prolong3 改为先算实际 stencil 窗口；只有窗口触及对称边界时才走全域 symmetry_bd，否则只复制必需窗口。restrict3 同样改成窗口判定，无触边时仅填 ii/jj/kk 必需窗口。

- compute fi_min/fi_max from output i-range and derive ii_lo/ii_hi
 - replace full ii sweep (-1:extf(1)) with windowed sweep in Z/Y precompute passes
 - keep stencil math unchanged; add bounds sanity check for ii window

AMSS_NCKU_Input.py

@@ -16,7 +16,7 @@ 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    = 2                          ## number of mpi processes used in the simulation
+MPI_processes    = 64                             ## number of mpi processes used in the simulation
 
 GPU_Calculation  = "no"                          ## Use GPU or not 
                                                  ## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
@@ -50,7 +50,7 @@ Check_Time               = 100.0
 Dump_Time                = 100.0                  ## time inteval dT for dumping binary data
 D2_Dump_Time             = 100.0                  ## dump the ascii data for 2d surface after dT'
 Analysis_Time            = 0.1                    ## dump the puncture position and GW psi4 after dT"
-Evolution_Step_Number    = 6               ## stop the calculation after the maximal step number
+Evolution_Step_Number    = 10000000               ## stop the calculation after the maximal step number
 Courant_Factor           = 0.5                    ## Courant Factor
 Dissipation              = 0.15                   ## Kreiss-Oliger Dissipation Strength
 

AMSS_NCKU_Program.py

@@ -8,6 +8,14 @@
 ##
 ##################################################################
 
+## Guard against re-execution by multiprocessing child processes.
+## Without this, using 'spawn' or 'forkserver' context would cause every
+## worker to re-run the entire script, spawning exponentially more
+## workers (fork bomb).
+if __name__ != '__main__':
+    import sys as _sys
+    _sys.exit(0)
+
 
 ##################################################################
 
@@ -49,32 +57,32 @@ import time
 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):
+if os.path.exists(File_directory):
-#     print( " Output dictionary has been existed !!!  "                                                              )
+    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 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( " 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( " simulation. Then you can reset the output dictionary in the input script file AMSS_NCKU_Input.py !!! " )
-#     print(                                                                                                          )
+    print(                                                                                                          )
-#     ## Prompt whether to overwrite the existing directory
+    ## Prompt whether to overwrite the existing directory
-#     while True:
+    while True:
-#         try:
+        try:
-#             inputvalue = input()
+            inputvalue = input()
-#             ## If the user agrees to overwrite, proceed and remove the existing directory
+            ## If the user agrees to overwrite, proceed and remove the existing directory
-#             if ( inputvalue == "continue" ):
+            if ( inputvalue == "continue" ):
-#                 print( " Continue the calculation !!! " )
+                print( " Continue the calculation !!! " )
-#                 print(                                  )
+                print(                                  )
-#                 break  
+                break  
-#             ## If the user chooses not to overwrite, exit and keep the existing directory
+            ## If the user chooses not to overwrite, exit and keep the existing directory
-#             elif ( inputvalue == "stop" ):
+            elif ( inputvalue == "stop" ):
-#                 print( " Stop the calculation !!! "    )
+                print( " Stop the calculation !!! "    )
-#                 sys.exit() 
+                sys.exit() 
-#             ## If the user input is invalid, prompt again
+            ## If the user input is invalid, prompt again
-#             else:
+            else:
-#                 print( " Please input your choice !!! "                   )
+                print( " Please input your choice !!! "                   )
-#                 print( " Input 'continue' or 'stop' in the terminal !!! " )
+                print( " Input 'continue' or 'stop' in the terminal !!! " )
-#         except ValueError:
+        except ValueError:
-#             print( " Please input your choice !!! "                   )
+            print( " Please input your choice !!! "                   )
-#             print( " Input 'continue' or 'stop' in the terminal !!! " )
+            print( " Input 'continue' or 'stop' in the terminal !!! " )
         
 ## Remove the existing output directory if present
 shutil.rmtree(File_directory, ignore_errors=True)
@@ -262,6 +270,12 @@ if not os.path.exists( ABE_file ):
 ## Copy the executable ABE (or ABEGPU) into the run directory
 shutil.copy2(ABE_file, output_directory)
 
+## Copy interp load balance profile if present (for optimize pass)
+interp_lb_profile = os.path.join(AMSS_NCKU_source_copy, "interp_lb_profile.bin")
+if os.path.exists(interp_lb_profile):
+    shutil.copy2(interp_lb_profile, output_directory)
+    print( " Copied interp_lb_profile.bin to run directory " )
+
 ###########################
 
 ## If the initial-data method is TwoPuncture, copy the TwoPunctureABE executable to the run directory
@@ -424,26 +438,31 @@ print(
 
 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_xiaoqu.generate_puncture_orbit_plot(   binary_results_directory, figure_directory )
+plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot,   (binary_results_directory, figure_directory) ) )
-plot_xiaoqu.generate_puncture_orbit_plot3D( 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_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
+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_xiaoqu.generate_gravitational_wave_psi4_plot( binary_results_directory, figure_directory, i )
+    plot_tasks.append( ( plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i) ) )
-    plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot( binary_results_directory, figure_directory, i )
+    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_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
+    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_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
+    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
 plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )

AMSS_NCKU_Verify_ASC26.py

@@ -1,9 +1,13 @@
 #!/usr/bin/env python3
 """
-AMSS-NCKU GW150914 Simulation Regression Test Script
+AMSS-NCKU GW150914 Simulation Regression Test Script (Comprehensive Version)
 
 Verification Requirements:
-1. XY-plane trajectory RMS error < 1% (Optimized vs. baseline, max of BH1 and BH2)
+1. RMS errors < 1% for:
+   - 3D Vector Total RMS
+   - X Component RMS
+   - Y Component RMS
+   - Z Component RMS
 2. ADM constraint violation < 2 (Grid Level 0)
 
 RMS Calculation Method:
@@ -57,79 +61,62 @@ def load_constraint_data(filepath):
                 data.append([float(x) for x in parts[:8]])
     return np.array(data)
 
-
+def calculate_all_rms_errors(bh_data_ref, bh_data_target):
-def calculate_rms_error(bh_data_ref, bh_data_target):
     """
-    Calculate trajectory-based RMS error on the XY plane between baseline and optimized simulations.
+    Calculate 3D Vector RMS and component-wise RMS (X, Y, Z) independently.
-
+    Uses r = sqrt(x^2 + y^2) as the denominator for all error normalizations.
-    This function computes the RMS error independently for BH1 and BH2 trajectories,
+    Returns the maximum error between BH1 and BH2 for each category.
-    then returns the maximum of the two as the final RMS error metric.
-
-    For each black hole, the RMS is calculated as:
-        RMS = sqrt( (1/M) * sum( (Δr_i / r_i^max)^2 ) ) × 100%
-
-    where:
-        Δr_i = sqrt((x_ref,i - x_new,i)^2 + (y_ref,i - y_new,i)^2)
-        r_i^max = max(sqrt(x_ref,i^2 + y_ref,i^2), sqrt(x_new,i^2 + y_new,i^2))
-
-    Args:
-        bh_data_ref: Reference (baseline) trajectory data
-        bh_data_target: Target (optimized) trajectory data
-
-    Returns:
-        rms_value: Final RMS error as a percentage (max of BH1 and BH2)
-        error: Error message if any
     """
-    # Align data: truncate to the length of the shorter dataset
     M = min(len(bh_data_ref['time']), len(bh_data_target['time']))
 
     if M < 10:
         return None, "Insufficient data points for comparison"
 
-    # Extract XY coordinates for both black holes
+    results = {}
-    x1_ref = bh_data_ref['x1'][:M]
-    y1_ref = bh_data_ref['y1'][:M]
-    x2_ref = bh_data_ref['x2'][:M]
-    y2_ref = bh_data_ref['y2'][:M]
 
-    x1_new = bh_data_target['x1'][:M]
+    for bh in ['1', '2']:
-    y1_new = bh_data_target['y1'][:M]
+        x_r, y_r, z_r = bh_data_ref[f'x{bh}'][:M], bh_data_ref[f'y{bh}'][:M], bh_data_ref[f'z{bh}'][:M]
-    x2_new = bh_data_target['x2'][:M]
+        x_n, y_n, z_n = bh_data_target[f'x{bh}'][:M], bh_data_target[f'y{bh}'][:M], bh_data_target[f'z{bh}'][:M]
-    y2_new = bh_data_target['y2'][:M]
 
-    # Calculate RMS for BH1
+        # 核心修改：根据组委会的邮件指示，分母统一使用 r = sqrt(x^2 + y^2)
-    delta_r1 = np.sqrt((x1_ref - x1_new)**2 + (y1_ref - y1_new)**2)
+        r_ref = np.sqrt(x_r**2 + y_r**2)
-    r1_ref = np.sqrt(x1_ref**2 + y1_ref**2)
+        r_new = np.sqrt(x_n**2 + y_n**2)
-    r1_new = np.sqrt(x1_new**2 + y1_new**2)
+        denom_max = np.maximum(r_ref, r_new)
-    r1_max = np.maximum(r1_ref, r1_new)
 
-    # Calculate RMS for BH2
+        valid = denom_max > 1e-15
-    delta_r2 = np.sqrt((x2_ref - x2_new)**2 + (y2_ref - y2_new)**2)
+        if np.sum(valid) < 10:
-    r2_ref = np.sqrt(x2_ref**2 + y2_ref**2)
+            results[f'BH{bh}'] = { '3D_Vector': 0.0, 'X_Component': 0.0, 'Y_Component': 0.0, 'Z_Component': 0.0 }
-    r2_new = np.sqrt(x2_new**2 + y2_new**2)
+            continue
-    r2_max = np.maximum(r2_ref, r2_new)
 
-    # Avoid division by zero for BH1
+        def calc_rms(delta):
-    valid_mask1 = r1_max > 1e-15
+            # 将对应分量的偏差除以统一的轨道半径分母 denom_max
-    if np.sum(valid_mask1) < 10:
+            return np.sqrt(np.mean((delta[valid] / denom_max[valid])**2)) * 100
-        return None, "Insufficient valid data points for BH1"
 
-    terms1 = (delta_r1[valid_mask1] / r1_max[valid_mask1])**2
+        # 1. Total 3D Vector RMS
-    rms_bh1 = np.sqrt(np.mean(terms1)) * 100
+        delta_vec = np.sqrt((x_r - x_n)**2 + (y_r - y_n)**2 + (z_r - z_n)**2)
+        rms_3d = calc_rms(delta_vec)
 
-    # Avoid division by zero for BH2
+        # 2. Component-wise RMS (分离计算各轴，但共用半径分母)
-    valid_mask2 = r2_max > 1e-15
+        rms_x = calc_rms(np.abs(x_r - x_n))
-    if np.sum(valid_mask2) < 10:
+        rms_y = calc_rms(np.abs(y_r - y_n))
-        return None, "Insufficient valid data points for BH2"
+        rms_z = calc_rms(np.abs(z_r - z_n))
 
-    terms2 = (delta_r2[valid_mask2] / r2_max[valid_mask2])**2
+        results[f'BH{bh}'] = {
-    rms_bh2 = np.sqrt(np.mean(terms2)) * 100
+            '3D_Vector': rms_3d,
+            'X_Component': rms_x,
+            'Y_Component': rms_y,
+            'Z_Component': rms_z
+        }
 
-    # Final RMS is the maximum of BH1 and BH2
+    # 获取 BH1 和 BH2 中的最大误差
-    rms_final = max(rms_bh1, rms_bh2)
+    max_rms = {
-
+        '3D_Vector': max(results['BH1']['3D_Vector'], results['BH2']['3D_Vector']),
-    return rms_final, None
+        'X_Component': max(results['BH1']['X_Component'], results['BH2']['X_Component']),
+        'Y_Component': max(results['BH1']['Y_Component'], results['BH2']['Y_Component']),
+        'Z_Component': max(results['BH1']['Z_Component'], results['BH2']['Z_Component'])
+    }
 
+    return max_rms, None
 
 def analyze_constraint_violation(constraint_data, n_levels=9):
     """
@@ -155,34 +142,32 @@ def analyze_constraint_violation(constraint_data, n_levels=9):
 
 
 def print_header():
-    """Print report header"""
     print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-    print(Color.BOLD + "   AMSS-NCKU GW150914 Simulation Regression Test Report" + Color.RESET)
+    print(Color.BOLD + "   AMSS-NCKU GW150914 Comprehensive Regression Test" + Color.RESET)
     print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
 
-
+def print_rms_results(rms_dict, error, threshold=1.0):
-def print_rms_results(rms_rel, error, threshold=1.0):
+    print(f"\n{Color.BOLD}1. RMS Error Analysis (Maximums of BH1 & BH2){Color.RESET}")
-    """Print RMS error results"""
+    print("-" * 65)
-    print(f"\n{Color.BOLD}1. RMS Error Analysis (Baseline vs Optimized){Color.RESET}")
-    print("-" * 45)
 
     if error:
         print(f"   {Color.RED}Error: {error}{Color.RESET}")
         return False
 
-    passed = rms_rel < threshold
+    all_passed = True
+    print(f"   Requirement: < {threshold}%\n")
 
-    print(f"   RMS relative error: {rms_rel:.4f}%")
+    for key, val in rms_dict.items():
-    print(f"   Requirement:        < {threshold}%")
+        passed = val < threshold
-    print(f"   Status:             {get_status_text(passed)}")
+        all_passed = all_passed and passed
-
+        status = get_status_text(passed)
-    return passed
+        print(f"   {key:15}: {val:8.4f}%   |   Status: {status}")
 
+    return all_passed
 
 def print_constraint_results(results, threshold=2.0):
-    """Print constraint violation results"""
     print(f"\n{Color.BOLD}2. ADM Constraint Violation Analysis (Grid Level 0){Color.RESET}")
-    print("-" * 45)
+    print("-" * 65)
 
     names = ['Ham', 'Px', 'Py', 'Pz', 'Gx', 'Gy', 'Gz']
     for i, name in enumerate(names):
@@ -200,7 +185,6 @@ def print_constraint_results(results, threshold=2.0):
 
 
 def print_summary(rms_passed, constraint_passed):
-    """Print summary"""
     print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
     print(Color.BOLD + "Verification Summary" + Color.RESET)
     print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
@@ -210,7 +194,7 @@ def print_summary(rms_passed, constraint_passed):
     res_rms = get_status_text(rms_passed)
     res_con = get_status_text(constraint_passed)
 
-    print(f"   [1] RMS trajectory check:         {res_rms}")
+    print(f"   [1] Comprehensive RMS check:      {res_rms}")
     print(f"   [2] ADM constraint check:         {res_con}")
     
     final_status = f"{Color.GREEN}{Color.BOLD}ALL CHECKS PASSED{Color.RESET}" if all_passed else f"{Color.RED}{Color.BOLD}SOME CHECKS FAILED{Color.RESET}"
@@ -219,61 +203,48 @@ def print_summary(rms_passed, constraint_passed):
 
     return all_passed
 
-
 def main():
-    # Determine target (optimized) output directory
     if len(sys.argv) > 1:
         target_dir = sys.argv[1]
     else:
         script_dir = os.path.dirname(os.path.abspath(__file__))
         target_dir = os.path.join(script_dir, "GW150914/AMSS_NCKU_output")
 
-    # Determine reference (baseline) directory
     script_dir = os.path.dirname(os.path.abspath(__file__))
     reference_dir = os.path.join(script_dir, "GW150914-origin/AMSS_NCKU_output")
 
-    # Data file paths
     bh_file_ref = os.path.join(reference_dir, "bssn_BH.dat")
     bh_file_target = os.path.join(target_dir, "bssn_BH.dat")
     constraint_file = os.path.join(target_dir, "bssn_constraint.dat")
 
-    # Check if files exist
     if not os.path.exists(bh_file_ref):
         print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Baseline trajectory file not found: {bh_file_ref}")
         sys.exit(1)
-
     if not os.path.exists(bh_file_target):
         print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Target trajectory file not found: {bh_file_target}")
         sys.exit(1)
-
     if not os.path.exists(constraint_file):
         print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Constraint data file not found: {constraint_file}")
         sys.exit(1)
 
-    # Print header
     print_header()
     print(f"\n{Color.BOLD}Reference (Baseline):{Color.RESET} {Color.BLUE}{reference_dir}{Color.RESET}")
     print(f"{Color.BOLD}Target (Optimized):  {Color.RESET} {Color.BLUE}{target_dir}{Color.RESET}")
 
-    # Load data
     bh_data_ref = load_bh_trajectory(bh_file_ref)
     bh_data_target = load_bh_trajectory(bh_file_target)
     constraint_data = load_constraint_data(constraint_file)
 
-    # Calculate RMS error
+    # Output modified RMS results
-    rms_rel, error = calculate_rms_error(bh_data_ref, bh_data_target)
+    rms_dict, error = calculate_all_rms_errors(bh_data_ref, bh_data_target)
-    rms_passed = print_rms_results(rms_rel, error)
+    rms_passed = print_rms_results(rms_dict, error)
 
-    # Analyze constraint violation
+    # Output constraint results
     constraint_results = analyze_constraint_violation(constraint_data)
     constraint_passed = print_constraint_results(constraint_results)
 
-    # Print summary
     all_passed = print_summary(rms_passed, constraint_passed)
-
-    # Return exit code
     sys.exit(0 if all_passed else 1)
 
-
 if __name__ == "__main__":
     main()

AMSS_NCKU_source/ABE.C

@@ -24,7 +24,7 @@ using namespace std;
 
 #include "misc.h"
 #include "macrodef.h"
-#include <omp.h>
+
 #ifndef ABEtype
 #error "not define ABEtype"
 #endif
@@ -71,7 +71,6 @@ int main(int argc, char *argv[])
       if (myrank == 0)
       {
             Begin_clock = MPI_Wtime();
-
       }
 
       if (argc > 1)

AMSS_NCKU_source/MPatch.C

@@ -7,13 +7,179 @@
 #include <string>
 #include <cmath>
 #include <new>
+#include <vector>
 using namespace std;
 
 #include "misc.h"
 #include "MPatch.h"
 #include "Parallel.h"
 #include "fmisc.h"
-#include "xh_global_interp.h"
+#ifdef INTERP_LB_PROFILE
+#include "interp_lb_profile.h"
+#endif
+
+namespace
+{
+struct InterpBlockView
+{
+  Block *bp;
+  double llb[dim];
+  double uub[dim];
+};
+
+struct BlockBinIndex
+{
+  int bins[dim];
+  double lo[dim];
+  double inv[dim];
+  vector<InterpBlockView> views;
+  vector<vector<int>> bin_to_blocks;
+  bool valid;
+
+  BlockBinIndex() : valid(false)
+  {
+    for (int i = 0; i < dim; i++)
+    {
+      bins[i] = 1;
+      lo[i] = 0.0;
+      inv[i] = 0.0;
+    }
+  }
+};
+
+inline int clamp_int(int v, int lo, int hi)
+{
+  return (v < lo) ? lo : ((v > hi) ? hi : v);
+}
+
+inline int coord_to_bin(double x, double lo, double inv, int nb)
+{
+  if (nb <= 1 || inv <= 0.0)
+    return 0;
+  int b = int(floor((x - lo) * inv));
+  return clamp_int(b, 0, nb - 1);
+}
+
+inline int bin_loc(const BlockBinIndex &index, int b0, int b1, int b2)
+{
+  return b0 + index.bins[0] * (b1 + index.bins[1] * b2);
+}
+
+inline bool point_in_block_view(const InterpBlockView &view, const double *pox, const double *DH)
+{
+  for (int i = 0; i < dim; i++)
+  {
+    if (pox[i] - view.llb[i] < -DH[i] / 2 || pox[i] - view.uub[i] > DH[i] / 2)
+      return false;
+  }
+  return true;
+}
+
+void build_block_bin_index(Patch *patch, const double *DH, BlockBinIndex &index)
+{
+  index = BlockBinIndex();
+
+  MyList<Block> *Bp = patch->blb;
+  while (Bp)
+  {
+    Block *BP = Bp->data;
+    InterpBlockView view;
+    view.bp = BP;
+    for (int i = 0; i < dim; i++)
+    {
+#ifdef Vertex
+#ifdef Cell
+#error Both Cell and Vertex are defined
+#endif
+      view.llb[i] = (feq(BP->bbox[i], patch->bbox[i], DH[i] / 2)) ? BP->bbox[i] + patch->lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
+      view.uub[i] = (feq(BP->bbox[dim + i], patch->bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - patch->uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
+#else
+#ifdef Cell
+      view.llb[i] = (feq(BP->bbox[i], patch->bbox[i], DH[i] / 2)) ? BP->bbox[i] + patch->lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
+      view.uub[i] = (feq(BP->bbox[dim + i], patch->bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - patch->uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
+#else
+#error Not define Vertex nor Cell
+#endif
+#endif
+    }
+    index.views.push_back(view);
+    if (Bp == patch->ble)
+      break;
+    Bp = Bp->next;
+  }
+
+  const int nblocks = int(index.views.size());
+  if (nblocks <= 0)
+    return;
+
+  int bins_1d = int(ceil(pow(double(nblocks), 1.0 / 3.0)));
+  bins_1d = clamp_int(bins_1d, 1, 32);
+  for (int i = 0; i < dim; i++)
+  {
+    index.bins[i] = bins_1d;
+    index.lo[i] = patch->bbox[i] + patch->lli[i] * DH[i];
+    const double hi = patch->bbox[dim + i] - patch->uui[i] * DH[i];
+    if (hi > index.lo[i] && bins_1d > 1)
+      index.inv[i] = bins_1d / (hi - index.lo[i]);
+    else
+      index.inv[i] = 0.0;
+  }
+
+  index.bin_to_blocks.resize(index.bins[0] * index.bins[1] * index.bins[2]);
+
+  for (int bi = 0; bi < nblocks; bi++)
+  {
+    const InterpBlockView &view = index.views[bi];
+    int bmin[dim], bmax[dim];
+    for (int d = 0; d < dim; d++)
+    {
+      const double low = view.llb[d] - DH[d] / 2;
+      const double up = view.uub[d] + DH[d] / 2;
+      bmin[d] = coord_to_bin(low, index.lo[d], index.inv[d], index.bins[d]);
+      bmax[d] = coord_to_bin(up, index.lo[d], index.inv[d], index.bins[d]);
+      if (bmax[d] < bmin[d])
+      {
+        int t = bmin[d];
+        bmin[d] = bmax[d];
+        bmax[d] = t;
+      }
+    }
+
+    for (int bz = bmin[2]; bz <= bmax[2]; bz++)
+      for (int by = bmin[1]; by <= bmax[1]; by++)
+        for (int bx = bmin[0]; bx <= bmax[0]; bx++)
+          index.bin_to_blocks[bin_loc(index, bx, by, bz)].push_back(bi);
+  }
+
+  index.valid = true;
+}
+
+int find_block_index_for_point(const BlockBinIndex &index, const double *pox, const double *DH)
+{
+  if (!index.valid)
+    return -1;
+
+  const int bx = coord_to_bin(pox[0], index.lo[0], index.inv[0], index.bins[0]);
+  const int by = coord_to_bin(pox[1], index.lo[1], index.inv[1], index.bins[1]);
+  const int bz = coord_to_bin(pox[2], index.lo[2], index.inv[2], index.bins[2]);
+  const vector<int> &cand = index.bin_to_blocks[bin_loc(index, bx, by, bz)];
+
+  for (size_t ci = 0; ci < cand.size(); ci++)
+  {
+    const int bi = cand[ci];
+    if (point_in_block_view(index.views[bi], pox, DH))
+      return bi;
+  }
+
+  // Fallback to full scan for numerical edge cases around bin boundaries.
+  for (size_t bi = 0; bi < index.views.size(); bi++)
+    if (point_in_block_view(index.views[bi], pox, DH))
+      return int(bi);
+
+  return -1;
+}
+} // namespace
+
 Patch::Patch(int DIM, int *shapei, double *bboxi, int levi, bool buflog, int Symmetry) : lev(levi)
 {
 
@@ -364,9 +530,11 @@ void Patch::Interp_Points(MyList<var> *VarList,
   for (int j = 0; j < NN; j++)
     owner_rank[j] = -1;
 
-  double DH[dim], llb[dim], uub[dim];
+  double DH[dim];
   for (int i = 0; i < dim; i++)
     DH[i] = getdX(i);
+  BlockBinIndex block_index;
+  build_block_bin_index(this, DH, block_index);
 
   for (int j = 0; j < NN; j++) // run along points
   {
@@ -389,38 +557,10 @@ void Patch::Interp_Points(MyList<var> *VarList,
       }
     }
 
-    MyList<Block> *Bp = blb;
+    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    bool notfind = true;
+    if (block_i >= 0)
-    while (notfind && Bp) // run along Blocks
     {
-      Block *BP = Bp->data;
+      Block *BP = block_index.views[block_i].bp;
-      bool flag = true;
-      for (int i = 0; i < dim; i++)
-      {
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
-#else
-#ifdef Cell
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
-        if (XX[i][j] - llb[i] < -DH[i] / 2 || XX[i][j] - uub[i] > DH[i] / 2)
-        {
-          flag = false;
-          break;
-        }
-      }
-
-      if (flag)
-      {
-        notfind = false;
       owner_rank[j] = BP->rank;
       if (myrank == BP->rank)
       {
@@ -429,20 +569,13 @@ void Patch::Interp_Points(MyList<var> *VarList,
         int k = 0;
         while (varl) // run along variables
         {
-
+          f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
-            xh_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
                           pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
-
           varl = varl->next;
           k++;
         }
       }
     }
-      if (Bp == ble)
-        break;
-      Bp = Bp->next;
-    }
-
   }
 
   // Replace MPI_Allreduce with per-owner MPI_Bcast:
@@ -509,11 +642,13 @@ void Patch::Interp_Points(MyList<var> *VarList,
   // Targeted point-to-point overload: each owner sends each point only to
   // the one rank that needs it for integration (consumer), reducing
   // communication volume by ~nprocs times compared to the Bcast version.
+#ifdef INTERP_LB_PROFILE
+  double t_interp_start = MPI_Wtime();
+#endif
   int myrank, nprocs;
   MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
   MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
-// printf("here----\n");
+
-  // int zzz = 0;
   int ordn = 2 * ghost_width;
   MyList<var> *varl;
   int num_var = 0;
@@ -535,90 +670,56 @@ void Patch::Interp_Points(MyList<var> *VarList,
   double DH[dim];
   for (int i = 0; i < dim; i++)
     DH[i] = getdX(i);
+  BlockBinIndex block_index;
+  build_block_bin_index(this, DH, block_index);
 
   // --- Interpolation phase (identical to original) ---
-  // printf("NN: %d, num_var = %d\n", NN, num_var);
-  #pragma omp parallel
-  {
-  #pragma omp for
   for (int j = 0; j < NN; j++)
   {
-    double pox[dim], llb[dim], uub[dim];
+    double pox[dim];
-    MyList<var> *varl1;
     for (int i = 0; i < dim; i++)
     {
       pox[i] = XX[i][j];
-      // if (myrank == 0 && (XX[i][j] < bbox[i] + lli[i] * DH[i] || XX[i][j] > bbox[dim + i] - uui[i] * DH[i]))
+      if (myrank == 0 && (XX[i][j] < bbox[i] + lli[i] * DH[i] || XX[i][j] > bbox[dim + i] - uui[i] * DH[i]))
-      // {
+      {
-      //   cout << "Patch::Interp_Points: point (";
+        cout << "Patch::Interp_Points: point (";
-      //   for (int k = 0; k < dim; k++)
+        for (int k = 0; k < dim; k++)
-      //   {
+        {
-      //     cout << XX[k][j];
+          cout << XX[k][j];
-      //     if (k < dim - 1)
+          if (k < dim - 1)
-      //       cout << ",";
+            cout << ",";
-      //     else
+          else
-      //       cout << ") is out of current Patch." << endl;
+            cout << ") is out of current Patch." << endl;
-      //   }
+        }
-      //   MPI_Abort(MPI_COMM_WORLD, 1);
+        MPI_Abort(MPI_COMM_WORLD, 1);
-      // }
+      }
     }
 
-    MyList<Block> *Bp = blb;
+    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    bool notfind = true;
+    if (block_i >= 0)
-    while (notfind && Bp)
     {
-      Block *BP = Bp->data;
+      Block *BP = block_index.views[block_i].bp;
-
-      bool flag = true;
-      for (int i = 0; i < dim; i++)
-      {
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
-#else
-#ifdef Cell
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
-        if (XX[i][j] - llb[i] < -DH[i] / 2 || XX[i][j] - uub[i] > DH[i] / 2)
-        {
-          flag = false;
-          break;
-        }
-      }
-      // printf("flag = %d\n", flag);
-      if (flag)
-      {
-        notfind = false;
       owner_rank[j] = BP->rank;
       if (myrank == BP->rank)
       {
-          varl1 = VarList;
+        varl = VarList;
         int k = 0;
-          while (varl1)
+        while (varl)
         {
-            
+          f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
-            xh_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl1->data->sgfn], Shellf[j * num_var + k],
+                          pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
-                            pox[0], pox[1], pox[2], ordn, varl1->data->SoA, Symmetry);
+          varl = varl->next;
-            varl1 = varl1->next;
           k++;
-            // zzz += 1;
         }
       }
     }
-      if (Bp == ble)
-        break;
-      Bp = Bp->next;
   }
-  }
+
-  }
+#ifdef INTERP_LB_PROFILE
-  // printf("Interpolation done, zzz = %d\n", zzz);
+  double t_interp_end = MPI_Wtime();
+  double t_interp_local = t_interp_end - t_interp_start;
+#endif
+
   // --- Error check for unfound points ---
   for (int j = 0; j < NN; j++)
   {
@@ -775,6 +876,31 @@ void Patch::Interp_Points(MyList<var> *VarList,
   delete[] recv_count;
   delete[] consumer_rank;
   delete[] owner_rank;
+
+#ifdef INTERP_LB_PROFILE
+  {
+    static bool profile_written = false;
+    if (!profile_written) {
+      double *all_times = nullptr;
+      if (myrank == 0) all_times = new double[nprocs];
+      MPI_Gather(&t_interp_local, 1, MPI_DOUBLE,
+                 all_times, 1, MPI_DOUBLE, 0, MPI_COMM_WORLD);
+      if (myrank == 0) {
+        int heavy[64];
+        int nh = InterpLBProfile::identify_heavy_ranks(
+            all_times, nprocs, 2.5, heavy, 64);
+        InterpLBProfile::write_profile(
+            "interp_lb_profile.bin", nprocs,
+            all_times, heavy, nh, 2.5);
+        printf("[InterpLB] Profile written: %d heavy ranks\n", nh);
+        for (int i = 0; i < nh; i++)
+          printf("  Heavy rank %d: %.6f s\n", heavy[i], all_times[heavy[i]]);
+        delete[] all_times;
+      }
+      profile_written = true;
+    }
+  }
+#endif
 }
 void Patch::Interp_Points(MyList<var> *VarList,
                           int NN, double **XX,
@@ -784,6 +910,7 @@ void Patch::Interp_Points(MyList<var> *VarList,
   int myrank, lmyrank;
   MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
   MPI_Comm_rank(Comm_here, &lmyrank);
+
   int ordn = 2 * ghost_width;
   MyList<var> *varl;
   int num_var = 0;
@@ -807,9 +934,11 @@ void Patch::Interp_Points(MyList<var> *VarList,
   MPI_Comm_group(MPI_COMM_WORLD, &world_group);
   MPI_Comm_group(Comm_here, &local_group);
 
-  double DH[dim], llb[dim], uub[dim];
+  double DH[dim];
   for (int i = 0; i < dim; i++)
     DH[i] = getdX(i);
+  BlockBinIndex block_index;
+  build_block_bin_index(this, DH, block_index);
 
   for (int j = 0; j < NN; j++) // run along points
   {
@@ -832,39 +961,10 @@ void Patch::Interp_Points(MyList<var> *VarList,
       }
     }
 
-    MyList<Block> *Bp = blb;
+    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    bool notfind = true;
+    if (block_i >= 0)
-    while (notfind && Bp) // run along Blocks
     {
-      Block *BP = Bp->data;
+      Block *BP = block_index.views[block_i].bp;
-
-      bool flag = true;
-      for (int i = 0; i < dim; i++)
-      {
-#ifdef Vertex
-#ifdef Cell
-#error Both Cell and Vertex are defined
-#endif
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
-#else
-#ifdef Cell
-        llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
-        uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
-#else
-#error Not define Vertex nor Cell
-#endif
-#endif
-        if (XX[i][j] - llb[i] < -DH[i] / 2 || XX[i][j] - uub[i] > DH[i] / 2)
-        {
-          flag = false;
-          break;
-        }
-      }
-
-      if (flag)
-      {
-        notfind = false;
       owner_rank[j] = BP->rank;
       if (myrank == BP->rank)
       {
@@ -873,17 +973,13 @@ void Patch::Interp_Points(MyList<var> *VarList,
         int k = 0;
         while (varl) // run along variables
         {
-            xh_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
+          f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
                           pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
           varl = varl->next;
           k++;
         }
       }
     }
-      if (Bp == ble)
-        break;
-      Bp = Bp->next;
-    }
   }
 
   // Collect unique global owner ranks and translate to local ranks in Comm_here
@@ -1105,7 +1201,7 @@ bool Patch::Interp_ONE_Point(MyList<var> *VarList, double *XX,
         {
           //              shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
           //	  		                                    pox,ordn,varl->data->SoA,Symmetry);
-          xh_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[k],
+          f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[k],
                           pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
           varl = varl->next;
           k++;
@@ -1347,7 +1443,7 @@ bool Patch::Interp_ONE_Point(MyList<var> *VarList, double *XX,
         {
           //              shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
           //	  		                                    pox,ordn,varl->data->SoA,Symmetry);
-          xh_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[k],
+          f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[k],
                           pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
           varl = varl->next;
           k++;

AMSS_NCKU_source/Parallel.h

@@ -32,6 +32,16 @@ namespace Parallel
   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));
@@ -130,6 +140,15 @@ namespace Parallel
   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);

AMSS_NCKU_source/bssn_class.C

@@ -40,7 +40,7 @@ using namespace std;
 
 #include "derivatives.h"
 #include "ricci_gamma.h"
-#include "xh_bssn_rhs_compute.h"
+
 //================================================================================================
 
 // define bssn_class
@@ -2029,7 +2029,6 @@ void bssn_class::Read_Ansorg()
 void bssn_class::Evolve(int Steps)
 {
   clock_t prev_clock, curr_clock;
-  double prev_time, curr_time;
   double LastDump = 0.0, LastCheck = 0.0, Last2dDump = 0.0;
   LastAnas = 0;
 #if 0
@@ -2142,10 +2141,8 @@ void bssn_class::Evolve(int Steps)
     //     if(fabs(Porg0[0][0]-Porg0[1][0])+fabs(Porg0[0][1]-Porg0[1][1])+fabs(Porg0[0][2]-Porg0[1][2])<1e-6) 
     //     { GH->levels=GH->movls; }
 
-    if (myrank == 0){
+    if (myrank == 0)
       curr_clock = clock();
-      curr_time = omp_get_wtime();
-    }
 #if (PSTR == 0)
     RecursiveStep(0);
 #elif (PSTR == 1 || PSTR == 2 || PSTR == 3)
@@ -2201,17 +2198,12 @@ void bssn_class::Evolve(int Steps)
     if (myrank == 0)
     {
       prev_clock = curr_clock;
-      prev_time = curr_time;
       curr_clock = clock();
-      curr_time = omp_get_wtime();
       cout << endl;
-      // cout << " Timestep # " << ncount << ": integrating to time: " << PhysTime << "   "
-      //      << " Computer used " << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
-      //      << " seconds! " << endl;
-      // // cout << endl;
       cout << " Timestep # " << ncount << ": integrating to time: " << PhysTime << "   "
-            << " Computer used " << (curr_time - prev_time) 
+           << " Computer used " << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
            << " seconds! " << endl;
+      // cout << endl;
     }
 
     if (PhysTime >= TotalTime)
@@ -2434,9 +2426,9 @@ void bssn_class::RecursiveStep(int lev)
 #endif
 
 #if (REGLEV == 0)
-  GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
+  if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                       SynchList_cor, OldStateList, StateList, SynchList_pre,
-                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
+                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
   for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 #endif
 }
@@ -2613,9 +2605,9 @@ void bssn_class::ParallelStep()
   delete[] tporg;
   delete[] tporgo;
 #if (REGLEV == 0)
-  GH->Regrid_Onelevel(GH->mylev, Symmetry, BH_num, Porgbr, Porg0,
+  if (GH->Regrid_Onelevel(GH->mylev, Symmetry, BH_num, Porgbr, Porg0,
                       SynchList_cor, OldStateList, StateList, SynchList_pre,
-                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
+                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
   for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 #endif
 }
@@ -2780,9 +2772,9 @@ void bssn_class::ParallelStep()
       if (lev + 1 >= GH->movls)
       {
         //	       GH->Regrid_Onelevel_aux(lev,Symmetry,BH_num,Porgbr,Porg0,
-        GH->Regrid_Onelevel(lev + 1, Symmetry, BH_num, Porgbr, Porg0,
+        if (GH->Regrid_Onelevel(lev + 1, Symmetry, BH_num, Porgbr, Porg0,
                             SynchList_cor, OldStateList, StateList, SynchList_pre,
-                            fgt(PhysTime - dT_levp1, StartTime, dT_levp1 / 2), ErrorMonitor);
+                            fgt(PhysTime - dT_levp1, StartTime, dT_levp1 / 2), ErrorMonitor))
         for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
         //               a_stream.clear();
@@ -2795,9 +2787,9 @@ void bssn_class::ParallelStep()
     // for this level
     if (YN == 1)
     {
-      GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
+      if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                           SynchList_cor, OldStateList, StateList, SynchList_pre,
-                          fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
+                          fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
       for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
       //               a_stream.clear();
@@ -2814,9 +2806,9 @@ void bssn_class::ParallelStep()
         if (YN == 1)
         {
           //	   GH->Regrid_Onelevel_aux(lev-2,Symmetry,BH_num,Porgbr,Porg0,
-          GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
+          if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
                               SynchList_cor, OldStateList, StateList, SynchList_pre,
-                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor);
+                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor))
           for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
           //               a_stream.clear();
@@ -2830,9 +2822,9 @@ void bssn_class::ParallelStep()
         if (i % 4 == 3)
         {
           //	   GH->Regrid_Onelevel_aux(lev-2,Symmetry,BH_num,Porgbr,Porg0,
-          GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
+          if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
                               SynchList_cor, OldStateList, StateList, SynchList_pre,
-                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor);
+                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor))
           for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
           //               a_stream.clear();
@@ -3100,7 +3092,7 @@ void bssn_class::Step(int lev, int YN)
                      cg->fgfs[Ayy0->sgfn], cg->fgfs[Ayz0->sgfn], cg->fgfs[Azz0->sgfn]);
 #endif
 
-        if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+        if (f_compute_rhs_bssn(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],
@@ -3300,7 +3292,7 @@ void bssn_class::Step(int lev, int YN)
                  << cg->bbox[2] << ":" << cg->bbox[5] << ")" << endl;
             ERROR = 1;
           }
-          // cout<<"....................................."<<endl;
+
           // rk4 substep and boundary
           {
             MyList<var> *varl0 = StateList, *varl = SynchList_pre, *varlrhs = RHSList; 
@@ -3465,7 +3457,7 @@ void bssn_class::Step(int lev, int YN)
                          cg->fgfs[Ayy->sgfn], cg->fgfs[Ayz->sgfn], cg->fgfs[Azz->sgfn]);
 #endif
 
-          if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+          if (f_compute_rhs_bssn(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],
@@ -3978,7 +3970,7 @@ void bssn_class::Step(int lev, int YN)
                      cg->fgfs[Ayy0->sgfn], cg->fgfs[Ayz0->sgfn], cg->fgfs[Azz0->sgfn]);
 #endif
 
-        if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+        if (f_compute_rhs_bssn(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],
@@ -4320,7 +4312,7 @@ void bssn_class::Step(int lev, int YN)
                          cg->fgfs[Ayy->sgfn], cg->fgfs[Ayz->sgfn], cg->fgfs[Azz->sgfn]);
 #endif
 
-          if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+          if (f_compute_rhs_bssn(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],
@@ -4856,7 +4848,7 @@ void bssn_class::Step(int lev, int YN)
                      cg->fgfs[Ayy0->sgfn], cg->fgfs[Ayz0->sgfn], cg->fgfs[Azz0->sgfn]);
 #endif
 
-        if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+        if (f_compute_rhs_bssn(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],
@@ -5056,7 +5048,7 @@ void bssn_class::Step(int lev, int YN)
                          cg->fgfs[Ayy->sgfn], cg->fgfs[Ayz->sgfn], cg->fgfs[Azz->sgfn]);
 #endif
 
-          if (f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+          if (f_compute_rhs_bssn(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],
@@ -5827,21 +5819,11 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 #endif
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_pre,SL,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, GH->bdsul[lev], Symmetry);
@@ -5888,21 +5870,11 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 #endif
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SL, SL, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SL, SL, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SL,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, GH->bdsul[lev], Symmetry);
@@ -5977,21 +5949,11 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
       Parallel::Sync_cached(GH->PatL[lev - 1], SynchList_pre, Symmetry, sync_cache_rp_coarse[lev]);
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_pre,SL,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, GH->bdsul[lev], Symmetry);
@@ -6009,21 +5971,11 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
       Parallel::Sync_cached(GH->PatL[lev - 1], SL, Symmetry, sync_cache_rp_coarse[lev]);
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SL, SL, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SL, SL, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SL,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, GH->bdsul[lev], Symmetry);
@@ -6084,21 +6036,11 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       Parallel::Sync_cached(GH->PatL[lev - 1], SynchList_pre, Symmetry, sync_cache_rp_coarse[lev]);
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_pre,SynchList_cor,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, GH->bdsul[lev], Symmetry);
@@ -6118,21 +6060,11 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       Parallel::Sync_cached(GH->PatL[lev - 1], StateList, Symmetry, sync_cache_rp_coarse[lev]);
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],StateList,SynchList_cor,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, GH->bdsul[lev], Symmetry);
@@ -6169,21 +6101,11 @@ void bssn_class::ProlongRestrict(int lev, int YN, bool BB)
       }
 
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_pre,SynchList_cor,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, GH->bdsul[lev], Symmetry);
@@ -6192,21 +6114,11 @@ void bssn_class::ProlongRestrict(int lev, int YN, bool BB)
     else // no time refinement levels and for all same time levels
     {
 #if (RPB == 0)
-      Ppc = GH->PatL[lev - 1];
-      while (Ppc)
-      {
-        Pp = GH->PatL[lev];
-        while (Pp)
-        {
 #if (MIXOUTB == 0)
-          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
+      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #endif
-          Pp = Pp->next;
-        }
-        Ppc = Ppc->next;
-      }
 #elif (RPB == 1)
       //       Parallel::OutBdLow2Hi_bam(GH->PatL[lev-1],GH->PatL[lev],StateList,SynchList_cor,Symmetry);
       Parallel::OutBdLow2Hi_bam(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, GH->bdsul[lev], Symmetry);
@@ -7351,7 +7263,7 @@ void bssn_class::Constraint_Out()
             Block *cg = BP->data;
             if (myrank == cg->rank)
             {
-              f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+              f_compute_rhs_bssn(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],
@@ -7854,7 +7766,7 @@ void bssn_class::Interp_Constraint(bool infg)
             Block *cg = BP->data;
             if (myrank == cg->rank)
             {
-              f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+              f_compute_rhs_bssn(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],
@@ -8112,7 +8024,7 @@ void bssn_class::Compute_Constraint()
           Block *cg = BP->data;
           if (myrank == cg->rank)
           {
-            f_compute_rhs_bssn_xh(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
+            f_compute_rhs_bssn(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],

AMSS_NCKU_source/bssn_rhs.f90

@@ -106,6 +106,38 @@
   call getpbh(BHN,Porg,Mass)
 #endif
 
+!!! sanity check (disabled in production builds for performance)
+#ifdef DEBUG
+  dX = sum(chi)+sum(trK)+sum(dxx)+sum(gxy)+sum(gxz)+sum(dyy)+sum(gyz)+sum(dzz) &
+      +sum(Axx)+sum(Axy)+sum(Axz)+sum(Ayy)+sum(Ayz)+sum(Azz)                   &
+      +sum(Gamx)+sum(Gamy)+sum(Gamz)                                           &
+      +sum(Lap)+sum(betax)+sum(betay)+sum(betaz)
+  if(dX.ne.dX) then
+     if(sum(chi).ne.sum(chi))write(*,*)"bssn.f90: find NaN in chi"
+     if(sum(trK).ne.sum(trK))write(*,*)"bssn.f90: find NaN in trk"
+     if(sum(dxx).ne.sum(dxx))write(*,*)"bssn.f90: find NaN in dxx"
+     if(sum(gxy).ne.sum(gxy))write(*,*)"bssn.f90: find NaN in gxy"
+     if(sum(gxz).ne.sum(gxz))write(*,*)"bssn.f90: find NaN in gxz"
+     if(sum(dyy).ne.sum(dyy))write(*,*)"bssn.f90: find NaN in dyy"
+     if(sum(gyz).ne.sum(gyz))write(*,*)"bssn.f90: find NaN in gyz"
+     if(sum(dzz).ne.sum(dzz))write(*,*)"bssn.f90: find NaN in dzz"
+     if(sum(Axx).ne.sum(Axx))write(*,*)"bssn.f90: find NaN in Axx"
+     if(sum(Axy).ne.sum(Axy))write(*,*)"bssn.f90: find NaN in Axy"
+     if(sum(Axz).ne.sum(Axz))write(*,*)"bssn.f90: find NaN in Axz"
+     if(sum(Ayy).ne.sum(Ayy))write(*,*)"bssn.f90: find NaN in Ayy"
+     if(sum(Ayz).ne.sum(Ayz))write(*,*)"bssn.f90: find NaN in Ayz"
+     if(sum(Azz).ne.sum(Azz))write(*,*)"bssn.f90: find NaN in Azz"
+     if(sum(Gamx).ne.sum(Gamx))write(*,*)"bssn.f90: find NaN in Gamx"
+     if(sum(Gamy).ne.sum(Gamy))write(*,*)"bssn.f90: find NaN in Gamy"
+     if(sum(Gamz).ne.sum(Gamz))write(*,*)"bssn.f90: find NaN in Gamz"
+     if(sum(Lap).ne.sum(Lap))write(*,*)"bssn.f90: find NaN in Lap"
+     if(sum(betax).ne.sum(betax))write(*,*)"bssn.f90: find NaN in betax"
+     if(sum(betay).ne.sum(betay))write(*,*)"bssn.f90: find NaN in betay"
+     if(sum(betaz).ne.sum(betaz))write(*,*)"bssn.f90: find NaN in betaz"
+     gont = 1
+     return
+  endif
+#endif
 
   PI = dacos(-ONE)
 
@@ -602,7 +634,7 @@
   gxxx = (gupxx * chix + gupxy * chiy + gupxz * chiz)/chin1
   gxxy = (gupxy * chix + gupyy * chiy + gupyz * chiz)/chin1
   gxxz = (gupxz * chix + gupyz * chiy + gupzz * chiz)/chin1
-
+! now get physical second kind of connection
   Gamxxx = Gamxxx - ( (chix + chix)/chin1 - gxx * gxxx )*HALF
   Gamyxx = Gamyxx - (                     - gxx * gxxy )*HALF
   Gamzxx = Gamzxx - (                     - gxx * gxxz )*HALF
@@ -913,103 +945,60 @@
   SSA(2)=SYM
   SSA(3)=ANTI
 
-!!!!!!!!!advection term part
+!!!!!!!!!advection term + Kreiss-Oliger dissipation (merged for cache efficiency)
+! lopsided_kodis shares the symmetry_bd buffer between advection and
+! dissipation, eliminating redundant full-grid copies. For metric variables
+! gxx/gyy/gzz (=dxx/dyy/dzz+1): kodis stencil coefficients sum to zero,
+! so the constant offset has no effect on dissipation.
 
-  call lopsided(ex,X,Y,Z,gxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,gxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided(ex,X,Y,Z,gxy,gxy_rhs,betax,betay,betaz,Symmetry,AAS)
+  call lopsided_kodis(ex,X,Y,Z,gxy,gxy_rhs,betax,betay,betaz,Symmetry,AAS,eps)
-  call lopsided(ex,X,Y,Z,gxz,gxz_rhs,betax,betay,betaz,Symmetry,ASA)
+  call lopsided_kodis(ex,X,Y,Z,gxz,gxz_rhs,betax,betay,betaz,Symmetry,ASA,eps)
-  call lopsided(ex,X,Y,Z,gyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,gyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA)
+  call lopsided_kodis(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA,eps)
-  call lopsided(ex,X,Y,Z,gzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,gzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
 
-  call lopsided(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS)
+  call lopsided_kodis(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS,eps)
-  call lopsided(ex,X,Y,Z,Axz,Axz_rhs,betax,betay,betaz,Symmetry,ASA)
+  call lopsided_kodis(ex,X,Y,Z,Axz,Axz_rhs,betax,betay,betaz,Symmetry,ASA,eps)
-  call lopsided(ex,X,Y,Z,Ayy,Ayy_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,Ayy,Ayy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided(ex,X,Y,Z,Ayz,Ayz_rhs,betax,betay,betaz,Symmetry,SAA)
+  call lopsided_kodis(ex,X,Y,Z,Ayz,Ayz_rhs,betax,betay,betaz,Symmetry,SAA,eps)
-  call lopsided(ex,X,Y,Z,Azz,Azz_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,Azz,Azz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
 
-  call lopsided(ex,X,Y,Z,chi,chi_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,chi,chi_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided(ex,X,Y,Z,trK,trK_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided_kodis(ex,X,Y,Z,trK,trK_rhs,betax,betay,betaz,Symmetry,SSS,eps)
 
-  call lopsided(ex,X,Y,Z,Gamx,Gamx_rhs,betax,betay,betaz,Symmetry,ASS)
+  call lopsided_kodis(ex,X,Y,Z,Gamx,Gamx_rhs,betax,betay,betaz,Symmetry,ASS,eps)
-  call lopsided(ex,X,Y,Z,Gamy,Gamy_rhs,betax,betay,betaz,Symmetry,SAS)
+  call lopsided_kodis(ex,X,Y,Z,Gamy,Gamy_rhs,betax,betay,betaz,Symmetry,SAS,eps)
-  call lopsided(ex,X,Y,Z,Gamz,Gamz_rhs,betax,betay,betaz,Symmetry,SSA)
+  call lopsided_kodis(ex,X,Y,Z,Gamz,Gamz_rhs,betax,betay,betaz,Symmetry,SSA,eps)
-!!
+
+#if 1 
+!! bam does not apply dissipation on gauge variables
+  call lopsided_kodis(ex,X,Y,Z,Lap,Lap_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+#if (GAUGE == 0 || GAUGE == 1 || GAUGE == 2 || GAUGE == 3 || GAUGE == 4 || GAUGE == 5 || GAUGE == 6 || GAUGE == 7)
+  call lopsided_kodis(ex,X,Y,Z,betax,betax_rhs,betax,betay,betaz,Symmetry,ASS,eps)
+  call lopsided_kodis(ex,X,Y,Z,betay,betay_rhs,betax,betay,betaz,Symmetry,SAS,eps)
+  call lopsided_kodis(ex,X,Y,Z,betaz,betaz_rhs,betax,betay,betaz,Symmetry,SSA,eps)
+#endif
+#if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
+  call lopsided_kodis(ex,X,Y,Z,dtSfx,dtSfx_rhs,betax,betay,betaz,Symmetry,ASS,eps)
+  call lopsided_kodis(ex,X,Y,Z,dtSfy,dtSfy_rhs,betax,betay,betaz,Symmetry,SAS,eps)
+  call lopsided_kodis(ex,X,Y,Z,dtSfz,dtSfz_rhs,betax,betay,betaz,Symmetry,SSA,eps)
+#endif
+#else
+! No dissipation on gauge variables (advection only)
   call lopsided(ex,X,Y,Z,Lap,Lap_rhs,betax,betay,betaz,Symmetry,SSS)
-
 #if (GAUGE == 0 || GAUGE == 1 || GAUGE == 2 || GAUGE == 3 || GAUGE == 4 || GAUGE == 5 || GAUGE == 6 || GAUGE == 7)
   call lopsided(ex,X,Y,Z,betax,betax_rhs,betax,betay,betaz,Symmetry,ASS)
   call lopsided(ex,X,Y,Z,betay,betay_rhs,betax,betay,betaz,Symmetry,SAS)
   call lopsided(ex,X,Y,Z,betaz,betaz_rhs,betax,betay,betaz,Symmetry,SSA)
 #endif
-
 #if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
   call lopsided(ex,X,Y,Z,dtSfx,dtSfx_rhs,betax,betay,betaz,Symmetry,ASS)
   call lopsided(ex,X,Y,Z,dtSfy,dtSfy_rhs,betax,betay,betaz,Symmetry,SAS)
   call lopsided(ex,X,Y,Z,dtSfz,dtSfz_rhs,betax,betay,betaz,Symmetry,SSA)
 #endif
-
-  if(eps>0)then 
-! usual Kreiss-Oliger dissipation      
-  call kodis(ex,X,Y,Z,chi,chi_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,trK,trK_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,dxx,gxx_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,gxy,gxy_rhs,AAS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,gxz,gxz_rhs,ASA,Symmetry,eps)
-  call kodis(ex,X,Y,Z,dyy,gyy_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,gyz,gyz_rhs,SAA,Symmetry,eps)
-  call kodis(ex,X,Y,Z,dzz,gzz_rhs,SSS,Symmetry,eps)
-#if 0
-#define i 42
-#define j 40
-#define k 40
-if(Lev == 1)then
-write(*,*) X(i),Y(j),Z(k)
-write(*,*) "before",Axx_rhs(i,j,k)
-endif
-#undef i
-#undef j
-#undef k
-!!stop
 #endif
-  call kodis(ex,X,Y,Z,Axx,Axx_rhs,SSS,Symmetry,eps)
-#if 0
-#define i 42
-#define j 40
-#define k 40
-if(Lev == 1)then
-write(*,*) X(i),Y(j),Z(k)
-write(*,*) "after",Axx_rhs(i,j,k)
-endif
-#undef i
-#undef j
-#undef k
-!!stop
-#endif
-  call kodis(ex,X,Y,Z,Axy,Axy_rhs,AAS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Axz,Axz_rhs,ASA,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Ayy,Ayy_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Ayz,Ayz_rhs,SAA,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Azz,Azz_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Gamx,Gamx_rhs,ASS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Gamy,Gamy_rhs,SAS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,Gamz,Gamz_rhs,SSA,Symmetry,eps)
-
-#if 1 
-!! bam does not apply dissipation on gauge variables
-  call kodis(ex,X,Y,Z,Lap,Lap_rhs,SSS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,betax,betax_rhs,ASS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,betay,betay_rhs,SAS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,betaz,betaz_rhs,SSA,Symmetry,eps)
-#if (GAUGE == 0 || GAUGE == 2 || GAUGE == 3 || GAUGE == 6 || GAUGE == 7)
-  call kodis(ex,X,Y,Z,dtSfx,dtSfx_rhs,ASS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,dtSfy,dtSfy_rhs,SAS,Symmetry,eps)
-  call kodis(ex,X,Y,Z,dtSfz,dtSfz_rhs,SSA,Symmetry,eps)
-#endif
-#endif
-
-  endif
 
   if(co == 0)then
 ! ham_Res = trR + 2/3 * K^2 - A_ij * A^ij - 16 * PI * rho

AMSS_NCKU_source/bssn_rhs_cuda.h

@@ -1,9 +1,11 @@
-#include "xh_tool.h"
+#ifndef BSSN_RHS_CUDA_H
+#define BSSN_RHS_CUDA_H
 
+#ifdef __cplusplus
+extern "C" {
+#endif
 
-extern "C"
+int f_compute_rhs_bssn(int *ex, double &T,
-{
-int f_compute_rhs_bssn_xh(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,
@@ -25,6 +27,10 @@ int f_compute_rhs_bssn_xh(int *ex, double &T,
                        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 &Symmetry, int &Lev, double &eps, int &co);
-                       ); 
+
+#ifdef __cplusplus
 }
+#endif
+
+#endif

AMSS_NCKU_source/cgh.C

@@ -130,7 +130,11 @@ void cgh::compose_cgh(int nprocs)
   for (int lev = 0; lev < levels; lev++)
   {
     checkPatchList(PatL[lev], false);
+#ifdef INTERP_LB_OPTIMIZE
+    Parallel::distribute_optimize(PatL[lev], nprocs, ingfs, fngfs, false);
+#else
     Parallel::distribute(PatL[lev], nprocs, ingfs, fngfs, false);
+#endif
 #if (RPB == 1)
     // we need distributed box of PatL[lev] and PatL[lev-1]
     if (lev > 0)
@@ -1301,13 +1305,13 @@ bool cgh::Interp_One_Point(MyList<var> *VarList,
 }
 
 
-void cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+bool cgh::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)
 {
   if (lev < movls)
-    return;
+    return false;
 
 #if (0)
   // #if (PSTR == 1 || PSTR == 2)
@@ -1396,7 +1400,7 @@ void cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, do
       for (bhi = 0; bhi < BH_num; bhi++)
         delete[] tmpPorg[bhi];
       delete[] tmpPorg;
-      return;
+      return false;
     }
     // x direction
     rr = (Porg0[bhi][0] - handle[lev][grd][0]) / dX;
@@ -1500,6 +1504,7 @@ void cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, do
   for (int bhi = 0; bhi < BH_num; bhi++)
     delete[] tmpPorg[bhi];
   delete[] tmpPorg;
+  return tot_flag;
 }
 
 

AMSS_NCKU_source/cgh.h

@@ -74,7 +74,7 @@ public:
                                MyList<var> *OldList, MyList<var> *StateList,
                                MyList<var> *FutureList, MyList<var> *tmList,
                                int Symmetry, bool BB);
-   void Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+   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);

AMSS_NCKU_source/diff_new.f90

@@ -69,6 +69,8 @@
   fy = ZEO
   fz = ZEO
 
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
+!DIR$ UNROLL PARTIAL(4)
   do k=1,ex(3)-1
   do j=1,ex(2)-1
   do i=1,ex(1)-1
@@ -371,6 +373,8 @@
   fxz = ZEO
   fyz = ZEO
 
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
+!DIR$ UNROLL PARTIAL(4)
   do k=1,ex(3)-1
   do j=1,ex(2)-1
   do i=1,ex(1)-1

AMSS_NCKU_source/extention/include/xh_bssn_rhs_compute.h

@@ -1,26 +0,0 @@
-#include "xh_macrodef.h"
-#include "xh_tool.h"
-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
-                       ); 

AMSS_NCKU_source/extention/include/xh_macrodef.h

@@ -1,66 +0,0 @@
-/* tetrad notes
-   v:r; u: phi; w: theta
-
-   tetradtype 0
-   v^a = (x,y,z)
-   orthonormal order: v,u,w
-   m = (phi - i theta)/sqrt(2) following Frans, Eq.(8) of  PRD 75, 124018(2007)
-
-   tetradtype 1
-   orthonormal order: w,u,v
-   m = (theta + i phi)/sqrt(2) following Sperhake, Eq.(3.2) of  PRD 85, 124062(2012)
-
-   tetradtype 2
-   v_a = (x,y,z)
-   orthonormal order: v,u,w
-   m = (phi - i theta)/sqrt(2) following Frans, Eq.(8) of  PRD 75, 124018(2007)
-*/
-#define tetradtype 2
-
-/* Cell center or Vertex center */
-#define Cell
-
-/* ghost_width meaning:
-   2nd order: 2
-   4th order: 3
-   6th order: 4
-   8th order: 5
-*/
-#define ghost_width 3
-
-/* use shell or not */
-#define WithShell
-
-/* use constraint preserving boundary condition or not
-   only affect Z4c
-*/
-#define CPBC
-
-/* Gauge condition type
-   0: B^i gauge
-   1: David's puncture gauge
-   2: MB B^i gauge
-   3: RIT B^i gauge
-   4: MB beta gauge (beta gauge not means Eq.(3) of PRD 84, 124006)
-   5: RIT beta gauge (beta gauge not means Eq.(3) of PRD 84, 124006)
-   6: MGB1 B^i gauge
-   7: MGB2 B^i gauge
-*/
-#define GAUGE 2
-
-/* buffer points for CPBC boundary */
-#define CPBC_ghost_width (ghost_width)
-
-/* using BSSN variable for constraint violation and psi4 calculation: 0
-   using ADM variable for constraint violation and psi4 calculation: 1
-*/
-#define ABV 0
-
-/* Type of Potential and Scalar Distribution 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 = infinity and phi(r) = phi0 * 0.5 * ( tanh((r+r0)/sigma) - tanh((r-r0)/sigma) )
-   5: shell with phi(r) = phi0*Exp(-(r-r0)**2/sigma), V = 0
-*/
-#define EScalar_CC 2

AMSS_NCKU_source/extention/include/xh_share_func.h

@@ -1,338 +0,0 @@
-#ifndef SHARE_FUNC_H
-#define SHARE_FUNC_H
-
-#include <stdlib.h>
-#include <stddef.h>
-#include <math.h>
-#include <stdio.h>
-#include <omp.h>
-/* 主网格：0-based -> 1D */
-static inline size_t idx_ex(int i0, int j0, int k0, const int ex[3]) {
-    const int ex1 = ex[0], ex2 = ex[1];
-    return (size_t)i0 + (size_t)j0 * (size_t)ex1 + (size_t)k0 * (size_t)ex1 * (size_t)ex2;
-}
-
-/*
- * fh 对应 Fortran: fh(-1:ex1, -1:ex2, -1:ex3)
- * ord=2 => shift=1
- * iF/jF/kF 为 Fortran 索引（可为 -1,0,1..ex）
- */
-static inline size_t idx_fh_F_ord2(int iF, int jF, int kF, const int ex[3]) {
-    const int shift = 1;
-    const int nx = ex[0] + 2;      // ex1 + ord
-    const int ny = ex[1] + 2;
-
-    const int ii = iF + shift;     // 0..ex1+1
-    const int jj = jF + shift;     // 0..ex2+1
-    const int kk = kF + shift;     // 0..ex3+1
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * fh 对应 Fortran: fh(-2:ex1, -2:ex2, -2:ex3)
- * ord=3 => shift=2
- * iF/jF/kF 是 Fortran 索引（可为负）
- */
-static inline size_t idx_fh_F(int iF, int jF, int kF, const int ex[3]) {
-    const int shift = 2;                 // ord=3 -> -2..ex
-    const int nx = ex[0] + 3;            // ex1 + ord
-    const int ny = ex[1] + 3;
-
-    const int ii = iF + shift;           // 0..ex1+2
-    const int jj = jF + shift;           // 0..ex2+2
-    const int kk = kF + shift;           // 0..ex3+2
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * func:  (1..extc1, 1..extc2, 1..extc3)   1-based in Fortran
- * funcc: (-ord+1..extc1, -ord+1..extc2, -ord+1..extc3) in Fortran
- *
- * C 里我们把：
- *   func  视为 0-based: i0=0..extc1-1, j0=0..extc2-1, k0=0..extc3-1
- *   funcc 用“平移下标”存为一维数组：
- *     iF in [-ord+1..extc1]  -> ii = iF + (ord-1)  in [0..extc1+ord-1]
- *     总长度 nx = extc1 + ord
- *     同理 ny = extc2 + ord, nz = extc3 + ord
- */
-
-static inline size_t idx_func0(int i0, int j0, int k0, const int extc[3]) {
-    const int nx = extc[0], ny = extc[1];
-    return (size_t)i0 + (size_t)j0 * (size_t)nx + (size_t)k0 * (size_t)nx * (size_t)ny;
-}
-
-static inline size_t idx_funcc_F(int iF, int jF, int kF, int ord, const int extc[3]) {
-    const int shift = ord - 1;          // iF = -shift .. extc1
-    const int nx = extc[0] + ord;       // [-shift..extc1] 共 extc1+ord 个
-    const int ny = extc[1] + ord;
-
-    const int ii = iF + shift;          // 0..extc1+shift
-    const int jj = jF + shift;          // 0..extc2+shift
-    const int kk = kF + shift;          // 0..extc3+shift
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * 等价于 Fortran:
- * funcc(1:extc1,1:extc2,1:extc3)=func
- * do i=0,ord-1
- *   funcc(-i,1:extc2,1:extc3) = funcc(i+1,1:extc2,1:extc3)*SoA(1)
- * enddo
- * do i=0,ord-1
- *   funcc(:,-i,1:extc3) = funcc(:,i+1,1:extc3)*SoA(2)
- * enddo
- * do i=0,ord-1
- *   funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
- * enddo
- */
-static inline void symmetry_bd(int ord,
-                 const int extc[3],
-                 const double *func,
-                 double *funcc,
-                 const double SoA[3])
-{
-    const int extc1 = extc[0], extc2 = extc[1], extc3 = extc[2];
-
-    // 1) funcc(1:extc1,1:extc2,1:extc3) = func
-    // Fortran 的 (iF=1..extc1) 对应 C 的 func(i0=0..extc1-1)
-    for (int k0 = 0; k0 < extc3; ++k0) {
-        for (int j0 = 0; j0 < extc2; ++j0) {
-            for (int i0 = 0; i0 < extc1; ++i0) {
-                const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1;
-                funcc[idx_funcc_F(iF, jF, kF, ord, extc)] = func[idx_func0(i0, j0, k0, extc)];
-            }
-        }
-    }
-
-    // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
-    for (int ii = 0; ii <= ord - 1; ++ii) {
-        const int iF_dst = -ii;       // 0, -1, -2, ...
-        const int iF_src = ii + 1;    // 1, 2, 3, ...
-        for (int kF = 1; kF <= extc3; ++kF) {
-            for (int jF = 1; jF <= extc2; ++jF) {
-                funcc[idx_funcc_F(iF_dst, jF, kF, ord, extc)] =
-                    funcc[idx_funcc_F(iF_src, jF, kF, ord, extc)] * SoA[0];
-            }
-        }
-    }
-
-    // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-    // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-    for (int jj = 0; jj <= ord - 1; ++jj) {
-        const int jF_dst = -jj;
-        const int jF_src = jj + 1;
-        for (int kF = 1; kF <= extc3; ++kF) {
-            for (int iF = -ord + 1; iF <= extc1; ++iF) {
-                funcc[idx_funcc_F(iF, jF_dst, kF, ord, extc)] =
-                    funcc[idx_funcc_F(iF, jF_src, kF, ord, extc)] * SoA[1];
-            }
-        }
-    }
-
-    // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-    for (int kk = 0; kk <= ord - 1; ++kk) {
-        const int kF_dst = -kk;
-        const int kF_src = kk + 1;
-        for (int jF = -ord + 1; jF <= extc2; ++jF) {
-            for (int iF = -ord + 1; iF <= extc1; ++iF) {
-                funcc[idx_funcc_F(iF, jF, kF_dst, ord, extc)] =
-                    funcc[idx_funcc_F(iF, jF, kF_src, ord, extc)] * SoA[2];
-            }
-        }
-    }
-}
-#endif
-
-/* 你已有的函数：idx_ex / idx_fh_F_ord2 以及 fh 的布局 */
-static inline void fdderivs_xh(
-    int i0, int j0, int k0,
-    const int ex[3],
-    const double *fh,
-    int iminF, int jminF, int kminF,
-    int imaxF, int jmaxF, int kmaxF,
-    double Fdxdx, double Fdydy, double Fdzdz,
-    double Fdxdy, double Fdxdz, double Fdydz,
-    double Sdxdx, double Sdydy, double Sdzdz,
-    double Sdxdy, double Sdxdz, double Sdydz,
-    double *fxx, double *fxy, double *fxz,
-    double *fyy, double *fyz, double *fzz
-){
-    const double F8  = 8.0;
-    const double F16 = 16.0;
-    const double F30 = 30.0;
-    const double TWO = 2.0;
-
-    const int iF = i0 + 1;
-    const int jF = j0 + 1;
-    const int kF = k0 + 1;
-
-    const size_t p = idx_ex(i0, j0, k0, ex);
-
-    /* 高阶分支：i±2,j±2,k±2 都在范围内 */
-    if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-        (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-        (kF + 2) <= kmaxF && (kF - 2) >= kminF)
-    {
-        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)]
-        );
-
-        /* fxy 高阶 */
-        {
-            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 );
-        }
-
-        /* fxz 高阶 */
-        {
-            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 );
-        }
-
-        /* fyz 高阶 */
-        {
-            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 );
-        }
-    }
-    /* 二阶分支：i±1,j±1,k±1 在范围内 */
-    else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-             (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-             (kF + 1) <= kmaxF && (kF - 1) >= kminF)
-    {
-        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)]
-        );
-    }
-    else {
-        fxx[p] = 0.0; fyy[p] = 0.0; fzz[p] = 0.0;
-        fxy[p] = 0.0; fxz[p] = 0.0; fyz[p] = 0.0;
-    }
-}

AMSS_NCKU_source/extention/src/main.c

@@ -1,7 +0,0 @@
-#include "include/bssn_rhs_compute.h"
-
-int main() {
-    // 这里可以写一些测试代码，调用 f_compute_rhs_bssn 来验证它的正确性
-    // 例如，定义一些小的网格和初始条件，调用函数，并检查输出是否合理。
-    return 0;
-}

AMSS_NCKU_source/extention/src/new.c

@@ -1,65 +0,0 @@
-        SoA[0] = SYM, SoA[1] = SYM, SoA[2] = SYM;
-        #pragma omp for collapse(3)
-        for (int k0 = 0; k0 < ex[2]; ++k0) {
-            for (int j0 = 0; j0 < ex[1]; ++j0) {
-                for (int i0 = 0; i0 < ex[0]; ++i0) {
-                    const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1; 
-                    fh[idx_funcc_F(iF, jF, kF, 2, ex)] = Lap[idx_func0(i0, j0, k0, ex)];
-                }
-            }
-        }
-
-        // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
-        #pragma omp for collapse(3)
-        for (int ii = 0; ii <= 2 - 1; ++ii) {
-            const int iF_dst = -ii;       // 0, -1, -2, ...
-            const int iF_src = ii + 1;    // 1, 2, 3, ...
-            for (int kF = 1; kF <= ex[2]; ++kF) {
-                for (int jF = 1; jF <= ex[1]; ++jF) {
-                    fh[idx_funcc_F(iF_dst, jF, kF, 2, ex)] = 
-                        fh[idx_funcc_F(iF_src, jF, kF, 2, ex)] * SoA[0];
-                }
-            }
-        }
-
-        // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-        // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-        #pragma omp for collapse(3)
-        for (int jj = 0; jj <= 2 - 1; ++jj) {
-            const int jF_dst = -jj;
-            const int jF_src = jj + 1;
-            for (int kF = 1; kF <= ex[2]; ++kF) {
-                for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                    fh[idx_funcc_F(iF, jF_dst, kF, 2, ex)] =
-                        fh[idx_funcc_F(iF, jF_src, kF, 2, ex)] * SoA[1];
-                }
-            }
-        }
-
-        // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-        #pragma omp for collapse(3)
-        for (int kk = 0; kk <= 2 - 1; ++kk) {
-            const int kF_dst = -kk;
-            const int kF_src = kk + 1;
-            for (int jF = -2 + 1; jF <= ex[1]; ++jF) {
-                for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                    fh[idx_funcc_F(iF, jF, kF_dst, 2, ex)] =
-                        fh[idx_funcc_F(iF, jF, kF_src, 2, ex)] * SoA[2];
-                }
-            }
-        }
-
-        #pragma omp for collapse(3)
-        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) {
-                    fdderivs_xh(i0, j0, k0, ex, fh, iminF, jminF, kminF, ex1, ex2, ex3, 
-                        Fdxdx, Fdydy, Fdzdz, Fdxdy, Fdxdz, Fdydz,
-                        Sdxdx, Sdydy, Sdzdz, Sdxdy, Sdxdz, Sdydz,
-                            fxx,fxy,fxz,fyy,fyz,fzz
-                    );
-                }
-            }
-        }

AMSS_NCKU_source/extention/src/xh_fdderivs.c

@@ -1,311 +0,0 @@
-#include "xh_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;
-
-
-    /* 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;
-
-    /* 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);
-
-    static thread_local double *fh = NULL;
-    static thread_local 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);
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    for (int k0 = 0; k0 < ex[2]; ++k0) {
-        for (int j0 = 0; j0 < ex[1]; ++j0) {
-            for (int i0 = 0; i0 < ex[0]; ++i0) {
-                const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1; 
-                fh[idx_funcc_F(iF, jF, kF, 2, ex)] = f[idx_func0(i0, j0, k0, ex)];
-            }
-        }
-    }
-
-    // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
-    for (int ii = 0; ii <= 2 - 1; ++ii) {
-        const int iF_dst = -ii;       // 0, -1, -2, ...
-        const int iF_src = ii + 1;    // 1, 2, 3, ...
-        for (int kF = 1; kF <= ex[2]; ++kF) {
-            for (int jF = 1; jF <= ex[1]; ++jF) {
-                fh[idx_funcc_F(iF_dst, jF, kF, 2, ex)] = 
-                    fh[idx_funcc_F(iF_src, jF, kF, 2, ex)] * SoA[0];
-            }
-        }
-    }
-
-    // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-    // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-    for (int jj = 0; jj <= 2 - 1; ++jj) {
-        const int jF_dst = -jj;
-        const int jF_src = jj + 1;
-        for (int kF = 1; kF <= ex[2]; ++kF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF_dst, kF, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF_src, kF, 2, ex)] * SoA[1];
-            }
-        }
-    }
-
-    // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-    for (int kk = 0; kk <= 2 - 1; ++kk) {
-        const int kF_dst = -kk;
-        const int kF_src = kk + 1;
-        for (int jF = -2 + 1; jF <= ex[1]; ++jF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF, kF_dst, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF, kF_src, 2, ex)] * SoA[2];
-            }
-        }
-    }
-    /* 输出清零：fxx,fyy,fzz,fxy,fxz,fyz = 0 */
-    // const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
-    // for (size_t p = 0; p < all; ++p) {
-    //     fxx[p] = ZEO; fyy[p] = ZEO; fzz[p] = ZEO;
-    //     fxy[p] = ZEO; fxz[p] = ZEO; fyz[p] = ZEO;
-    // }
-
-    /*
-     * Fortran:
-     * do k=1,ex3-1
-     * do j=1,ex2-1
-     * do i=1,ex1-1
-     */
-    
-    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);
-
-                /* 高阶分支：i±2,j±2,k±2 都在范围内 */
-                if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-                    (kF + 2) <= kmaxF && (kF - 2) >= kminF)
-                {
-                    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)]
-                    );
-
-                    /* fxy 高阶：完全照搬 Fortran 的括号结构 */
-                    {
-                        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 );
-                    }
-
-                    /* fxz 高阶 */
-                    {
-                        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 );
-                    }
-
-                    /* fyz 高阶 */
-                    {
-                        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 );
-                    }
-                }
-                /* 二阶分支：i±1,j±1,k±1 在范围内 */
-                else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-                         (kF + 1) <= kmaxF && (kF - 1) >= kminF)
-                {
-                    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)]
-                    );
-                }else{
-                    fxx[p] = 0.0;
-                    fyy[p] = 0.0;
-                    fzz[p] = 0.0;
-                    fxy[p] = 0.0;
-                    fxz[p] = 0.0;
-                    fyz[p] = 0.0;
-                }
-            }
-        }
-    }
-    // free(fh);
-}

AMSS_NCKU_source/extention/src/xh_kodiss.c

@@ -1,116 +0,0 @@
-#include "xh_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;
-
-    static thread_local double *fh = NULL;
-    static thread_local size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
-    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, ...
-     */
-    for (int k0 = 0; k0 < ex3; ++k0) {
-        const int kF = k0 + 1;
-        for (int j0 = 0; j0 < ex2; ++j0) {
-            const int jF = j0 + 1;
-            for (int i0 = 0; i0 < ex1; ++i0) {
-                const int iF = i0 + 1;
-
-                // Fortran if 条件：
-                // i-3 >= imin .and. i+3 <= imax  等（都是 Fortran 索引）
-                if ((iF - 3) >= iminF && (iF + 3) <= imaxF &&
-                    (jF - 3) >= jminF && (jF + 3) <= jmaxF &&
-                    (kF - 3) >= kminF && (kF + 3) <= kmaxF)
-                {
-                    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/extention/src/xh_lopsided.c

@@ -1,262 +0,0 @@
-#include "xh_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;
-
-    static thread_local double *fh = NULL;
-    static thread_local size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
-    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/fdderivs_c.C

@@ -1,4 +1,4 @@
-#include "../include/tool.h"
+#include "tool.h"
 void fdderivs(const int ex[3],
               const double *f,
               double *fxx, double *fxy, double *fxz,
@@ -8,6 +8,7 @@ void fdderivs(const int ex[3],
               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
@@ -32,6 +33,7 @@ void fdderivs(const int ex[3],
     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;
@@ -39,6 +41,19 @@ void fdderivs(const int ex[3],
     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);
@@ -56,208 +71,99 @@ void fdderivs(const int ex[3],
     const double Fdxdz = F1o144 / (dX * dZ);
     const double Fdydz = F1o144 / (dY * dZ);
 
-    static thread_local double *fh = NULL;
+    /* 只清零不被主循环覆盖的边界面 */
-    static thread_local size_t cap = 0;
+    {
-
+        /* 高边界：k0=ex3-1 */
-    if (fh_size > cap) {
+        for (int j0 = 0; j0 < ex2; ++j0)
-        free(fh);
+            for (int i0 = 0; i0 < ex1; ++i0) {
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
+                const size_t p = idx_ex(i0, j0, ex3 - 1, ex);
-        cap = fh_size;
+                fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-    }
+                fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-    // double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    // symmetry_bd(2, ex, f, fh, SoA);
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    for (int k0 = 0; k0 < ex[2]; ++k0) {
-        for (int j0 = 0; j0 < ex[1]; ++j0) {
-            for (int i0 = 0; i0 < ex[0]; ++i0) {
-                const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1; 
-                fh[idx_funcc_F(iF, jF, kF, 2, ex)] = f[idx_func0(i0, j0, k0, ex)];
             }
+        /* 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;
             }
 
-    // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
+        /* 低边界：当二阶模板也不可用时，对应 i0/j0/k0=0 面 */
-    for (int ii = 0; ii <= 2 - 1; ++ii) {
+        if (kminF == 1) {
-        const int iF_dst = -ii;       // 0, -1, -2, ...
+            for (int j0 = 0; j0 < ex2; ++j0)
-        const int iF_src = ii + 1;    // 1, 2, 3, ...
+                for (int i0 = 0; i0 < ex1; ++i0) {
-        for (int kF = 1; kF <= ex[2]; ++kF) {
+                    const size_t p = idx_ex(i0, j0, 0, ex);
-            for (int jF = 1; jF <= ex[1]; ++jF) {
+                    fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
-                fh[idx_funcc_F(iF_dst, jF, kF, 2, ex)] = 
+                    fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
-                    fh[idx_funcc_F(iF_src, jF, kF, 2, ex)] * SoA[0];
+                }
+        }
+        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;
                 }
         }
     }
 
-    // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-    // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-    for (int jj = 0; jj <= 2 - 1; ++jj) {
-        const int jF_dst = -jj;
-        const int jF_src = jj + 1;
-        for (int kF = 1; kF <= ex[2]; ++kF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF_dst, kF, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF_src, kF, 2, ex)] * SoA[1];
-            }
-        }
-    }
-
-    // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-    for (int kk = 0; kk <= 2 - 1; ++kk) {
-        const int kF_dst = -kk;
-        const int kF_src = kk + 1;
-        for (int jF = -2 + 1; jF <= ex[1]; ++jF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF, kF_dst, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF, kF_src, 2, ex)] * SoA[2];
-            }
-        }
-    }
-    /* 输出清零：fxx,fyy,fzz,fxy,fxz,fyz = 0 */
-    // const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
-    // for (size_t p = 0; p < all; ++p) {
-    //     fxx[p] = ZEO; fyy[p] = ZEO; fzz[p] = ZEO;
-    //     fxy[p] = ZEO; fxz[p] = ZEO; fyz[p] = ZEO;
-    // }
-
     /*
-     * Fortran:
+     * 两段式：
-     * do k=1,ex3-1
+     * 1) 二阶可用区域先计算二阶模板
-     * do j=1,ex2-1
+     * 2) 高阶可用区域再覆盖四阶模板
-     * do i=1,ex1-1
      */
+    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;
 
-    for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
+    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 = 0; j0 <= ex2 - 2; ++j0) {
+            for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
                 const int jF = j0 + 1;
-            for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
+                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);
 
-                /* 高阶分支：i±2,j±2,k±2 都在范围内 */
-                if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-                    (kF + 2) <= kmaxF && (kF - 2) >= kminF)
-                {
-                    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)]
-                    );
-
-                    /* fxy 高阶：完全照搬 Fortran 的括号结构 */
-                    {
-                        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 );
-                    }
-
-                    /* fxz 高阶 */
-                    {
-                        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 );
-                    }
-
-                    /* fyz 高阶 */
-                    {
-                        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 );
-                    }
-                }
-                /* 二阶分支：i±1,j±1,k±1 在范围内 */
-                else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-                         (kF + 1) <= kmaxF && (kF - 1) >= kminF)
-                {
                     fxx[p] = Sdxdx * (
                         fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] -
                         TWO * fh[idx_fh_F_ord2(iF,     jF,     kF,     ex)] +
@@ -296,16 +202,131 @@ void fdderivs(const int ex[3],
                         fh[idx_fh_F_ord2(iF, jF - 1, kF + 1, ex)] +
                         fh[idx_fh_F_ord2(iF, jF + 1, kF + 1, ex)]
                     );
-                }else{
-                    fxx[p] = 0.0;
-                    fyy[p] = 0.0;
-                    fzz[p] = 0.0;
-                    fxy[p] = 0.0;
-                    fxz[p] = 0.0;
-                    fyz[p] = 0.0;
                 }
             }
         }
     }
+
+    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/fderivs_c.C

@@ -1,4 +1,4 @@
-#include "xh_tool.h"
+#include "tool.h"
 
 /*
  * C 版 fderivs
@@ -32,6 +32,11 @@ void fderivs(const int ex[3],
     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;
@@ -45,8 +50,8 @@ void fderivs(const int ex[3],
     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 thread_local double *fh = NULL;
+    static double *fh = NULL;
-    static thread_local size_t cap = 0;
+    static size_t cap = 0;
 
     if (fh_size > cap) {
         free(fh);
@@ -92,9 +97,9 @@ void fderivs(const int ex[3],
                 const size_t p = idx_ex(i0, j0, k0, ex);
 
                 // if(i+2 <= imax .and. i-2 >= imin ... )  (全是 Fortran 索引)
-                if ((iF + 2) <= ex1 && (iF - 2) >= iminF &&
+                if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-                    (jF + 2) <= ex2 && (jF - 2) >= jminF &&
+                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-                    (kF + 2) <= ex3 && (kF - 2) >= kminF)
+                    (kF + 2) <= kmaxF && (kF - 2) >= kminF)
                 {
                     fx[p] = d12dx * (
                         fh[idx_fh_F_ord2(iF - 2, jF,     kF,     ex)] -
@@ -118,9 +123,9 @@ void fderivs(const int ex[3],
                     );
                 }
                 // elseif(i+1 <= imax .and. i-1 >= imin ...)
-                else if ((iF + 1) <= ex1 && (iF - 1) >= iminF &&
+                else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-                         (jF + 1) <= ex2 && (jF - 1) >= jminF &&
+                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-                         (kF + 1) <= ex3 && (kF - 1) >= kminF)
+                         (kF + 1) <= kmaxF && (kF - 1) >= kminF)
                 {
                     fx[p] = d2dx * (
                         -fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +

AMSS_NCKU_source/fmisc.f90

@@ -883,13 +883,17 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
    enddo
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(:,-i,1:extc(3)) = funcc(:,i+1,1:extc(3))*SoA(2)
    enddo
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
    enddo
@@ -1111,7 +1115,149 @@ end subroutine d2dump
 !------------------------------------------------------------------------------
 ! Lagrangian polynomial interpolation
 !------------------------------------------------------------------------------
+#ifndef POLINT6_USE_BARYCENTRIC
+#define POLINT6_USE_BARYCENTRIC 1
+#endif
 
+!DIR$ ATTRIBUTES FORCEINLINE :: polint6_neville
+  subroutine polint6_neville(xa, ya, x, y, dy)
+  implicit none
+
+  real*8, dimension(6), intent(in) :: xa, ya
+  real*8, intent(in) :: x
+  real*8, intent(out) :: y, dy
+
+  integer :: i, m, ns, n_m
+  real*8, dimension(6) :: c, d, ho
+  real*8 :: dif, dift, hp, h, den_val
+
+  c = ya
+  d = ya
+  ho = xa - x
+
+  ns = 1
+  dif = abs(x - xa(1))
+
+  do i = 2, 6
+    dift = abs(x - xa(i))
+    if (dift < dif) then
+      ns = i
+      dif = dift
+    end if
+  end do
+
+  y = ya(ns)
+  ns = ns - 1
+
+  do m = 1, 5
+    n_m = 6 - m
+    do i = 1, n_m
+      hp = ho(i)
+      h  = ho(i+m)
+      den_val = hp - h
+
+      if (den_val == 0.0d0) then
+        write(*,*) 'failure in polint for point',x
+        write(*,*) 'with input points: ',xa
+        stop
+      end if
+
+      den_val = (c(i+1) - d(i)) / den_val
+
+      d(i) = h * den_val
+      c(i) = hp * den_val
+    end do
+
+    if (2 * ns < n_m) then
+      dy = c(ns + 1)
+    else
+      dy = d(ns)
+      ns = ns - 1
+    end if
+    y = y + dy
+  end do
+
+  return
+  end subroutine polint6_neville
+
+!DIR$ ATTRIBUTES FORCEINLINE :: polint6_barycentric
+  subroutine polint6_barycentric(xa, ya, x, y, dy)
+  implicit none
+
+  real*8, dimension(6), intent(in) :: xa, ya
+  real*8, intent(in) :: x
+  real*8, intent(out) :: y, dy
+
+  integer :: i, j
+  logical :: is_uniform
+  real*8, dimension(6) :: lambda
+  real*8 :: dx, den_i, term, num, den, step, tol
+  real*8, parameter :: c_uniform(6) = (/ -1.d0, 5.d0, -10.d0, 10.d0, -5.d0, 1.d0 /)
+
+  do i = 1, 6
+    if (x == xa(i)) then
+      y = ya(i)
+      dy = 0.d0
+      return
+    end if
+  end do
+
+  step = xa(2) - xa(1)
+  is_uniform = (step /= 0.d0)
+  if (is_uniform) then
+    tol = 64.d0 * epsilon(1.d0) * max(1.d0, abs(step))
+    do i = 3, 6
+      if (abs((xa(i) - xa(i-1)) - step) > tol) then
+        is_uniform = .false.
+        exit
+      end if
+    end do
+  end if
+
+  if (is_uniform) then
+    num = 0.d0
+    den = 0.d0
+    do i = 1, 6
+      term = c_uniform(i) / (x - xa(i))
+      num = num + term * ya(i)
+      den = den + term
+    end do
+    y = num / den
+    dy = 0.d0
+    return
+  end if
+
+  do i = 1, 6
+    den_i = 1.d0
+    do j = 1, 6
+      if (j /= i) then
+        dx = xa(i) - xa(j)
+        if (dx == 0.0d0) then
+          write(*,*) 'failure in polint for point',x
+          write(*,*) 'with input points: ',xa
+          stop
+        end if
+        den_i = den_i * dx
+      end if
+    end do
+    lambda(i) = 1.d0 / den_i
+  end do
+
+  num = 0.d0
+  den = 0.d0
+  do i = 1, 6
+    term = lambda(i) / (x - xa(i))
+    num = num + term * ya(i)
+    den = den + term
+  end do
+
+  y = num / den
+  dy = 0.d0
+
+  return
+  end subroutine polint6_barycentric
+
+!DIR$ ATTRIBUTES FORCEINLINE :: polint
   subroutine polint(xa, ya, x, y, dy, ordn)
   implicit none
 
@@ -1124,6 +1270,15 @@ end subroutine d2dump
   real*8, dimension(ordn) :: c, d, ho
   real*8 :: dif, dift, hp, h, den_val
 
+  if (ordn == 6) then
+#if POLINT6_USE_BARYCENTRIC
+    call polint6_barycentric(xa, ya, x, y, dy)
+#else
+    call polint6_neville(xa, ya, x, y, dy)
+#endif
+    return
+  end if
+
   c = ya
   d = ya
   ho = xa - x
@@ -1172,6 +1327,70 @@ end subroutine d2dump
 
   return
   end subroutine polint
+
+  subroutine polint0(xa, ya, y, ordn)
+  ! Lagrange interpolation at x=0, O(n) direct formula
+  implicit none
+  integer, intent(in) :: ordn
+  real*8, dimension(ordn), intent(in) :: xa, ya
+  real*8, intent(out) :: y
+
+  integer :: j, k
+  real*8 :: wj
+
+  y = 0.d0
+  do j = 1, ordn
+    wj = 1.d0
+    do k = 1, ordn
+      if (k .ne. j) then
+        wj = wj * xa(k) / (xa(k) - xa(j))
+      endif
+    enddo
+    y = y + wj * ya(j)
+  enddo
+
+  return
+  end subroutine polint0
+!------------------------------------------------------------------------------
+!
+! interpolation in 2 dimensions, follow yx order
+!
+!------------------------------------------------------------------------------
+!------------------------------------------------------------------------------
+! Compute Lagrange interpolation basis weights for one target point.
+!------------------------------------------------------------------------------
+!DIR$ ATTRIBUTES FORCEINLINE :: polint_lagrange_weights
+  subroutine polint_lagrange_weights(xa, x, w, ordn)
+  implicit none
+
+  integer, intent(in) :: ordn
+  real*8, dimension(1:ordn), intent(in) :: xa
+  real*8, intent(in) :: x
+  real*8, dimension(1:ordn), intent(out) :: w
+
+  integer :: i, j
+  real*8 :: num, den, dx
+
+  do i = 1, ordn
+    num = 1.d0
+    den = 1.d0
+    do j = 1, ordn
+      if (j /= i) then
+        dx = xa(i) - xa(j)
+        if (dx == 0.0d0) then
+          write(*,*) 'failure in polint for point',x
+          write(*,*) 'with input points: ',xa
+          stop
+        end if
+        num = num * (x - xa(j))
+        den = den * dx
+      end if
+    end do
+    w(i) = num / den
+  end do
+
+  return
+  end subroutine polint_lagrange_weights
 !------------------------------------------------------------------------------
 !
 ! interpolation in 2 dimensions, follow yx order
@@ -1243,19 +1462,26 @@ end subroutine d2dump
   end do
   call polint(x1a,ymtmp,x1,y,dy,ordn)
 #else
-  integer  :: j, k
+  integer  :: i, j, k
-  real*8, dimension(ordn,ordn) :: yatmp
+  real*8, dimension(ordn) :: w1, w2
   real*8, dimension(ordn) :: ymtmp
-  real*8 :: dy_temp
+  real*8 :: yx_sum, x_sum
+
+  call polint_lagrange_weights(x1a, x1, w1, ordn)
+  call polint_lagrange_weights(x2a, x2, w2, ordn)
 
   do k = 1, ordn
+    yx_sum = 0.d0
     do j = 1, ordn
-      call polint(x1a, ya(:,j,k), x1, yatmp(j,k), dy_temp, ordn)
+      x_sum = 0.d0
+      do i = 1, ordn
+        x_sum = x_sum + w1(i) * ya(i,j,k)
       end do
+      yx_sum = yx_sum + w2(j) * x_sum
     end do
-  do k=1,ordn
+    ymtmp(k) = yx_sum
-    call polint(x2a, yatmp(:,k), x2, ymtmp(k), dy_temp, ordn)
   end do
+
   call polint(x3a, ymtmp, x3, y, dy, ordn)
 #endif
 
@@ -1604,8 +1830,11 @@ deallocate(f_flat)
 ! f=3/8*f_1 + 3/4*f_2 - 1/8*f_3
 
   real*8,parameter::C1=3.d0/8.d0,C2=3.d0/4.d0,C3=-1.d0/8.d0
+  integer :: i,j,k
 
-  fout = C1*f1+C2*f2+C3*f3
+  do concurrent (k=1:ext(3), j=1:ext(2), i=1:ext(1))
+    fout(i,j,k) = C1*f1(i,j,k)+C2*f2(i,j,k)+C3*f3(i,j,k)
+  end do
 
   return
 

AMSS_NCKU_source/interp_lb_profile.C

@@ -0,0 +1,107 @@
+#include "interp_lb_profile.h"
+#include <cstdio>
+#include <cstring>
+#include <algorithm>
+
+namespace InterpLBProfile {
+
+bool write_profile(const char *filepath, int nprocs,
+                   const double *rank_times,
+                   const int *heavy_ranks, int num_heavy,
+                   double threshold_ratio)
+{
+    FILE *fp = fopen(filepath, "wb");
+    if (!fp) return false;
+
+    ProfileHeader hdr;
+    hdr.magic = MAGIC;
+    hdr.version = VERSION;
+    hdr.nprocs = nprocs;
+    hdr.num_heavy = num_heavy;
+    hdr.threshold_ratio = threshold_ratio;
+
+    fwrite(&hdr, sizeof(hdr), 1, fp);
+    fwrite(rank_times, sizeof(double), nprocs, fp);
+    fwrite(heavy_ranks, sizeof(int), num_heavy, fp);
+    fclose(fp);
+    return true;
+}
+
+bool read_profile(const char *filepath, int current_nprocs,
+                  int *heavy_ranks, int &num_heavy,
+                  double *rank_times, MPI_Comm comm)
+{
+    int myrank;
+    MPI_Comm_rank(comm, &myrank);
+
+    int valid = 0;
+    ProfileHeader hdr;
+    memset(&hdr, 0, sizeof(hdr));
+
+    if (myrank == 0) {
+        FILE *fp = fopen(filepath, "rb");
+        if (fp) {
+            if (fread(&hdr, sizeof(hdr), 1, fp) == 1 &&
+                hdr.magic == MAGIC && hdr.version == VERSION &&
+                hdr.nprocs == current_nprocs)
+            {
+                if (fread(rank_times, sizeof(double), current_nprocs, fp)
+                    == (size_t)current_nprocs &&
+                    fread(heavy_ranks, sizeof(int), hdr.num_heavy, fp)
+                    == (size_t)hdr.num_heavy)
+                {
+                    num_heavy = hdr.num_heavy;
+                    valid = 1;
+                }
+            } else if (fp) {
+                printf("[InterpLB] Profile rejected: magic=0x%X version=%u "
+                       "nprocs=%d (current=%d)\n",
+                       hdr.magic, hdr.version, hdr.nprocs, current_nprocs);
+            }
+            fclose(fp);
+        }
+    }
+
+    MPI_Bcast(&valid, 1, MPI_INT, 0, comm);
+    if (!valid) return false;
+
+    MPI_Bcast(&num_heavy, 1, MPI_INT, 0, comm);
+    MPI_Bcast(heavy_ranks, num_heavy, MPI_INT, 0, comm);
+    MPI_Bcast(rank_times, current_nprocs, MPI_DOUBLE, 0, comm);
+    return true;
+}
+
+int identify_heavy_ranks(const double *rank_times, int nprocs,
+                         double threshold_ratio,
+                         int *heavy_ranks, int max_heavy)
+{
+    double sum = 0;
+    for (int i = 0; i < nprocs; i++) sum += rank_times[i];
+    double mean = sum / nprocs;
+    double threshold = threshold_ratio * mean;
+
+    // Collect candidates
+    struct RankTime { int rank; double time; };
+    RankTime *candidates = new RankTime[nprocs];
+    int ncand = 0;
+
+    for (int i = 0; i < nprocs; i++) {
+        if (rank_times[i] > threshold)
+            candidates[ncand++] = {i, rank_times[i]};
+    }
+
+    // Sort descending by time
+    std::sort(candidates, candidates + ncand,
+              [](const RankTime &a, const RankTime &b) {
+                  return a.time > b.time;
+              });
+
+    int count = (ncand < max_heavy) ? ncand : max_heavy;
+    for (int i = 0; i < count; i++)
+        heavy_ranks[i] = candidates[i].rank;
+
+    delete[] candidates;
+    return count;
+}
+
+} // namespace InterpLBProfile

AMSS_NCKU_source/interp_lb_profile.h

@@ -0,0 +1,38 @@
+#ifndef INTERP_LB_PROFILE_H
+#define INTERP_LB_PROFILE_H
+
+#include <mpi.h>
+
+namespace InterpLBProfile {
+
+static const unsigned int MAGIC   = 0x494C4250; // "ILBP"
+static const unsigned int VERSION = 1;
+
+struct ProfileHeader {
+    unsigned int magic;
+    unsigned int version;
+    int nprocs;
+    int num_heavy;
+    double threshold_ratio;
+};
+
+// Write profile file (rank 0 only)
+bool write_profile(const char *filepath, int nprocs,
+                   const double *rank_times,
+                   const int *heavy_ranks, int num_heavy,
+                   double threshold_ratio);
+
+// Read profile file (rank 0 reads, then broadcasts to all)
+// Returns true if file found and valid for current nprocs
+bool read_profile(const char *filepath, int current_nprocs,
+                  int *heavy_ranks, int &num_heavy,
+                  double *rank_times, MPI_Comm comm);
+
+// Identify heavy ranks: those with time > threshold_ratio * mean
+int identify_heavy_ranks(const double *rank_times, int nprocs,
+                         double threshold_ratio,
+                         int *heavy_ranks, int max_heavy);
+
+} // namespace InterpLBProfile
+
+#endif /* INTERP_LB_PROFILE_H */

AMSS_NCKU_source/interp_lb_profile_data.h

@@ -0,0 +1,27 @@
+/* Auto-generated from interp_lb_profile.bin — do not edit */
+#ifndef INTERP_LB_PROFILE_DATA_H
+#define INTERP_LB_PROFILE_DATA_H
+
+#define INTERP_LB_NPROCS 64
+#define INTERP_LB_NUM_HEAVY 4
+
+static const int interp_lb_heavy_blocks[4] = {27, 35, 28, 36};
+
+/* Split table: {block_id, r_left, r_right} */
+static const int interp_lb_splits[4][3] = {
+    {27, 26, 27},
+    {35, 34, 35},
+    {28, 28, 29},
+    {36, 36, 37},
+};
+
+/* Rank remap for displaced neighbor blocks */
+static const int interp_lb_num_remaps = 4;
+static const int interp_lb_remaps[][2] = {
+    {26, 25},
+    {29, 30},
+    {34, 33},
+    {37, 38},
+};
+
+#endif /* INTERP_LB_PROFILE_DATA_H */

AMSS_NCKU_source/kodiss.f90

@@ -65,6 +65,8 @@ real*8,intent(in) :: eps
 !                       dx^4
 
 !  note the sign (-1)^r-1, now r=2
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
+!DIR$ UNROLL PARTIAL(4)
   do k=1,ex(3)
   do j=1,ex(2)
   do i=1,ex(1)

AMSS_NCKU_source/kodiss_c.C

@@ -1,4 +1,4 @@
-#include "xh_tool.h"
+#include "tool.h"
 
 /*
  * C 版 kodis
@@ -48,14 +48,7 @@ void kodis(const int ex[3],
     const size_t nz = (size_t)ex3 + 3;
     const size_t fh_size = nx * ny * nz;
 
-    static thread_local double *fh = NULL;
+    double *fh = (double*)malloc(fh_size * sizeof(double));
-    static thread_local size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
     if (!fh) return;
 
     // Fortran: call symmetry_bd(3,ex,f,fh,SoA)
@@ -112,5 +105,5 @@ void kodis(const int ex[3],
         }
     }
 
-    // free(fh);
+    free(fh);
 }

AMSS_NCKU_source/lopsided_c.C

@@ -1,4 +1,4 @@
-#include "xh_tool.h"
+#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)
@@ -60,14 +60,7 @@ void lopsided(const int ex[3],
     const size_t nz = (size_t)ex3 + 3;
     const size_t fh_size = nx * ny * nz;
 
-    static thread_local double *fh = NULL;
+    double *fh = (double*)malloc(fh_size * sizeof(double));
-    static thread_local size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
     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)
@@ -253,7 +246,7 @@ void lopsided(const int ex[3],
             }
         }
     }
-    // free(fh);
+    free(fh);
 }
 
 

AMSS_NCKU_source/lopsidediff.f90

@@ -487,6 +487,201 @@ subroutine lopsided(ex,X,Y,Z,f,f_rhs,Sfx,Sfy,Sfz,Symmetry,SoA)
 
   end subroutine lopsided
 
+!-----------------------------------------------------------------------------
+! Combined advection (lopsided) + Kreiss-Oliger dissipation (kodis)
+! Shares the symmetry_bd buffer fh, eliminating one full-grid copy per call.
+! Mathematically identical to calling lopsided then kodis separately.
+!-----------------------------------------------------------------------------
+subroutine lopsided_kodis(ex,X,Y,Z,f,f_rhs,Sfx,Sfy,Sfz,Symmetry,SoA,eps)
+  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)   :: f,Sfx,Sfy,Sfz
+
+  real*8,dimension(ex(1),ex(2),ex(3)),intent(inout):: f_rhs
+  real*8,dimension(3),intent(in) ::SoA
+  real*8,intent(in) :: eps
+
+!~~~~~~> local variables:
+! note index -2,-1,0, so we have 3 extra points
+  real*8,dimension(-2:ex(1),-2:ex(2),-2:ex(3))   :: fh
+  integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
+  real*8 :: dX,dY,dZ
+  real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
+  real*8,  parameter :: ZEO=0.d0,ONE=1.d0, F3=3.d0
+  real*8,  parameter :: TWO=2.d0,F6=6.0d0,F18=1.8d1
+  real*8,  parameter :: F12=1.2d1, F10=1.d1,EIT=8.d0
+  integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
+! kodis parameters
+  real*8, parameter :: SIX=6.d0,FIT=1.5d1,TWT=2.d1
+  real*8, parameter :: cof=6.4d1   ! 2^6
+
+  dX = X(2)-X(1)
+  dY = Y(2)-Y(1)
+  dZ = Z(2)-Z(1)
+
+  d12dx = ONE/F12/dX
+  d12dy = ONE/F12/dY
+  d12dz = ONE/F12/dZ
+
+  d2dx = ONE/TWO/dX
+  d2dy = ONE/TWO/dY
+  d2dz = ONE/TWO/dZ
+
+  imax = ex(1)
+  jmax = ex(2)
+  kmax = ex(3)
+
+  imin = 1
+  jmin = 1
+  kmin = 1
+  if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -2
+  if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -2
+  if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -2
+
+! Single symmetry_bd call shared by both advection and dissipation
+  call symmetry_bd(3,ex,f,fh,SoA)
+
+! ---- Advection (lopsided) loop ----
+! upper bound set ex-1 only for efficiency, 
+! the loop body will set ex 0 also
+  do k=1,ex(3)-1
+  do j=1,ex(2)-1
+  do i=1,ex(1)-1
+! x direction   
+    if(Sfx(i,j,k) > ZEO)then
+      if(i+3 <= imax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfx(i,j,k)*d12dx*(-F3*fh(i-1,j,k)-F10*fh(i,j,k)+F18*fh(i+1,j,k) &
+                                    -F6*fh(i+2,j,k)+    fh(i+3,j,k))
+     elseif(i+2 <= imax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfx(i,j,k)*d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
+
+     elseif(i+1 <= imax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfx(i,j,k)*d12dx*(-F3*fh(i+1,j,k)-F10*fh(i,j,k)+F18*fh(i-1,j,k) &
+                                    -F6*fh(i-2,j,k)+    fh(i-3,j,k))
+     endif
+   elseif(Sfx(i,j,k) < ZEO)then
+      if(i-3 >= imin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfx(i,j,k)*d12dx*(-F3*fh(i+1,j,k)-F10*fh(i,j,k)+F18*fh(i-1,j,k) &
+                                    -F6*fh(i-2,j,k)+    fh(i-3,j,k))
+     elseif(i-2 >= imin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfx(i,j,k)*d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
+
+     elseif(i-1 >= imin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfx(i,j,k)*d12dx*(-F3*fh(i-1,j,k)-F10*fh(i,j,k)+F18*fh(i+1,j,k) &
+                                    -F6*fh(i+2,j,k)+    fh(i+3,j,k))
+     endif
+   endif
+
+! y direction   
+    if(Sfy(i,j,k) > ZEO)then
+      if(j+3 <= jmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfy(i,j,k)*d12dy*(-F3*fh(i,j-1,k)-F10*fh(i,j,k)+F18*fh(i,j+1,k) &
+                                    -F6*fh(i,j+2,k)+    fh(i,j+3,k))
+     elseif(j+2 <= jmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfy(i,j,k)*d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
+
+     elseif(j+1 <= jmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfy(i,j,k)*d12dy*(-F3*fh(i,j+1,k)-F10*fh(i,j,k)+F18*fh(i,j-1,k) &
+                                    -F6*fh(i,j-2,k)+    fh(i,j-3,k))
+     endif
+   elseif(Sfy(i,j,k) < ZEO)then
+      if(j-3 >= jmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfy(i,j,k)*d12dy*(-F3*fh(i,j+1,k)-F10*fh(i,j,k)+F18*fh(i,j-1,k) &
+                                    -F6*fh(i,j-2,k)+    fh(i,j-3,k))
+     elseif(j-2 >= jmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfy(i,j,k)*d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
+
+     elseif(j-1 >= jmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfy(i,j,k)*d12dy*(-F3*fh(i,j-1,k)-F10*fh(i,j,k)+F18*fh(i,j+1,k) &
+                                    -F6*fh(i,j+2,k)+    fh(i,j+3,k))
+     endif
+   endif
+
+! z direction   
+    if(Sfz(i,j,k) > ZEO)then
+      if(k+3 <= kmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfz(i,j,k)*d12dz*(-F3*fh(i,j,k-1)-F10*fh(i,j,k)+F18*fh(i,j,k+1) &
+                                    -F6*fh(i,j,k+2)+    fh(i,j,k+3))
+     elseif(k+2 <= kmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfz(i,j,k)*d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
+
+     elseif(k+1 <= kmax)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfz(i,j,k)*d12dz*(-F3*fh(i,j,k+1)-F10*fh(i,j,k)+F18*fh(i,j,k-1) &
+                                    -F6*fh(i,j,k-2)+    fh(i,j,k-3))
+     endif
+   elseif(Sfz(i,j,k) < ZEO)then
+      if(k-3 >= kmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)-                                                   &
+                  Sfz(i,j,k)*d12dz*(-F3*fh(i,j,k+1)-F10*fh(i,j,k)+F18*fh(i,j,k-1) &
+                                    -F6*fh(i,j,k-2)+    fh(i,j,k-3))
+     elseif(k-2 >= kmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                           &
+                  Sfz(i,j,k)*d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
+
+     elseif(k-1 >= kmin)then
+     f_rhs(i,j,k)=f_rhs(i,j,k)+                                                   &
+                  Sfz(i,j,k)*d12dz*(-F3*fh(i,j,k-1)-F10*fh(i,j,k)+F18*fh(i,j,k+1) &
+                                    -F6*fh(i,j,k+2)+    fh(i,j,k+3))
+     endif
+   endif
+  enddo
+  enddo
+  enddo
+
+! ---- Dissipation (kodis) loop ----
+  if(eps > ZEO) then
+  do k=1,ex(3)
+  do j=1,ex(2)
+  do i=1,ex(1)
+
+  if(i-3 >= imin .and. i+3 <= imax .and. &
+     j-3 >= jmin .and. j+3 <= jmax .and. &
+     k-3 >= kmin .and. k+3 <= kmax) then
+   f_rhs(i,j,k)       = f_rhs(i,j,k) + eps/cof *( (     &
+                              (fh(i-3,j,k)+fh(i+3,j,k)) - &
+                          SIX*(fh(i-2,j,k)+fh(i+2,j,k)) + &
+                          FIT*(fh(i-1,j,k)+fh(i+1,j,k)) - &
+                          TWT* fh(i,j,k)            )/dX + &
+                                                  (     &
+                              (fh(i,j-3,k)+fh(i,j+3,k)) - &
+                          SIX*(fh(i,j-2,k)+fh(i,j+2,k)) + &
+                          FIT*(fh(i,j-1,k)+fh(i,j+1,k)) - &
+                          TWT* fh(i,j,k)            )/dY + &
+                                                  (     &
+                              (fh(i,j,k-3)+fh(i,j,k+3)) - &
+                          SIX*(fh(i,j,k-2)+fh(i,j,k+2)) + &
+                          FIT*(fh(i,j,k-1)+fh(i,j,k+1)) - &
+                          TWT* fh(i,j,k)            )/dZ )
+  endif
+
+  enddo
+  enddo
+  enddo
+  endif
+
+  return
+
+  end subroutine lopsided_kodis
+
 #elif (ghost_width == 4)
 ! sixth order code
 ! Compute advection terms in right hand sides of field equations

AMSS_NCKU_source/macrodef.fh

@@ -1,7 +1,23 @@
 
+#define tetradtype 2
+
+#define Cell
+
+#define ghost_width 3
+
+
+
+#define GAUGE 0
+
+#define CPBC_ghost_width  (ghost_width)
+
+#define ABV 0
+
+#define EScalar_CC 2
 
 #if 0
-note here
+
+define tetradtype
     v:r; u: phi; w: theta
     tetradtype 0
     v^a = (x,y,z)
@@ -14,70 +30,48 @@ tetradtype 2
     v_a = (x,y,z)
     orthonormal order: v,u,w
     m = (phi - i theta)/sqrt(2) following Frans, Eq.(8) of  PRD 75, 124018(2007)
-#endif
-#define tetradtype 2
 
-#if 0
+define Cell or Vertex
-note here
     Cell center or Vertex center
-#endif
-#define Cell
 
-#if 0
+define ghost_width
-note here
     2nd order: 2
     4th order: 3
     6th order: 4
     8th order: 5
-#endif
-#define ghost_width 3
 
-#if 0
+define WithShell
-note here
     use shell or not
-#endif
-#define WithShell
 
-#if 0
+define CPBC
-note here
     use constraint preserving boundary condition or not
     only affect Z4c
-#endif
+    CPBC only supports WithShell
-#define CPBC
 
-#if 0
+define GAUGE
-note here
-Gauge condition type
     0: B^i gauge
-1: David's puncture gauge
+    1: David puncture gauge
     2: MB B^i gauge
     3: RIT B^i gauge
     4: MB beta gauge (beta gauge not means Eq.(3) of PRD 84, 124006)
     5: RIT beta gauge (beta gauge not means Eq.(3) of PRD 84, 124006)
     6: MGB1 B^i gauge
     7: MGB2 B^i gauge
-#endif
-#define GAUGE 2
 
-#if 0
+define CPBC_ghost_width  (ghost_width)
     buffer points for CPBC boundary
-#endif
-#define CPBC_ghost_width  (ghost_width)
 
-#if 0
+define ABV
-using BSSN variable for constraint violation and psi4 calculation: 0
+    0: using BSSN variable for constraint violation and psi4 calculation
-using ADM variable for constraint violation and psi4 calculation: 1
+    1: using ADM variable for constraint violation and psi4 calculation
-#endif
-#define ABV 0
 
-#if 0
+define EScalar_CC
 Type of Potential and Scalar Distribution 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
+    2: shell with   phi(r) = phi0 * a2^2/(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(r) = phi0 * 0.5 * ( tanh((r+r0)/sigma) - tanh((r-r0)/sigma) )
+    4: a2 = +oo and phi(r) = phi0 * 0.5 * ( tanh((r+r0)/sigma) - tanh((r-r0)/sigma) )
     5: shell with   phi(r) = phi0 * Exp(-(r-r0)**2/sigma), V = 0
+
 #endif
-#define EScalar_CC 2
-
 

AMSS_NCKU_source/macrodef.h

@@ -6,93 +6,125 @@
 
 // application parameters
 
-/// ****
-// sommerfeld boundary type
-// 0: bam, 1: shibata
 #define SommerType 0
 
-/// ****
-// for Using Gauss-Legendre quadrature in theta direction
 #define GaussInt
 
-/// ****
+#define ABEtype 0
+
+//#define With_AHF
+#define Psi4type 0
+
+//#define Point_Psi4
+
+#define RPS 1
+
+#define AGM 0
+
+#define RPB 0
+
+#define MAPBH 1
+
+#define PSTR 0
+
+#define REGLEV 0
+
+//#define USE_GPU
+
+//#define CHECKDETAIL
+
+//#define FAKECHECK
+
+//
+// define SommerType
+//     sommerfeld boundary type
+//     0: bam
+//     1: shibata
+//
+// define GaussInt
+//     for Using Gauss-Legendre quadrature in theta direction
+//
+// define ABEtype
 //     0: BSSN vacuum
 //     1: coupled to scalar field
 //     2: Z4c vacuum
 //     3: coupled to Maxwell field
 //
-#define ABEtype 2
+// define With_AHF
-
-/// ****
 //     using Apparent Horizon Finder
-//#define With_AHF
+//
-
+// define Psi4type
-/// ****
 //     Psi4 calculation method
 //     0: EB method
 //     1: 4-D method
 //
-#define Psi4type 0
+// define Point_Psi4
-
-/// ****
 //     for Using point psi4 or not
-//#define Point_Psi4
+//
-
+// define RPS
-/// ****
 //     RestrictProlong in Step (0) or after Step (1)
-#define RPS 1
+//
-
+// define AGM
-/// ****
 //     Enforce algebra constraint
 //     for every RK4 sub step: 0
 //     only when iter_count == 3: 1
 //     after routine Step: 2
-#define AGM 0
+//
-
+// define RPB
-/// ****
 //     Restrict Prolong using BAM style 1 or old style 0
-#define RPB 0
+//
-
+// define MAPBH
-/// ****
 //     1: move Analysis out ot 4 sub steps and treat PBH with Euler method
-#define MAPBH 1
+//
-
+// define PSTR
-/// ****
+//     parallel structure
-// parallel structure, 0: level by level, 1: considering all levels, 2: as 1 but reverse the CPU order, 3: Frank's scheme
+//     0: level by level
-#define PSTR 0
+//     1: considering all levels
-
+//     2: as 1 but reverse the CPU order
-/// ****
+//     3: Frank's scheme
+//
+// define REGLEV
 //     regrid for every level or for all levels at a time
-// 0: for every level; 1: for all
+//     0: for every level;
-#define REGLEV 0
+//     1: for all
-
+//
-/// ****
+// define USE_GPU
 //     use gpu or not
-//#define USE_GPU
+//
-
+// define CHECKDETAIL
-/// ****
 //     use checkpoint for every process
-//#define CHECKDETAIL
+//
-
+// define FAKECHECK
-/// ****
 //     use FakeCheckPrepare to write CheckPoint
-//#define FAKECHECK
+//
+
 ////================================================================
 //  some basic parameters for numerical calculation
+////================================================================
+
 #define dim 3
 
-//#define Cell or Vertex in "microdef.fh"
+//#define Cell or Vertex in "macrodef.fh" 
 
-// ******
-// buffer point number for mesh refinement interface
 #define buffer_width 6
 
-// ******
-// buffer point number shell-box interface, on shell
 #define SC_width buffer_width
-// buffer point number shell-box interface, on box
+
 #define CS_width (2*buffer_width)
 
+//
+// define Cell or Vertex in "macrodef.fh" 
+//
+// define buffer_width
+//     buffer point number for mesh refinement interface
+//
+// define SC_width buffer_width
+//     buffer point number shell-box interface, on shell
+//
+// define CS_width
+//     buffer point number shell-box interface, on box
+//
+
 #if(buffer_width < ghost_width)
 #   error we always assume buffer_width>ghost_width
 #endif
@@ -110,3 +142,4 @@
 #define TINY 1e-10
 
 #endif   /* MICRODEF_H */
+

AMSS_NCKU_source/makefile

@@ -2,13 +2,40 @@
 
 include makefile.inc
 
+## polint(ordn=6) kernel selector:
+##   1 (default): barycentric fast path
+##   0          : fallback to Neville path
+POLINT6_USE_BARY ?= 1
+POLINT6_FLAG = -DPOLINT6_USE_BARYCENTRIC=$(POLINT6_USE_BARY)
+
+## ABE build flags selected by PGO_MODE (set in makefile.inc, default: opt)
+##   make                        -> opt  (PGO-guided, maximum performance)
+##   make PGO_MODE=instrument    -> instrument (Phase 1: collect fresh profile data)
+PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
+
+ifeq ($(PGO_MODE),instrument)
+## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
+CXXAPPFLAGS = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
+f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+              -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
+else
+## opt (default): maximum performance with PGO profile data
+CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(PROFDATA) \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
+f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(PROFDATA) \
+              -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
+endif
+
 .SUFFIXES: .o .f90 .C .for .cu
 
 .f90.o:
 	$(f90) $(f90appflags) -c $< -o $@
 
 .C.o:
-	${CXX} $(CXXAPPFLAGS) -qopenmp -c $< $(filein) -o $@
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
 
 .for.o:
 	$(f77) -c $< -o $@
@@ -16,20 +43,70 @@ include makefile.inc
 .cu.o:
 	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
 
+# CUDA rewrite of BSSN RHS (drop-in replacement for bssn_rhs_c + stencil helpers)
+bssn_rhs_cuda.o: bssn_rhs_cuda.cu macrodef.h
+	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
+
+# C rewrite of BSSN RHS kernel and helpers
+bssn_rhs_c.o: bssn_rhs_c.C
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+fderivs_c.o: fderivs_c.C
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+fdderivs_c.o: fdderivs_c.C
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+kodiss_c.o: kodiss_c.C
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+lopsided_c.o: lopsided_c.C
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+interp_lb_profile.o: interp_lb_profile.C interp_lb_profile.h
+	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
+
+## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
+TP_PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/TwoPunctureABE.profdata
+TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(TP_PROFDATA) \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
+
 TwoPunctures.o: TwoPunctures.C
-	${CXX} $(CXXAPPFLAGS) -qopenmp -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 TwoPunctureABE.o: TwoPunctureABE.C
-	${CXX} $(CXXAPPFLAGS) -qopenmp -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 # Input files
+
+## Kernel implementation switch (set USE_CXX_KERNELS=0 to fall back to Fortran)
+ifeq ($(USE_CXX_KERNELS),0)
+# Fortran mode: no C rewrite files; bssn_rhs.o is included via F90FILES below
+CFILES =
+else
+# C++ mode (default): C rewrite of bssn_rhs and helper kernels
+CFILES = bssn_rhs_c.o fderivs_c.o fdderivs_c.o kodiss_c.o lopsided_c.o
+endif
+
+# CUDA rewrite: bssn_rhs_cuda.o replaces all CFILES (stencils are built-in)
+CFILES_CUDA = bssn_rhs_cuda.o
+
+## RK4 kernel switch (independent from USE_CXX_KERNELS)
+ifeq ($(USE_CXX_RK4),1)
+CFILES += rungekutta4_rout_c.o
+CFILES_CUDA += rungekutta4_rout_c.o
+RK4_F90_OBJ =
+else
+RK4_F90_OBJ = rungekutta4_rout.o
+endif
+
 C++FILES = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
            cgh.o bssn_class.o surface_integral.o ShellPatch.o\
 	   bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
 	   bssnEM_class.o cpbc_util.o z4c_rhs_point.o checkpoint.o\
            Parallel_bam.o scalar_class.o transpbh.o NullShellPatch2.o\
-	   NullShellPatch2_Evo.o writefile_f.o xh_bssn_rhs.o xh_fdderivs.o xh_fderivs.o xh_kodiss.o xh_lopsided.o \
+	   NullShellPatch2_Evo.o writefile_f.o interp_lb_profile.o
-	   xh_global_interp.o xh_polint3.o
 	   
 C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
            cgh.o surface_integral.o ShellPatch.o\
@@ -39,9 +116,9 @@ C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o
 	   NullShellPatch2_Evo.o \
 	   bssn_gpu_class.o bssn_step_gpu.o bssn_macro.o writefile_f.o
 
-F90FILES = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
+F90FILES_BASE = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
 	   prolongrestrict_cell.o prolongrestrict_vertex.o\
-	   rungekutta4_rout.o bssn_rhs.o diff_new.o kodiss.o kodiss_sh.o\
+	   $(RK4_F90_OBJ) diff_new.o kodiss.o kodiss_sh.o\
 	   lopsidediff.o sommerfeld_rout.o getnp4.o diff_new_sh.o\
 	   shellfunctions.o bssn_rhs_ss.o Set_Rho_ADM.o\
            getnp4EScalar.o bssnEScalar_rhs.o bssn_constraint.o ricci_gamma.o\
@@ -52,6 +129,14 @@ F90FILES = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
 	   scalar_rhs.o initial_scalar.o NullEvol2.o initial_null2.o\
 	   NullNews2.o tool_f.o
 
+ifeq ($(USE_CXX_KERNELS),0)
+# Fortran mode: include original bssn_rhs.o
+F90FILES = $(F90FILES_BASE) bssn_rhs.o
+else
+# C++ mode (default): bssn_rhs.o replaced by C++ kernel
+F90FILES = $(F90FILES_BASE)
+endif
+
 F77FILES = zbesh.o
 
 AHFDOBJS = expansion.o expansion_Jacobian.o patch.o coords.o patch_info.o patch_interp.o patch_system.o \
@@ -64,7 +149,7 @@ TwoPunctureFILES = TwoPunctureABE.o TwoPunctures.o
 CUDAFILES = bssn_gpu.o bssn_gpu_rhs_ss.o
 
 # file dependences
-$(C++FILES) $(C++FILESGPU) $(F90FILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
+$(C++FILES) $(C++FILES_GPU) $(F90FILES) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
 
 $(C++FILES): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
 	     misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
@@ -73,7 +158,7 @@ $(C++FILES): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
              fadmquantites_bssn.h cpbc.h getnp4.h initial_null.h NullEvol.h\
 	     NullShellPatch.h initial_maxwell.h bssnEM_class.h getnpem2.h\
 	     empart.h NullNews.h kodiss.h Parallel_bam.h ricci_gamma.h\
-             initial_null2.h NullShellPatch2.h xh_bssn_rhs_compute.h xh_global_interp.h
+             initial_null2.h NullShellPatch2.h 
              
 $(C++FILES_GPU): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
 	     misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
@@ -87,7 +172,7 @@ $(C++FILES_GPU): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h
              
 $(AHFDOBJS): cctk.h cctk_Config.h cctk_Types.h cctk_Constants.h myglobal.h
 
-$(C++FILES) $(C++FILES_GPU) $(AHFDOBJS) $(CUDAFILES): macrodef.h
+$(C++FILES) $(C++FILES_GPU) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.h
 
 TwoPunctureFILES: TwoPunctures.h
 
@@ -96,14 +181,17 @@ $(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
 misc.o : zbesh.o
 
 # projects
-ABE: $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) 
+ABE: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
-	$(CLINKER) $(CXXAPPFLAGS) -qopenmp -o $@ $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS) -lcudart $(CUDA_LIB_PATH)
 
-ABEGPU: $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
+ABE_CUDA: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
-	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS) -lcudart $(CUDA_LIB_PATH)
+
+ABEGPU: $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
 
 TwoPunctureABE: $(TwoPunctureFILES)
-	$(CLINKER) $(CXXAPPFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
+	$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
 
 clean:
-	rm *.o ABE ABEGPU TwoPunctureABE make.log -f
+	rm *.o ABE ABE_CUDA ABEGPU TwoPunctureABE make.log -f

AMSS_NCKU_source/makefile.inc

@@ -8,18 +8,51 @@ filein  = -I/usr/include/ -I${MKLROOT}/include
 
 ## Using sequential MKL (OpenMP disabled for better single-threaded performance)
 ## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
-LDLIBS  = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl
+LDLIBS  = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
+
+## Memory allocator switch
+##   1 (default) : link Intel oneTBB allocator (libtbbmalloc)
+##   0           : use system default allocator (ptmalloc)
+USE_TBBMALLOC ?= 1
+TBBMALLOC_SO ?= /home/intel/oneapi/2025.3/lib/libtbbmalloc.so
+ifneq ($(wildcard $(TBBMALLOC_SO)),)
+TBBMALLOC_LIBS = -Wl,--no-as-needed $(TBBMALLOC_SO) -Wl,--as-needed
+else
+TBBMALLOC_LIBS = -Wl,--no-as-needed -ltbbmalloc -Wl,--as-needed
+endif
+ifeq ($(USE_TBBMALLOC),1)
+LDLIBS := $(TBBMALLOC_LIBS) $(LDLIBS)
+endif
+
+## PGO build mode switch (ABE only; TwoPunctureABE always uses opt flags)
+##   opt        : (default) maximum performance with PGO profile-guided optimization
+##   instrument : PGO Phase 1 instrumentation to collect fresh profile data
+PGO_MODE ?= opt
+
+## Interp_Points load balance profiling mode
+##   off        : (default) no load balance instrumentation
+##   profile    : Pass 1 — instrument Interp_Points to collect timing profile
+##   optimize   : Pass 2 — read profile and apply block rebalancing
+INTERP_LB_MODE ?= off
+
+ifeq ($(INTERP_LB_MODE),profile)
+INTERP_LB_FLAGS = -DINTERP_LB_PROFILE
+else ifeq ($(INTERP_LB_MODE),optimize)
+INTERP_LB_FLAGS = -DINTERP_LB_OPTIMIZE
+else
+INTERP_LB_FLAGS =
+endif
+
+## Kernel implementation switch
+##   1 (default) : use C++ rewrite of bssn_rhs and helper kernels (faster)
+##   0           : fall back to original Fortran kernels
+USE_CXX_KERNELS ?= 1
+
+## RK4 kernel implementation switch
+##   1 (default) : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
+##   0           : use original Fortran rungekutta4_rout.o
+USE_CXX_RK4 ?= 1
 
-## Aggressive optimization flags + PGO Phase 2 (profile-guided optimization)
-## -fprofile-instr-use: use collected profile data to guide optimization decisions
-##   (branch prediction, basic block layout, inlining, loop unrolling)
-PROFDATA     = /home/hxh/AMSS-NCKU/pgo_profile/default.profdata
-CXXAPPFLAGS  = -O3 -xHost -fp-model fast=2 -fma -ipo \
-               -fprofile-instr-use=$(PROFDATA) \
-               -Dfortran3 -Dnewc -I${MKLROOT}/include
-f90appflags  = -O3 -xHost -fp-model fast=2 -fma -ipo \
-               -fprofile-instr-use=$(PROFDATA) \
-               -align array64byte -fpp -I${MKLROOT}/include
 f90          = ifx
 f77          = ifx
 CXX          = icpx
@@ -29,4 +62,4 @@ CLINKER      = mpiicpx
 Cu = nvcc
 CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
 #CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
-CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc
+CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc -arch=sm_80

AMSS_NCKU_source/prolongrestrict_cell.f90

@@ -217,7 +217,6 @@
   real*8,dimension(2*ghost_width) :: X,Y,Z
   real*8, dimension(2*ghost_width,2*ghost_width) :: tmp2
   real*8, dimension(2*ghost_width) :: tmp1
-  real*8 :: ddy
   real*8,dimension(3) :: ccp
 
 #if (ghost_width == 2)
@@ -580,7 +579,7 @@
             tmp1(ghost_width-cxI(1)+cxB(1)  :ghost_width-cxI(1)+cxT(1)  ) = funf(cxB(1):cxT(1),j,k)
          endif
 
-         call polint(X,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(X,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for y direction
        elseif(sum(fg).eq.2.and.fg(2) .eq. 0.and. &
@@ -690,7 +689,7 @@
             tmp1(ghost_width-cxI(2)+cxB(2)  :ghost_width-cxI(2)+cxT(2)  ) = funf(i,cxB(2):cxT(2),k)
          endif
 
-         call polint(Y,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Y,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for z direction
        elseif(sum(fg).eq.2.and.fg(3) .eq. 0.and. &
@@ -802,7 +801,7 @@
             tmp1(ghost_width-cxI(3)+cxB(3)  :ghost_width-cxI(3)+cxT(3)  ) = funf(i,j,cxB(3):cxT(3))
          endif
 
-         call polint(Z,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Z,tmp1,funf(i,j,k),2*ghost_width)
 
 #else
 
@@ -1934,18 +1933,35 @@
 ! when if=1 -> ic=0, this is different to vertex center grid 
   real*8, dimension(-2:extc(1),-2:extc(2),-2:extc(3))   :: funcc
   integer,dimension(3) :: cxI
-  integer :: i,j,k,ii,jj,kk
+  integer :: i,j,k,ii,jj,kk,px,py,pz
   real*8, dimension(6,6) :: tmp2
   real*8, dimension(6) :: tmp1
+  integer, dimension(extf(1)) :: cix
+  integer, dimension(extf(2)) :: ciy
+  integer, dimension(extf(3)) :: ciz
+  integer, dimension(extf(1)) :: pix
+  integer, dimension(extf(2)) :: piy
+  integer, dimension(extf(3)) :: piz
 
   real*8, parameter :: C1=7.7d1/8.192d3,C2=-6.93d2/8.192d3,C3=3.465d3/4.096d3
   real*8, parameter :: C6=6.3d1/8.192d3,C5=-4.95d2/8.192d3,C4=1.155d3/4.096d3
+  real*8, dimension(6,2), parameter :: WC = reshape((/&
+      C1,C2,C3,C4,C5,C6,&
+      C6,C5,C4,C3,C2,C1/), (/6,2/))
 
   integer::imini,imaxi,jmini,jmaxi,kmini,kmaxi
   integer::imino,imaxo,jmino,jmaxo,kmino,kmaxo
+  integer::maxcx,maxcy,maxcz
 
   real*8,dimension(3) :: CD,FD
-  
+  real*8 :: tmp_yz(extc(1), 6)      ! 存储整条 X 线上 6 个 Y 轴偏置的 Z 向插值结果
+  real*8 :: tmp_xyz_line(-2:extc(1))   ! 包含 X 向 6 点模板访问所需下界
+  real*8 :: v1, v2, v3, v4, v5, v6
+  integer :: ic, jc, kc, ix_offset,ix,iy,iz,jc_min,jc_max,ic_min,ic_max,kc_min,kc_max
+  integer :: i_lo, i_hi, j_lo, j_hi, k_lo, k_hi
+  logical :: need_full_symmetry
+  real*8 :: res_line
+  real*8 :: tmp_z_slab(-2:extc(1), -2:extc(2))  ! 包含 Y/X 向模板访问所需下界
   if(wei.ne.3)then
      write(*,*)"prolongrestrict.f90::prolong3: this routine only surport 3 dimension"
      write(*,*)"dim = ",wei
@@ -2020,145 +2036,140 @@
           return
   endif
 
+  do i = imino,imaxo
+     ii = i + lbf(1) - 1
+     cix(i) = ii/2 - lbc(1) + 1
+     if(ii/2*2 == ii)then
+        pix(i) = 1
+     else
+        pix(i) = 2
+     endif
+  enddo
+  do j = jmino,jmaxo
+     jj = j + lbf(2) - 1
+     ciy(j) = jj/2 - lbc(2) + 1
+     if(jj/2*2 == jj)then
+        piy(j) = 1
+     else
+        piy(j) = 2
+     endif
+  enddo
+  do k = kmino,kmaxo
+     kk = k + lbf(3) - 1
+     ciz(k) = kk/2 - lbc(3) + 1
+     if(kk/2*2 == kk)then
+        piz(k) = 1
+     else
+        piz(k) = 2
+     endif
+  enddo
+
+  ic_min = minval(cix(imino:imaxo))
+  ic_max = maxval(cix(imino:imaxo))
+  jc_min = minval(ciy(jmino:jmaxo))
+  jc_max = maxval(ciy(jmino:jmaxo))
+  kc_min = minval(ciz(kmino:kmaxo))
+  kc_max = maxval(ciz(kmino:kmaxo))
+
+  maxcx = ic_max
+  maxcy = jc_max
+  maxcz = kc_max
+  if(maxcx+3 > extc(1) .or. maxcy+3 > extc(2) .or. maxcz+3 > extc(3))then
+     write(*,*)"error in prolong"
+     return
+  endif
+
+  i_lo = ic_min - 2
+  i_hi = ic_max + 3
+  j_lo = jc_min - 2
+  j_hi = jc_max + 3
+  k_lo = kc_min - 2
+  k_hi = kc_max + 3
+  need_full_symmetry = (i_lo < 1) .or. (j_lo < 1) .or. (k_lo < 1)
+  if(need_full_symmetry)then
      call symmetry_bd(3,extc,func,funcc,SoA)
+  else
+     funcc(i_lo:i_hi,j_lo:j_hi,k_lo:k_hi) = func(i_lo:i_hi,j_lo:j_hi,k_lo:k_hi)
+  endif
+
+     ! 对每个 k（pz, kc 固定）预计算 Z 向插值的 2D 切片
+
+do k = kmino, kmaxo
+    pz = piz(k); kc = ciz(k)
+    ! --- Pass 1: Z 方向，只算一次 ---
+    do iy = jc_min-2, jc_max+3   ! 仅需的 iy 范围（对应 jc-2:jc+3）
+        do ii = ic_min-2, ic_max+3  ! 仅需的 ii 范围（对应 cix-2:cix+3）
+            tmp_z_slab(ii, iy) = sum(WC(:,pz) * funcc(ii, iy, kc-2:kc+3))
+        end do
+    end do
+
+    do j = jmino, jmaxo
+        py = piy(j); jc = ciy(j)
+        ! --- Pass 2: Y 方向 ---
+        do ii = ic_min-2, ic_max+3
+            tmp_xyz_line(ii) = sum(WC(:,py) * tmp_z_slab(ii, jc-2:jc+3))
+        end do
+        ! --- Pass 3: X 方向 ---
+        do i = imino, imaxo
+            funf(i,j,k) = sum(WC(:,pix(i)) * tmp_xyz_line(cix(i)-2:cix(i)+3))
+        end do
+    end do
+end do
 
 !~~~~~~> prolongation start...
-  do k = kmino,kmaxo
-   do j = jmino,jmaxo
-    do i = imino,imaxo
-       cxI(1) = i
-       cxI(2) = j
-       cxI(3) = k
-! change to coarse level reference
-!|---*--- ---*--- ---*--- ---*--- ---*--- ---*--- ---*--- ---*---| 
-!|=======x===============x===============x===============x=======|
-       cxI = (cxI+lbf-1)/2
-! change to array index      
-       cxI = cxI - lbc + 1
-
-       if(any(cxI+3 > extc)) write(*,*)"error in prolong"
-       ii=i+lbf(1)-1
-       jj=j+lbf(2)-1
-       kk=k+lbf(3)-1
 #if 0
-       if(ii/2*2==ii)then
+ do k = kmino, kmaxo
-         if(jj/2*2==jj)then
+     pz = piz(k)
-           if(kk/2*2==kk)then
+     kc = ciz(k)
-             tmp2= C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
-             funf(i,j,k)= C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
-           else
-             tmp2= C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
-             funf(i,j,k)=  C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
-           endif
-         else
-           if(kk/2*2==kk)then
-             tmp2= C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
-             funf(i,j,k)= C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
-           else
-             tmp2= C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
-             funf(i,j,k)=  C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
-           endif
-         endif
-       else
-         if(jj/2*2==jj)then
-           if(kk/2*2==kk)then               
-             tmp2= C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
-             funf(i,j,k)= C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
-           else
-             tmp2= C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
-             funf(i,j,k)=  C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
-           endif
-         else
-           if(kk/2*2==kk)then
-             tmp2= C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
-             funf(i,j,k)= C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
-           else
-             tmp2= C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
-             funf(i,j,k)=  C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
-           endif
-         endif
-       endif
-#else 
-       if(kk/2*2==kk)then
-             tmp2= C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-       else
-             tmp2= C6*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-2)+&
-                   C5*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)-1)+&
-                   C4*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)  )+&
-                   C3*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+1)+&
-                   C2*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+2)+&
-                   C1*funcc(cxI(1)-2:cxI(1)+3,cxI(2)-2:cxI(2)+3,cxI(3)+3)
-       endif
 
-       if(jj/2*2==jj)then
+     do j = jmino, jmaxo
-             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
+        py = piy(j)
-       else
+        jc = ciy(j)
-             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
-       endif
 
-       if(ii/2*2==ii)then
+! --- 步骤 1 & 2 融合：分段处理 X 轴，提升 Cache 命中率 ---
-             funf(i,j,k)= C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
+        ! 我们将 ii 循环逻辑重组，减少对 funcc 的跨行重复访问
-       else
+        do ii = 1, extc(1)
-             funf(i,j,k)= C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
+           ! 1. 先做 Z 方向的 6 条线插值（针对当前的 ii 和当前的 6 个 iy）
-       endif
+           ! 我们直接在这里把 Y 方向的加权也做了，省去 tmp_yz 数组
+           ! 这样 funcc 的数据读进来后立即完成所有维度的贡献，不再写回内存
+           
+           res_line = 0.0d0
+           do jj = 1, 6
+              iy = jc - 3 + jj
+              ! 这一行代码是核心：一次性完成 Z 插值并加上 Y 的权重
+              ! 编译器会把 WC(jj, py) 存在寄存器里
+              res_line = res_line + WC(jj, py) * ( &
+                         WC(1, pz) * funcc(ii, iy, kc-2) + &
+                         WC(2, pz) * funcc(ii, iy, kc-1) + &
+                         WC(3, pz) * funcc(ii, iy, kc  ) + &
+                         WC(4, pz) * funcc(ii, iy, kc+1) + &
+                         WC(5, pz) * funcc(ii, iy, kc+2) + &
+                         WC(6, pz) * funcc(ii, iy, kc+3) )
+           end do
+           tmp_xyz_line(ii) = res_line
+        end do
+
+
+
+
+        ! 3. 【降维：X 向】最后在最内层只处理 X 方向的 6 点加权
+        ! 此时每个点的计算量从原来的 200+ 次乘法降到了仅 6 次
+        do i = imino, imaxo
+           px = pix(i)
+           ic = cix(i)
+           
+           ! 直接从预计算好的 line 中读取连续的 6 个点
+           ! ic-2 到 ic+3 对应原始 6 点算子
+           funf(i,j,k) = WC(1,px)*tmp_xyz_line(ic-2) + &
+                         WC(2,px)*tmp_xyz_line(ic-1) + &
+                         WC(3,px)*tmp_xyz_line(ic  ) + &
+                         WC(4,px)*tmp_xyz_line(ic+1) + &
+                         WC(5,px)*tmp_xyz_line(ic+2) + &
+                         WC(6,px)*tmp_xyz_line(ic+3)
+        end do
+     end do
+  end do
 #endif
-    enddo
-   enddo
-  enddo
-
   return
 
   end subroutine prolong3
@@ -2358,6 +2369,13 @@
 
   real*8,dimension(3) :: CD,FD
 
+  real*8 :: tmp_xz_plane(-1:extf(1), 6)
+  real*8 :: tmp_x_line(-1:extf(1))
+  integer :: fi, fj, fk, ii, jj, kk
+  integer :: fi_min, fi_max, ii_lo, ii_hi
+  integer :: fj_min, fj_max, fk_min, fk_max, jj_lo, jj_hi, kk_lo, kk_hi
+  logical :: need_full_symmetry
+
   if(wei.ne.3)then
      write(*,*)"prolongrestrict.f90::restrict3: this routine only surport 3 dimension"
      write(*,*)"dim = ",wei
@@ -2436,9 +2454,86 @@
           stop
   endif
 
+  ! 仅计算 X 向最终写回所需的窗口：
+  ! func(i,j,k) 只访问 tmp_x_line(fi-2:fi+3)
+  fi_min = 2*(imino + lbc(1) - 1) - 1 - lbf(1) + 1
+  fi_max = 2*(imaxo + lbc(1) - 1) - 1 - lbf(1) + 1
+  fj_min = 2*(jmino + lbc(2) - 1) - 1 - lbf(2) + 1
+  fj_max = 2*(jmaxo + lbc(2) - 1) - 1 - lbf(2) + 1
+  fk_min = 2*(kmino + lbc(3) - 1) - 1 - lbf(3) + 1
+  fk_max = 2*(kmaxo + lbc(3) - 1) - 1 - lbf(3) + 1
+  ii_lo = fi_min - 2
+  ii_hi = fi_max + 3
+  jj_lo = fj_min - 2
+  jj_hi = fj_max + 3
+  kk_lo = fk_min - 2
+  kk_hi = fk_max + 3
+  if(ii_lo < -1 .or. ii_hi > extf(1) .or. &
+     jj_lo < -1 .or. jj_hi > extf(2) .or. &
+     kk_lo < -1 .or. kk_hi > extf(3))then
+      write(*,*)"restrict3: invalid stencil window"
+      write(*,*)"ii=",ii_lo,ii_hi," jj=",jj_lo,jj_hi," kk=",kk_lo,kk_hi
+      write(*,*)"extf=",extf
+      stop
+  endif
+  need_full_symmetry = (ii_lo < 1) .or. (jj_lo < 1) .or. (kk_lo < 1)
+  if(need_full_symmetry)then
       call symmetry_bd(2,extf,funf,funff,SoA)
+  else
+      funff(ii_lo:ii_hi,jj_lo:jj_hi,kk_lo:kk_hi) = funf(ii_lo:ii_hi,jj_lo:jj_hi,kk_lo:kk_hi)
+  endif
 
 !~~~~~~> restriction start...
+do k = kmino, kmaxo
+    fk = 2*(k + lbc(3) - 1) - 1 - lbf(3) + 1
+
+    do j = jmino, jmaxo
+        fj = 2*(j + lbc(2) - 1) - 1 - lbf(2) + 1
+        
+        ! 优化点 1: 显式展开 Z 方向计算，减少循环开销
+        ! 确保 ii 循环是最内层且连续访问
+        !DIR$ VECTOR ALWAYS
+        do ii = ii_lo, ii_hi
+            ! 预计算当前 j 对应的 6 行在 Z 方向的压缩结果
+            ! 这里直接硬编码 jj 的偏移，彻底消除一层循环
+            tmp_xz_plane(ii, 1) = C1*(funff(ii,fj-2,fk-2)+funff(ii,fj-2,fk+3)) + &
+                                  C2*(funff(ii,fj-2,fk-1)+funff(ii,fj-2,fk+2)) + &
+                                  C3*(funff(ii,fj-2,fk  )+funff(ii,fj-2,fk+1))
+            tmp_xz_plane(ii, 2) = C1*(funff(ii,fj-1,fk-2)+funff(ii,fj-1,fk+3)) + &
+                                  C2*(funff(ii,fj-1,fk-1)+funff(ii,fj-1,fk+2)) + &
+                                  C3*(funff(ii,fj-1,fk  )+funff(ii,fj-1,fk+1))
+            tmp_xz_plane(ii, 3) = C1*(funff(ii,fj  ,fk-2)+funff(ii,fj  ,fk+3)) + &
+                                  C2*(funff(ii,fj  ,fk-1)+funff(ii,fj  ,fk+2)) + &
+                                  C3*(funff(ii,fj  ,fk  )+funff(ii,fj  ,fk+1))
+            tmp_xz_plane(ii, 4) = C1*(funff(ii,fj+1,fk-2)+funff(ii,fj+1,fk+3)) + &
+                                  C2*(funff(ii,fj+1,fk-1)+funff(ii,fj+1,fk+2)) + &
+                                  C3*(funff(ii,fj+1,fk  )+funff(ii,fj+1,fk+1))
+            tmp_xz_plane(ii, 5) = C1*(funff(ii,fj+2,fk-2)+funff(ii,fj+2,fk+3)) + &
+                                  C2*(funff(ii,fj+2,fk-1)+funff(ii,fj+2,fk+2)) + &
+                                  C3*(funff(ii,fj+2,fk  )+funff(ii,fj+2,fk+1))
+            tmp_xz_plane(ii, 6) = C1*(funff(ii,fj+3,fk-2)+funff(ii,fj+3,fk+3)) + &
+                                  C2*(funff(ii,fj+3,fk-1)+funff(ii,fj+3,fk+2)) + &
+                                  C3*(funff(ii,fj+3,fk  )+funff(ii,fj+3,fk+1))
+        end do
+
+        ! 优化点 2: 同样向量化 Y 方向压缩
+        !DIR$ VECTOR ALWAYS
+        do ii = ii_lo, ii_hi
+            tmp_x_line(ii) = C1*(tmp_xz_plane(ii, 1) + tmp_xz_plane(ii, 6)) + &
+                            C2*(tmp_xz_plane(ii, 2) + tmp_xz_plane(ii, 5)) + &
+                            C3*(tmp_xz_plane(ii, 3) + tmp_xz_plane(ii, 4))
+        end do
+
+        ! 优化点 3: 最终写入，利用已经缓存在 tmp_x_line 的数据
+        do i = imino, imaxo
+            fi = 2*(i + lbc(1) - 1) - 1 - lbf(1) + 1
+            func(i, j, k) = C1*(tmp_x_line(fi-2) + tmp_x_line(fi+3)) + &
+                            C2*(tmp_x_line(fi-1) + tmp_x_line(fi+2)) + &
+                            C3*(tmp_x_line(fi  ) + tmp_x_line(fi+1))
+        end do
+    end do
+end do
+#if 0
   do k = kmino,kmaxo
    do j = jmino,jmaxo
     do i = imino,imaxo
@@ -2462,7 +2557,7 @@
     enddo
    enddo
   enddo
-  
+#endif
   return
 
   end subroutine restrict3

AMSS_NCKU_source/prolongrestrict_vertex.f90

@@ -217,7 +217,6 @@
   real*8,dimension(2*ghost_width) :: X,Y,Z
   real*8, dimension(2*ghost_width,2*ghost_width) :: tmp2
   real*8, dimension(2*ghost_width) :: tmp1
-  real*8 :: ddy
 
 #if (ghost_width == 2)
   real*8, parameter :: C1=-1.d0/16,C2=9.d0/16
@@ -470,7 +469,7 @@
 
          tmp1(cxB(1)+ghost_width-i+1:cxT(1)+ghost_width-i+1) = fh(cxB(1):cxT(1),j,k)
 
-         call polint(X,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(X,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for y direction
        elseif (fg(2) .eq. 0)then
@@ -529,7 +528,7 @@
 
          tmp1(cxB(2)+ghost_width-j+1:cxT(2)+ghost_width-j+1) = fh(i,cxB(2):cxT(2),k)
 
-         call polint(Y,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Y,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for z direction
        else
@@ -588,7 +587,7 @@
 
          tmp1(cxB(3)+ghost_width-k+1:cxT(3)+ghost_width-k+1) = fh(i,j,cxB(3):cxT(3))
 
-         call polint(Z,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Z,tmp1,funf(i,j,k),2*ghost_width)
 
        endif
       

AMSS_NCKU_source/rungekutta4_rout_c.C

@@ -0,0 +1,155 @@
+#include "rungekutta4_rout.h"
+#include <cstdio>
+#include <cstdlib>
+#include <cstddef>
+#include <immintrin.h>
+
+namespace {
+
+inline void rk4_stage0(std::size_t n,
+                       const double *__restrict f0,
+                       const double *__restrict frhs,
+                       double *__restrict f1,
+                       double c) {
+    std::size_t i = 0;
+#if defined(__AVX512F__)
+    const __m512d vc = _mm512_set1_pd(c);
+    for (; i + 7 < n; i += 8) {
+        const __m512d v0 = _mm512_loadu_pd(f0 + i);
+        const __m512d vr = _mm512_loadu_pd(frhs + i);
+        _mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, vr, v0));
+    }
+#elif defined(__AVX2__)
+    const __m256d vc = _mm256_set1_pd(c);
+    for (; i + 3 < n; i += 4) {
+        const __m256d v0 = _mm256_loadu_pd(f0 + i);
+        const __m256d vr = _mm256_loadu_pd(frhs + i);
+        _mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, vr, v0));
+    }
+#endif
+#pragma ivdep
+    for (; i < n; ++i) {
+        f1[i] = f0[i] + c * frhs[i];
+    }
+}
+
+inline void rk4_rhs_accum(std::size_t n,
+                          const double *__restrict f1,
+                          double *__restrict frhs) {
+    std::size_t i = 0;
+#if defined(__AVX512F__)
+    const __m512d v2 = _mm512_set1_pd(2.0);
+    for (; i + 7 < n; i += 8) {
+        const __m512d v1 = _mm512_loadu_pd(f1 + i);
+        const __m512d vrhs = _mm512_loadu_pd(frhs + i);
+        _mm512_storeu_pd(frhs + i, _mm512_fmadd_pd(v2, v1, vrhs));
+    }
+#elif defined(__AVX2__)
+    const __m256d v2 = _mm256_set1_pd(2.0);
+    for (; i + 3 < n; i += 4) {
+        const __m256d v1 = _mm256_loadu_pd(f1 + i);
+        const __m256d vrhs = _mm256_loadu_pd(frhs + i);
+        _mm256_storeu_pd(frhs + i, _mm256_fmadd_pd(v2, v1, vrhs));
+    }
+#endif
+#pragma ivdep
+    for (; i < n; ++i) {
+        frhs[i] = frhs[i] + 2.0 * f1[i];
+    }
+}
+
+inline void rk4_f1_from_f0_f1(std::size_t n,
+                              const double *__restrict f0,
+                              double *__restrict f1,
+                              double c) {
+    std::size_t i = 0;
+#if defined(__AVX512F__)
+    const __m512d vc = _mm512_set1_pd(c);
+    for (; i + 7 < n; i += 8) {
+        const __m512d v0 = _mm512_loadu_pd(f0 + i);
+        const __m512d v1 = _mm512_loadu_pd(f1 + i);
+        _mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, v1, v0));
+    }
+#elif defined(__AVX2__)
+    const __m256d vc = _mm256_set1_pd(c);
+    for (; i + 3 < n; i += 4) {
+        const __m256d v0 = _mm256_loadu_pd(f0 + i);
+        const __m256d v1 = _mm256_loadu_pd(f1 + i);
+        _mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, v1, v0));
+    }
+#endif
+#pragma ivdep
+    for (; i < n; ++i) {
+        f1[i] = f0[i] + c * f1[i];
+    }
+}
+
+inline void rk4_stage3(std::size_t n,
+                       const double *__restrict f0,
+                       double *__restrict f1,
+                       const double *__restrict frhs,
+                       double c) {
+    std::size_t i = 0;
+#if defined(__AVX512F__)
+    const __m512d vc = _mm512_set1_pd(c);
+    for (; i + 7 < n; i += 8) {
+        const __m512d v0 = _mm512_loadu_pd(f0 + i);
+        const __m512d v1 = _mm512_loadu_pd(f1 + i);
+        const __m512d vr = _mm512_loadu_pd(frhs + i);
+        _mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, _mm512_add_pd(v1, vr), v0));
+    }
+#elif defined(__AVX2__)
+    const __m256d vc = _mm256_set1_pd(c);
+    for (; i + 3 < n; i += 4) {
+        const __m256d v0 = _mm256_loadu_pd(f0 + i);
+        const __m256d v1 = _mm256_loadu_pd(f1 + i);
+        const __m256d vr = _mm256_loadu_pd(frhs + i);
+        _mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, _mm256_add_pd(v1, vr), v0));
+    }
+#endif
+#pragma ivdep
+    for (; i < n; ++i) {
+        f1[i] = f0[i] + c * (f1[i] + frhs[i]);
+    }
+}
+
+} // namespace
+
+extern "C" {
+
+int f_rungekutta4_rout(int *ex, double &dT,
+                       double *f0, double *f1, double *f_rhs,
+                       int &RK4) {
+    const std::size_t n = static_cast<std::size_t>(ex[0]) *
+                          static_cast<std::size_t>(ex[1]) *
+                          static_cast<std::size_t>(ex[2]);
+    const double *const __restrict f0r = f0;
+    double *const __restrict f1r = f1;
+    double *const __restrict frhs = f_rhs;
+
+    if (__builtin_expect(static_cast<unsigned>(RK4) > 3u, 0)) {
+        std::fprintf(stderr, "rungekutta4_rout_c: invalid RK4 stage %d\n", RK4);
+        std::abort();
+    }
+
+    switch (RK4) {
+    case 0:
+        rk4_stage0(n, f0r, frhs, f1r, 0.5 * dT);
+        break;
+    case 1:
+        rk4_rhs_accum(n, f1r, frhs);
+        rk4_f1_from_f0_f1(n, f0r, f1r, 0.5 * dT);
+        break;
+    case 2:
+        rk4_rhs_accum(n, f1r, frhs);
+        rk4_f1_from_f0_f1(n, f0r, f1r, dT);
+        break;
+    default:
+        rk4_stage3(n, f0r, f1r, frhs, (1.0 / 6.0) * dT);
+        break;
+    }
+
+    return 0;
+}
+
+} // extern "C"

AMSS_NCKU_source/share_func.h

@@ -0,0 +1,246 @@
+#ifndef SHARE_FUNC_H
+#define SHARE_FUNC_H
+
+#include <stdlib.h>
+#include <stddef.h>
+#include <math.h>
+#include <stdio.h>
+#include <string.h>
+/* 主网格：0-based -> 1D */
+static inline size_t idx_ex(int i0, int j0, int k0, const int ex[3]) {
+    const int ex1 = ex[0], ex2 = ex[1];
+    return (size_t)i0 + (size_t)j0 * (size_t)ex1 + (size_t)k0 * (size_t)ex1 * (size_t)ex2;
+}
+
+/*
+ * fh 对应 Fortran: fh(-1:ex1, -1:ex2, -1:ex3)
+ * ord=2 => shift=1
+ * iF/jF/kF 为 Fortran 索引（可为 -1,0,1..ex）
+ */
+static inline size_t idx_fh_F_ord2(int iF, int jF, int kF, const int ex[3]) {
+    const int shift = 1;
+    const int nx = ex[0] + 2;      // ex1 + ord
+    const int ny = ex[1] + 2;
+
+    const int ii = iF + shift;     // 0..ex1+1
+    const int jj = jF + shift;     // 0..ex2+1
+    const int kk = kF + shift;     // 0..ex3+1
+
+    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
+}
+
+/*
+ * fh 对应 Fortran: fh(-2:ex1, -2:ex2, -2:ex3)
+ * ord=3 => shift=2
+ * iF/jF/kF 是 Fortran 索引（可为负）
+ */
+static inline size_t idx_fh_F(int iF, int jF, int kF, const int ex[3]) {
+    const int shift = 2;                 // ord=3 -> -2..ex
+    const int nx = ex[0] + 3;            // ex1 + ord
+    const int ny = ex[1] + 3;
+
+    const int ii = iF + shift;           // 0..ex1+2
+    const int jj = jF + shift;           // 0..ex2+2
+    const int kk = kF + shift;           // 0..ex3+2
+
+    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
+}
+
+/*
+ * func:  (1..extc1, 1..extc2, 1..extc3)   1-based in Fortran
+ * funcc: (-ord+1..extc1, -ord+1..extc2, -ord+1..extc3) in Fortran
+ *
+ * C 里我们把：
+ *   func  视为 0-based: i0=0..extc1-1, j0=0..extc2-1, k0=0..extc3-1
+ *   funcc 用“平移下标”存为一维数组：
+ *     iF in [-ord+1..extc1]  -> ii = iF + (ord-1)  in [0..extc1+ord-1]
+ *     总长度 nx = extc1 + ord
+ *     同理 ny = extc2 + ord, nz = extc3 + ord
+ */
+
+static inline size_t idx_func0(int i0, int j0, int k0, const int extc[3]) {
+    const int nx = extc[0], ny = extc[1];
+    return (size_t)i0 + (size_t)j0 * (size_t)nx + (size_t)k0 * (size_t)nx * (size_t)ny;
+}
+
+static inline size_t idx_funcc_F(int iF, int jF, int kF, int ord, const int extc[3]) {
+    const int shift = ord - 1;          // iF = -shift .. extc1
+    const int nx = extc[0] + ord;       // [-shift..extc1] 共 extc1+ord 个
+    const int ny = extc[1] + ord;
+
+    const int ii = iF + shift;          // 0..extc1+shift
+    const int jj = jF + shift;          // 0..extc2+shift
+    const int kk = kF + shift;          // 0..extc3+shift
+
+    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
+}
+
+/*
+ * 等价于 Fortran:
+ * funcc(1:extc1,1:extc2,1:extc3)=func
+ * do i=0,ord-1
+ *   funcc(-i,1:extc2,1:extc3) = funcc(i+1,1:extc2,1:extc3)*SoA(1)
+ * enddo
+ * do i=0,ord-1
+ *   funcc(:,-i,1:extc3) = funcc(:,i+1,1:extc3)*SoA(2)
+ * enddo
+ * do i=0,ord-1
+ *   funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
+ * enddo
+ */
+static inline void symmetry_bd_impl(int ord,
+                 int shift,
+                 const int extc[3],
+                 const double *__restrict func,
+                 double *__restrict funcc,
+                 const double SoA[3])
+{
+    const int extc1 = extc[0], extc2 = extc[1], extc3 = extc[2];
+    const int nx = extc1 + ord;
+    const int ny = extc2 + ord;
+
+    const size_t snx = (size_t)nx;
+    const size_t splane = (size_t)nx * (size_t)ny;
+    const size_t interior_i = (size_t)shift + 1u;          /* iF = 1 */
+    const size_t interior_j = ((size_t)shift + 1u) * snx;  /* jF = 1 */
+    const size_t interior_k = ((size_t)shift + 1u) * splane; /* kF = 1 */
+    const size_t interior0 = interior_k + interior_j + interior_i;
+
+    /* 1) funcc(1:extc1,1:extc2,1:extc3) = func */
+    for (int k0 = 0; k0 < extc3; ++k0) {
+        const double *src_k = func + (size_t)k0 * (size_t)extc2 * (size_t)extc1;
+        const size_t dst_k0 = interior0 + (size_t)k0 * splane;
+        for (int j0 = 0; j0 < extc2; ++j0) {
+            const double *src = src_k + (size_t)j0 * (size_t)extc1;
+            double *dst = funcc + dst_k0 + (size_t)j0 * snx;
+            memcpy(dst, src, (size_t)extc1 * sizeof(double));
+        }
+    }
+
+    /* 2) funcc(-i,1:extc2,1:extc3) = funcc(i+1,1:extc2,1:extc3)*SoA(1) */
+    const double s1 = SoA[0];
+    if (s1 == 1.0) {
+        for (int ii = 0; ii < ord; ++ii) {
+            const size_t dst_i = (size_t)(shift - ii);
+            const size_t src_i = (size_t)(shift + ii + 1);
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane + interior_j;
+                for (int j0 = 0; j0 < extc2; ++j0) {
+                    const size_t off = kbase + (size_t)j0 * snx;
+                    funcc[off + dst_i] = funcc[off + src_i];
+                }
+            }
+        }
+    } else if (s1 == -1.0) {
+        for (int ii = 0; ii < ord; ++ii) {
+            const size_t dst_i = (size_t)(shift - ii);
+            const size_t src_i = (size_t)(shift + ii + 1);
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane + interior_j;
+                for (int j0 = 0; j0 < extc2; ++j0) {
+                    const size_t off = kbase + (size_t)j0 * snx;
+                    funcc[off + dst_i] = -funcc[off + src_i];
+                }
+            }
+        }
+    } else {
+        for (int ii = 0; ii < ord; ++ii) {
+            const size_t dst_i = (size_t)(shift - ii);
+            const size_t src_i = (size_t)(shift + ii + 1);
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane + interior_j;
+                for (int j0 = 0; j0 < extc2; ++j0) {
+                    const size_t off = kbase + (size_t)j0 * snx;
+                    funcc[off + dst_i] = funcc[off + src_i] * s1;
+                }
+            }
+        }
+    }
+
+    /* 3) funcc(:,-j,1:extc3) = funcc(:,j+1,1:extc3)*SoA(2) */
+    const double s2 = SoA[1];
+    if (s2 == 1.0) {
+        for (int jj = 0; jj < ord; ++jj) {
+            const size_t dst_j = (size_t)(shift - jj) * snx;
+            const size_t src_j = (size_t)(shift + jj + 1) * snx;
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane;
+                double *dst = funcc + kbase + dst_j;
+                const double *src = funcc + kbase + src_j;
+                for (int i = 0; i < nx; ++i) dst[i] = src[i];
+            }
+        }
+    } else if (s2 == -1.0) {
+        for (int jj = 0; jj < ord; ++jj) {
+            const size_t dst_j = (size_t)(shift - jj) * snx;
+            const size_t src_j = (size_t)(shift + jj + 1) * snx;
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane;
+                double *dst = funcc + kbase + dst_j;
+                const double *src = funcc + kbase + src_j;
+                for (int i = 0; i < nx; ++i) dst[i] = -src[i];
+            }
+        }
+    } else {
+        for (int jj = 0; jj < ord; ++jj) {
+            const size_t dst_j = (size_t)(shift - jj) * snx;
+            const size_t src_j = (size_t)(shift + jj + 1) * snx;
+            for (int k0 = 0; k0 < extc3; ++k0) {
+                const size_t kbase = interior_k + (size_t)k0 * splane;
+                double *dst = funcc + kbase + dst_j;
+                const double *src = funcc + kbase + src_j;
+                for (int i = 0; i < nx; ++i) dst[i] = src[i] * s2;
+            }
+        }
+    }
+
+    /* 4) funcc(:,:,-k) = funcc(:,:,k+1)*SoA(3) */
+    const double s3 = SoA[2];
+    if (s3 == 1.0) {
+        for (int kk = 0; kk < ord; ++kk) {
+            const size_t dst_k = (size_t)(shift - kk) * splane;
+            const size_t src_k = (size_t)(shift + kk + 1) * splane;
+            double *dst = funcc + dst_k;
+            const double *src = funcc + src_k;
+            for (size_t p = 0; p < splane; ++p) dst[p] = src[p];
+        }
+    } else if (s3 == -1.0) {
+        for (int kk = 0; kk < ord; ++kk) {
+            const size_t dst_k = (size_t)(shift - kk) * splane;
+            const size_t src_k = (size_t)(shift + kk + 1) * splane;
+            double *dst = funcc + dst_k;
+            const double *src = funcc + src_k;
+            for (size_t p = 0; p < splane; ++p) dst[p] = -src[p];
+        }
+    } else {
+        for (int kk = 0; kk < ord; ++kk) {
+            const size_t dst_k = (size_t)(shift - kk) * splane;
+            const size_t src_k = (size_t)(shift + kk + 1) * splane;
+            double *dst = funcc + dst_k;
+            const double *src = funcc + src_k;
+            for (size_t p = 0; p < splane; ++p) dst[p] = src[p] * s3;
+        }
+    }
+}
+
+static inline void symmetry_bd(int ord,
+                 const int extc[3],
+                 const double *func,
+                 double *funcc,
+                 const double SoA[3])
+{
+    if (ord <= 0) return;
+
+    /* Fast paths used by current C kernels: ord=2 (derivs), ord=3 (lopsided/KO). */
+    if (ord == 2) {
+        symmetry_bd_impl(2, 1, extc, func, funcc, SoA);
+        return;
+    }
+    if (ord == 3) {
+        symmetry_bd_impl(3, 2, extc, func, funcc, SoA);
+        return;
+    }
+
+    symmetry_bd_impl(ord, ord - 1, extc, func, funcc, SoA);
+}
+#endif

AMSS_NCKU_source/surface_integral.C

@@ -2653,7 +2653,6 @@ void surface_integral::surf_MassPAng(double rex, int lev, cgh *GH, var *chi, var
 
   // we have assumed there is only one box on this level,
   // so we do not need loop boxes
-
   GH->PatL[lev]->data->Interp_Points(DG_List, n_tot, pox, shellf, Symmetry, Comm_here);
 
   double Mass_out = 0;

AMSS_NCKU_source/tool.h

@@ -1,4 +1,4 @@
-#include "xh_share_func.h"
+#include "share_func.h"
 void fdderivs(const int ex[3],
               const double *f,
               double *fxx, double *fxy, double *fxz,

AMSS_NCKU_source/xh_fdderivs.C

@@ -1,311 +0,0 @@
-#include "xh_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;
-
-
-    /* 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;
-
-    /* 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);
-
-    static thread_local double *fh = NULL;
-    static thread_local 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);
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    for (int k0 = 0; k0 < ex[2]; ++k0) {
-        for (int j0 = 0; j0 < ex[1]; ++j0) {
-            for (int i0 = 0; i0 < ex[0]; ++i0) {
-                const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1; 
-                fh[idx_funcc_F(iF, jF, kF, 2, ex)] = f[idx_func0(i0, j0, k0, ex)];
-            }
-        }
-    }
-
-    // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
-    for (int ii = 0; ii <= 2 - 1; ++ii) {
-        const int iF_dst = -ii;       // 0, -1, -2, ...
-        const int iF_src = ii + 1;    // 1, 2, 3, ...
-        for (int kF = 1; kF <= ex[2]; ++kF) {
-            for (int jF = 1; jF <= ex[1]; ++jF) {
-                fh[idx_funcc_F(iF_dst, jF, kF, 2, ex)] = 
-                    fh[idx_funcc_F(iF_src, jF, kF, 2, ex)] * SoA[0];
-            }
-        }
-    }
-
-    // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-    // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-    for (int jj = 0; jj <= 2 - 1; ++jj) {
-        const int jF_dst = -jj;
-        const int jF_src = jj + 1;
-        for (int kF = 1; kF <= ex[2]; ++kF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF_dst, kF, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF_src, kF, 2, ex)] * SoA[1];
-            }
-        }
-    }
-
-    // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-    for (int kk = 0; kk <= 2 - 1; ++kk) {
-        const int kF_dst = -kk;
-        const int kF_src = kk + 1;
-        for (int jF = -2 + 1; jF <= ex[1]; ++jF) {
-            for (int iF = -2 + 1; iF <= ex[0]; ++iF) {
-                fh[idx_funcc_F(iF, jF, kF_dst, 2, ex)] =
-                    fh[idx_funcc_F(iF, jF, kF_src, 2, ex)] * SoA[2];
-            }
-        }
-    }
-    /* 输出清零：fxx,fyy,fzz,fxy,fxz,fyz = 0 */
-    // const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
-    // for (size_t p = 0; p < all; ++p) {
-    //     fxx[p] = ZEO; fyy[p] = ZEO; fzz[p] = ZEO;
-    //     fxy[p] = ZEO; fxz[p] = ZEO; fyz[p] = ZEO;
-    // }
-
-    /*
-     * Fortran:
-     * do k=1,ex3-1
-     * do j=1,ex2-1
-     * do i=1,ex1-1
-     */
-    
-    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);
-
-                /* 高阶分支：i±2,j±2,k±2 都在范围内 */
-                if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-                    (kF + 2) <= kmaxF && (kF - 2) >= kminF)
-                {
-                    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)]
-                    );
-
-                    /* fxy 高阶：完全照搬 Fortran 的括号结构 */
-                    {
-                        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 );
-                    }
-
-                    /* fxz 高阶 */
-                    {
-                        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 );
-                    }
-
-                    /* fyz 高阶 */
-                    {
-                        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 );
-                    }
-                }
-                /* 二阶分支：i±1,j±1,k±1 在范围内 */
-                else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-                         (kF + 1) <= kmaxF && (kF - 1) >= kminF)
-                {
-                    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)]
-                    );
-                }else{
-                    fxx[p] = 0.0;
-                    fyy[p] = 0.0;
-                    fzz[p] = 0.0;
-                    fxy[p] = 0.0;
-                    fxz[p] = 0.0;
-                    fyz[p] = 0.0;
-                }
-            }
-        }
-    }
-    // free(fh);
-}

AMSS_NCKU_source/xh_fderivs.C

@@ -1,145 +0,0 @@
-#include "xh_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];
-
-    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 thread_local double *fh = NULL;
-    static thread_local 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;
-    }
-
-    /*
-     * Fortran loops:
-     * do k=1,ex3-1
-     * do j=1,ex2-1
-     * do i=1,ex1-1
-     *
-     * C: k0=0..ex3-2, j0=0..ex2-2, i0=0..ex1-2
-     */
-    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);
-
-                // if(i+2 <= imax .and. i-2 >= imin ... )  (全是 Fortran 索引)
-                if ((iF + 2) <= ex1 && (iF - 2) >= iminF &&
-                    (jF + 2) <= ex2 && (jF - 2) >= jminF &&
-                    (kF + 2) <= ex3 && (kF - 2) >= kminF)
-                {
-                    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)]
-                    );
-                }
-                // elseif(i+1 <= imax .and. i-1 >= imin ...)
-                else if ((iF + 1) <= ex1 && (iF - 1) >= iminF &&
-                         (jF + 1) <= ex2 && (jF - 1) >= jminF &&
-                         (kF + 1) <= ex3 && (kF - 1) >= kminF)
-                {
-                    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)]
-                    );
-                }
-            }
-        }
-    }
-
-    // free(fh);
-}

AMSS_NCKU_source/xh_global_interp.C

@@ -1,143 +0,0 @@
-#include "xh_global_interp.h"
-
-/* 你已有的 polin3（由前面 Fortran->C 翻译得到） */
-// void polin3(const double *x1a, const double *x2a, const double *x3a,
-//             const double *ya, double x1, double x2, double x3,
-//             double *y, double *dy, int ordn);
-
-/*
-  你需要提供 decide3d 的实现（这里仅声明）。
-  Fortran: decide3d(ex,f,f,cxB,cxT,SoA,ya,ORDN,Symmetry)
-  - ex: [3]
-  - f: 三维场（列主序）
-  - cxB/cxT: 3 维窗口起止（Fortran 1-based，且可能 <=0）
-  - SoA: [3]
-  - ya: 输出 ORDN^3 的采样块（列主序）
-  - return: 0 表示正常；非 0 表示错误（对应 Fortran logical = .true.）
-*/
-// int xh_decide3d(const int ex[3],
-//              const double *f_in,
-//              const double *f_in2,   /* Fortran 里传了 f,f；按原样保留 */
-//              const int cxB[3],
-//              const int cxT[3],
-//              const double SoA[3],
-//              double *ya,
-//              int ordn,
-//              int symmetry);
-
-/* 把 Fortran 1-based 下标 idxF (可为负/0) 映射到 C 的 X[idx] 访问（只用于 X(2-cxB) 这种表达式） */
-static inline double X_at_FortranIndex(const double *X, int idxF) {
-    /* Fortran: X(1) 对应 C: X[0] */
-    return X[idxF - 1];
-}
-
-/* Fortran 整数截断：idint 在这里可用 (int) 实现（对正数等价于 floor） */
-static inline int idint_like(double a) {
-    return (int)a;  /* trunc toward zero */
-}
-
-/* global_interp 的 C 版 */
-void xh_global_interp(const int ex[3],
-                   const double *X, const double *Y, const double *Z,
-                   const double *f,                 /* f(ex1,ex2,ex3) column-major */
-                   double &f_int,
-                   double x1, double y1, double z1,
-                   int ORDN,
-                   const double SoA[3],
-                   int symmetry)
-{
-    // double time1, time2;
-    // time1 = omp_get_wtime();
-    enum { NO_SYMM = 0, EQUATORIAL = 1, OCTANT = 2 };
-
-    int j, m;
-    int imin, jmin, kmin;
-    int cxB[3], cxT[3], cxI[3], cmin[3], cmax[3];
-    double cx[3];
-    double dX, dY, dZ, ddy;
-
-    /* Fortran: imin=lbound(f,1) ... 通常是 1；这里按 1 处理 */
-    imin = 1; jmin = 1; kmin = 1;
-
-    dX = X_at_FortranIndex(X, imin + 1) - X_at_FortranIndex(X, imin);
-    dY = X_at_FortranIndex(Y, jmin + 1) - X_at_FortranIndex(Y, jmin);
-    dZ = X_at_FortranIndex(Z, kmin + 1) - X_at_FortranIndex(Z, kmin);
-
-    /* x1a(j) = (j-1)*1.0  (j=1..ORDN) */
-    double *x1a = (double*)malloc((size_t)ORDN * sizeof(double));
-    double *ya  = (double*)malloc((size_t)ORDN * (size_t)ORDN * (size_t)ORDN * sizeof(double));
-    if (!x1a || !ya) {
-        fprintf(stderr, "global_interp: malloc failed\n");
-        exit(1);
-    }
-    for (j = 0; j < ORDN; j++) x1a[j] = (double)j;
-
-    /* cxI(m) = idint((p - P(1))/dP + 0.4) + 1  (Fortran 1-based) */
-    cxI[0] = idint_like((x1 - X_at_FortranIndex(X, 1)) / dX + 0.4) + 1;
-    cxI[1] = idint_like((y1 - X_at_FortranIndex(Y, 1)) / dY + 0.4) + 1;
-    cxI[2] = idint_like((z1 - X_at_FortranIndex(Z, 1)) / dZ + 0.4) + 1;
-
-    /* cxB = cxI - ORDN/2 + 1 ; cxT = cxB + ORDN - 1 */
-    int half = ORDN / 2;  /* Fortran 整数除法 */
-    for (m = 0; m < 3; m++) {
-        cxB[m] = cxI[m] - half + 1;
-        cxT[m] = cxB[m] + ORDN - 1;
-    }
-
-    /* cmin=1; cmax=ex */
-    cmin[0] = cmin[1] = cmin[2] = 1;
-    cmax[0] = ex[0];
-    cmax[1] = ex[1];
-    cmax[2] = ex[2];
-
-    /* 对称边界时允许 cxB 为负/0（与 Fortran 一致） */
-    if (symmetry == OCTANT && fabs(X_at_FortranIndex(X, 1)) < dX) cmin[0] = -half + 2;
-    if (symmetry == OCTANT && fabs(X_at_FortranIndex(Y, 1)) < dY) cmin[1] = -half + 2;
-    if (symmetry != NO_SYMM && fabs(X_at_FortranIndex(Z, 1)) < dZ) cmin[2] = -half + 2;
-
-    /* 夹紧窗口 [cxB,cxT] 到 [cmin,cmax] */
-    for (m = 0; m < 3; m++) {
-        if (cxB[m] < cmin[m]) {
-            cxB[m] = cmin[m];
-            cxT[m] = cxB[m] + ORDN - 1;
-        }
-        if (cxT[m] > cmax[m]) {
-            cxT[m] = cmax[m];
-            cxB[m] = cxT[m] + 1 - ORDN;
-        }
-    }
-
-    /*
-      cx(m) 的计算：如果 cxB>0:
-        cx = (p - P(cxB))/dP
-      else:
-        cx = (p + P(2 - cxB))/dP
-      注意这里的 cxB 是 Fortran 1-based 语义下的整数，可能 <=0。
-    */
-    if (cxB[0] > 0) cx[0] = (x1 - X_at_FortranIndex(X, cxB[0])) / dX;
-    else           cx[0] = (x1 + X_at_FortranIndex(X, 2 - cxB[0])) / dX;
-
-    if (cxB[1] > 0) cx[1] = (y1 - X_at_FortranIndex(Y, cxB[1])) / dY;
-    else           cx[1] = (y1 + X_at_FortranIndex(Y, 2 - cxB[1])) / dY;
-
-    if (cxB[2] > 0) cx[2] = (z1 - X_at_FortranIndex(Z, cxB[2])) / dZ;
-    else           cx[2] = (z1 + X_at_FortranIndex(Z, 2 - cxB[2])) / dZ;
-
-    /* decide3d: 填充 ya(1:ORDN,1:ORDN,1:ORDN) */
-    if (xh_decide3d(ex, f, f, cxB, cxT, SoA, ya, ORDN, symmetry)) {
-        printf("global_interp position: %g %g %g\n", x1, y1, z1);
-        printf("data range: %g %g   %g %g   %g %g\n",
-               X_at_FortranIndex(X, 1), X_at_FortranIndex(X, ex[0]),
-               X_at_FortranIndex(Y, 1), X_at_FortranIndex(Y, ex[1]),
-               X_at_FortranIndex(Z, 1), X_at_FortranIndex(Z, ex[2]));
-        exit(1);
-    }
-
-    /* polin3(x1a,x1a,x1a,ya,cx(1),cx(2),cx(3),f_int,ddy,ORDN) */
-    xh_polin3(x1a, x1a, x1a, ya, cx[0], cx[1], cx[2], f_int, &ddy, ORDN);
- 
-    free(x1a);
-    free(ya);
-    // time2 = omp_get_wtime();
-    // printf("Time for global_interp: %lf seconds\n", time2 - time1);
-}

AMSS_NCKU_source/xh_global_interp.h

@@ -1,12 +0,0 @@
-#include "xh_po.h"
-
-extern "C"{
-    void xh_global_interp(const int ex[3],
-                    const double *X, const double *Y, const double *Z,
-                    const double *f,                 /* f(ex1,ex2,ex3) column-major */
-                    double &f_int,
-                    double x1, double y1, double z1,
-                    int ORDN,
-                    const double SoA[3],
-                    int symmetry);
-}

AMSS_NCKU_source/xh_po.h

@@ -1,19 +0,0 @@
-#include <stdio.h>
-#include <stdlib.h>
-#include <math.h>
-#include <omp.h>
-int xh_decide3d(const int ex[3],
-             const double *f,
-             const double *fpi,   /* 这里未用，Fortran 也没用到 */
-             const int cxB[3],
-             const int cxT[3],
-             const double SoA[3],
-             double *ya,
-             int ordn,
-             int Symmetry);
-void xh_polint(const double *xa, const double *ya, double x,
-                   double *y, double *dy, int ordn);
-
-void xh_polin3(const double *x1a, const double *x2a, const double *x3a,
-                   const double *ya, double x1, double x2, double x3,
-                   double &y, double *dy, int ordn);

AMSS_NCKU_source/xh_polint3.C

@@ -1,258 +0,0 @@
-#include "xh_po.h"
-/*
-  ex[0..2]  == Fortran ex(1:3)
-  cxB/cxT   == Fortran cxB(1:3), cxT(1:3)  (可能 <=0)
-  SoA[0..2] == Fortran SoA(1:3)
-  f, fpi    == Fortran f(ex1,ex2,ex3) column-major (1-based in formulas)
-  ya        == 连续内存，尺寸为 ORDN^3，对应 Fortran ya(cxB1:cxT1, cxB2:cxT2, cxB3:cxT3)
-              但注意：我们用 offset 映射把 Fortran 的 i/j/k 坐标写进去。
-*/
-
-static inline int imax(int a, int b) { return a > b ? a : b; }
-static inline int imin(int a, int b) { return a < b ? a : b; }
-
-/* f(i,j,k): Fortran column-major, i/j/k are Fortran 1-based in [1..ex] */
-#define F(i,j,k) f[((i)-1) + ex1 * (((j)-1) + ex2 * ((k)-1))]
-
-/*
-  ya(i,j,k): i in [cxB1..cxT1], j in [cxB2..cxT2], k in [cxB3..cxT3]
-  我们把它映射到 C 的 0..ORDN-1 立方体：
-    ii = i - cxB1
-    jj = j - cxB2
-    kk = k - cxB3
-  并按 column-major 存储（与 Fortran 一致，方便直接喂给你的 polin3）
-*/
-#define YA(i,j,k) ya[((i)-cxB1) + ordn * (((j)-cxB2) + ordn * ((k)-cxB3))]
-
-int xh_decide3d(const int ex[3],
-             const double *f,
-             const double *fpi,   /* 这里未用，Fortran 也没用到 */
-             const int cxB[3],
-             const int cxT[3],
-             const double SoA[3],
-             double *ya,
-             int ordn,
-             int Symmetry)         /* Symmetry 在 decide3d 里也没直接用 */
-{
-    (void)fpi;
-    (void)Symmetry;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    int fmin1[3], fmin2[3], fmax1[3], fmax2[3];
-    int i, j, k, m;
-
-    int gont = 0;
-
-    /* 方便 YA 宏使用 */
-    const int cxB1 = cxB[0], cxB2 = cxB[1], cxB3 = cxB[2];
-
-    for (m = 0; m < 3; m++) {
-        /* Fortran 的 “NaN 检查” 在整数上基本无意义，这里不额外处理 */
-
-        fmin1[m] = imax(1, cxB[m]);
-        fmax1[m] = cxT[m];
-
-        fmin2[m] = cxB[m];
-        fmax2[m] = imin(0, cxT[m]);
-
-        /* if((fmin1<=fmax1) and (fmin1<1 or fmax1>ex)) gont=true */
-        if ((fmin1[m] <= fmax1[m]) && (fmin1[m] < 1 || fmax1[m] > ex[m])) gont = 1;
-
-        /* if((fmin2<=fmax2) and (2-fmax2<1 or 2-fmin2>ex)) gont=true */
-        if ((fmin2[m] <= fmax2[m]) && (2 - fmax2[m] < 1 || 2 - fmin2[m] > ex[m])) gont = 1;
-    }
-
-    if (gont) {
-        printf("error in decide3d\n");
-        printf("cxB: %d %d %d   cxT: %d %d %d   ex: %d %d %d\n",
-               cxB[0], cxB[1], cxB[2], cxT[0], cxT[1], cxT[2], ex[0], ex[1], ex[2]);
-        printf("fmin1: %d %d %d  fmax1: %d %d %d\n",
-               fmin1[0], fmin1[1], fmin1[2], fmax1[0], fmax1[1], fmax1[2]);
-        printf("fmin2: %d %d %d  fmax2: %d %d %d\n",
-               fmin2[0], fmin2[1], fmin2[2], fmax2[0], fmax2[1], fmax2[2]);
-        return 1;
-    }
-
-    /* ---- 填充 ya：完全照 Fortran 两大块循环写 ---- */
-
-    /* k in [fmin1(3)..fmax1(3)] */
-    for (k = fmin1[2]; k <= fmax1[2]; k++) {
-
-        /* j in [fmin1(2)..fmax1(2)] */
-        for (j = fmin1[1]; j <= fmax1[1]; j++) {
-
-            /* i in [fmin1(1)..fmax1(1)] : ya(i,j,k)=f(i,j,k) */
-            for (i = fmin1[0]; i <= fmax1[0]; i++) {
-                YA(i, j, k) = F(i, j, k);
-            }
-
-            /* i in [fmin2(1)..fmax2(1)] : ya(i,j,k)=f(2-i,j,k)*SoA(1) */
-            for (i = fmin2[0]; i <= fmax2[0]; i++) {
-                YA(i, j, k) = F(2 - i, j, k) * SoA[0];
-            }
-        }
-
-        /* j in [fmin2(2)..fmax2(2)] */
-        for (j = fmin2[1]; j <= fmax2[1]; j++) {
-
-            /* i in [fmin1(1)..fmax1(1)] : ya(i,j,k)=f(i,2-j,k)*SoA(2) */
-            for (i = fmin1[0]; i <= fmax1[0]; i++) {
-                YA(i, j, k) = F(i, 2 - j, k) * SoA[1];
-            }
-
-            /* i in [fmin2(1)..fmax2(1)] : ya=f(2-i,2-j,k)*SoA(1)*SoA(2) */
-            for (i = fmin2[0]; i <= fmax2[0]; i++) {
-                YA(i, j, k) = F(2 - i, 2 - j, k) * SoA[0] * SoA[1];
-            }
-        }
-    }
-
-    /* k in [fmin2(3)..fmax2(3)] */
-    for (k = fmin2[2]; k <= fmax2[2]; k++) {
-
-        /* j in [fmin1(2)..fmax1(2)] */
-        for (j = fmin1[1]; j <= fmax1[1]; j++) {
-
-            /* i in [fmin1(1)..fmax1(1)] : ya=f(i,j,2-k)*SoA(3) */
-            for (i = fmin1[0]; i <= fmax1[0]; i++) {
-                YA(i, j, k) = F(i, j, 2 - k) * SoA[2];
-            }
-
-            /* i in [fmin2(1)..fmax2(1)] : ya=f(2-i,j,2-k)*SoA(1)*SoA(3) */
-            for (i = fmin2[0]; i <= fmax2[0]; i++) {
-                YA(i, j, k) = F(2 - i, j, 2 - k) * SoA[0] * SoA[2];
-            }
-        }
-
-        /* j in [fmin2(2)..fmax2(2)] */
-        for (j = fmin2[1]; j <= fmax2[1]; j++) {
-
-            /* i in [fmin1(1)..fmax1(1)] : ya=f(i,2-j,2-k)*SoA(2)*SoA(3) */
-            for (i = fmin1[0]; i <= fmax1[0]; i++) {
-                YA(i, j, k) = F(i, 2 - j, 2 - k) * SoA[1] * SoA[2];
-            }
-
-            /* i in [fmin2(1)..fmax2(1)] : ya=f(2-i,2-j,2-k)*SoA1*SoA2*SoA3 */
-            for (i = fmin2[0]; i <= fmax2[0]; i++) {
-                YA(i, j, k) = F(2 - i, 2 - j, 2 - k) * SoA[0] * SoA[1] * SoA[2];
-            }
-        }
-    }
-
-    return 0;
-}
-
-#undef F
-#undef YA
-
-void xh_polint(const double *xa, const double *ya, double x,
-                   double *y, double *dy, int ordn)
-{
-    int i, m, ns, n_m;
-    double dif, dift, hp, h, den_val;
-
-    double *c  = (double*)malloc((size_t)ordn * sizeof(double));
-    double *d  = (double*)malloc((size_t)ordn * sizeof(double));
-    double *ho = (double*)malloc((size_t)ordn * sizeof(double));
-    if (!c || !d || !ho) {
-        fprintf(stderr, "polint: malloc failed\n");
-        exit(1);
-    }
-
-    for (i = 0; i < ordn; i++) {
-        c[i]  = ya[i];
-        d[i]  = ya[i];
-        ho[i] = xa[i] - x;
-    }
-
-    ns  = 0;                      // Fortran ns=1 -> C ns=0
-    dif = fabs(x - xa[0]);
-
-    for (i = 1; i < ordn; i++) {
-        dift = fabs(x - xa[i]);
-        if (dift < dif) {
-            ns  = i;
-            dif = dift;
-        }
-    }
-
-    *y  = ya[ns];
-    ns -= 1;                      // Fortran ns=ns-1
-
-    for (m = 1; m <= ordn - 1; m++) {
-        n_m = ordn - m;           // number of active points this round
-        for (i = 0; i < n_m; i++) {
-            hp      = ho[i];
-            h       = ho[i + m];
-            den_val = hp - h;
-
-            if (den_val == 0.0) {
-                fprintf(stderr, "failure in polint for point %g\n", x);
-                fprintf(stderr, "with input points xa: ");
-                for (int t = 0; t < ordn; t++) fprintf(stderr, "%g ", xa[t]);
-                fprintf(stderr, "\n");
-                exit(1);
-            }
-
-            den_val = (c[i + 1] - d[i]) / den_val;
-            d[i]    = h  * den_val;
-            c[i]    = hp * den_val;
-        }
-
-        // Fortran: if (2*ns < n_m) then dy=c(ns+1) else dy=d(ns); ns=ns-1
-        // Here ns is C-indexed and can be -1; logic still matches.
-        if (2 * ns < n_m) {
-            *dy = c[ns + 1];
-        } else {
-            *dy = d[ns];
-            ns -= 1;
-        }
-        *y += *dy;
-    }
-
-    free(c);
-    free(d);
-    free(ho);
-}
-
-void xh_polin3(const double *x1a, const double *x2a, const double *x3a,
-                   const double *ya, double x1, double x2, double x3,
-                   double &y, double *dy, int ordn)
-{
-    // ya is ordn x ordn x ordn in Fortran layout (column-major)
-    #define YA3(i,j,k) ya[(i) + ordn*((j) + ordn*(k))]  // i,j,k: 0..ordn-1
-
-    int j, k;
-    double dy_temp;
-
-    // yatmp(j,k) in Fortran code is ordn x ordn, treat column-major:
-    // yatmp(j,k) -> yatmp[j + ordn*k]
-    double *yatmp = (double*)malloc((size_t)ordn * (size_t)ordn * sizeof(double));
-    double *ymtmp = (double*)malloc((size_t)ordn * sizeof(double));
-    if (!yatmp || !ymtmp) {
-        fprintf(stderr, "polin3: malloc failed\n");
-        exit(1);
-    }
-    #define YAT(j,k) yatmp[(j) + ordn*(k)]
-
-    for (k = 0; k < ordn; k++) {
-        for (j = 0; j < ordn; j++) {
-            // call polint(x1a, ya(:,j,k), x1, yatmp(j,k), dy_temp)
-            // ya(:,j,k) contiguous: base is &YA3(0,j,k)
-            xh_polint(x1a, &YA3(0, j, k), x1, &YAT(j, k), &dy_temp, ordn);
-        }
-    }
-
-    for (k = 0; k < ordn; k++) {
-        // call polint(x2a, yatmp(:,k), x2, ymtmp(k), dy_temp)
-        xh_polint(x2a, &YAT(0, k), x2, &ymtmp[k], &dy_temp, ordn);
-    }
-
-    xh_polint(x3a, ymtmp, x3, &y, dy, ordn);
-
-    #undef YAT
-    free(yatmp);
-    free(ymtmp);
-    #undef YA3
-}

AMSS_NCKU_source/xh_share_func.h

@@ -1,338 +0,0 @@
-#ifndef SHARE_FUNC_H
-#define SHARE_FUNC_H
-
-#include <stdlib.h>
-#include <stddef.h>
-#include <math.h>
-#include <stdio.h>
-#include <omp.h>
-/* 主网格：0-based -> 1D */
-static inline size_t idx_ex(int i0, int j0, int k0, const int ex[3]) {
-    const int ex1 = ex[0], ex2 = ex[1];
-    return (size_t)i0 + (size_t)j0 * (size_t)ex1 + (size_t)k0 * (size_t)ex1 * (size_t)ex2;
-}
-
-/*
- * fh 对应 Fortran: fh(-1:ex1, -1:ex2, -1:ex3)
- * ord=2 => shift=1
- * iF/jF/kF 为 Fortran 索引（可为 -1,0,1..ex）
- */
-static inline size_t idx_fh_F_ord2(int iF, int jF, int kF, const int ex[3]) {
-    const int shift = 1;
-    const int nx = ex[0] + 2;      // ex1 + ord
-    const int ny = ex[1] + 2;
-
-    const int ii = iF + shift;     // 0..ex1+1
-    const int jj = jF + shift;     // 0..ex2+1
-    const int kk = kF + shift;     // 0..ex3+1
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * fh 对应 Fortran: fh(-2:ex1, -2:ex2, -2:ex3)
- * ord=3 => shift=2
- * iF/jF/kF 是 Fortran 索引（可为负）
- */
-static inline size_t idx_fh_F(int iF, int jF, int kF, const int ex[3]) {
-    const int shift = 2;                 // ord=3 -> -2..ex
-    const int nx = ex[0] + 3;            // ex1 + ord
-    const int ny = ex[1] + 3;
-
-    const int ii = iF + shift;           // 0..ex1+2
-    const int jj = jF + shift;           // 0..ex2+2
-    const int kk = kF + shift;           // 0..ex3+2
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * func:  (1..extc1, 1..extc2, 1..extc3)   1-based in Fortran
- * funcc: (-ord+1..extc1, -ord+1..extc2, -ord+1..extc3) in Fortran
- *
- * C 里我们把：
- *   func  视为 0-based: i0=0..extc1-1, j0=0..extc2-1, k0=0..extc3-1
- *   funcc 用“平移下标”存为一维数组：
- *     iF in [-ord+1..extc1]  -> ii = iF + (ord-1)  in [0..extc1+ord-1]
- *     总长度 nx = extc1 + ord
- *     同理 ny = extc2 + ord, nz = extc3 + ord
- */
-
-static inline size_t idx_func0(int i0, int j0, int k0, const int extc[3]) {
-    const int nx = extc[0], ny = extc[1];
-    return (size_t)i0 + (size_t)j0 * (size_t)nx + (size_t)k0 * (size_t)nx * (size_t)ny;
-}
-
-static inline size_t idx_funcc_F(int iF, int jF, int kF, int ord, const int extc[3]) {
-    const int shift = ord - 1;          // iF = -shift .. extc1
-    const int nx = extc[0] + ord;       // [-shift..extc1] 共 extc1+ord 个
-    const int ny = extc[1] + ord;
-
-    const int ii = iF + shift;          // 0..extc1+shift
-    const int jj = jF + shift;          // 0..extc2+shift
-    const int kk = kF + shift;          // 0..extc3+shift
-
-    return (size_t)ii + (size_t)jj * (size_t)nx + (size_t)kk * (size_t)nx * (size_t)ny;
-}
-
-/*
- * 等价于 Fortran:
- * funcc(1:extc1,1:extc2,1:extc3)=func
- * do i=0,ord-1
- *   funcc(-i,1:extc2,1:extc3) = funcc(i+1,1:extc2,1:extc3)*SoA(1)
- * enddo
- * do i=0,ord-1
- *   funcc(:,-i,1:extc3) = funcc(:,i+1,1:extc3)*SoA(2)
- * enddo
- * do i=0,ord-1
- *   funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
- * enddo
- */
-static inline void symmetry_bd(int ord,
-                 const int extc[3],
-                 const double *func,
-                 double *funcc,
-                 const double SoA[3])
-{
-    const int extc1 = extc[0], extc2 = extc[1], extc3 = extc[2];
-
-    // 1) funcc(1:extc1,1:extc2,1:extc3) = func
-    // Fortran 的 (iF=1..extc1) 对应 C 的 func(i0=0..extc1-1)
-    for (int k0 = 0; k0 < extc3; ++k0) {
-        for (int j0 = 0; j0 < extc2; ++j0) {
-            for (int i0 = 0; i0 < extc1; ++i0) {
-                const int iF = i0 + 1, jF = j0 + 1, kF = k0 + 1;
-                funcc[idx_funcc_F(iF, jF, kF, ord, extc)] = func[idx_func0(i0, j0, k0, extc)];
-            }
-        }
-    }
-
-    // 2) do i=0..ord-1: funcc(-i, 1:extc2, 1:extc3) = funcc(i+1, ...)*SoA(1)
-    for (int ii = 0; ii <= ord - 1; ++ii) {
-        const int iF_dst = -ii;       // 0, -1, -2, ...
-        const int iF_src = ii + 1;    // 1, 2, 3, ...
-        for (int kF = 1; kF <= extc3; ++kF) {
-            for (int jF = 1; jF <= extc2; ++jF) {
-                funcc[idx_funcc_F(iF_dst, jF, kF, ord, extc)] =
-                    funcc[idx_funcc_F(iF_src, jF, kF, ord, extc)] * SoA[0];
-            }
-        }
-    }
-
-    // 3) do i=0..ord-1: funcc(:,-i, 1:extc3) = funcc(:, i+1, 1:extc3)*SoA(2)
-    // 注意 Fortran 这里的 ":" 表示 iF 从 (-ord+1..extc1) 全覆盖
-    for (int jj = 0; jj <= ord - 1; ++jj) {
-        const int jF_dst = -jj;
-        const int jF_src = jj + 1;
-        for (int kF = 1; kF <= extc3; ++kF) {
-            for (int iF = -ord + 1; iF <= extc1; ++iF) {
-                funcc[idx_funcc_F(iF, jF_dst, kF, ord, extc)] =
-                    funcc[idx_funcc_F(iF, jF_src, kF, ord, extc)] * SoA[1];
-            }
-        }
-    }
-
-    // 4) do i=0..ord-1: funcc(:,:,-i) = funcc(:,:, i+1)*SoA(3)
-    for (int kk = 0; kk <= ord - 1; ++kk) {
-        const int kF_dst = -kk;
-        const int kF_src = kk + 1;
-        for (int jF = -ord + 1; jF <= extc2; ++jF) {
-            for (int iF = -ord + 1; iF <= extc1; ++iF) {
-                funcc[idx_funcc_F(iF, jF, kF_dst, ord, extc)] =
-                    funcc[idx_funcc_F(iF, jF, kF_src, ord, extc)] * SoA[2];
-            }
-        }
-    }
-}
-#endif
-
-/* 你已有的函数：idx_ex / idx_fh_F_ord2 以及 fh 的布局 */
-static inline void fdderivs_xh(
-    int i0, int j0, int k0,
-    const int ex[3],
-    const double *fh,
-    int iminF, int jminF, int kminF,
-    int imaxF, int jmaxF, int kmaxF,
-    double Fdxdx, double Fdydy, double Fdzdz,
-    double Fdxdy, double Fdxdz, double Fdydz,
-    double Sdxdx, double Sdydy, double Sdzdz,
-    double Sdxdy, double Sdxdz, double Sdydz,
-    double *fxx, double *fxy, double *fxz,
-    double *fyy, double *fyz, double *fzz
-){
-    const double F8  = 8.0;
-    const double F16 = 16.0;
-    const double F30 = 30.0;
-    const double TWO = 2.0;
-
-    const int iF = i0 + 1;
-    const int jF = j0 + 1;
-    const int kF = k0 + 1;
-
-    const size_t p = idx_ex(i0, j0, k0, ex);
-
-    /* 高阶分支：i±2,j±2,k±2 都在范围内 */
-    if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
-        (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-        (kF + 2) <= kmaxF && (kF - 2) >= kminF)
-    {
-        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)]
-        );
-
-        /* fxy 高阶 */
-        {
-            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 );
-        }
-
-        /* fxz 高阶 */
-        {
-            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 );
-        }
-
-        /* fyz 高阶 */
-        {
-            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 );
-        }
-    }
-    /* 二阶分支：i±1,j±1,k±1 在范围内 */
-    else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
-             (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-             (kF + 1) <= kmaxF && (kF - 1) >= kminF)
-    {
-        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)]
-        );
-    }
-    else {
-        fxx[p] = 0.0; fyy[p] = 0.0; fzz[p] = 0.0;
-        fxy[p] = 0.0; fxz[p] = 0.0; fyz[p] = 0.0;
-    }
-}

AMSS_NCKU_source/xh_tool.h

@@ -1,27 +0,0 @@
-#include "xh_share_func.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 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 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);
-
-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]);

generate_interp_lb_header.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+"""Convert interp_lb_profile.bin to a C header for compile-time embedding."""
+import struct, sys
+
+if len(sys.argv) < 3:
+    print(f"Usage: {sys.argv[0]} <profile.bin> <output.h>")
+    sys.exit(1)
+
+with open(sys.argv[1], 'rb') as f:
+    magic, version, nprocs, num_heavy = struct.unpack('IIii', f.read(16))
+    threshold = struct.unpack('d', f.read(8))[0]
+    times = list(struct.unpack(f'{nprocs}d', f.read(nprocs * 8)))
+    heavy = list(struct.unpack(f'{num_heavy}i', f.read(num_heavy * 4)))
+
+# For each heavy rank, compute split: left half -> lighter neighbor, right half -> heavy rank
+# (or vice versa depending on which neighbor is lighter)
+splits = []
+for hr in heavy:
+    prev_t = times[hr - 1] if hr > 0 else 1e30
+    next_t = times[hr + 1] if hr < nprocs - 1 else 1e30
+    if prev_t <= next_t:
+        splits.append((hr, hr - 1, hr))  # (block_id, r_left, r_right)
+    else:
+        splits.append((hr, hr, hr + 1))
+
+# Also remap the displaced neighbor blocks
+remaps = {}
+for hr, r_l, r_r in splits:
+    if r_l != hr:
+        # We took r_l's slot, so remap block r_l to its other neighbor
+        displaced = r_l
+        if displaced > 0 and displaced - 1 not in [s[0] for s in splits]:
+            remaps[displaced] = displaced - 1
+        elif displaced < nprocs - 1:
+            remaps[displaced] = displaced + 1
+    else:
+        displaced = r_r
+        if displaced < nprocs - 1 and displaced + 1 not in [s[0] for s in splits]:
+            remaps[displaced] = displaced + 1
+        elif displaced > 0:
+            remaps[displaced] = displaced - 1
+
+with open(sys.argv[2], 'w') as out:
+    out.write("/* Auto-generated from interp_lb_profile.bin — do not edit */\n")
+    out.write("#ifndef INTERP_LB_PROFILE_DATA_H\n")
+    out.write("#define INTERP_LB_PROFILE_DATA_H\n\n")
+    out.write(f"#define INTERP_LB_NPROCS {nprocs}\n")
+    out.write(f"#define INTERP_LB_NUM_HEAVY {num_heavy}\n\n")
+    out.write(f"static const int interp_lb_heavy_blocks[{num_heavy}] = {{")
+    out.write(", ".join(str(h) for h in heavy))
+    out.write("};\n\n")
+    out.write("/* Split table: {block_id, r_left, r_right} */\n")
+    out.write(f"static const int interp_lb_splits[{num_heavy}][3] = {{\n")
+    for bid, rl, rr in splits:
+        out.write(f"    {{{bid}, {rl}, {rr}}},\n")
+    out.write("};\n\n")
+    out.write("/* Rank remap for displaced neighbor blocks */\n")
+    out.write(f"static const int interp_lb_num_remaps = {len(remaps)};\n")
+    out.write(f"static const int interp_lb_remaps[][2] = {{\n")
+    for src, dst in sorted(remaps.items()):
+        out.write(f"    {{{src}, {dst}}},\n")
+    if not remaps:
+        out.write("    {-1, -1},\n")
+    out.write("};\n\n")
+    out.write("#endif /* INTERP_LB_PROFILE_DATA_H */\n")
+
+print(f"Generated {sys.argv[2]}:")
+print(f"  {num_heavy} heavy blocks to split: {heavy}")
+for bid, rl, rr in splits:
+    print(f"    block {bid}: split -> rank {rl} (left), rank {rr} (right)")
+for src, dst in sorted(remaps.items()):
+    print(f"    block {src}: remap -> rank {dst}")

makefile_and_run.py

@@ -11,23 +11,53 @@
 import AMSS_NCKU_Input as input_data
 import subprocess
 import time
-## CPU core binding configuration using taskset
+
-## taskset ensures all child processes inherit the CPU affinity mask
+
-## This forces make and all compiler processes to use only nohz_full cores (4-55, 60-111)
+def get_last_n_cores_per_socket(n=32):
-## Format: taskset -c 4-55,60-111 ensures processes only run on these cores
+    """
-#NUMACTL_CPU_BIND = "taskset -c 0-111"
+    Read CPU topology via lscpu and return a taskset -c string
-NUMACTL_CPU_BIND = "taskset -c 0-47"
+    selecting the last `n` cores of each NUMA node (socket).
-NUMACTL_CPU_BIND2 = "OMP_NUM_THREADS=48 OMP_PROC_BIND=close OMP_PLACES={0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47} taskset -c 0-47"
+
-#NUMACTL_CPU_BIND2 = "taskset -c 0-1"
+    Example: 2 sockets x 56 cores each, n=32 -> node0: 24-55, node1: 80-111
-## Build parallelism configuration
+    -> "taskset -c 24-55,80-111"
-## Use nohz_full cores (4-55, 60-111) for compilation: 52 + 52 = 104 cores
+    """
-## Set make -j to utilize available cores for faster builds
+    result = subprocess.run(["lscpu", "--parse=NODE,CPU"], capture_output=True, text=True)
-BUILD_JOBS = 32
+
+    # Build a dict: node_id -> sorted list of CPU ids
+    node_cpus = {}
+    for line in result.stdout.splitlines():
+        if line.startswith("#") or not line.strip():
+            continue
+        parts = line.split(",")
+        if len(parts) < 2:
+            continue
+        node_id, cpu_id = int(parts[0]), int(parts[1])
+        node_cpus.setdefault(node_id, []).append(cpu_id)
+
+    segments = []
+    for node_id in sorted(node_cpus):
+        cpus = sorted(node_cpus[node_id])
+        selected = cpus[-n:]          # last n cores of this socket
+        segments.append(f"{selected[0]}-{selected[-1]}")
+
+    cpu_str = ",".join(segments)
+    total = len(segments) * n
+    print(f" CPU binding: taskset -c {cpu_str}  ({total} cores, last {n} per socket)")
+    #return f"taskset -c {cpu_str}"
+    return f""
+
+
+## CPU core binding: dynamically select the last 32 cores of each socket (64 cores total)
+NUMACTL_CPU_BIND = get_last_n_cores_per_socket(n=32)
+
+## Build parallelism: match the number of bound cores
+BUILD_JOBS = 64
 
 
 ##################################################################
 
 
+
 ##################################################################
 
 ## Compile the AMSS-NCKU main program ABE
@@ -40,7 +70,7 @@ def makefile_ABE():
 
     ## Build command with CPU binding to nohz_full cores
     if (input_data.GPU_Calculation == "no"):
-        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABE"
+        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} INTERP_LB_MODE=optimize ABE"
     elif (input_data.GPU_Calculation == "yes"):
         makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABEGPU"
     else:
@@ -117,12 +147,11 @@ def run_ABE():
     ## Define the command to run; cast other values to strings as needed
     
     if (input_data.GPU_Calculation == "no"):
-        #mpi_command         = NUMACTL_CPU_BIND2 + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
+        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
         #mpi_command         = " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
-        mpi_command = """ OMP_NUM_THREADS=48 OMP_PROC_BIND=close OMP_PLACES=cores mpirun -np 1 --cpu-bind=sockets  ./ABE """
         mpi_command_outfile = "ABE_out.log"
     elif (input_data.GPU_Calculation == "yes"):
-        mpi_command         = NUMACTL_CPU_BIND2 + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
+        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
         mpi_command_outfile = "ABEGPU_out.log"
  
     ## Execute the MPI command and stream output

parallel_plot_helper.py

@@ -0,0 +1,29 @@
+import multiprocessing
+
+def run_plot_task(task):
+    """Execute a single plotting task.
+    
+    Parameters
+    ----------
+    task : tuple
+        A tuple of (function, args_tuple) where function is a callable
+        plotting function and args_tuple contains its arguments.
+    """
+    func, args = task
+    return func(*args)
+
+
+def run_plot_tasks_parallel(plot_tasks):
+    """Execute a list of independent plotting tasks in parallel.
+
+    Uses the 'fork' context to create worker processes so that the main
+    script is NOT re-imported/re-executed in child processes.
+
+    Parameters
+    ----------
+    plot_tasks : list of tuples
+        Each element is (function, args_tuple).
+    """
+    ctx = multiprocessing.get_context('fork')
+    with ctx.Pool() as pool:
+        pool.map(run_plot_task, plot_tasks)

plot_GW_strain_amplitude_xiaoqu.py

@@ -11,6 +11,8 @@
 import numpy                               ## numpy for array operations
 import scipy                               ## scipy for interpolation and signal processing
 import math
+import matplotlib
+matplotlib.use('Agg')                      ## use non-interactive backend for multiprocessing safety
 import matplotlib.pyplot    as     plt     ## matplotlib for plotting
 import os                                  ## os for system/file operations
 

plot_binary_data.py

@@ -8,16 +8,23 @@
 ##
 #################################################
 
+## Restrict OpenMP to one thread per process so that running
+## many workers in parallel does not create an O(workers * BLAS_threads)
+## thread explosion.  The variable MUST be set before numpy/scipy
+## are imported, because the BLAS library reads them only at load time.
+import os
+os.environ.setdefault("OMP_NUM_THREADS",        "1")
+
 import numpy
 import scipy
+import matplotlib
+matplotlib.use('Agg')                      ## use non-interactive backend for multiprocessing safety
 import matplotlib.pyplot    as     plt
 from   matplotlib.colors    import LogNorm
 from   mpl_toolkits.mplot3d import Axes3D
 ## import torch
 import AMSS_NCKU_Input      as input_data
 
-import os
-
 
 #########################################################################################
 
@@ -192,3 +199,19 @@ def get_data_xy( Rmin, Rmax, n, data0, time, figure_title, figure_outdir ):
 
 ####################################################################################
 
+
+####################################################################################
+## Allow this module to be run as a standalone script so that each
+## binary-data plot can be executed in a fresh subprocess whose BLAS
+## environment variables (set above) take effect before numpy loads.
+##
+## Usage:  python3 plot_binary_data.py <filename> <binary_outdir> <figure_outdir>
+####################################################################################
+
+if __name__ == '__main__':
+    import sys
+    if len(sys.argv) != 4:
+        print(f"Usage: {sys.argv[0]} <filename> <binary_outdir> <figure_outdir>")
+        sys.exit(1)
+    plot_binary_data(sys.argv[1], sys.argv[2], sys.argv[3])
+

plot_xiaoqu.py

@@ -8,6 +8,8 @@
 #################################################
 
 import numpy                               ## numpy for array operations
+import matplotlib
+matplotlib.use('Agg')                      ## use non-interactive backend for multiprocessing safety
 import matplotlib.pyplot    as     plt     ## matplotlib for plotting
 from   mpl_toolkits.mplot3d import Axes3D  ## needed for 3D plots
 import glob
@@ -15,6 +17,9 @@ import os                                  ## operating system utilities
 
 import plot_binary_data
 import AMSS_NCKU_Input as input_data
+import subprocess
+import sys
+import multiprocessing
 
 # plt.rcParams['text.usetex'] = True  ## enable LaTeX fonts in plots
 
@@ -50,10 +55,40 @@ def generate_binary_data_plot( binary_outdir, figure_outdir ):
         file_list.append(x)
         print(x)
 
-    ## Plot each file in the list
+    ## Plot each file in parallel using subprocesses.
+    ## Each subprocess is a fresh Python process where the BLAS thread-count
+    ## environment variables (set at the top of plot_binary_data.py) take
+    ## effect before numpy is imported.  This avoids the thread explosion
+    ## that occurs when multiprocessing.Pool with 'fork' context inherits
+    ## already-initialized multi-threaded BLAS from the parent.
+    script = os.path.join( os.path.dirname(__file__), "plot_binary_data.py" )
+    max_workers = min( multiprocessing.cpu_count(), len(file_list) ) if file_list else 0
+
+    running = []
+    failed  = []
     for filename in file_list:
         print(filename)
-        plot_binary_data.plot_binary_data(filename, binary_outdir, figure_outdir)
+        proc = subprocess.Popen(
+            [sys.executable, script, filename, binary_outdir, figure_outdir],
+        )
+        running.append( (proc, filename) )
+        ## Keep at most max_workers subprocesses active at a time
+        if len(running) >= max_workers:
+            p, fn = running.pop(0)
+            p.wait()
+            if p.returncode != 0:
+                failed.append(fn)
+
+    ## Wait for all remaining subprocesses to finish
+    for p, fn in running:
+        p.wait()
+        if p.returncode != 0:
+            failed.append(fn)
+
+    if failed:
+        print( " WARNING: the following binary data plots failed:" )
+        for fn in failed:
+            print( "   ", fn )
 
     print(                        )
     print( " Binary Data Plot Has been Finished " )