double *, double *, double *,                        // ex,T,X,Y,Z
+                              double *, double *,                                                   // chi, trK
+                              double *, double *, double *, double *, double *, double *,           // gij
+                              double *, double *, double *, double *, double *, double *,           // Aij
+                              double *, double *, double *,                                         // Gam
+                              double *, double *, double *, double *, double *, double *, double *, // Gauge
+                              double *,                                                             // Z4
+                              double *, double *,                                                   // chi, trK
+                              double *, double *, double *, double *, double *, double *,           // gij
+                              double *, double *, double *, double *, double *, double *,           // Aij
+                              double *, double *, double *,                                         // Gam
+                              double *, double *, double *, double *, double *, double *, double *, // Gauge
+                              double *,                                                             // Z4
+                              double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
+                              double *, double *, double *, double *, double *, double *,
+                              double *, double *, double *, double *, double *, double *,
+                              double *, double *, double *, double *, double *, double *,
+                              double *, double *, double *, double *, double *, double *,
+                              double *, double *, double *, double *, double *, double *, double *,
+                              int &, int &, double &, int &);
+}
+
+extern "C"
+{
+        int f_compute_rhs_Z4c_ss(int *, double &, double *, double *, double *,                                                      // ex,T,rho,sigma,R
+                                 double *, double *, double *,                                                                       // X,Y,Z
+                                 double *, double *, double *,                                                                       // drhodx,drhody,drhodz
+                                 double *, double *, double *,                                                                       // dsigmadx,dsigmady,dsigmadz
+                                 double *, double *, double *,                                                                       // dRdx,dRdy,dRdz
+                                 double *, double *, double *, double *, double *, double *,                                         // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+                                 double *, double *, double *, double *, double *, double *,                                         // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+                                 double *, double *, double *, double *, double *, double *,                                         // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+                                 double *, double *,                                                                                 // chi, trK
+                                 double *, double *, double *, double *, double *, double *,                                         // gij
+                                 double *, double *, double *, double *, double *, double *,                                         // Aij
+                                 double *, double *, double *,                                                                       // Gam
+                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                 double *,                                                                                           // TZ
+                                 double *, double *,                                                                                 // chi, trK
+                                 double *, double *, double *, double *, double *, double *,                                         // gij
+                                 double *, double *, double *, double *, double *, double *,                                         // Aij
+                                 double *, double *, double *,                                                                       // Gam
+                                 double *, double *, double *, double *, double *, double *, double *,                               // Gauge
+                                 double *,                                                                                           // TZ
+                                 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *, // stress-energy
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Christoffel
+                                 double *, double *, double *, double *, double *, double *,                                         // Ricci
+                                 double *, double *, double *, double *, double *, double *, double *,                               // constraint violation
+                                 int &, int &, double &, int &, int &);
+}
+
+extern "C"
+{
+        int f_compute_rhs_Z4cnot(int *, double &, double *, double *, double *,                        // ex,T,X,Y,Z
+                                 double *, double *,                                                   // chi, trK
+                                 double *, double *, double *, double *, double *, double *,           // gij
+                                 double *, double *, double *, double *, double *, double *,           // Aij
+                                 double *, double *, double *,                                         // Gam
+                                 double *, double *, double *, double *, double *, double *, double *, // Gauge
+                                 double *,                                                             // Z4
+                                 double *, double *,                                                   // chi, trK
+                                 double *, double *, double *, double *, double *, double *,           // gij
+                                 double *, double *, double *, double *, double *, double *,           // Aij
+                                 double *, double *, double *,                                         // Gam
+                                 double *, double *, double *, double *, double *, double *, double *, // Gauge
+                                 double *,                                                             // Z4
+                                 double *, double *, double *, double *, double *, double *, double *, double *, double *, double *,
+                                 double *, double *, double *, double *, double *, double *,
+                                 double *, double *, double *, double *, double *, double *,
+                                 double *, double *, double *, double *, double *, double *,
+                                 double *, double *, double *, double *, double *, double *,
+                                 double *, double *, double *, double *, double *, double *, double *,
+                                 int &, int &, double &, int &, double &);
+}
+
+extern "C"
+{
+        void f_compute_constraint_fr(int *, double *, double *, double *,                        // ex,X,Y,Z
+                                     double *, double *, double *, double *,                     // chi, trK,rho,Sphi
+                                     double *, double *, double *, double *, double *, double *, // gij
+                                     double *, double *, double *, double *, double *, double *, // Aij
+                                     double *, double *, double *, double *, double *, double *, // Rij
+                                     double *, double *, double *, double *, double *, double *, // Sij
+                                     double *);
+} // FR_cons
+
+// BSSN-EM C kernel (replaces empart.f90 + bssn_rhs.f90 for BSSN+Maxwell)
+int f_compute_rhs_bssn_em_c(int *, double &, double *, double *, double *,
+                             double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *,
+                             double *, double *,
+                             double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *,
+                             double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             double *, double *, double *, double *, double *, double *,
+                             int &, int &, double &, int &);
+
+#endif /* BSSN_H */

AMSS_NCKU_source/bssn_rhs_c.C

@@ -1075,6 +1075,10 @@ int f_compute_rhs_bssn(int *ex, double &T,
         }
         #endif
 
+        #if (GAUGE == 2 || GAUGE == 3 || GAUGE == 4 || GAUGE == 5)
+        fderivs(ex,chi,dtSfx_rhs,dtSfy_rhs,dtSfz_rhs,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev);
+        #endif
+
         for (int i = 0; i < all; i += 1) {
             #if (GAUGE == 0)
             betax_rhs[i] = FF * dtSfx[i];
@@ -1098,12 +1102,12 @@ int f_compute_rhs_bssn(int *ex, double &T,
             betaz_rhs[i] = FF * dtSfz[i];
 
             reta[i] =
-                gupxx[i] * dtSfx_rhs[i] * dtSfx_rhs[i]
-                + gupyy[i] * dtSfy_rhs[i] * dtSfy_rhs[i]
-                + gupzz[i] * dtSfz_rhs[i] * dtSfz_rhs[i]
-                + TWO * ( gupxy[i] * dtSfx_rhs[i] * dtSfy_rhs[i]
-                        + gupxz[i] * dtSfx_rhs[i] * dtSfz_rhs[i]
-                        + gupyz[i] * dtSfy_rhs[i] * dtSfz_rhs[i] );
+                gupxx[i] * chix[i] * chix[i]
+                + gupyy[i] * chiy[i] * chiy[i]
+                + gupzz[i] * chiz[i] * chiz[i]
+                + TWO * ( gupxy[i] * chix[i] * chiy[i]
+                        + gupxz[i] * chix[i] * chiz[i]
+                        + gupyz[i] * chiy[i] * chiz[i] );
 
             #if (GAUGE == 2)
             reta[i] = 1.31 / 2.0 * sqrt( reta[i] / chin1[i] ) / pow( (ONE - sqrt(chin1[i])), 2.0 );
@@ -1116,12 +1120,12 @@ int f_compute_rhs_bssn(int *ex, double &T,
             dtSfz_rhs[i] = Gamz_rhs[i] - reta[i] * dtSfz[i];
             #elif (GAUGE == 4 || GAUGE == 5)
             reta[i] =
-                gupxx[i] * dtSfx_rhs[i] * dtSfx_rhs[i]
-                + gupyy[i] * dtSfy_rhs[i] * dtSfy_rhs[i]
-                + gupzz[i] * dtSfz_rhs[i] * dtSfz_rhs[i]
-                + TWO * ( gupxy[i] * dtSfx_rhs[i] * dtSfy_rhs[i]
-                        + gupxz[i] * dtSfx_rhs[i] * dtSfz_rhs[i]
-                        + gupyz[i] * dtSfy_rhs[i] * dtSfz_rhs[i] );
+                gupxx[i] * chix[i] * chix[i]
+                + gupyy[i] * chiy[i] * chiy[i]
+                + gupzz[i] * chiz[i] * chiz[i]
+                + TWO * ( gupxy[i] * chix[i] * chiy[i]
+                        + gupxz[i] * chix[i] * chiz[i]
+                        + gupyz[i] * chiy[i] * chiz[i] );
 
             #if (GAUGE == 4)
             reta[i] = 1.31 / 2.0 * sqrt( reta[i] / chin1[i] ) / pow( (ONE - sqrt(chin1[i])), 2.0 );
@@ -1160,11 +1164,17 @@ int f_compute_rhs_bssn(int *ex, double &T,
         lopsided_kodis(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA,eps);
         lopsided_kodis(ex,X,Y,Z,betaz,betaz_rhs,betax,betay,betaz,Symmetry,SSA,eps);
         lopsided_kodis(ex,X,Y,Z,dzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS,eps);
+        #if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
         lopsided_kodis(ex,X,Y,Z,dtSfx,dtSfx_rhs,betax,betay,betaz,Symmetry,ASS,eps);
+        #endif
         lopsided_kodis(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS,eps);
+        #if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
         lopsided_kodis(ex,X,Y,Z,dtSfy,dtSfy_rhs,betax,betay,betaz,Symmetry,SAS,eps);
+        #endif
         lopsided_kodis(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS,eps);
+        #if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
         lopsided_kodis(ex,X,Y,Z,dtSfz,dtSfz_rhs,betax,betay,betaz,Symmetry,SSA,eps);
+        #endif
         lopsided_kodis(ex,X,Y,Z,Axz,Axz_rhs,betax,betay,betaz,Symmetry,ASA,eps);
         lopsided_kodis(ex,X,Y,Z,Ayy,Ayy_rhs,betax,betay,betaz,Symmetry,SSS,eps);
         lopsided_kodis(ex,X,Y,Z,Ayz,Ayz_rhs,betax,betay,betaz,Symmetry,SAA,eps);

AMSS_NCKU_source/bssn_rhs_cuda.h

@@ -0,0 +1,413 @@
+#ifndef BSSN_RHS_CUDA_H
+#define BSSN_RHS_CUDA_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+enum {
+    BSSN_CUDA_STATE_COUNT = 24,
+    BSSN_ESCALAR_CUDA_STATE_COUNT = 26,
+    BSSN_EM_CUDA_STATE_COUNT = 32,
+    BSSN_EM_CUDA_SOURCE_COUNT = 4,
+    BSSN_CUDA_MATTER_COUNT = 10
+};
+
+int f_compute_rhs_bssn(int *ex, double &T,
+                       double *X, double *Y, double *Z,
+                       double *chi, double *trK,
+                       double *dxx, double *gxy, double *gxz, double *dyy, double *gyz, double *dzz,
+                       double *Axx, double *Axy, double *Axz, double *Ayy, double *Ayz, double *Azz,
+                       double *Gamx, double *Gamy, double *Gamz,
+                       double *Lap, double *betax, double *betay, double *betaz,
+                       double *dtSfx, double *dtSfy, double *dtSfz,
+                       double *chi_rhs, double *trK_rhs,
+                       double *gxx_rhs, double *gxy_rhs, double *gxz_rhs, double *gyy_rhs, double *gyz_rhs, double *gzz_rhs,
+                       double *Axx_rhs, double *Axy_rhs, double *Axz_rhs, double *Ayy_rhs, double *Ayz_rhs, double *Azz_rhs,
+                       double *Gamx_rhs, double *Gamy_rhs, double *Gamz_rhs,
+                       double *Lap_rhs, double *betax_rhs, double *betay_rhs, double *betaz_rhs,
+                       double *dtSfx_rhs, double *dtSfy_rhs, double *dtSfz_rhs,
+                       double *rho, double *Sx, double *Sy, double *Sz,
+                       double *Sxx, double *Sxy, double *Sxz, double *Syy, double *Syz, double *Szz,
+                       double *Gamxxx, double *Gamxxy, double *Gamxxz, double *Gamxyy, double *Gamxyz, double *Gamxzz,
+                       double *Gamyxx, double *Gamyxy, double *Gamyxz, double *Gamyyy, double *Gamyyz, double *Gamyzz,
+                       double *Gamzxx, double *Gamzxy, double *Gamzxz, double *Gamzyy, double *Gamzyz, double *Gamzzz,
+                       double *Rxx, double *Rxy, double *Rxz, double *Ryy, double *Ryz, double *Rzz,
+                       double *ham_Res, double *movx_Res, double *movy_Res, double *movz_Res,
+                       double *Gmx_Res, double *Gmy_Res, double *Gmz_Res,
+                       int &Symmetry, int &Lev, double &eps, int &co);
+
+int bssn_cuda_rk4_substep(void *block_tag,
+                          int *ex, double *X, double *Y, double *Z,
+                          double **state_host_in,
+                          double **state_host_out,
+                          double **matter_host,
+                          const double *propspeed,
+                          const double *soa_flat,
+                          const double *bbox,
+                          double &dT,
+                          double &T,
+                          int &RK4,
+                          int &apply_bam_bc,
+                          int &Symmetry,
+                          int &Lev,
+                          double &eps,
+                          int &co,
+                          int &use_zero_matter,
+                          int &keep_resident_state,
+                          int &apply_enforce_ga,
+                          double &chitiny);
+
+int bssn_escalar_cuda_rk4_substep(void *block_tag,
+                                  int *ex, double *X, double *Y, double *Z,
+                                  double **state_host_in,
+                                  double **state_host_out,
+                                  const double *propspeed,
+                                  const double *soa_flat,
+                                  const double *bbox,
+                                  double &dT,
+                                  double &T,
+                                  int &RK4,
+                                  int &apply_bam_bc,
+                                  int &Symmetry,
+	                                  int &Lev,
+	                                  double &eps,
+	                                  int &co,
+	                                  int &keep_resident_state,
+	                                  int &apply_enforce_ga,
+	                                  double &chitiny);
+
+int bssn_escalar_cuda_compute_constraints(int *ex, double *X, double *Y, double *Z,
+                                          double **state_host_in,
+                                          double **constraint_host_out,
+                                          int &Symmetry,
+                                          int &Lev,
+                                          double &eps);
+
+int bssn_em_cuda_rk4_substep(void *block_tag,
+                             int *ex, double *X, double *Y, double *Z,
+                             double **state_host_in,
+                             double **state_host_out,
+                             double **source_host,
+                             const double *propspeed,
+                             const double *soa_flat,
+                             const double *bbox,
+                             double &dT,
+                             double &T,
+                             int &RK4,
+                             int &apply_bam_bc,
+                             int &Symmetry,
+                             int &Lev,
+                             double &eps,
+                             int &co,
+                             int &keep_resident_state,
+                             int &apply_enforce_ga,
+                             double &chitiny);
+
+int bssn_em_cuda_resident_zero_fast_state(void *block_tag);
+
+int bssn_cuda_copy_state_region_to_host(void *block_tag,
+                                        int state_index,
+                                        double *host_state,
+                                        int *ex,
+                                        int i0, int j0, int k0,
+                                        int sx, int sy, int sz);
+
+int bssn_cuda_copy_state_region_from_host(void *block_tag,
+                                          int state_index,
+                                          double *host_state,
+                                          int *ex,
+                                          int i0, int j0, int k0,
+                                          int sx, int sy, int sz);
+
+int bssn_cuda_download_resident_state(void *block_tag,
+                                      int *ex,
+                                      double **state_host_out);
+
+int bssn_escalar_cuda_download_resident_state(void *block_tag,
+                                              int *ex,
+                                              double **state_host_out);
+
+int bssn_cuda_upload_resident_state_count(void *block_tag,
+                                          int *ex,
+                                          double **state_host_in,
+                                          int state_count);
+
+int bssn_escalar_cuda_upload_resident_state(void *block_tag,
+                                            int *ex,
+                                            double **state_host_in);
+
+int bssn_cuda_keep_only_resident_state_count(void *block_tag,
+                                             int *ex,
+                                             double **state_host_key,
+                                             int state_count);
+
+int bssn_escalar_cuda_keep_only_resident_state(void *block_tag,
+                                               int *ex,
+                                               double **state_host_key);
+
+int bssn_cuda_download_resident_state_count_if_present(void *block_tag,
+                                                       int *ex,
+                                                       double **state_host_out,
+                                                       int state_count);
+
+int bssn_cuda_download_resident_state_if_present(void *block_tag,
+                                                int *ex,
+                                                double **state_host_out);
+
+int bssn_cuda_download_constraint_outputs(int *ex,
+                                          double **constraint_host_out);
+
+int bssn_cuda_pack_state_region_to_host_buffer(void *block_tag,
+                                               int state_index,
+                                               double *host_buffer,
+                                               int *ex,
+                                               int i0, int j0, int k0,
+                                               int sx, int sy, int sz);
+
+int bssn_cuda_interp_state_point3(void *block_tag,
+                                  int *ex,
+                                  int state0,
+                                  int state1,
+                                  int state2,
+                                  double x0,
+                                  double y0,
+                                  double z0,
+                                  double dx,
+                                  double dy,
+                                  double dz,
+                                  double px,
+                                  double py,
+                                  double pz,
+                                  int ordn,
+                                  int symmetry,
+                                  double **state_host_key,
+                                  const double *soa3,
+                                  double *out3);
+
+int bssn_cuda_interp_host_two_fields(void *block_tag,
+                                     int *ex,
+                                     double *field0,
+                                     double *field1,
+                                     double x0,
+                                     double y0,
+                                     double z0,
+                                     double dx,
+                                     double dy,
+                                     double dz,
+                                     const double *px,
+                                     const double *py,
+                                     const double *pz,
+                                     int npoints,
+                                     int ordn,
+                                     int symmetry,
+                                     const double *soa6,
+                                     double *out_interleaved);
+
+int bssn_cuda_unpack_state_region_from_host_buffer(void *block_tag,
+                                                   int state_index,
+                                                   double *host_buffer,
+                                                   int *ex,
+                                                   int i0, int j0, int k0,
+                                                   int sx, int sy, int sz);
+
+int bssn_cuda_unpack_state_region_from_host_buffer_for_host_views(void *block_tag,
+                                                                  double **state_host_key,
+                                                                  int state_count,
+                                                                  int state_index,
+                                                                  double *host_buffer,
+                                                                  int *ex,
+                                                                  int i0, int j0, int k0,
+                                                                  int sx, int sy, int sz);
+
+int bssn_cuda_pack_state_batch_to_host_buffer(void *block_tag,
+                                              int state_count,
+                                              double *host_buffer,
+                                              int *ex,
+                                              int i0, int j0, int k0,
+                                              int sx, int sy, int sz);
+
+int bssn_cuda_pack_state_batch_to_host_buffer_for_host_views(void *block_tag,
+                                                             double **state_host_key,
+                                                             int state_count,
+                                                             double *host_buffer,
+                                                             int *ex,
+                                                             int i0, int j0, int k0,
+                                                             int sx, int sy, int sz);
+
+int bssn_cuda_unpack_state_batch_from_host_buffer(void *block_tag,
+                                                  int state_count,
+                                                  double *host_buffer,
+                                                  int *ex,
+                                                  int i0, int j0, int k0,
+                                                  int sx, int sy, int sz);
+
+int bssn_cuda_unpack_state_batch_from_host_buffer_for_host_views(void *block_tag,
+                                                                 double **state_host_key,
+                                                                 int state_count,
+                                                                 double *host_buffer,
+                                                                 int *ex,
+                                                                 int i0, int j0, int k0,
+                                                                 int sx, int sy, int sz);
+
+int bssn_cuda_pack_state_batch_to_device_buffer(void *block_tag,
+                                                int state_count,
+                                                double *device_buffer,
+                                                int *ex,
+                                                int i0, int j0, int k0,
+                                                int sx, int sy, int sz);
+
+int bssn_cuda_pack_state_batch_to_device_buffer_for_host_views(void *block_tag,
+                                                               double **state_host_key,
+                                                               int state_count,
+                                                               double *device_buffer,
+                                                               int *ex,
+                                                               int i0, int j0, int k0,
+                                                               int sx, int sy, int sz);
+
+int bssn_cuda_unpack_state_batch_from_device_buffer(void *block_tag,
+                                                    int state_count,
+                                                    double *device_buffer,
+                                                    int *ex,
+                                                    int i0, int j0, int k0,
+                                                    int sx, int sy, int sz);
+
+int bssn_cuda_unpack_state_batch_from_device_buffer_for_host_views(void *block_tag,
+                                                                   double **state_host_key,
+                                                                   int state_count,
+                                                                   double *device_buffer,
+                                                                   int *ex,
+                                                                   int i0, int j0, int k0,
+                                                                   int sx, int sy, int sz);
+
+int bssn_cuda_pack_state_segments_to_device_buffer(void *block_tag,
+                                                   int state_count,
+                                                   double *device_buffer,
+                                                   int *ex,
+                                                   int segment_count,
+                                                   const int *segment_meta);
+
+int bssn_cuda_pack_state_segments_to_device_buffer_for_host_views(void *block_tag,
+                                                                  double **state_host_key,
+                                                                  int state_count,
+                                                                  double *device_buffer,
+                                                                  int *ex,
+                                                                  int segment_count,
+                                                                  const int *segment_meta);
+
+int bssn_cuda_unpack_state_segments_from_device_buffer(void *block_tag,
+                                                       int state_count,
+                                                       double *device_buffer,
+                                                       int *ex,
+                                                       int segment_count,
+                                                       const int *segment_meta);
+
+int bssn_cuda_unpack_state_segments_from_device_buffer_for_host_views(void *block_tag,
+                                                                      double **state_host_key,
+                                                                      int state_count,
+                                                                      double *device_buffer,
+                                                                      int *ex,
+                                                                      int segment_count,
+                                                                      const int *segment_meta);
+
+int bssn_cuda_restrict_state_segments_to_device_buffer(void *block_tag,
+                                                       int state_count,
+                                                       double *device_buffer,
+                                                       int *ex,
+                                                       int segment_count,
+                                                       const int *segment_meta);
+
+int bssn_cuda_restrict_state_segments_to_device_buffer_for_host_views(void *block_tag,
+                                                                      double **state_host_key,
+                                                                      int state_count,
+                                                                      double *device_buffer,
+                                                                      int *ex,
+                                                                      int segment_count,
+                                                                      const int *segment_meta,
+                                                                      const double *state_soa);
+
+int bssn_cuda_prolong_state_segments_to_device_buffer(void *block_tag,
+                                                      int state_count,
+                                                      double *device_buffer,
+                                                      int *ex,
+                                                      int segment_count,
+                                                      const int *segment_meta);
+
+int bssn_cuda_prolong_state_segments_to_device_buffer_for_host_views(void *block_tag,
+                                                                     double **state_host_key,
+                                                                     int state_count,
+                                                                     double *device_buffer,
+                                                                     int *ex,
+                                                                     int segment_count,
+                                                                     const int *segment_meta,
+                                                                     const double *state_soa);
+
+int bssn_cuda_restrict_state_batch_to_device_buffer(void *block_tag,
+                                                    int state_count,
+                                                    double *device_buffer,
+                                                    int *ex,
+                                                    int sx, int sy, int sz,
+                                                    int fi0, int fj0, int fk0);
+
+int bssn_cuda_restrict_state_batch_to_device_buffer_for_host_views(void *block_tag,
+                                                                   double **state_host_key,
+                                                                   int state_count,
+                                                                   double *device_buffer,
+                                                                   int *ex,
+                                                                   int sx, int sy, int sz,
+                                                                   int fi0, int fj0, int fk0,
+                                                                   const double *state_soa);
+
+int bssn_cuda_prolong_state_batch_to_device_buffer(void *block_tag,
+                                                   int state_count,
+                                                   double *device_buffer,
+                                                   int *ex,
+                                                   int sx, int sy, int sz,
+                                                   int ii0, int jj0, int kk0,
+                                                   int lbc_i, int lbc_j, int lbc_k);
+
+int bssn_cuda_prolong_state_batch_to_device_buffer_for_host_views(void *block_tag,
+                                                                  double **state_host_key,
+                                                                  int state_count,
+                                                                  double *device_buffer,
+                                                                  int *ex,
+                                                                  int sx, int sy, int sz,
+                                                                  int ii0, int jj0, int kk0,
+                                                                  int lbc_i, int lbc_j, int lbc_k,
+                                                                  const double *state_soa);
+
+int bssn_cuda_download_state_subset(void *block_tag,
+                                    int *ex,
+                                    int subset_count,
+                                    const int *state_indices,
+                                    double **state_host_out);
+
+int bssn_cuda_upload_state_subset(void *block_tag,
+                                  int *ex,
+                                  int subset_count,
+                                  const int *state_indices,
+                                  double **state_host_in);
+
+int bssn_cuda_prepare_inter_time_level(void *block_tag,
+                                       int *ex,
+                                       int state_count,
+                                       double **src1_host_key,
+                                       double **src2_host_key,
+                                       double **src3_host_key,
+                                       double **dst_host_key,
+                                       int source_count,
+                                       int tindex);
+
+int bssn_cuda_has_resident_state(void *block_tag);
+
+void bssn_cuda_release_step_ctx(void *block_tag);
+
+#ifdef __cplusplus
+}
+// C++-only helpers declared for derived equation classes (Z4C, etc.)
+// Defined in bssn_class.C. Requires MyList, Patch, var from including TU.
+bool bssn_cuda_use_resident_sync(int lev);
+void bssn_cuda_download_level_state_if_present(MyList<Patch> *PatL, MyList<var> *vars, int myrank);
+#endif
+
+#endif

AMSS_NCKU_source/cctk.h

@@ -1,58 +1,58 @@
-#ifndef _CCTK_H_
-#define _CCTK_H_ 1
-
-/* Grab the main configuration info. */
-#include "cctk_Config.h"
-
-#define CCTK_THORNSTRING "AHFinderDirect"
-
-/* Include the constants */
-#include "cctk_Constants.h"
-
-/* get the definition of ptrdiff_t */
-#include <stddef.h>
-int CCTK_VInfo(const char *thorn, const char *format, ...);
-int CCTK_VWarn(int level,
-               int line,
-               const char *file,
-               const char *thorn,
-               const char *format,
-               ...);
-#define CCTK_ERROR_INTERP_GHOST_SIZE_TOO_SMALL (-1001)
-#ifdef __cplusplus
-#define HAVE_INLINE
-#else
-#ifndef inline
-#define HAVE_INLINE
-#endif
-#endif
-
-#define CCTK_PRINTSEPARATOR \
-  printf("--------------------------------------------------------------------------------\n");
-
-#define _DECLARE_CCTK_ARGUMENTS _DECLARE_CCTK_CARGUMENTS
-#define _DECLARE_CCTK_CARGUMENTS          \
-  ptrdiff_t cctki_dummy_int;              \
-  CCTK_REAL cctk_time = cctkGH->PhysTime; \
-  int cctk_iteration = 1;                 \
-  int cctk_dim = 3;
-
-#define CCTK_EQUALS(a, b) (CCTK_Equals((a), (b)))
-
-#define CCTK_PASS_CTOC cctkGH
-
-#define CCTK_ORIGIN_SPACE(x) (cctk_origin_space[x] + cctk_delta_space[x] / cctk_levfac[x] * cctk_levoff[x] / cctk_levoffdenom[x])
-#define CCTK_DELTA_SPACE(x) (cctk_delta_space[x] / cctk_levfac[x])
-#define CCTK_DELTA_TIME (cctk_delta_time / cctk_timefac)
-#define CCTK_LSSH(stag, dim) cctk_lssh[(stag) + CCTK_NSTAGGER * (dim)]
-#define CCTK_LSSH_IDX(stag, dim) ((stag) + CCTK_NSTAGGER * (dim))
-
-#define CCTK_WARN(a, b) CCTK_Warn(a, __LINE__, __FILE__, CCTK_THORNSTRING, b)
-
-#define CCTK_MALLOC(s) CCTKi_Malloc(s, __LINE__, __FILE__)
-#define CCTK_FREE(p) CCTKi_Free(p)
-
-#define CCTK_INFO(a) CCTK_Info(CCTK_THORNSTRING, (a))
-#define CCTK_PARAMWARN(a) CCTK_ParamWarn(CCTK_THORNSTRING, (a))
-
-#endif
+#ifndef _CCTK_H_
+#define _CCTK_H_ 1
+
+/* Grab the main configuration info. */
+#include "cctk_Config.h"
+
+#define CCTK_THORNSTRING "AHFinderDirect"
+
+/* Include the constants */
+#include "cctk_Constants.h"
+
+/* get the definition of ptrdiff_t */
+#include <stddef.h>
+int CCTK_VInfo(const char *thorn, const char *format, ...);
+int CCTK_VWarn(int level,
+               int line,
+               const char *file,
+               const char *thorn,
+               const char *format,
+               ...);
+#define CCTK_ERROR_INTERP_GHOST_SIZE_TOO_SMALL (-1001)
+#ifdef __cplusplus
+#define HAVE_INLINE
+#else
+#ifndef inline
+#define HAVE_INLINE
+#endif
+#endif
+
+#define CCTK_PRINTSEPARATOR \
+  printf("--------------------------------------------------------------------------------\n");
+
+#define _DECLARE_CCTK_ARGUMENTS _DECLARE_CCTK_CARGUMENTS
+#define _DECLARE_CCTK_CARGUMENTS          \
+  ptrdiff_t cctki_dummy_int;              \
+  CCTK_REAL cctk_time = cctkGH->PhysTime; \
+  int cctk_iteration = 1;                 \
+  int cctk_dim = 3;
+
+#define CCTK_EQUALS(a, b) (CCTK_Equals((a), (b)))
+
+#define CCTK_PASS_CTOC cctkGH
+
+#define CCTK_ORIGIN_SPACE(x) (cctk_origin_space[x] + cctk_delta_space[x] / cctk_levfac[x] * cctk_levoff[x] / cctk_levoffdenom[x])
+#define CCTK_DELTA_SPACE(x) (cctk_delta_space[x] / cctk_levfac[x])
+#define CCTK_DELTA_TIME (cctk_delta_time / cctk_timefac)
+#define CCTK_LSSH(stag, dim) cctk_lssh[(stag) + CCTK_NSTAGGER * (dim)]
+#define CCTK_LSSH_IDX(stag, dim) ((stag) + CCTK_NSTAGGER * (dim))
+
+#define CCTK_WARN(a, b) CCTK_Warn(a, __LINE__, __FILE__, CCTK_THORNSTRING, b)
+
+#define CCTK_MALLOC(s) CCTKi_Malloc(s, __LINE__, __FILE__)
+#define CCTK_FREE(p) CCTKi_Free(p)
+
+#define CCTK_INFO(a) CCTK_Info(CCTK_THORNSTRING, (a))
+#define CCTK_PARAMWARN(a) CCTK_ParamWarn(CCTK_THORNSTRING, (a))
+
+#endif

AMSS_NCKU_source/cctk_Config.h

@@ -1,168 +1,168 @@
-#ifndef _CCTK_CONFIG_H_
-#define _CCTK_CONFIG_H_
-
-#define STDC_HEADERS 1
-
-#define CCTK_FCALL 
-
-#define HAVE_GETHOSTBYNAME 1
-#define HAVE_GETOPT_LONG_ONLY 1
-#define HAVE_CRYPT 1
-#define HAVE_FINITE 1
-#define HAVE_ISNAN 1
-#define HAVE_ISINF 1
-#define HAVE_MKSTEMP 1
-#define HAVE_VA_COPY 1
-
-/* Do we have mode_t ? */
-#define HAVE_MODE_T 1
-
-#define HAVE_SOCKLEN_T 1
-#ifdef HAVE_SOCKLEN_T
-#  define CCTK_SOCKLEN_T socklen_t
-#else
-#  define CCTK_SOCKLEN_T int
-#endif
-
-#define HAVE_TIME_H 1
-#define HAVE_SYS_IOCTL_H 1
-#define HAVE_SYS_SOCKET_H 1
-#define HAVE_SYS_TIME_H 1
-#define HAVE_SYS_TYPES_H 1
-#define HAVE_UNISTD_H 1
-#define HAVE_STRING_H 1
-#define HAVE_ASSERT_H 1
-#define HAVE_TGMATH_H 1
-#define HAVE_SYS_STAT_H 1
-#define HAVE_GETOPT_H 1
-#define HAVE_REGEX_H 1
-#define HAVE_NETINET_IN_H 1
-#define HAVE_NETDB_H 1
-#define HAVE_ARPA_INET_H 1
-#define HAVE_CRYPT_H 1
-#define HAVE_DIRENT_H 1
-#define HAVE_SIGNAL_H 1
-#define HAVE_MALLOC_H 1
-#define HAVE_MALLINFO 1
-#define HAVE_MALLOPT 1
-#define HAVE_M_MMAP_THRESHOLD_VALUE 1
-
-#define TIME_WITH_SYS_TIME 1
-
-#define HAVE_VECTOR 1
-#define HAVE_VECTOR_H 1
-
-#define GETTIMEOFDAY_NEEDS_TIMEZONE 1
-
-#define CCTK_CACHELINE_BYTES 64
-#define CCTK_CACHE_SIZE 1024*1024
-
-#define NULL_DEVICE "/dev/null"
-
-#define CCTK_BUILD_OS "linux-gnu"
-#define CCTK_BUILD_CPU "x86_64"
-#define CCTK_BUILD_VENDOR "unknown"
-
-#define SIZEOF_SHORT_INT 2
-#define SIZEOF_INT 4
-#define SIZEOF_LONG_INT 8
-#define SIZEOF_LONG_LONG 8
-#define SIZEOF_LONG_DOUBLE 16
-#define SIZEOF_DOUBLE 8
-#define SIZEOF_FLOAT 4
-#define SIZEOF_CHAR_P 8
-
-#define CCTK_REAL_PRECISION_8 1
-
-#define CCTK_INTEGER_PRECISION_4 1
-
-#define HAVE_CCTK_INT8 1
-#define HAVE_CCTK_INT4 1
-#define HAVE_CCTK_INT2 1
-#define HAVE_CCTK_INT1 1
-
-#define HAVE_CCTK_REAL16 1
-#define HAVE_CCTK_REAL8 1
-#define HAVE_CCTK_REAL4 1
-
-#define CCTK_INT8 long int
-#define CCTK_INT4 int
-#define CCTK_INT2 short int
-#define CCTK_INT1 signed char
-
-#define CCTK_REAL16 long double
-#define CCTK_REAL8 double
-#define CCTK_REAL4 float
-
-#ifndef __cplusplus
-
-#ifdef CCTK_C_RESTRICT
-#define restrict CCTK_C_RESTRICT
-#endif
-
-/* Allow the use of CCTK_RESTRICT as a qualifier always. */
-#ifdef CCTK_C_RESTRICT
-#define CCTK_RESTRICT CCTK_C_RESTRICT
-#else
-#define CCTK_RESTRICT restrict
-#endif
-
-#ifdef HAVE_CCTK_C_BOOL
-#define CCTK_HAVE_C_BOOL
-#endif
-
-#endif /* ! defined __cplusplus */
-/****************************************************************************/
-
-/****************************************************************************/
-/* C++ specific stuff */
-/****************************************************************************/
-#ifdef __cplusplus
-
-/* Some C++ compilers don't have bool ! */
-#define HAVE_CCTK_CXX_BOOL 1
-
-#ifndef HAVE_CCTK_CXX_BOOL
-typedef enum {false, true} bool;
-#else
-/* deprecated in beta15 */
-#define CCTK_HAVE_CXX_BOOL
-#endif
-
-/* Some C++ compilers recognise the restrict keyword */
-#define CCTK_CXX_RESTRICT __restrict__
-
-/* Since this is non-standard leave commented out for the moment */
-#if 0
-/* Define to empty if the keyword does not work. */
-#ifdef CCTK_CXX_RESTRICT
-#define restrict CCTK_CXX_RESTRICT
-#endif
-#endif
-
-/* Allow the use of CCTK_RESTRICT as a qualifier always. */
-#ifdef CCTK_CXX_RESTRICT
-#define CCTK_RESTRICT CCTK_CXX_RESTRICT
-#else
-#define CCTK_RESTRICT restrict
-#endif
-
-#endif /* __cplusplus */
-/****************************************************************************/
-
-#ifdef FCODE
-
-#define HAVE_CCTK_FORTRAN_REAL4 1
-#define HAVE_CCTK_FORTRAN_REAL8 1
-#define HAVE_CCTK_FORTRAN_REAL16 1
-
-#define HAVE_CCTK_FORTRAN_COMPLEX8 1
-#define HAVE_CCTK_FORTRAN_COMPLEX16 1
-#define HAVE_CCTK_FORTRAN_COMPLEX32 1
-
-#endif /* FCODE */
-
-/* Now include the code to pick an appropriate precison for reals and ints */
-#include "cctk_Types.h"
-
-#endif /* _CCTK_CONFIG_H_ */
+#ifndef _CCTK_CONFIG_H_
+#define _CCTK_CONFIG_H_
+
+#define STDC_HEADERS 1
+
+#define CCTK_FCALL 
+
+#define HAVE_GETHOSTBYNAME 1
+#define HAVE_GETOPT_LONG_ONLY 1
+#define HAVE_CRYPT 1
+#define HAVE_FINITE 1
+#define HAVE_ISNAN 1
+#define HAVE_ISINF 1
+#define HAVE_MKSTEMP 1
+#define HAVE_VA_COPY 1
+
+/* Do we have mode_t ? */
+#define HAVE_MODE_T 1
+
+#define HAVE_SOCKLEN_T 1
+#ifdef HAVE_SOCKLEN_T
+#  define CCTK_SOCKLEN_T socklen_t
+#else
+#  define CCTK_SOCKLEN_T int
+#endif
+
+#define HAVE_TIME_H 1
+#define HAVE_SYS_IOCTL_H 1
+#define HAVE_SYS_SOCKET_H 1
+#define HAVE_SYS_TIME_H 1
+#define HAVE_SYS_TYPES_H 1
+#define HAVE_UNISTD_H 1
+#define HAVE_STRING_H 1
+#define HAVE_ASSERT_H 1
+#define HAVE_TGMATH_H 1
+#define HAVE_SYS_STAT_H 1
+#define HAVE_GETOPT_H 1
+#define HAVE_REGEX_H 1
+#define HAVE_NETINET_IN_H 1
+#define HAVE_NETDB_H 1
+#define HAVE_ARPA_INET_H 1
+#define HAVE_CRYPT_H 1
+#define HAVE_DIRENT_H 1
+#define HAVE_SIGNAL_H 1
+#define HAVE_MALLOC_H 1
+#define HAVE_MALLINFO 1
+#define HAVE_MALLOPT 1
+#define HAVE_M_MMAP_THRESHOLD_VALUE 1
+
+#define TIME_WITH_SYS_TIME 1
+
+#define HAVE_VECTOR 1
+#define HAVE_VECTOR_H 1
+
+#define GETTIMEOFDAY_NEEDS_TIMEZONE 1
+
+#define CCTK_CACHELINE_BYTES 64
+#define CCTK_CACHE_SIZE 1024*1024
+
+#define NULL_DEVICE "/dev/null"
+
+#define CCTK_BUILD_OS "linux-gnu"
+#define CCTK_BUILD_CPU "x86_64"
+#define CCTK_BUILD_VENDOR "unknown"
+
+#define SIZEOF_SHORT_INT 2
+#define SIZEOF_INT 4
+#define SIZEOF_LONG_INT 8
+#define SIZEOF_LONG_LONG 8
+#define SIZEOF_LONG_DOUBLE 16
+#define SIZEOF_DOUBLE 8
+#define SIZEOF_FLOAT 4
+#define SIZEOF_CHAR_P 8
+
+#define CCTK_REAL_PRECISION_8 1
+
+#define CCTK_INTEGER_PRECISION_4 1
+
+#define HAVE_CCTK_INT8 1
+#define HAVE_CCTK_INT4 1
+#define HAVE_CCTK_INT2 1
+#define HAVE_CCTK_INT1 1
+
+#define HAVE_CCTK_REAL16 1
+#define HAVE_CCTK_REAL8 1
+#define HAVE_CCTK_REAL4 1
+
+#define CCTK_INT8 long int
+#define CCTK_INT4 int
+#define CCTK_INT2 short int
+#define CCTK_INT1 signed char
+
+#define CCTK_REAL16 long double
+#define CCTK_REAL8 double
+#define CCTK_REAL4 float
+
+#ifndef __cplusplus
+
+#ifdef CCTK_C_RESTRICT
+#define restrict CCTK_C_RESTRICT
+#endif
+
+/* Allow the use of CCTK_RESTRICT as a qualifier always. */
+#ifdef CCTK_C_RESTRICT
+#define CCTK_RESTRICT CCTK_C_RESTRICT
+#else
+#define CCTK_RESTRICT restrict
+#endif
+
+#ifdef HAVE_CCTK_C_BOOL
+#define CCTK_HAVE_C_BOOL
+#endif
+
+#endif /* ! defined __cplusplus */
+/****************************************************************************/
+
+/****************************************************************************/
+/* C++ specific stuff */
+/****************************************************************************/
+#ifdef __cplusplus
+
+/* Some C++ compilers don't have bool ! */
+#define HAVE_CCTK_CXX_BOOL 1
+
+#ifndef HAVE_CCTK_CXX_BOOL
+typedef enum {false, true} bool;
+#else
+/* deprecated in beta15 */
+#define CCTK_HAVE_CXX_BOOL
+#endif
+
+/* Some C++ compilers recognise the restrict keyword */
+#define CCTK_CXX_RESTRICT __restrict__
+
+/* Since this is non-standard leave commented out for the moment */
+#if 0
+/* Define to empty if the keyword does not work. */
+#ifdef CCTK_CXX_RESTRICT
+#define restrict CCTK_CXX_RESTRICT
+#endif
+#endif
+
+/* Allow the use of CCTK_RESTRICT as a qualifier always. */
+#ifdef CCTK_CXX_RESTRICT
+#define CCTK_RESTRICT CCTK_CXX_RESTRICT
+#else
+#define CCTK_RESTRICT restrict
+#endif
+
+#endif /* __cplusplus */
+/****************************************************************************/
+
+#ifdef FCODE
+
+#define HAVE_CCTK_FORTRAN_REAL4 1
+#define HAVE_CCTK_FORTRAN_REAL8 1
+#define HAVE_CCTK_FORTRAN_REAL16 1
+
+#define HAVE_CCTK_FORTRAN_COMPLEX8 1
+#define HAVE_CCTK_FORTRAN_COMPLEX16 1
+#define HAVE_CCTK_FORTRAN_COMPLEX32 1
+
+#endif /* FCODE */
+
+/* Now include the code to pick an appropriate precison for reals and ints */
+#include "cctk_Types.h"
+
+#endif /* _CCTK_CONFIG_H_ */

AMSS_NCKU_source/cctk_Constants.h

@@ -1,57 +1,57 @@
-#ifndef _CCTK_CONSTANTS_H_
-#define _CCTK_CONSTANTS_H_
-
-#define CCTK_VARIABLE_VOID             100
-#define CCTK_VARIABLE_BYTE             101
-#define CCTK_VARIABLE_INT              102
-#define CCTK_VARIABLE_INT1             103
-#define CCTK_VARIABLE_INT2             104
-#define CCTK_VARIABLE_INT4             105
-#define CCTK_VARIABLE_INT8             106
-#define CCTK_VARIABLE_REAL             107
-#define CCTK_VARIABLE_REAL4            108
-#define CCTK_VARIABLE_REAL8            109
-#define CCTK_VARIABLE_REAL16           110
-#define CCTK_VARIABLE_COMPLEX          111
-#define CCTK_VARIABLE_COMPLEX8         112
-#define CCTK_VARIABLE_COMPLEX16        113
-#define CCTK_VARIABLE_COMPLEX32        114
-#define CCTK_VARIABLE_CHAR             115
-#define CCTK_VARIABLE_STRING           116
-#define CCTK_VARIABLE_POINTER          117
-#define CCTK_VARIABLE_POINTER_TO_CONST 118
-#define CCTK_VARIABLE_FPOINTER         119
-
-/* DEPRECATED IN BETA 12 */
-#define CCTK_VARIABLE_FN_POINTER CCTK_VARIABLE_FPOINTER
-
-/* steerable status of parameters */
-#define CCTK_STEERABLE_NEVER   200
-#define CCTK_STEERABLE_ALWAYS  201
-#define CCTK_STEERABLE_RECOVER 202
-
-/* number of staggerings */
-#define CCTK_NSTAGGER      3
-
-/* group distributions */
-#define CCTK_DISTRIB_CONSTANT 301
-#define CCTK_DISTRIB_DEFAULT  302
-
-/* group types */
-#define CCTK_SCALAR 401
-#define CCTK_GF     402
-#define CCTK_ARRAY  403
-
-/* group scopes */
-#define CCTK_PRIVATE   501
-#define CCTK_PROTECTED 502
-#define CCTK_PUBLIC    503
-
-/* constants for CCTK_TraverseString() */
-#define CCTK_VAR          601
-#define CCTK_GROUP        602
-#define CCTK_GROUP_OR_VAR 603
-
-
-#endif /* _CCTK_CONSTANTS_ */
-
+#ifndef _CCTK_CONSTANTS_H_
+#define _CCTK_CONSTANTS_H_
+
+#define CCTK_VARIABLE_VOID             100
+#define CCTK_VARIABLE_BYTE             101
+#define CCTK_VARIABLE_INT              102
+#define CCTK_VARIABLE_INT1             103
+#define CCTK_VARIABLE_INT2             104
+#define CCTK_VARIABLE_INT4             105
+#define CCTK_VARIABLE_INT8             106
+#define CCTK_VARIABLE_REAL             107
+#define CCTK_VARIABLE_REAL4            108
+#define CCTK_VARIABLE_REAL8            109
+#define CCTK_VARIABLE_REAL16           110
+#define CCTK_VARIABLE_COMPLEX          111
+#define CCTK_VARIABLE_COMPLEX8         112
+#define CCTK_VARIABLE_COMPLEX16        113
+#define CCTK_VARIABLE_COMPLEX32        114
+#define CCTK_VARIABLE_CHAR             115
+#define CCTK_VARIABLE_STRING           116
+#define CCTK_VARIABLE_POINTER          117
+#define CCTK_VARIABLE_POINTER_TO_CONST 118
+#define CCTK_VARIABLE_FPOINTER         119
+
+/* DEPRECATED IN BETA 12 */
+#define CCTK_VARIABLE_FN_POINTER CCTK_VARIABLE_FPOINTER
+
+/* steerable status of parameters */
+#define CCTK_STEERABLE_NEVER   200
+#define CCTK_STEERABLE_ALWAYS  201
+#define CCTK_STEERABLE_RECOVER 202
+
+/* number of staggerings */
+#define CCTK_NSTAGGER      3
+
+/* group distributions */
+#define CCTK_DISTRIB_CONSTANT 301
+#define CCTK_DISTRIB_DEFAULT  302
+
+/* group types */
+#define CCTK_SCALAR 401
+#define CCTK_GF     402
+#define CCTK_ARRAY  403
+
+/* group scopes */
+#define CCTK_PRIVATE   501
+#define CCTK_PROTECTED 502
+#define CCTK_PUBLIC    503
+
+/* constants for CCTK_TraverseString() */
+#define CCTK_VAR          601
+#define CCTK_GROUP        602
+#define CCTK_GROUP_OR_VAR 603
+
+
+#endif /* _CCTK_CONSTANTS_ */
+

AMSS_NCKU_source/cctk_Types.h

@@ -1,180 +1,180 @@
-#ifndef _CCTK_TYPES_H_
-#define _CCTK_TYPES_H_
-
-#ifndef _CCTK_CONFIG_H_
-#include "cctk_Config.h"
-#endif
-
-typedef void *CCTK_POINTER;
-typedef const void *CCTK_POINTER_TO_CONST;
-typedef void (*CCTK_FPOINTER)(void);
-#define HAVE_CCTK_POINTER 1
-#define HAVE_CCTK_POINTER_TO_CONST 1
-#define HAVE_CCTK_FPOINTER 1
-
-/* Character types */
-typedef char CCTK_CHAR;
-typedef const char * CCTK_STRING;
-#define HAVE_CCTK_CHAR 1
-#define HAVE_CCTK_STRING 1
-
-/* Structures for complex types */
-
-#ifdef HAVE_CCTK_REAL16
-#define HAVE_CCTK_COMPLEX32 1
-typedef struct CCTK_COMPLEX32
-{
-  CCTK_REAL16 Re;
-  CCTK_REAL16 Im;
-#ifdef __cplusplus
-  CCTK_REAL16 real() const { return Re; }
-  CCTK_REAL16 imag() const { return Im; }
-#endif
-} CCTK_COMPLEX32;
-#endif
-
-#ifdef HAVE_CCTK_REAL8
-#define HAVE_CCTK_COMPLEX16 1
-typedef struct CCTK_COMPLEX16
-{
-  CCTK_REAL8 Re;
-  CCTK_REAL8 Im;
-#ifdef __cplusplus
-  CCTK_REAL8 real() const { return Re; }
-  CCTK_REAL8 imag() const { return Im; }
-#endif
-} CCTK_COMPLEX16;
-#endif
-
-#ifdef HAVE_CCTK_REAL4
-#define HAVE_CCTK_COMPLEX8 1
-typedef struct CCTK_COMPLEX8
-{
-  CCTK_REAL4 Re;
-  CCTK_REAL4 Im;
-#ifdef __cplusplus
-  CCTK_REAL4 real() const { return Re; }
-  CCTK_REAL4 imag() const { return Im; }
-#endif
-} CCTK_COMPLEX8;
-#endif
-
-/* Small positive integer type */
-typedef unsigned char CCTK_BYTE;
-#define HAVE_CCTK_BYTE 1
-
-/* Define stuff for fortran. */
-#ifdef FCODE
-
-#define CCTK_POINTER          integer*SIZEOF_CHAR_P
-#define CCTK_POINTER_TO_CONST integer*SIZEOF_CHAR_P
-/* TODO: add autoconf for determining the size of function pointers */
-#define CCTK_FPOINTER         integer*SIZEOF_CHAR_P
-#define HAVE_CCTK_POINTER 1
-#define HAVE_CCTK_POINTER_TO_CONST 1
-#define HAVE_CCTK_FPOINTER 1
-
-/* Character types */
-/* A single character does not exist in Fortran; in Fortran, all
-   character types are strings.  Hence we do not define CCTK_CHAR.  */
-/* #define CCTK_CHAR   CHARACTER */
-/* #define HAVE_CCTK_CHAR 1 */
-/* This is a C-string, i.e., only a pointer */
-#define CCTK_STRING CCTK_POINTER_TO_CONST
-#define HAVE_CCTK_STRING 1
-
-#ifdef HAVE_CCTK_INT8
-#define CCTK_INT8 INTEGER*8
-#endif
-#ifdef HAVE_CCTK_INT4
-#define CCTK_INT4 INTEGER*4
-#endif
-#ifdef HAVE_CCTK_INT2
-#define CCTK_INT2 INTEGER*2
-#endif
-#ifdef HAVE_CCTK_INT1
-#define CCTK_INT1 INTEGER*1
-#endif
-
-#ifdef HAVE_CCTK_REAL16
-#define CCTK_REAL16 REAL*16
-#define HAVE_CCTK_COMPLEX32 1
-#define CCTK_COMPLEX32  COMPLEX*32
-#endif
-
-#ifdef HAVE_CCTK_REAL8
-#define CCTK_REAL8  REAL*8
-#define HAVE_CCTK_COMPLEX16 1
-#define CCTK_COMPLEX16  COMPLEX*16
-#endif
-
-#ifdef HAVE_CCTK_REAL4
-#define CCTK_REAL4  REAL*4
-#define HAVE_CCTK_COMPLEX8 1
-#define CCTK_COMPLEX8   COMPLEX*8
-#endif
-
-/* Should be unsigned, but Fortran doesn't have that */
-#define CCTK_BYTE INTEGER*1
-#define HAVE_CCTK_BYTE 1
-
-#endif /*FCODE */
-
-/* Now pick the types based upon the precision variable. */
-
-/* Floating point precision */
-#ifdef CCTK_REAL_PRECISION_16
-#define CCTK_REAL_PRECISION 16
-#define CCTK_REAL CCTK_REAL16
-#endif
-
-#ifdef CCTK_REAL_PRECISION_8
-#define CCTK_REAL_PRECISION 8
-#define CCTK_REAL CCTK_REAL8
-#endif
-
-#ifdef CCTK_REAL_PRECISION_4
-#define CCTK_REAL_PRECISION 4
-#define CCTK_REAL CCTK_REAL4
-#endif
-
-/* Integer precision */
-
-#ifdef CCTK_INTEGER_PRECISION_8
-#define CCTK_INTEGER_PRECISION 8
-#define CCTK_INT CCTK_INT8
-#endif
-
-#ifdef CCTK_INTEGER_PRECISION_4
-#define CCTK_INTEGER_PRECISION 4
-#define CCTK_INT CCTK_INT4
-#endif
-
-#ifdef CCTK_INTEGER_PRECISION_2
-#define CCTK_INTEGER_PRECISION 2
-#define CCTK_INT CCTK_INT2
-#endif
-
-#ifdef CCTK_INTEGER_PRECISION_1
-#define CCTK_INTEGER_PRECISION 1
-#define CCTK_INT CCTK_INT1
-#endif
-
-/* Complex precision */
-#ifdef CCTK_REAL_PRECISION_16
-#define CCTK_COMPLEX_PRECISION 32
-#define CCTK_COMPLEX CCTK_COMPLEX32
-#endif
-
-#ifdef CCTK_REAL_PRECISION_8
-#define CCTK_COMPLEX_PRECISION 16
-#define CCTK_COMPLEX CCTK_COMPLEX16
-#endif
-
-#ifdef CCTK_REAL_PRECISION_4
-#define CCTK_COMPLEX_PRECISION 8
-#define CCTK_COMPLEX CCTK_COMPLEX8
-#endif
-
-#endif /*_CCTK_TYPES_H_ */
-
+#ifndef _CCTK_TYPES_H_
+#define _CCTK_TYPES_H_
+
+#ifndef _CCTK_CONFIG_H_
+#include "cctk_Config.h"
+#endif
+
+typedef void *CCTK_POINTER;
+typedef const void *CCTK_POINTER_TO_CONST;
+typedef void (*CCTK_FPOINTER)(void);
+#define HAVE_CCTK_POINTER 1
+#define HAVE_CCTK_POINTER_TO_CONST 1
+#define HAVE_CCTK_FPOINTER 1
+
+/* Character types */
+typedef char CCTK_CHAR;
+typedef const char * CCTK_STRING;
+#define HAVE_CCTK_CHAR 1
+#define HAVE_CCTK_STRING 1
+
+/* Structures for complex types */
+
+#ifdef HAVE_CCTK_REAL16
+#define HAVE_CCTK_COMPLEX32 1
+typedef struct CCTK_COMPLEX32
+{
+  CCTK_REAL16 Re;
+  CCTK_REAL16 Im;
+#ifdef __cplusplus
+  CCTK_REAL16 real() const { return Re; }
+  CCTK_REAL16 imag() const { return Im; }
+#endif
+} CCTK_COMPLEX32;
+#endif
+
+#ifdef HAVE_CCTK_REAL8
+#define HAVE_CCTK_COMPLEX16 1
+typedef struct CCTK_COMPLEX16
+{
+  CCTK_REAL8 Re;
+  CCTK_REAL8 Im;
+#ifdef __cplusplus
+  CCTK_REAL8 real() const { return Re; }
+  CCTK_REAL8 imag() const { return Im; }
+#endif
+} CCTK_COMPLEX16;
+#endif
+
+#ifdef HAVE_CCTK_REAL4
+#define HAVE_CCTK_COMPLEX8 1
+typedef struct CCTK_COMPLEX8
+{
+  CCTK_REAL4 Re;
+  CCTK_REAL4 Im;
+#ifdef __cplusplus
+  CCTK_REAL4 real() const { return Re; }
+  CCTK_REAL4 imag() const { return Im; }
+#endif
+} CCTK_COMPLEX8;
+#endif
+
+/* Small positive integer type */
+typedef unsigned char CCTK_BYTE;
+#define HAVE_CCTK_BYTE 1
+
+/* Define stuff for fortran. */
+#ifdef FCODE
+
+#define CCTK_POINTER          integer*SIZEOF_CHAR_P
+#define CCTK_POINTER_TO_CONST integer*SIZEOF_CHAR_P
+/* TODO: add autoconf for determining the size of function pointers */
+#define CCTK_FPOINTER         integer*SIZEOF_CHAR_P
+#define HAVE_CCTK_POINTER 1
+#define HAVE_CCTK_POINTER_TO_CONST 1
+#define HAVE_CCTK_FPOINTER 1
+
+/* Character types */
+/* A single character does not exist in Fortran; in Fortran, all
+   character types are strings.  Hence we do not define CCTK_CHAR.  */
+/* #define CCTK_CHAR   CHARACTER */
+/* #define HAVE_CCTK_CHAR 1 */
+/* This is a C-string, i.e., only a pointer */
+#define CCTK_STRING CCTK_POINTER_TO_CONST
+#define HAVE_CCTK_STRING 1
+
+#ifdef HAVE_CCTK_INT8
+#define CCTK_INT8 INTEGER*8
+#endif
+#ifdef HAVE_CCTK_INT4
+#define CCTK_INT4 INTEGER*4
+#endif
+#ifdef HAVE_CCTK_INT2
+#define CCTK_INT2 INTEGER*2
+#endif
+#ifdef HAVE_CCTK_INT1
+#define CCTK_INT1 INTEGER*1
+#endif
+
+#ifdef HAVE_CCTK_REAL16
+#define CCTK_REAL16 REAL*16
+#define HAVE_CCTK_COMPLEX32 1
+#define CCTK_COMPLEX32  COMPLEX*32
+#endif
+
+#ifdef HAVE_CCTK_REAL8
+#define CCTK_REAL8  REAL*8
+#define HAVE_CCTK_COMPLEX16 1
+#define CCTK_COMPLEX16  COMPLEX*16
+#endif
+
+#ifdef HAVE_CCTK_REAL4
+#define CCTK_REAL4  REAL*4
+#define HAVE_CCTK_COMPLEX8 1
+#define CCTK_COMPLEX8   COMPLEX*8
+#endif
+
+/* Should be unsigned, but Fortran doesn't have that */
+#define CCTK_BYTE INTEGER*1
+#define HAVE_CCTK_BYTE 1
+
+#endif /*FCODE */
+
+/* Now pick the types based upon the precision variable. */
+
+/* Floating point precision */
+#ifdef CCTK_REAL_PRECISION_16
+#define CCTK_REAL_PRECISION 16
+#define CCTK_REAL CCTK_REAL16
+#endif
+
+#ifdef CCTK_REAL_PRECISION_8
+#define CCTK_REAL_PRECISION 8
+#define CCTK_REAL CCTK_REAL8
+#endif
+
+#ifdef CCTK_REAL_PRECISION_4
+#define CCTK_REAL_PRECISION 4
+#define CCTK_REAL CCTK_REAL4
+#endif
+
+/* Integer precision */
+
+#ifdef CCTK_INTEGER_PRECISION_8
+#define CCTK_INTEGER_PRECISION 8
+#define CCTK_INT CCTK_INT8
+#endif
+
+#ifdef CCTK_INTEGER_PRECISION_4
+#define CCTK_INTEGER_PRECISION 4
+#define CCTK_INT CCTK_INT4
+#endif
+
+#ifdef CCTK_INTEGER_PRECISION_2
+#define CCTK_INTEGER_PRECISION 2
+#define CCTK_INT CCTK_INT2
+#endif
+
+#ifdef CCTK_INTEGER_PRECISION_1
+#define CCTK_INTEGER_PRECISION 1
+#define CCTK_INT CCTK_INT1
+#endif
+
+/* Complex precision */
+#ifdef CCTK_REAL_PRECISION_16
+#define CCTK_COMPLEX_PRECISION 32
+#define CCTK_COMPLEX CCTK_COMPLEX32
+#endif
+
+#ifdef CCTK_REAL_PRECISION_8
+#define CCTK_COMPLEX_PRECISION 16
+#define CCTK_COMPLEX CCTK_COMPLEX16
+#endif
+
+#ifdef CCTK_REAL_PRECISION_4
+#define CCTK_COMPLEX_PRECISION 8
+#define CCTK_COMPLEX CCTK_COMPLEX8
+#endif
+
+#endif /*_CCTK_TYPES_H_ */
+

AMSS_NCKU_source/cgh.h

@@ -1,92 +1,92 @@
-
-#ifndef CGH_H
-#define CGH_H
-
-#include <mpi.h>
-#include "MyList.h"
-#include "MPatch.h"
-#include "macrodef.h"
-#include "monitor.h"
-#include "Parallel.h"
-
-class cgh
-{
-
-public:
-   int levels, movls, BH_num_in;
-   // information of boxes
-   int *grids;
-   double ***bbox;
-   int ***shape;
-   double ***handle;
-   double ***Porgls;
-   double *Lt;
-
-   // information of Patch list
-   MyList<Patch> **PatL;
-
-// information of OutBdLow2Hi point list and Restrict point list
-#if (RPB == 1)
-   MyList<Parallel::pointstru_bam> **bdsul, **rsul;
-#endif
-
-#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
-   int mylev;
-   int *start_rank, *end_rank;
-   MPI_Comm *Commlev;
-#endif
-
-protected:
-   int ingfs, fngfs;
-   static constexpr double ratio = 0.75;
-   int trfls;
-
-public:
-   cgh(int ingfsi, int fngfsi, int Symmetry, char *filename, int checkrun, monitor *ErrorMonitor);
-
-   ~cgh();
-
-   void compose_cgh(int nprocs);
-   void sethandle(monitor *ErrorMonitor);
-   void checkPatchList(MyList<Patch> *PatL, bool buflog);
-   void Regrid(int Symmetry, int BH_num, double **Porgbr, double **Porg0,
-               MyList<var> *OldList, MyList<var> *StateList,
-               MyList<var> *FutureList, MyList<var> *tmList, bool BB,
-               monitor *ErrorMonitor);
-   void Regrid_fake(int Symmetry, int BH_num, double **Porgbr, double **Porg0,
-                    MyList<var> *OldList, MyList<var> *StateList,
-                    MyList<var> *FutureList, MyList<var> *tmList, bool BB,
-                    monitor *ErrorMonitor);
-   void recompose_cgh(int nprocs, bool *lev_flag,
-                      MyList<var> *OldList, MyList<var> *StateList,
-                      MyList<var> *FutureList, MyList<var> *tmList,
-                      int Symmetry, bool BB);
-   void recompose_cgh_fake(int nprocs, bool *lev_flag,
-                           MyList<var> *OldList, MyList<var> *StateList,
-                           MyList<var> *FutureList, MyList<var> *tmList,
-                           int Symmetry, bool BB);
-   void read_bbox(int Symmetry, char *filename);
-   MyList<Patch> *construct_patchlist(int lev, int Symmetry);
-   bool Interp_One_Point(MyList<var> *VarList,
-                         double *XX, /*input global Cartesian coordinate*/
-                         double *Shellf, int Symmetry);
-   void recompose_cgh_Onelevel(int nprocs, int lev,
-                               MyList<var> *OldList, MyList<var> *StateList,
-                               MyList<var> *FutureList, MyList<var> *tmList,
-                               int Symmetry, bool BB);
-   bool Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
-                        MyList<var> *OldList, MyList<var> *StateList,
-                        MyList<var> *FutureList, MyList<var> *tmList, bool BB,
-                        monitor *ErrorMonitor);
-   void Regrid_Onelevel_aux(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
-                            MyList<var> *OldList, MyList<var> *StateList,
-                            MyList<var> *FutureList, MyList<var> *tmList, bool BB,
-                            monitor *ErrorMonitor);
-   void settrfls(const int lev);
-
-#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
-   void construct_mylev(int nprocs);
-#endif
-};
-
-#endif /* CGH_H */
+
+#ifndef CGH_H
+#define CGH_H
+
+#include <mpi.h>
+#include "MyList.h"
+#include "MPatch.h"
+#include "macrodef.h"
+#include "monitor.h"
+#include "Parallel.h"
+
+class cgh
+{
+
+public:
+   int levels, movls, BH_num_in;
+   // information of boxes
+   int *grids;
+   double ***bbox;
+   int ***shape;
+   double ***handle;
+   double ***Porgls;
+   double *Lt;
+
+   // information of Patch list
+   MyList<Patch> **PatL;
+
+// information of OutBdLow2Hi point list and Restrict point list
+#if (RPB == 1)
+   MyList<Parallel::pointstru_bam> **bdsul, **rsul;
+#endif
+
+#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
+   int mylev;
+   int *start_rank, *end_rank;
+   MPI_Comm *Commlev;
+#endif
+
+protected:
+   int ingfs, fngfs;
+   static constexpr double ratio = 0.75;
+   int trfls;
+
+public:
+   cgh(int ingfsi, int fngfsi, int Symmetry, char *filename, int checkrun, monitor *ErrorMonitor);
+
+   ~cgh();
+
+   void compose_cgh(int nprocs);
+   void sethandle(monitor *ErrorMonitor);
+   void checkPatchList(MyList<Patch> *PatL, bool buflog);
+   void Regrid(int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+               MyList<var> *OldList, MyList<var> *StateList,
+               MyList<var> *FutureList, MyList<var> *tmList, bool BB,
+               monitor *ErrorMonitor);
+   void Regrid_fake(int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+                    MyList<var> *OldList, MyList<var> *StateList,
+                    MyList<var> *FutureList, MyList<var> *tmList, bool BB,
+                    monitor *ErrorMonitor);
+   void recompose_cgh(int nprocs, bool *lev_flag,
+                      MyList<var> *OldList, MyList<var> *StateList,
+                      MyList<var> *FutureList, MyList<var> *tmList,
+                      int Symmetry, bool BB);
+   void recompose_cgh_fake(int nprocs, bool *lev_flag,
+                           MyList<var> *OldList, MyList<var> *StateList,
+                           MyList<var> *FutureList, MyList<var> *tmList,
+                           int Symmetry, bool BB);
+   void read_bbox(int Symmetry, char *filename);
+   MyList<Patch> *construct_patchlist(int lev, int Symmetry);
+   bool Interp_One_Point(MyList<var> *VarList,
+                         double *XX, /*input global Cartesian coordinate*/
+                         double *Shellf, int Symmetry);
+   void recompose_cgh_Onelevel(int nprocs, int lev,
+                               MyList<var> *OldList, MyList<var> *StateList,
+                               MyList<var> *FutureList, MyList<var> *tmList,
+                               int Symmetry, bool BB);
+   bool Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+                        MyList<var> *OldList, MyList<var> *StateList,
+                        MyList<var> *FutureList, MyList<var> *tmList, bool BB,
+                        monitor *ErrorMonitor);
+   void Regrid_Onelevel_aux(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+                            MyList<var> *OldList, MyList<var> *StateList,
+                            MyList<var> *FutureList, MyList<var> *tmList, bool BB,
+                            monitor *ErrorMonitor);
+   void settrfls(const int lev);
+
+#if (PSTR == 1 || PSTR == 2 || PSTR == 3)
+   void construct_mylev(int nprocs);
+#endif
+};
+
+#endif /* CGH_H */

AMSS_NCKU_source/checkpoint.h

@@ -1,60 +1,60 @@
-
-#ifndef CHECKPOINT_H
-#define CHECKPOINT_H
-
-#ifdef newc
-#include <iostream>
-#include <iomanip>
-#include <strstream>
-#include <fstream>
-#include <string>
-using namespace std;
-#else
-#include <iostream.h>
-#include <iomanip.h>
-#include <strstream>
-#include <fstream.h>
-#include <string.h>
-#endif
-#include <time.h>
-#include <stdlib.h>
-
-#include <mpi.h>
-
-#include "var.h"
-#include "MyList.h"
-#include "cgh.h"
-#include "macrodef.h"
-#include "ShellPatch.h"
-
-class checkpoint
-{
-
-public:
-  bool checkedrun;
-  bool I_Print;
-  char *filename;
-  MyList<var> *CheckList;
-  string out_dir;
-
-public:
-  checkpoint(bool checked, const char fname[], int myrank);
-  // checkpoint(bool checked, char fname[50], int myrank);
-
-  ~checkpoint();
-  void addvariable(var *VV);
-  void addvariablelist(MyList<var> *VL);
-
-  void write_Black_Hole_position(int BH_num_input, int BH_num, double **Porg0, double **Porgbr, double *Mass);
-  void read_Black_Hole_position(int &BH_num_input, int &BH_num, double **&Porg0, double *&Pmom,
-                                double *&Spin, double *&Mass, double **&Porgbr, double **&Porg,
-                                double **&Porg1, double **&Porg_rhs);
-  void writecheck_cgh(double time, cgh *GH);
-  void readcheck_cgh(double &time, cgh *GH, int myrank, int nprocs, int Symmetry);
-  void writecheck_sh(double time, ShellPatch *SH);
-  void readcheck_sh(ShellPatch *SH, int myrank);
-  void write_bssn(double LastDump, double Last2dDump, double LastAnas);
-  void read_bssn(double &LastDump, double &Last2dDump, double &LastAnas);
-};
-
-#endif /* CHECKPOINT */
+
+#ifndef CHECKPOINT_H
+#define CHECKPOINT_H
+
+#ifdef newc
+#include <iostream>
+#include <iomanip>
+#include <strstream>
+#include <fstream>
+#include <string>
+using namespace std;
+#else
+#include <iostream.h>
+#include <iomanip.h>
+#include <strstream>
+#include <fstream.h>
+#include <string.h>
+#endif
+#include <time.h>
+#include <stdlib.h>
+
+#include <mpi.h>
+
+#include "var.h"
+#include "MyList.h"
+#include "cgh.h"
+#include "macrodef.h"
+#include "ShellPatch.h"
+
+class checkpoint
+{
+
+public:
+  bool checkedrun;
+  bool I_Print;
+  char *filename;
+  MyList<var> *CheckList;
+  string out_dir;
+
+public:
+  checkpoint(bool checked, const char fname[], int myrank);
+  // checkpoint(bool checked, char fname[50], int myrank);
+
+  ~checkpoint();
+  void addvariable(var *VV);
+  void addvariablelist(MyList<var> *VL);
+
+  void write_Black_Hole_position(int BH_num_input, int BH_num, double **Porg0, double **Porgbr, double *Mass);
+  void read_Black_Hole_position(int &BH_num_input, int &BH_num, double **&Porg0, double *&Pmom,
+                                double *&Spin, double *&Mass, double **&Porgbr, double **&Porg,
+                                double **&Porg1, double **&Porg_rhs);
+  void writecheck_cgh(double time, cgh *GH);
+  void readcheck_cgh(double &time, cgh *GH, int myrank, int nprocs, int Symmetry);
+  void writecheck_sh(double time, ShellPatch *SH);
+  void readcheck_sh(ShellPatch *SH, int myrank);
+  void write_bssn(double LastDump, double Last2dDump, double LastAnas);
+  void read_bssn(double &LastDump, double &Last2dDump, double &LastAnas);
+};
+
+#endif /* CHECKPOINT */

AMSS_NCKU_source/config.h

@@ -1,16 +1,16 @@
-#ifndef AHFINDERDIRECT__CONFIG_H
-#define AHFINDERDIRECT__CONFIG_H
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <stdarg.h>
-#include <string.h>
-
-size_t Util_Strlcat(char* dst, const char* src, size_t dst_size);
-size_t Util_Strlcpy(char* dst, const char* src, size_t dst_size);
-
-typedef CCTK_REAL fp;
-
-typedef CCTK_INT integer;
-
-#endif	/* AHFINDERDIRECT__CONFIG_H */
+#ifndef AHFINDERDIRECT__CONFIG_H
+#define AHFINDERDIRECT__CONFIG_H
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+size_t Util_Strlcat(char* dst, const char* src, size_t dst_size);
+size_t Util_Strlcpy(char* dst, const char* src, size_t dst_size);
+
+typedef CCTK_REAL fp;
+
+typedef CCTK_INT integer;
+
+#endif	/* AHFINDERDIRECT__CONFIG_H */

AMSS_NCKU_source/coords.h

@@ -1,173 +1,173 @@
-#ifndef COORDS_H
-#define COORDS_H
-namespace AHFinderDirect
-{
-	namespace local_coords
-	{
-
-		// compare if two angles are fuzzily equal mod 2*pi radians (360 degrees)
-		bool fuzzy_EQ_ang(fp ang1, fp ang2);	// radians
-		bool fuzzy_EQ_dang(fp dang1, fp dang2); // degrees
-
-		// modulo-reduce  {ang,dang}  to be (fuzzily) within the range
-		// [min,max]_{ang,dang}, or error_exit() if no such value exists
-		fp modulo_reduce_ang(fp ang, fp min_ang, fp max_ang);
-		fp modulo_reduce_dang(fp dang, fp min_dang, fp max_dang);
-
-	} // close namespace local_coords::
-
-	namespace local_coords
-	{
-		// (r,(mu,nu,phi)) <--> (x,y,z)
-		void xyz_of_r_mu_nu(fp r, fp mu, fp nu, fp &x, fp &y, fp &z);
-		void xyz_of_r_mu_phi(fp r, fp mu, fp phi, fp &x, fp &y, fp &z);
-		void xyz_of_r_nu_phi(fp r, fp nu, fp phi, fp &x, fp &y, fp &z);
-		fp r_of_xyz(fp x, fp y, fp z);
-		fp mu_of_yz(fp y, fp z);
-		fp nu_of_xz(fp x, fp z);
-		fp phi_of_xy(fp x, fp y);
-
-		// ((mu,nu,phi)) --> the 3rd
-		fp phi_of_mu_nu(fp mu, fp nu);
-		fp nu_of_mu_phi(fp mu, fp phi);
-		fp mu_of_nu_phi(fp nu, fp phi);
-
-		// partial {x,y,z} / partial {mu,nu,phi}
-		void partial_xyz_wrt_r_mu_nu(fp r, fp mu, fp nu,
-									 fp &partial_x_wrt_r, fp &partial_x_wrt_mu, fp &partial_x_wrt_nu,
-									 fp &partial_y_wrt_r, fp &partial_y_wrt_mu, fp &partial_y_wrt_nu,
-									 fp &partial_z_wrt_r, fp &partial_z_wrt_mu, fp &partial_z_wrt_nu);
-		void partial_xyz_wrt_r_mu_phi(fp r, fp mu, fp phi,
-									  fp &partial_x_wrt_r, fp &partial_x_wrt_mu, fp &partial_x_wrt_phi,
-									  fp &partial_y_wrt_r, fp &partial_y_wrt_mu, fp &partial_y_wrt_phi,
-									  fp &partial_z_wrt_r, fp &partial_z_wrt_mu, fp &partial_z_wrt_phi);
-		void partial_xyz_wrt_r_nu_phi(fp r, fp nu, fp phi,
-									  fp &partial_x_wrt_r, fp &partial_x_wrt_nu, fp &partial_x_wrt_phi,
-									  fp &partial_y_wrt_r, fp &partial_y_wrt_nu, fp &partial_y_wrt_phi,
-									  fp &partial_z_wrt_r, fp &partial_z_wrt_nu, fp &partial_z_wrt_phi);
-
-		// partial {mu,nu,phi} / partial {x,y,z}
-		fp partial_mu_wrt_y(fp y, fp z);
-		fp partial_mu_wrt_z(fp y, fp z);
-		fp partial_nu_wrt_x(fp x, fp z);
-		fp partial_nu_wrt_z(fp x, fp z);
-		fp partial_phi_wrt_x(fp x, fp y);
-		fp partial_phi_wrt_y(fp x, fp y);
-
-		// partial^2 {mu,nu,phi} / partial {x,y,z}{x,y,z}
-		fp partial2_mu_wrt_yy(fp y, fp z);
-		fp partial2_mu_wrt_yz(fp y, fp z);
-		fp partial2_mu_wrt_zz(fp y, fp z);
-		fp partial2_nu_wrt_xx(fp x, fp z);
-		fp partial2_nu_wrt_xz(fp x, fp z);
-		fp partial2_nu_wrt_zz(fp x, fp z);
-		fp partial2_phi_wrt_xx(fp x, fp y);
-		fp partial2_phi_wrt_xy(fp x, fp y);
-		fp partial2_phi_wrt_yy(fp x, fp y);
-
-		// usual polar spherical (r,theta,phi) <--> (x,y,z)
-		void xyz_of_r_theta_phi(fp r, fp theta, fp phi, fp &x, fp &y, fp &z);
-		void r_theta_phi_of_xyz(fp x, fp y, fp z, fp &r, fp &theta, fp &phi);
-		// ... already have r_of_xyz()
-		// ... already have phi_of_xy()
-		fp theta_of_xyz(fp x, fp y, fp z);
-
-		// ((mu,nu,phi)) <--> usual polar spherical (theta,phi)
-		// ... note phi is the same coordinate in both systems
-		void theta_phi_of_mu_nu(fp mu, fp nu, fp &ps_theta, fp &ps_phi);
-		void theta_phi_of_mu_phi(fp mu, fp phi, fp &ps_theta, fp &ps_phi);
-		void theta_phi_of_nu_phi(fp nu, fp phi, fp &ps_theta, fp &ps_phi);
-		void mu_nu_of_theta_phi(fp ps_theta, fp ps_phi, fp &mu, fp &nu);
-		void mu_phi_of_theta_phi(fp ps_theta, fp ps_phi, fp &mu, fp &phi);
-		void nu_phi_of_theta_phi(fp ps_theta, fp ps_phi, fp &nu, fp &phi);
-
-		// ((mu,nu,phi)) --> direction cosines (xcos,ycos,zcos)
-		void xyzcos_of_mu_nu(fp mu, fp nu, fp &xcos, fp &ycos, fp &zcos);
-		void xyzcos_of_mu_phi(fp mu, fp phi, fp &xcos, fp &ycos, fp &zcos);
-		void xyzcos_of_nu_phi(fp nu, fp phi, fp &xcos, fp &ycos, fp &zcos);
-	} // close namespace local_coords::
-
-	//*****************************************************************************
-
-	//
-	// ***** bit masks for coordinates ****
-	//
-
-	//
-	// We need to manipulate coordinates to do calculations like "which
-	// coordinate do these two patches have in common".  We do these by
-	// Boolean operations on integers using the following bit masks:
-	//
-
-	namespace local_coords
-	{
-
-		typedef int coords_set;
-
-		enum
-		{
-			coords_set_mu = 0x1,
-			coords_set_nu = 0x2,
-			coords_set_phi = 0x4,
-
-			coords_set_empty = 0x0,
-			coords_set_all = coords_set_mu | coords_set_nu | coords_set_phi // no comma
-		};
-
-		// human-readable coordinate names for debugging etc
-		const char *name_of_coords_set(coords_set S);
-
-		// set complement of coordinates
-		inline coords_set coords_set_not(coords_set S)
-		{
-			return coords_set_all & ~S;
-		}
-
-	} // close namespace local_coords::
-
-	//******************************************************************************
-
-	//
-	// This class stores the origin point of our local coordinates, and
-	// provides conversions between local and global coordinates.
-	//
-	class global_coords
-	{
-	public:
-		// get global (x,y,z) coordinates of local origin point
-		fp origin_x() const { return origin_x_; }
-		fp origin_y() const { return origin_y_; }
-		fp origin_z() const { return origin_z_; }
-
-		// constructor: specify global (x,y,z) coordinates of local origin point
-		global_coords(fp origin_x_in, fp origin_y_in, fp origin_z_in)
-			: origin_x_(origin_x_in),
-			  origin_y_(origin_y_in),
-			  origin_z_(origin_z_in)
-		{
-		}
-		// destructor: compiler-generated no-op is ok
-
-		void recentering(fp x, fp y, fp z)
-		{
-			origin_x_ = x;
-			origin_y_ = y;
-			origin_z_ = z;
-		}
-
-	private:
-		// we forbid copying and passing by value
-		// by declaring the copy constructor and assignment operator
-		// private, but never defining them
-		global_coords(const global_coords &rhs);
-		global_coords &operator=(const global_coords &rhs);
-
-	private:
-		// global (x,y,z) coordinates of local origin point
-		fp origin_x_, origin_y_, origin_z_;
-	};
-
-	//******************************************************************************
-
-} // namespace AHFinderDirect
-#endif /*  COORDS_H  */
+#ifndef COORDS_H
+#define COORDS_H
+namespace AHFinderDirect
+{
+	namespace local_coords
+	{
+
+		// compare if two angles are fuzzily equal mod 2*pi radians (360 degrees)
+		bool fuzzy_EQ_ang(fp ang1, fp ang2);	// radians
+		bool fuzzy_EQ_dang(fp dang1, fp dang2); // degrees
+
+		// modulo-reduce  {ang,dang}  to be (fuzzily) within the range
+		// [min,max]_{ang,dang}, or error_exit() if no such value exists
+		fp modulo_reduce_ang(fp ang, fp min_ang, fp max_ang);
+		fp modulo_reduce_dang(fp dang, fp min_dang, fp max_dang);
+
+	} // close namespace local_coords::
+
+	namespace local_coords
+	{
+		// (r,(mu,nu,phi)) <--> (x,y,z)
+		void xyz_of_r_mu_nu(fp r, fp mu, fp nu, fp &x, fp &y, fp &z);
+		void xyz_of_r_mu_phi(fp r, fp mu, fp phi, fp &x, fp &y, fp &z);
+		void xyz_of_r_nu_phi(fp r, fp nu, fp phi, fp &x, fp &y, fp &z);
+		fp r_of_xyz(fp x, fp y, fp z);
+		fp mu_of_yz(fp y, fp z);
+		fp nu_of_xz(fp x, fp z);
+		fp phi_of_xy(fp x, fp y);
+
+		// ((mu,nu,phi)) --> the 3rd
+		fp phi_of_mu_nu(fp mu, fp nu);
+		fp nu_of_mu_phi(fp mu, fp phi);
+		fp mu_of_nu_phi(fp nu, fp phi);
+
+		// partial {x,y,z} / partial {mu,nu,phi}
+		void partial_xyz_wrt_r_mu_nu(fp r, fp mu, fp nu,
+									 fp &partial_x_wrt_r, fp &partial_x_wrt_mu, fp &partial_x_wrt_nu,
+									 fp &partial_y_wrt_r, fp &partial_y_wrt_mu, fp &partial_y_wrt_nu,
+									 fp &partial_z_wrt_r, fp &partial_z_wrt_mu, fp &partial_z_wrt_nu);
+		void partial_xyz_wrt_r_mu_phi(fp r, fp mu, fp phi,
+									  fp &partial_x_wrt_r, fp &partial_x_wrt_mu, fp &partial_x_wrt_phi,
+									  fp &partial_y_wrt_r, fp &partial_y_wrt_mu, fp &partial_y_wrt_phi,
+									  fp &partial_z_wrt_r, fp &partial_z_wrt_mu, fp &partial_z_wrt_phi);
+		void partial_xyz_wrt_r_nu_phi(fp r, fp nu, fp phi,
+									  fp &partial_x_wrt_r, fp &partial_x_wrt_nu, fp &partial_x_wrt_phi,
+									  fp &partial_y_wrt_r, fp &partial_y_wrt_nu, fp &partial_y_wrt_phi,
+									  fp &partial_z_wrt_r, fp &partial_z_wrt_nu, fp &partial_z_wrt_phi);
+
+		// partial {mu,nu,phi} / partial {x,y,z}
+		fp partial_mu_wrt_y(fp y, fp z);
+		fp partial_mu_wrt_z(fp y, fp z);
+		fp partial_nu_wrt_x(fp x, fp z);
+		fp partial_nu_wrt_z(fp x, fp z);
+		fp partial_phi_wrt_x(fp x, fp y);
+		fp partial_phi_wrt_y(fp x, fp y);
+
+		// partial^2 {mu,nu,phi} / partial {x,y,z}{x,y,z}
+		fp partial2_mu_wrt_yy(fp y, fp z);
+		fp partial2_mu_wrt_yz(fp y, fp z);
+		fp partial2_mu_wrt_zz(fp y, fp z);
+		fp partial2_nu_wrt_xx(fp x, fp z);
+		fp partial2_nu_wrt_xz(fp x, fp z);
+		fp partial2_nu_wrt_zz(fp x, fp z);
+		fp partial2_phi_wrt_xx(fp x, fp y);
+		fp partial2_phi_wrt_xy(fp x, fp y);
+		fp partial2_phi_wrt_yy(fp x, fp y);
+
+		// usual polar spherical (r,theta,phi) <--> (x,y,z)
+		void xyz_of_r_theta_phi(fp r, fp theta, fp phi, fp &x, fp &y, fp &z);
+		void r_theta_phi_of_xyz(fp x, fp y, fp z, fp &r, fp &theta, fp &phi);
+		// ... already have r_of_xyz()
+		// ... already have phi_of_xy()
+		fp theta_of_xyz(fp x, fp y, fp z);
+
+		// ((mu,nu,phi)) <--> usual polar spherical (theta,phi)
+		// ... note phi is the same coordinate in both systems
+		void theta_phi_of_mu_nu(fp mu, fp nu, fp &ps_theta, fp &ps_phi);
+		void theta_phi_of_mu_phi(fp mu, fp phi, fp &ps_theta, fp &ps_phi);
+		void theta_phi_of_nu_phi(fp nu, fp phi, fp &ps_theta, fp &ps_phi);
+		void mu_nu_of_theta_phi(fp ps_theta, fp ps_phi, fp &mu, fp &nu);
+		void mu_phi_of_theta_phi(fp ps_theta, fp ps_phi, fp &mu, fp &phi);
+		void nu_phi_of_theta_phi(fp ps_theta, fp ps_phi, fp &nu, fp &phi);
+
+		// ((mu,nu,phi)) --> direction cosines (xcos,ycos,zcos)
+		void xyzcos_of_mu_nu(fp mu, fp nu, fp &xcos, fp &ycos, fp &zcos);
+		void xyzcos_of_mu_phi(fp mu, fp phi, fp &xcos, fp &ycos, fp &zcos);
+		void xyzcos_of_nu_phi(fp nu, fp phi, fp &xcos, fp &ycos, fp &zcos);
+	} // close namespace local_coords::
+
+	//*****************************************************************************
+
+	//
+	// ***** bit masks for coordinates ****
+	//
+
+	//
+	// We need to manipulate coordinates to do calculations like "which
+	// coordinate do these two patches have in common".  We do these by
+	// Boolean operations on integers using the following bit masks:
+	//
+
+	namespace local_coords
+	{
+
+		typedef int coords_set;
+
+		enum
+		{
+			coords_set_mu = 0x1,
+			coords_set_nu = 0x2,
+			coords_set_phi = 0x4,
+
+			coords_set_empty = 0x0,
+			coords_set_all = coords_set_mu | coords_set_nu | coords_set_phi // no comma
+		};
+
+		// human-readable coordinate names for debugging etc
+		const char *name_of_coords_set(coords_set S);
+
+		// set complement of coordinates
+		inline coords_set coords_set_not(coords_set S)
+		{
+			return coords_set_all & ~S;
+		}
+
+	} // close namespace local_coords::
+
+	//******************************************************************************
+
+	//
+	// This class stores the origin point of our local coordinates, and
+	// provides conversions between local and global coordinates.
+	//
+	class global_coords
+	{
+	public:
+		// get global (x,y,z) coordinates of local origin point
+		fp origin_x() const { return origin_x_; }
+		fp origin_y() const { return origin_y_; }
+		fp origin_z() const { return origin_z_; }
+
+		// constructor: specify global (x,y,z) coordinates of local origin point
+		global_coords(fp origin_x_in, fp origin_y_in, fp origin_z_in)
+			: origin_x_(origin_x_in),
+			  origin_y_(origin_y_in),
+			  origin_z_(origin_z_in)
+		{
+		}
+		// destructor: compiler-generated no-op is ok
+
+		void recentering(fp x, fp y, fp z)
+		{
+			origin_x_ = x;
+			origin_y_ = y;
+			origin_z_ = z;
+		}
+
+	private:
+		// we forbid copying and passing by value
+		// by declaring the copy constructor and assignment operator
+		// private, but never defining them
+		global_coords(const global_coords &rhs);
+		global_coords &operator=(const global_coords &rhs);
+
+	private:
+		// global (x,y,z) coordinates of local origin point
+		fp origin_x_, origin_y_, origin_z_;
+	};
+
+	//******************************************************************************
+
+} // namespace AHFinderDirect
+#endif /*  COORDS_H  */

AMSS_NCKU_source/cpbc.h

@@ -1,56 +1,56 @@
-
-#ifndef CPBC_H
-#define CPBC_H
-
-#ifdef fortran1
-#define f_david_milton_extroplate_ss david_milton_extroplate_ss
-#define f_david_milton_cpbc_ss david_milton_cpbc_ss
-#endif
-#ifdef fortran2
-#define f_david_milton_extroplate_ss DAVID_MILTON_EXTROPLATE_SS
-#define f_david_milton_cpbc_ss DAVID_MILTON_CPBC_SS
-#endif
-#ifdef fortran3
-#define f_david_milton_extroplate_ss david_milton_extroplate_ss_
-#define f_david_milton_cpbc_ss david_milton_cpbc_ss_
-#endif
-extern "C"
-{
-	int f_david_milton_extroplate_ss(int *, double *, double *, double *,								   // ex,crho,sigma,R
-									 double *, double *, double *,										   // TZ, chi, trK
-									 double *, double *, double *, double *, double *, double *,		   // gij
-									 double *, double *, double *, double *, double *, double *,		   // Aij
-									 double *, double *, double *,										   // Gam
-									 double *, double *, double *, double *, double *, double *, double *, // Gauge
-									 double &, double &);
-} // zmin,zmax
-
-extern "C"
-{
-	int f_david_milton_cpbc_ss(int *, double *, double *, double *,									 // ex,crho,sigma,R
-							   double *, double *, double *,										 // x,y,z
-							   double *, double *, double *,										 // drhodx,drhody,drhodz
-							   double *, double *, double *,										 // dsigmadx,dsigmady,dsigmadz
-							   double *, double *, double *,										 // dRdx,dRdy,dRdz
-							   double *, double *, double *, double *, double *, double *,			 // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
-							   double *, double *, double *, double *, double *, double *,			 // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
-							   double *, double *, double *, double *, double *, double *,			 // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
-							   double &, double &, double &, double &, double &, double &,			 // xmin,ymin,zmin,xmax,ymax,zmax
-							   double *, double *, double *,										 // TZ,chi, trK
-							   double *, double *, double *, double *, double *, double *,			 // gij
-							   double *, double *, double *, double *, double *, double *,			 // Aij
-							   double *, double *, double *,										 // Gam
-							   double *, double *, double *, double *, double *, double *, double *, // Gauge
-							   double *, double *, double *,										 // TZ, chi, trK
-							   double *, double *, double *, double *, double *, double *,			 // gij
-							   double *, double *, double *, double *, double *, double *,			 // Aij
-							   double *, double *, double *,										 // Gam
-							   double *, double *, double *, double *, double *, double *, double *, // Gauge
-							   double *, double *, double *, double *, double *, double *,			 // Christoffel
-							   double *, double *, double *, double *, double *, double *,			 // Christoffel
-							   double *, double *, double *, double *, double *, double *,			 // Christoffel
-							   double *, double *, double *, double *, double *, double *,			 // Ricci
-							   double *, double *, double *,										 // Gama constraint
-							   int &, double &, int &);
-} // Symmetry, eps, sst
-#endif /* CPBC_H */
+
+#ifndef CPBC_H
+#define CPBC_H
+
+#ifdef fortran1
+#define f_david_milton_extroplate_ss david_milton_extroplate_ss
+#define f_david_milton_cpbc_ss david_milton_cpbc_ss
+#endif
+#ifdef fortran2
+#define f_david_milton_extroplate_ss DAVID_MILTON_EXTROPLATE_SS
+#define f_david_milton_cpbc_ss DAVID_MILTON_CPBC_SS
+#endif
+#ifdef fortran3
+#define f_david_milton_extroplate_ss david_milton_extroplate_ss_
+#define f_david_milton_cpbc_ss david_milton_cpbc_ss_
+#endif
+extern "C"
+{
+	int f_david_milton_extroplate_ss(int *, double *, double *, double *,								   // ex,crho,sigma,R
+									 double *, double *, double *,										   // TZ, chi, trK
+									 double *, double *, double *, double *, double *, double *,		   // gij
+									 double *, double *, double *, double *, double *, double *,		   // Aij
+									 double *, double *, double *,										   // Gam
+									 double *, double *, double *, double *, double *, double *, double *, // Gauge
+									 double &, double &);
+} // zmin,zmax
+
+extern "C"
+{
+	int f_david_milton_cpbc_ss(int *, double *, double *, double *,									 // ex,crho,sigma,R
+							   double *, double *, double *,										 // x,y,z
+							   double *, double *, double *,										 // drhodx,drhody,drhodz
+							   double *, double *, double *,										 // dsigmadx,dsigmady,dsigmadz
+							   double *, double *, double *,										 // dRdx,dRdy,dRdz
+							   double *, double *, double *, double *, double *, double *,			 // drhodxx,drhodxy,drhodxz,drhodyy,drhodyz,drhodzz
+							   double *, double *, double *, double *, double *, double *,			 // dsigmadxx,dsigmadxy,dsigmadxz,dsigmadyy,dsigmadyz,dsigmadzz
+							   double *, double *, double *, double *, double *, double *,			 // dRdxx,dRdxy,dRdxz,dRdyy,dRdyz,dRdzz
+							   double &, double &, double &, double &, double &, double &,			 // xmin,ymin,zmin,xmax,ymax,zmax
+							   double *, double *, double *,										 // TZ,chi, trK
+							   double *, double *, double *, double *, double *, double *,			 // gij
+							   double *, double *, double *, double *, double *, double *,			 // Aij
+							   double *, double *, double *,										 // Gam
+							   double *, double *, double *, double *, double *, double *, double *, // Gauge
+							   double *, double *, double *,										 // TZ, chi, trK
+							   double *, double *, double *, double *, double *, double *,			 // gij
+							   double *, double *, double *, double *, double *, double *,			 // Aij
+							   double *, double *, double *,										 // Gam
+							   double *, double *, double *, double *, double *, double *, double *, // Gauge
+							   double *, double *, double *, double *, double *, double *,			 // Christoffel
+							   double *, double *, double *, double *, double *, double *,			 // Christoffel
+							   double *, double *, double *, double *, double *, double *,			 // Christoffel
+							   double *, double *, double *, double *, double *, double *,			 // Ricci
+							   double *, double *, double *,										 // Gama constraint
+							   int &, double &, int &);
+} // Symmetry, eps, sst
+#endif /* CPBC_H */

AMSS_NCKU_source/cpm_map.C

@@ -1,93 +1,93 @@
-#include <assert.h>
-#include <stdio.h>
-
-#include "stdc.h"
-#include "util.h"
-#include "cpm_map.h"
-
-namespace AHFinderDirect
-{
-	namespace jtutil
-	{
-
-		template <typename fp_t>
-		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
-							   fp_t fixed_point)
-			: min_i_(min_i_in), max_i_(max_i_in),
-			  map_is_plus_(false)
-		{
-			const fp_t d_offset = 2.0 * fixed_point;
-			if (!fuzzy<fp_t>::is_integer(d_offset))
-				then error_exit(ERROR_EXIT,
-								"***** cpm_map::cpm_map (mirror):\n"
-								"        fixed_point=%g isn't (fuzzily) integral or half-integral!\n",
-								double(fixed_point)); /*NOTREACHED*/
-
-			offset_ = round<fp_t>::to_integer(d_offset);
-
-			assert(
-				map_unchecked(fuzzy<fp_t>::floor(fixed_point)) ==
-				fuzzy<fp_t>::ceiling(fixed_point));
-		}
-
-		//******************************************************************************
-
-		//
-		// This function constructs a generic  cpm_map  object, with the mapping
-		// specified by a sample point  sample_i --> sample_j  and by sign.
-		// The sample point need not be in the map's domain/range.
-		//
-		template <typename fp_t>
-		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
-							   int sample_i, int sample_j,
-							   bool map_is_plus_in)
-			: min_i_(min_i_in), max_i_(max_i_in),
-			  offset_(map_is_plus_in ? sample_j - sample_i
-									 : sample_j + sample_i),
-			  map_is_plus_(map_is_plus_in)
-		{
-			assert(map_unchecked(sample_i) == sample_j);
-		}
-
-		//******************************************************************************
-
-		//
-		// This function constructs a generic  cpm_map  object, with the mapping
-		// specified by a *fp* sample point  sample_i --> sample_j  (which
-		// must specify an  integer --> integer  mapping, i.e.  4.2 --> 4.2  is
-		// ok for a + map, and 4.5 --> 4.5 is ok for a minus map, but  4.2 --> 4.7
-		// is never ok) and by sign.  The sample point need not be in the map's
-		// domain/range.
-		//
-		template <typename fp_t>
-		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
-							   fp_t sample_i, fp_t sample_j,
-							   bool map_is_plus_in)
-			: min_i_(min_i_in), max_i_(max_i_in),
-			  map_is_plus_(map_is_plus_in)
-		{
-			const fp_t fp_offset = map_is_plus_in ? sample_j - sample_i
-												  : sample_j + sample_i;
-			if (!fuzzy<fp_t>::is_integer(fp_offset))
-				then error_exit(ERROR_EXIT,
-								"***** cpm_map::cpm_map (generic via fp sample point):\n"
-								"        fp_offset=%g isn't fuzzily integral!\n"
-								"        ==> sample_i=%g --> sample_j=%g\n"
-								"            doesn't fuzzily specify an  integer --> integer  mapping!\n",
-								double(fp_offset),
-								double(sample_i), double(sample_j)); /*NOTREACHED*/
-
-			offset_ = round<fp_t>::to_integer(fp_offset);
-
-			// verify that we have setup correct
-			assert(
-				map_unchecked(fuzzy<fp_t>::floor(sample_i)) ==
-				(map_is_plus_in ? fuzzy<fp_t>::floor(sample_j)
-								: fuzzy<fp_t>::ceiling(sample_j)));
-		}
-
-		template class cpm_map<float>;
-		template class cpm_map<double>;
-
-	} // namespace jtutil
-} // namespace AHFinderDirect
+#include <assert.h>
+#include <stdio.h>
+
+#include "stdc.h"
+#include "util.h"
+#include "cpm_map.h"
+
+namespace AHFinderDirect
+{
+	namespace jtutil
+	{
+
+		template <typename fp_t>
+		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
+							   fp_t fixed_point)
+			: min_i_(min_i_in), max_i_(max_i_in),
+			  map_is_plus_(false)
+		{
+			const fp_t d_offset = 2.0 * fixed_point;
+			if (!fuzzy<fp_t>::is_integer(d_offset))
+				then error_exit(ERROR_EXIT,
+								"***** cpm_map::cpm_map (mirror):\n"
+								"        fixed_point=%g isn't (fuzzily) integral or half-integral!\n",
+								double(fixed_point)); /*NOTREACHED*/
+
+			offset_ = round<fp_t>::to_integer(d_offset);
+
+			assert(
+				map_unchecked(fuzzy<fp_t>::floor(fixed_point)) ==
+				fuzzy<fp_t>::ceiling(fixed_point));
+		}
+
+		//******************************************************************************
+
+		//
+		// This function constructs a generic  cpm_map  object, with the mapping
+		// specified by a sample point  sample_i --> sample_j  and by sign.
+		// The sample point need not be in the map's domain/range.
+		//
+		template <typename fp_t>
+		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
+							   int sample_i, int sample_j,
+							   bool map_is_plus_in)
+			: min_i_(min_i_in), max_i_(max_i_in),
+			  offset_(map_is_plus_in ? sample_j - sample_i
+									 : sample_j + sample_i),
+			  map_is_plus_(map_is_plus_in)
+		{
+			assert(map_unchecked(sample_i) == sample_j);
+		}
+
+		//******************************************************************************
+
+		//
+		// This function constructs a generic  cpm_map  object, with the mapping
+		// specified by a *fp* sample point  sample_i --> sample_j  (which
+		// must specify an  integer --> integer  mapping, i.e.  4.2 --> 4.2  is
+		// ok for a + map, and 4.5 --> 4.5 is ok for a minus map, but  4.2 --> 4.7
+		// is never ok) and by sign.  The sample point need not be in the map's
+		// domain/range.
+		//
+		template <typename fp_t>
+		cpm_map<fp_t>::cpm_map(int min_i_in, int max_i_in,
+							   fp_t sample_i, fp_t sample_j,
+							   bool map_is_plus_in)
+			: min_i_(min_i_in), max_i_(max_i_in),
+			  map_is_plus_(map_is_plus_in)
+		{
+			const fp_t fp_offset = map_is_plus_in ? sample_j - sample_i
+												  : sample_j + sample_i;
+			if (!fuzzy<fp_t>::is_integer(fp_offset))
+				then error_exit(ERROR_EXIT,
+								"***** cpm_map::cpm_map (generic via fp sample point):\n"
+								"        fp_offset=%g isn't fuzzily integral!\n"
+								"        ==> sample_i=%g --> sample_j=%g\n"
+								"            doesn't fuzzily specify an  integer --> integer  mapping!\n",
+								double(fp_offset),
+								double(sample_i), double(sample_j)); /*NOTREACHED*/
+
+			offset_ = round<fp_t>::to_integer(fp_offset);
+
+			// verify that we have setup correct
+			assert(
+				map_unchecked(fuzzy<fp_t>::floor(sample_i)) ==
+				(map_is_plus_in ? fuzzy<fp_t>::floor(sample_j)
+								: fuzzy<fp_t>::ceiling(sample_j)));
+		}
+
+		template class cpm_map<float>;
+		template class cpm_map<double>;
+
+	} // namespace jtutil
+} // namespace AHFinderDirect

AMSS_NCKU_source/cpm_map.h

@@ -1,120 +1,120 @@
-#ifndef AHFINDERDIRECT__CPM_MAP_HH
-#define AHFINDERDIRECT__CPM_MAP_HH
-namespace AHFinderDirect
-{
-	namespace jtutil
-	{
-
-		template <typename fp_t>
-		class cpm_map
-		{
-		public:
-			// bounds info -- domain
-			int min_i() const { return min_i_; }
-			int max_i() const { return max_i_; }
-			int N_points() const
-			{
-				return jtutil::how_many_in_range(min_i_, max_i_);
-			}
-			bool in_domain(int i) const { return (i >= min_i_) && (i <= max_i_); }
-
-			// is the mapping + or - ?
-			bool is_plus() const { return map_is_plus_; }
-			bool is_minus() const { return !map_is_plus_; }
-			int sign() const { return map_is_plus_ ? +1 : -1; }
-			fp_t fp_sign() const { return map_is_plus_ ? +1.0 : -1.0; }
-
-			// the mapping itself
-			int map_unchecked(int i) const
-			{
-				return map_is_plus_ ? offset_ + i
-									: offset_ - i;
-			}
-			int inv_map_unchecked(int j) const
-			{
-				return map_is_plus_ ? j - offset_
-									: offset_ - j;
-			}
-			int map(int i) const
-			{
-				assert(in_domain(i));
-				return map_unchecked(i);
-			}
-			int inv_map(int j) const
-			{
-				int i = inv_map_unchecked(j);
-				assert(in_domain(i));
-				return i;
-			}
-
-			// bounds info -- range
-			// ... we use the unchecked map here in case the domain is empty
-			int min_j() const
-			{
-				return map_is_plus_ ? map_unchecked(min_i_)
-									: map_unchecked(max_i_);
-			}
-			int max_j() const
-			{
-				return map_is_plus_ ? map_unchecked(max_i_)
-									: map_unchecked(min_i_);
-			}
-			bool in_range(int j) const { return in_domain(inv_map_unchecked(j)); }
-
-			//
-			// constructors
-			//
-
-			// "mirror" map: i --> const - i
-			// ... map specified by fixed point (must be integer or half-integer)
-			// ... fixed point need not be in domain/range
-			cpm_map(int min_i_in, int max_i_in,
-					fp_t fixed_point);
-
-			// "shift" map: i --> const + i
-			// ... map specified by shift amount
-			// ... default is identity map
-			cpm_map(int min_i_in, int max_i_in,
-					int shift_amount = 0)
-				: min_i_(min_i_in), max_i_(max_i_in),
-				  offset_(shift_amount), map_is_plus_(true)
-			{
-			}
-
-			// generic map: i --> const +/- i
-			// ... map specified by sample point sample_i --> sample_j
-			//     and by sign (one of  {plus,minus}_map )
-			// ... sample point need not be in domain/range
-			cpm_map(int min_i_in, int max_i_in,
-					int sample_i, int sample_j,
-					bool map_is_plus_in);
-
-			// generic map: i --> const +/- i
-			// ... map specified by *fp* sample point sample_i --> sample_j
-			//     (must specify an integer --> integer mapping)
-			//     and by sign (one of  {plus,minus}_map )
-			// ... hence if sign is -1, then sample_i and sample_j
-			//     must both be half-integral
-			// ... sample point need *not* be in domain/range
-			cpm_map(int min_i_in, int max_i_in,
-					fp_t sample_i, fp_t sample_j,
-					bool map_is_plus_in);
-
-			// no need for explicit destructor, compiler-generated no-op is ok
-			// ditto for copy constructor and assignment operator
-
-		private:
-			// bounds (inclusive)
-			int min_i_, max_i_;
-
-			// these define the actual mapping
-			int offset_;
-			bool map_is_plus_;
-		};
-
-		//******************************************************************************
-
-	} // namespace jtutil
-} // namespace AHFinderDirect
-
-#endif /* AHFINDERDIRECT__CPM_MAP_HH */
+#ifndef AHFINDERDIRECT__CPM_MAP_HH
+#define AHFINDERDIRECT__CPM_MAP_HH
+namespace AHFinderDirect
+{
+	namespace jtutil
+	{
+
+		template <typename fp_t>
+		class cpm_map
+		{
+		public:
+			// bounds info -- domain
+			int min_i() const { return min_i_; }
+			int max_i() const { return max_i_; }
+			int N_points() const
+			{
+				return jtutil::how_many_in_range(min_i_, max_i_);
+			}
+			bool in_domain(int i) const { return (i >= min_i_) && (i <= max_i_); }
+
+			// is the mapping + or - ?
+			bool is_plus() const { return map_is_plus_; }
+			bool is_minus() const { return !map_is_plus_; }
+			int sign() const { return map_is_plus_ ? +1 : -1; }
+			fp_t fp_sign() const { return map_is_plus_ ? +1.0 : -1.0; }
+
+			// the mapping itself
+			int map_unchecked(int i) const
+			{
+				return map_is_plus_ ? offset_ + i
+									: offset_ - i;
+			}
+			int inv_map_unchecked(int j) const
+			{
+				return map_is_plus_ ? j - offset_
+									: offset_ - j;
+			}
+			int map(int i) const
+			{
+				assert(in_domain(i));
+				return map_unchecked(i);
+			}
+			int inv_map(int j) const
+			{
+				int i = inv_map_unchecked(j);
+				assert(in_domain(i));
+				return i;
+			}
+
+			// bounds info -- range
+			// ... we use the unchecked map here in case the domain is empty
+			int min_j() const
+			{
+				return map_is_plus_ ? map_unchecked(min_i_)
+									: map_unchecked(max_i_);
+			}
+			int max_j() const
+			{
+				return map_is_plus_ ? map_unchecked(max_i_)
+									: map_unchecked(min_i_);
+			}
+			bool in_range(int j) const { return in_domain(inv_map_unchecked(j)); }
+
+			//
+			// constructors
+			//
+
+			// "mirror" map: i --> const - i
+			// ... map specified by fixed point (must be integer or half-integer)
+			// ... fixed point need not be in domain/range
+			cpm_map(int min_i_in, int max_i_in,
+					fp_t fixed_point);
+
+			// "shift" map: i --> const + i
+			// ... map specified by shift amount
+			// ... default is identity map
+			cpm_map(int min_i_in, int max_i_in,
+					int shift_amount = 0)
+				: min_i_(min_i_in), max_i_(max_i_in),
+				  offset_(shift_amount), map_is_plus_(true)
+			{
+			}
+
+			// generic map: i --> const +/- i
+			// ... map specified by sample point sample_i --> sample_j
+			//     and by sign (one of  {plus,minus}_map )
+			// ... sample point need not be in domain/range
+			cpm_map(int min_i_in, int max_i_in,
+					int sample_i, int sample_j,
+					bool map_is_plus_in);
+
+			// generic map: i --> const +/- i
+			// ... map specified by *fp* sample point sample_i --> sample_j
+			//     (must specify an integer --> integer mapping)
+			//     and by sign (one of  {plus,minus}_map )
+			// ... hence if sign is -1, then sample_i and sample_j
+			//     must both be half-integral
+			// ... sample point need *not* be in domain/range
+			cpm_map(int min_i_in, int max_i_in,
+					fp_t sample_i, fp_t sample_j,
+					bool map_is_plus_in);
+
+			// no need for explicit destructor, compiler-generated no-op is ok
+			// ditto for copy constructor and assignment operator
+
+		private:
+			// bounds (inclusive)
+			int min_i_, max_i_;
+
+			// these define the actual mapping
+			int offset_;
+			bool map_is_plus_;
+		};
+
+		//******************************************************************************
+
+	} // namespace jtutil
+} // namespace AHFinderDirect
+
+#endif /* AHFINDERDIRECT__CPM_MAP_HH */

AMSS_NCKU_source/derivatives.h

@@ -1,76 +1,76 @@
-
-#ifndef DERIVATIVES
-#define DERIVATIVES
-
-#ifdef fortran1
-#define f_fderivs fderivs
-#define f_fderivs_sh fderivs_sh
-#define f_fderivs_shc fderivs_shc
-#define f_fdderivs_shc fdderivs_shc
-#define f_fdderivs fdderivs
-#endif
-#ifdef fortran2
-#define f_fderivs FDERIVS
-#define f_fderivs_sh FDERIVS_SH
-#define f_fderivs_shc FDERIVS_SHC
-#define f_fdderivs_shc FDDERIVS_SHC
-#define f_fdderivs FDDERIVS
-#endif
-#ifdef fortran3
-#define f_fderivs fderivs_
-#define f_fderivs_sh fderivs_sh_
-#define f_fderivs_shc fderivs_shc_
-#define f_fdderivs_shc fdderivs_shc_
-#define f_fdderivs fdderivs_
-#endif
-
-extern "C"
-{
-	void f_fderivs(int *, double *,
-				   double *, double *, double *,
-				   double *, double *, double *,
-				   double &, double &, double &, int &, int &);
-}
-
-extern "C"
-{
-	void f_fderivs_sh(int *, double *,
-					  double *, double *, double *,
-					  double *, double *, double *,
-					  double &, double &, double &, int &, int &, int &);
-}
-
-extern "C"
-{
-	void f_fderivs_shc(int *, double *,
-					   double *, double *, double *,
-					   double *, double *, double *,
-					   double &, double &, double &, int &, int &, int &,
-					   double *, double *, double *,
-					   double *, double *, double *,
-					   double *, double *, double *);
-}
-
-extern "C"
-{
-	void f_fdderivs_shc(int *, double *,
-						double *, double *, double *, double *, double *, double *,
-						double *, double *, double *,
-						double &, double &, double &, int &, int &, int &,
-						double *, double *, double *,
-						double *, double *, double *,
-						double *, double *, double *,
-						double *, double *, double *, double *, double *, double *,
-						double *, double *, double *, double *, double *, double *,
-						double *, double *, double *, double *, double *, double *);
-}
-
-extern "C"
-{
-	void f_fdderivs(int *, double *,
-					double *, double *, double *, double *, double *, double *,
-					double *, double *, double *,
-					double &, double &, double &, int &, int &);
-}
-
-#endif /* DERIVATIVES */
+
+#ifndef DERIVATIVES
+#define DERIVATIVES
+
+#ifdef fortran1
+#define f_fderivs fderivs
+#define f_fderivs_sh fderivs_sh
+#define f_fderivs_shc fderivs_shc
+#define f_fdderivs_shc fdderivs_shc
+#define f_fdderivs fdderivs
+#endif
+#ifdef fortran2
+#define f_fderivs FDERIVS
+#define f_fderivs_sh FDERIVS_SH
+#define f_fderivs_shc FDERIVS_SHC
+#define f_fdderivs_shc FDDERIVS_SHC
+#define f_fdderivs FDDERIVS
+#endif
+#ifdef fortran3
+#define f_fderivs fderivs_
+#define f_fderivs_sh fderivs_sh_
+#define f_fderivs_shc fderivs_shc_
+#define f_fdderivs_shc fdderivs_shc_
+#define f_fdderivs fdderivs_
+#endif
+
+extern "C"
+{
+	void f_fderivs(int *, double *,
+				   double *, double *, double *,
+				   double *, double *, double *,
+				   double &, double &, double &, int &, int &);
+}
+
+extern "C"
+{
+	void f_fderivs_sh(int *, double *,
+					  double *, double *, double *,
+					  double *, double *, double *,
+					  double &, double &, double &, int &, int &, int &);
+}
+
+extern "C"
+{
+	void f_fderivs_shc(int *, double *,
+					   double *, double *, double *,
+					   double *, double *, double *,
+					   double &, double &, double &, int &, int &, int &,
+					   double *, double *, double *,
+					   double *, double *, double *,
+					   double *, double *, double *);
+}
+
+extern "C"
+{
+	void f_fdderivs_shc(int *, double *,
+						double *, double *, double *, double *, double *, double *,
+						double *, double *, double *,
+						double &, double &, double &, int &, int &, int &,
+						double *, double *, double *,
+						double *, double *, double *,
+						double *, double *, double *,
+						double *, double *, double *, double *, double *, double *,
+						double *, double *, double *, double *, double *, double *,
+						double *, double *, double *, double *, double *, double *);
+}
+
+extern "C"
+{
+	void f_fdderivs(int *, double *,
+					double *, double *, double *, double *, double *, double *,
+					double *, double *, double *,
+					double &, double &, double &, int &, int &);
+}
+
+#endif /* DERIVATIVES */