feat: port GPU code to CUDA 13 and enable GPU computation

Major changes:
   - Update makefile.inc for CUDA 13.1 with sm_89 architecture (RTX 4050)
   - Replace deprecated cudaThreadSynchronize() with cudaDeviceSynchronize()
   - Add CUDA_SAFE_CALL macro for CUDA 13 compatibility
   - Fix duplicate function definitions (compare_result_gpu, SHStep)
   - Fix syntax error in bssn_step_gpu.C
   - Enable GPU calculation in AMSS_NCKU_Input.py
   - Successfully build ABEGPU executable

.gitignore

@@ -1,6 +1,3 @@
 __pycache__
 GW150914
-GW150914-origin
-docs
-*.tmp
 

AMSS_NCKU_Input.py

@@ -16,12 +16,12 @@ import numpy
 File_directory   = "GW150914"                    ## output file directory
 Output_directory = "binary_output"               ## binary data file directory
                                                  ## The file directory name should not be too long
-MPI_processes    = 64                             ## number of mpi processes used in the simulation
+MPI_processes    = 96                             ## number of mpi processes used in the simulation
 
-GPU_Calculation  = "no"                          ## Use GPU or not 
-                                                 ## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
-CPU_Part         = 1.0
-GPU_Part         = 0.0
+GPU_Calculation  = "yes"                         ## Use GPU or not
+                                                 ## GPU support has been updated for CUDA 13
+CPU_Part         = 0.0
+GPU_Part         = 1.0
 
 #################################################
 

AMSS_NCKU_Program.py

@@ -8,14 +8,6 @@
 ##
 ##################################################################
 
-## 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)
-
 
 ##################################################################
 
@@ -270,12 +262,6 @@ 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
@@ -438,31 +424,26 @@ 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_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot,   (binary_results_directory, figure_directory) ) )
-plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot3D, (binary_results_directory, figure_directory) ) )
+plot_xiaoqu.generate_puncture_orbit_plot(   binary_results_directory, figure_directory )
+plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
 
 ## Plot black hole separation vs. time
-plot_tasks.append( ( plot_xiaoqu.generate_puncture_distence_plot, (binary_results_directory, figure_directory) ) )
+plot_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
 
 ## Plot gravitational waveforms (psi4 and strain amplitude)
 for i in range(input_data.Detector_Number):
-    plot_tasks.append( ( plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i) ) )
-    plot_tasks.append( ( plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot, (binary_results_directory, figure_directory, i) ) )
+    plot_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 ADM mass evolution
 for i in range(input_data.Detector_Number):
-    plot_tasks.append( ( plot_xiaoqu.generate_ADMmass_plot, (binary_results_directory, figure_directory, i) ) )
+    plot_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
 
 ## Plot Hamiltonian constraint violation over time
 for i in range(input_data.grid_level):
-    plot_tasks.append( ( plot_xiaoqu.generate_constraint_check_plot, (binary_results_directory, figure_directory, i) ) )
-
-run_plot_tasks_parallel(plot_tasks)
+    plot_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
 
 ## Plot stored binary data
 plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )

AMSS_NCKU_Verify_ASC26.py

@@ -1,250 +0,0 @@
-#!/usr/bin/env python3
-"""
-AMSS-NCKU GW150914 Simulation Regression Test Script (Comprehensive Version)
-
-Verification Requirements:
-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:
-- Computes trajectory deviation on the XY plane independently for BH1 and BH2
-- For each black hole: RMS = sqrt((1/M) * sum((Δr_i / r_i^max)^2)) × 100%
-- Final RMS = max(RMS_BH1, RMS_BH2)
-
-Usage: python3 AMSS_NCKU_Verify_ASC26.py [output_dir]
-Default: output_dir = GW150914/AMSS_NCKU_output
-Reference: GW150914-origin (baseline simulation)
-"""
-
-import numpy as np
-import sys
-import os
-
-# ANSI Color Codes
-class Color:
-    GREEN = '\033[92m'
-    RED = '\033[91m'
-    YELLOW = '\033[93m'
-    BLUE = '\033[94m'
-    BOLD = '\033[1m'
-    RESET = '\033[0m'
-
-def get_status_text(passed):
-    if passed:
-        return f"{Color.GREEN}{Color.BOLD}PASS{Color.RESET}"
-    else:
-        return f"{Color.RED}{Color.BOLD}FAIL{Color.RESET}"
-
-def load_bh_trajectory(filepath):
-    """Load black hole trajectory data"""
-    data = np.loadtxt(filepath)
-    return {
-        'time': data[:, 0],
-        'x1': data[:, 1], 'y1': data[:, 2], 'z1': data[:, 3],
-        'x2': data[:, 4], 'y2': data[:, 5], 'z2': data[:, 6]
-    }
-
-
-def load_constraint_data(filepath):
-    """Load constraint violation data"""
-    data = []
-    with open(filepath, 'r') as f:
-        for line in f:
-            if line.startswith('#'):
-                continue
-            parts = line.split()
-            if len(parts) >= 8:
-                data.append([float(x) for x in parts[:8]])
-    return np.array(data)
-
-def calculate_all_rms_errors(bh_data_ref, bh_data_target):
-    """
-    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.
-    Returns the maximum error between BH1 and BH2 for each category.
-    """
-    M = min(len(bh_data_ref['time']), len(bh_data_target['time']))
-
-    if M < 10:
-        return None, "Insufficient data points for comparison"
-
-    results = {}
-
-    for bh in ['1', '2']:
-        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]
-        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]
-
-        # 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)
-        r_ref = np.sqrt(x_r**2 + y_r**2)
-        r_new = np.sqrt(x_n**2 + y_n**2)
-        denom_max = np.maximum(r_ref, r_new)
-
-        valid = denom_max > 1e-15
-        if np.sum(valid) < 10:
-            results[f'BH{bh}'] = { '3D_Vector': 0.0, 'X_Component': 0.0, 'Y_Component': 0.0, 'Z_Component': 0.0 }
-            continue
-
-        def calc_rms(delta):
-            # 将对应分量的偏差除以统一的轨道半径分母 denom_max
-            return np.sqrt(np.mean((delta[valid] / denom_max[valid])**2)) * 100
-
-        # 1. Total 3D Vector RMS
-        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)
-
-        # 2. Component-wise RMS (分离计算各轴，但共用半径分母)
-        rms_x = calc_rms(np.abs(x_r - x_n))
-        rms_y = calc_rms(np.abs(y_r - y_n))
-        rms_z = calc_rms(np.abs(z_r - z_n))
-
-        results[f'BH{bh}'] = {
-            '3D_Vector': rms_3d,
-            'X_Component': rms_x,
-            'Y_Component': rms_y,
-            'Z_Component': rms_z
-        }
-
-    # 获取 BH1 和 BH2 中的最大误差
-    max_rms = {
-        '3D_Vector': max(results['BH1']['3D_Vector'], results['BH2']['3D_Vector']),
-        '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):
-    """
-    Analyze ADM constraint violation
-    Return maximum constraint violation for Grid Level 0
-    """
-    # Extract Grid Level 0 data (first entry for each time step)
-    level0_data = constraint_data[::n_levels]
-
-    # Calculate maximum absolute value for each constraint
-    results = {
-        'Ham': np.max(np.abs(level0_data[:, 1])),
-        'Px': np.max(np.abs(level0_data[:, 2])),
-        'Py': np.max(np.abs(level0_data[:, 3])),
-        'Pz': np.max(np.abs(level0_data[:, 4])),
-        'Gx': np.max(np.abs(level0_data[:, 5])),
-        'Gy': np.max(np.abs(level0_data[:, 6])),
-        'Gz': np.max(np.abs(level0_data[:, 7]))
-    }
-
-    results['max_violation'] = max(results.values())
-    return results
-
-
-def print_header():
-    print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + 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):
-    print(f"\n{Color.BOLD}1. RMS Error Analysis (Maximums of BH1 & BH2){Color.RESET}")
-    print("-" * 65)
-
-    if error:
-        print(f"   {Color.RED}Error: {error}{Color.RESET}")
-        return False
-
-    all_passed = True
-    print(f"   Requirement: < {threshold}%\n")
-
-    for key, val in rms_dict.items():
-        passed = val < threshold
-        all_passed = all_passed and passed
-        status = get_status_text(passed)
-        print(f"   {key:15}: {val:8.4f}%   |   Status: {status}")
-
-    return all_passed
-
-def print_constraint_results(results, threshold=2.0):
-    print(f"\n{Color.BOLD}2. ADM Constraint Violation Analysis (Grid Level 0){Color.RESET}")
-    print("-" * 65)
-
-    names = ['Ham', 'Px', 'Py', 'Pz', 'Gx', 'Gy', 'Gz']
-    for i, name in enumerate(names):
-        print(f"   Max |{name:3}|: {results[name]:.6f}", end="   ")
-        if (i + 1) % 2 == 0: print()
-    if len(names) % 2 != 0: print()
-
-    passed = results['max_violation'] < threshold
-    
-    print(f"\n   Maximum violation:  {results['max_violation']:.6f}")
-    print(f"   Requirement:        < {threshold}")
-    print(f"   Status:             {get_status_text(passed)}")
-
-    return passed
-
-
-def print_summary(rms_passed, constraint_passed):
-    print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-    print(Color.BOLD + "Verification Summary" + Color.RESET)
-    print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-
-    all_passed = rms_passed and constraint_passed
-    
-    res_rms = get_status_text(rms_passed)
-    res_con = get_status_text(constraint_passed)
-
-    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}"
-    print(f"\n   Overall result: {final_status}")
-    print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET + "\n")
-
-    return all_passed
-
-def main():
-    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")
-
-    script_dir = os.path.dirname(os.path.abspath(__file__))
-    reference_dir = os.path.join(script_dir, "GW150914-origin/AMSS_NCKU_output")
-
-    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")
-
-    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(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}")
-
-    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)
-
-    # Output modified RMS results
-    rms_dict, error = calculate_all_rms_errors(bh_data_ref, bh_data_target)
-    rms_passed = print_rms_results(rms_dict, error)
-
-    # Output constraint results
-    constraint_results = analyze_constraint_violation(constraint_data)
-    constraint_passed = print_constraint_results(constraint_results)
-
-    all_passed = print_summary(rms_passed, constraint_passed)
-    sys.exit(0 if all_passed else 1)
-
-if __name__ == "__main__":
-    main()

AMSS_NCKU_source/FFT.f90

@@ -37,51 +37,57 @@ close(77)
 end program checkFFT
 #endif
 
-!-------------
-! Optimized FFT using Intel oneMKL DFTI
-! Mathematical equivalence: Standard DFT definition
-!   Forward (isign=1):  X[k] = sum_{n=0}^{N-1} x[n] * exp(-2*pi*i*k*n/N)
-!   Backward (isign=-1): X[k] = sum_{n=0}^{N-1} x[n] * exp(+2*pi*i*k*n/N)
-! Input/Output: dataa is interleaved complex array [Re(0),Im(0),Re(1),Im(1),...]
 !-------------
 SUBROUTINE four1(dataa,nn,isign)
-use MKL_DFTI
 implicit none
-INTEGER, intent(in) :: isign, nn
-DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
-
-type(DFTI_DESCRIPTOR), pointer :: desc
-integer :: status
-
-! Create DFTI descriptor for 1D complex-to-complex transform
-status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
-if (status /= 0) return
-
-! Set input/output storage as interleaved complex (default)
-status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
-if (status /= 0) then
-   status = DftiFreeDescriptor(desc)
-   return
+INTEGER::isign,nn
+double precision,dimension(2*nn)::dataa
+INTEGER::i,istep,j,m,mmax,n
+double precision::tempi,tempr
+DOUBLE PRECISION::theta,wi,wpi,wpr,wr,wtemp
+n=2*nn
+j=1
+do i=1,n,2
+  if(j.gt.i)then
+     tempr=dataa(j)
+     tempi=dataa(j+1)
+     dataa(j)=dataa(i)
+     dataa(j+1)=dataa(i+1)
+     dataa(i)=tempr
+     dataa(i+1)=tempi
+  endif
+  m=nn
+1 if ((m.ge.2).and.(j.gt.m)) then
+  j=j-m
+  m=m/2
+goto 1
+  endif
+j=j+m
+enddo
+mmax=2
+2  if (n.gt.mmax) then
+     istep=2*mmax
+     theta=6.28318530717959d0/(isign*mmax)
+     wpr=-2.d0*sin(0.5d0*theta)**2
+     wpi=sin(theta)
+     wr=1.d0
+     wi=0.d0
+     do m=1,mmax,2
+       do i=m,n,istep
+         j=i+mmax
+         tempr=sngl(wr)*dataa(j)-sngl(wi)*dataa(j+1)
+         tempi=sngl(wr)*dataa(j+1)+sngl(wi)*dataa(j)
+         dataa(j)=dataa(i)-tempr
+         dataa(j+1)=dataa(i+1)-tempi
+         dataa(i)=dataa(i)+tempr
+         dataa(i+1)=dataa(i+1)+tempi
+       enddo
+          wtemp=wr
+          wr=wr*wpr-wi*wpi+wr
+          wi=wi*wpr+wtemp*wpi+wi
+     enddo
+mmax=istep
+goto 2
 endif
-
-! Commit the descriptor
-status = DftiCommitDescriptor(desc)
-if (status /= 0) then
-   status = DftiFreeDescriptor(desc)
-   return
-endif
-
-! Execute FFT based on direction
-if (isign == 1) then
-   ! Forward FFT: exp(-2*pi*i*k*n/N)
-   status = DftiComputeForward(desc, dataa)
-else
-   ! Backward FFT: exp(+2*pi*i*k*n/N)
-   status = DftiComputeBackward(desc, dataa)
-endif
-
-! Free descriptor
-status = DftiFreeDescriptor(desc)
-
 return
 END SUBROUTINE four1

AMSS_NCKU_source/MPatch.C

@@ -7,178 +7,12 @@
 #include <string>
 #include <cmath>
 #include <new>
-#include <vector>
 using namespace std;
 
 #include "misc.h"
 #include "MPatch.h"
 #include "Parallel.h"
 #include "fmisc.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)
 {
@@ -507,9 +341,8 @@ void Patch::Interp_Points(MyList<var> *VarList,
                           double *Shellf, int Symmetry)
 {
   // NOTE: we do not Synchnize variables here, make sure of that before calling this routine
-  int myrank, nprocs;
+  int myrank;
   MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-  MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
 
   int ordn = 2 * ghost_width;
   MyList<var> *varl;
@@ -521,20 +354,24 @@ void Patch::Interp_Points(MyList<var> *VarList,
     varl = varl->next;
   }
 
-  memset(Shellf, 0, sizeof(double) * NN * num_var);
+  double *shellf;
+  shellf = new double[NN * num_var];
+  memset(shellf, 0, sizeof(double) * NN * num_var);
 
-  // owner_rank[j] records which MPI rank owns point j
-  // All ranks traverse the same block list so they all agree on ownership
-  int *owner_rank;
-  owner_rank = new int[NN];
-  for (int j = 0; j < NN; j++)
-    owner_rank[j] = -1;
+  // we use weight to monitor code, later some day we can move it for optimization
+  int *weight;
+  weight = new int[NN];
+  memset(weight, 0, sizeof(int) * NN);
+
+  double *DH, *llb, *uub;
+  DH = new double[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);
+  }
+  llb = new double[dim];
+  uub = new double[dim];
 
   for (int j = 0; j < NN; j++) // run along points
   {
@@ -557,350 +394,165 @@ void Patch::Interp_Points(MyList<var> *VarList,
       }
     }
 
-    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    if (block_i >= 0)
+    MyList<Block> *Bp = blb;
+    bool notfind = true;
+    while (notfind && Bp) // run along Blocks
     {
-      Block *BP = block_index.views[block_i].bp;
-      owner_rank[j] = BP->rank;
-      if (myrank == BP->rank)
-      {
-        //---> interpolation
-        varl = 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],
-                          pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
-          varl = varl->next;
-          k++;
-        }
-      }
-    }
-  }
+      Block *BP = Bp->data;
 
-  // Replace MPI_Allreduce with per-owner MPI_Bcast:
-  // Group consecutive points by owner rank and broadcast each group.
-  // Since each point's data is non-zero only on the owner rank,
-  // Bcast from owner is equivalent to Allreduce(MPI_SUM) but much cheaper.
-  {
-    int j = 0;
-    while (j < NN)
-    {
-      int cur_owner = owner_rank[j];
-      if (cur_owner < 0)
+      bool flag = true;
+      for (int i = 0; i < dim; i++)
       {
-        if (myrank == 0)
-        {
-          cout << "ERROR: Patch::Interp_Points fails to find point (";
-          for (int d = 0; d < dim; d++)
-          {
-            cout << XX[d][j];
-            if (d < dim - 1)
-              cout << ",";
-            else
-              cout << ")";
-          }
-          cout << " on Patch (";
-          for (int d = 0; d < dim; d++)
-          {
-            cout << bbox[d] << "+" << lli[d] * DH[d];
-            if (d < dim - 1)
-              cout << ",";
-            else
-              cout << ")--";
-          }
-          cout << "(";
-          for (int d = 0; d < dim; d++)
-          {
-            cout << bbox[dim + d] << "-" << uui[d] * DH[d];
-            if (d < dim - 1)
-              cout << ",";
-            else
-              cout << ")" << endl;
-          }
-          MPI_Abort(MPI_COMM_WORLD, 1);
-        }
-        j++;
-        continue;
-      }
-      // Find contiguous run of points with the same owner
-      int jstart = j;
-      while (j < NN && owner_rank[j] == cur_owner)
-        j++;
-      int count = (j - jstart) * num_var;
-      MPI_Bcast(Shellf + jstart * num_var, count, MPI_DOUBLE, cur_owner, MPI_COMM_WORLD);
-    }
-  }
-
-  delete[] owner_rank;
-}
-void Patch::Interp_Points(MyList<var> *VarList,
-                          int NN, double **XX,
-                          double *Shellf, int Symmetry,
-                          int Nmin_consumer, int Nmax_consumer)
-{
-  // 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();
+// NOTE: our dividing structure is (exclude ghost)
+// -1 0
+//       1  2
+// so (0,1) does not belong to any part for vertex structure
+// here we put (0,0.5) to left part and (0.5,1) to right part
+// BUT for cell structure the bbox is (-1.5,0.5) and (0.5,2.5), there is no missing region at all
+#ifdef Vertex
+#ifdef Cell
+#error Both Cell and Vertex are defined
 #endif
-  int myrank, nprocs;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-  MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
-
-  int ordn = 2 * ghost_width;
-  MyList<var> *varl;
-  int num_var = 0;
-  varl = VarList;
-  while (varl)
-  {
-    num_var++;
-    varl = varl->next;
-  }
-
-  memset(Shellf, 0, sizeof(double) * NN * num_var);
-
-  // owner_rank[j] records which MPI rank owns point j
-  int *owner_rank;
-  owner_rank = new int[NN];
-  for (int j = 0; j < NN; j++)
-    owner_rank[j] = -1;
-
-  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) ---
-  for (int j = 0; j < NN; j++)
-  {
-    double pox[dim];
-    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]))
-      {
-        cout << "Patch::Interp_Points: point (";
-        for (int k = 0; k < dim; k++)
-        {
-          cout << XX[k][j];
-          if (k < dim - 1)
-            cout << ",";
-          else
-            cout << ") is out of current Patch." << endl;
-        }
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-    }
-
-    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    if (block_i >= 0)
-    {
-      Block *BP = block_index.views[block_i].bp;
-      owner_rank[j] = BP->rank;
-      if (myrank == BP->rank)
-      {
-        varl = VarList;
-        int k = 0;
-        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],
-                          pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
-          varl = varl->next;
-          k++;
-        }
-      }
-    }
-  }
-
-#ifdef INTERP_LB_PROFILE
-  double t_interp_end = MPI_Wtime();
-  double t_interp_local = t_interp_end - t_interp_start;
+        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;
+        }
+      }
 
-  // --- Error check for unfound points ---
-  for (int j = 0; j < NN; j++)
+      if (flag)
+      {
+        notfind = false;
+        if (myrank == BP->rank)
+        {
+          //---> interpolation
+          varl = VarList;
+          int k = 0;
+          while (varl) // run along variables
+          {
+            //              shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
+            //	  		                                    pox,ordn,varl->data->SoA,Symmetry);
+            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++;
+          }
+          weight[j] = 1;
+        }
+      }
+      if (Bp == ble)
+        break;
+      Bp = Bp->next;
+    }
+  }
+
+  MPI_Allreduce(shellf, Shellf, NN * num_var, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  int *Weight;
+  Weight = new int[NN];
+  MPI_Allreduce(weight, Weight, NN, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+
+  //  misc::tillherecheck("print me");
+
+  for (int i = 0; i < NN; i++)
   {
-    if (owner_rank[j] < 0 && myrank == 0)
+    if (Weight[i] > 1)
+    {
+      if (myrank == 0)
+        cout << "WARNING: Patch::Interp_Points meets multiple weight" << endl;
+      for (int j = 0; j < num_var; j++)
+        Shellf[j + i * num_var] = Shellf[j + i * num_var] / Weight[i];
+    }
+    else if (Weight[i] == 0 && myrank == 0)
     {
       cout << "ERROR: Patch::Interp_Points fails to find point (";
-      for (int d = 0; d < dim; d++)
+      for (int j = 0; j < dim; j++)
       {
-        cout << XX[d][j];
-        if (d < dim - 1)
+        cout << XX[j][i];
+        if (j < dim - 1)
           cout << ",";
         else
           cout << ")";
       }
       cout << " on Patch (";
-      for (int d = 0; d < dim; d++)
+      for (int j = 0; j < dim; j++)
       {
-        cout << bbox[d] << "+" << lli[d] * DH[d];
-        if (d < dim - 1)
+        cout << bbox[j] << "+" << lli[j] * getdX(j);
+        if (j < dim - 1)
           cout << ",";
         else
           cout << ")--";
       }
       cout << "(";
-      for (int d = 0; d < dim; d++)
+      for (int j = 0; j < dim; j++)
       {
-        cout << bbox[dim + d] << "-" << uui[d] * DH[d];
-        if (d < dim - 1)
+        cout << bbox[dim + j] << "-" << uui[j] * getdX(j);
+        if (j < dim - 1)
           cout << ",";
         else
           cout << ")" << endl;
       }
+#if 0
+       checkBlock();
+#else
+      cout << "splited domains:" << endl;
+      {
+        MyList<Block> *Bp = blb;
+        while (Bp)
+        {
+          Block *BP = Bp->data;
+
+          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
+          }
+          cout << "(";
+          for (int j = 0; j < dim; j++)
+          {
+            cout << llb[j] << ":" << uub[j];
+            if (j < dim - 1)
+              cout << ",";
+            else
+              cout << ")" << endl;
+          }
+          if (Bp == ble)
+            break;
+          Bp = Bp->next;
+        }
+      }
+#endif
       MPI_Abort(MPI_COMM_WORLD, 1);
     }
   }
 
-  // --- Targeted point-to-point communication phase ---
-  // Compute consumer_rank[j] using the same deterministic formula as surface_integral
-  int *consumer_rank = new int[NN];
-  {
-    int mp = NN / nprocs;
-    int Lp = NN - nprocs * mp;
-    for (int j = 0; j < NN; j++)
-    {
-      if (j < Lp * (mp + 1))
-        consumer_rank[j] = j / (mp + 1);
-      else
-        consumer_rank[j] = Lp + (j - Lp * (mp + 1)) / mp;
-    }
-  }
-
-  // Count sends and recvs per rank
-  int *send_count = new int[nprocs];
-  int *recv_count = new int[nprocs];
-  memset(send_count, 0, sizeof(int) * nprocs);
-  memset(recv_count, 0, sizeof(int) * nprocs);
-
-  for (int j = 0; j < NN; j++)
-  {
-    int own = owner_rank[j];
-    int con = consumer_rank[j];
-    if (own == con)
-      continue; // local — no communication needed
-    if (own == myrank)
-      send_count[con]++;
-    if (con == myrank)
-      recv_count[own]++;
-  }
-
-  // Build send buffers: for each destination rank, pack (index, data) pairs
-  // Each entry: 1 int (point index j) + num_var doubles
-  int total_send = 0, total_recv = 0;
-  int *send_offset = new int[nprocs];
-  int *recv_offset = new int[nprocs];
-  for (int r = 0; r < nprocs; r++)
-  {
-    send_offset[r] = total_send;
-    total_send += send_count[r];
-    recv_offset[r] = total_recv;
-    total_recv += recv_count[r];
-  }
-
-  // Pack send buffers: each message contains (j, data[0..num_var-1]) per point
-  int stride = 1 + num_var; // 1 double for index + num_var doubles for data
-  double *sendbuf = new double[total_send * stride];
-  double *recvbuf = new double[total_recv * stride];
-
-  // Temporary counters for packing
-  int *pack_pos = new int[nprocs];
-  memset(pack_pos, 0, sizeof(int) * nprocs);
-
-  for (int j = 0; j < NN; j++)
-  {
-    int own = owner_rank[j];
-    int con = consumer_rank[j];
-    if (own != myrank || con == myrank)
-      continue;
-    int pos = (send_offset[con] + pack_pos[con]) * stride;
-    sendbuf[pos] = (double)j; // point index
-    for (int v = 0; v < num_var; v++)
-      sendbuf[pos + 1 + v] = Shellf[j * num_var + v];
-    pack_pos[con]++;
-  }
-
-  // Post non-blocking recvs and sends
-  int n_req = 0;
-  for (int r = 0; r < nprocs; r++)
-  {
-    if (recv_count[r] > 0) n_req++;
-    if (send_count[r] > 0) n_req++;
-  }
-
-  MPI_Request *reqs = new MPI_Request[n_req];
-  int req_idx = 0;
-
-  for (int r = 0; r < nprocs; r++)
-  {
-    if (recv_count[r] > 0)
-    {
-      MPI_Irecv(recvbuf + recv_offset[r] * stride,
-                recv_count[r] * stride, MPI_DOUBLE,
-                r, 0, MPI_COMM_WORLD, &reqs[req_idx++]);
-    }
-  }
-  for (int r = 0; r < nprocs; r++)
-  {
-    if (send_count[r] > 0)
-    {
-      MPI_Isend(sendbuf + send_offset[r] * stride,
-                send_count[r] * stride, MPI_DOUBLE,
-                r, 0, MPI_COMM_WORLD, &reqs[req_idx++]);
-    }
-  }
-
-  if (n_req > 0)
-    MPI_Waitall(n_req, reqs, MPI_STATUSES_IGNORE);
-
-  // Unpack recv buffers into Shellf
-  for (int i = 0; i < total_recv; i++)
-  {
-    int pos = i * stride;
-    int j = (int)recvbuf[pos];
-    for (int v = 0; v < num_var; v++)
-      Shellf[j * num_var + v] = recvbuf[pos + 1 + v];
-  }
-
-  delete[] reqs;
-  delete[] sendbuf;
-  delete[] recvbuf;
-  delete[] pack_pos;
-  delete[] send_offset;
-  delete[] recv_offset;
-  delete[] send_count;
-  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
+  delete[] shellf;
+  delete[] weight;
+  delete[] Weight;
+  delete[] DH;
+  delete[] llb;
+  delete[] uub;
 }
 void Patch::Interp_Points(MyList<var> *VarList,
                           int NN, double **XX,
@@ -921,24 +573,24 @@ void Patch::Interp_Points(MyList<var> *VarList,
     varl = varl->next;
   }
 
-  memset(Shellf, 0, sizeof(double) * NN * num_var);
+  double *shellf;
+  shellf = new double[NN * num_var];
+  memset(shellf, 0, sizeof(double) * NN * num_var);
 
-  // owner_rank[j] stores the global rank that owns point j
-  int *owner_rank;
-  owner_rank = new int[NN];
-  for (int j = 0; j < NN; j++)
-    owner_rank[j] = -1;
+  // we use weight to monitor code, later some day we can move it for optimization
+  int *weight;
+  weight = new int[NN];
+  memset(weight, 0, sizeof(int) * NN);
 
-  // Build global-to-local rank translation for Comm_here
-  MPI_Group world_group, local_group;
-  MPI_Comm_group(MPI_COMM_WORLD, &world_group);
-  MPI_Comm_group(Comm_here, &local_group);
+  double *DH, *llb, *uub;
+  DH = new double[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);
+  }
+  llb = new double[dim];
+  uub = new double[dim];
 
   for (int j = 0; j < NN; j++) // run along points
   {
@@ -961,56 +613,159 @@ void Patch::Interp_Points(MyList<var> *VarList,
       }
     }
 
-    const int block_i = find_block_index_for_point(block_index, pox, DH);
-    if (block_i >= 0)
+    MyList<Block> *Bp = blb;
+    bool notfind = true;
+    while (notfind && Bp) // run along Blocks
     {
-      Block *BP = block_index.views[block_i].bp;
-      owner_rank[j] = BP->rank;
-      if (myrank == BP->rank)
+      Block *BP = Bp->data;
+
+      bool flag = true;
+      for (int i = 0; i < dim; i++)
       {
-        //---> interpolation
-        varl = VarList;
-        int k = 0;
-        while (varl) // run along variables
+// NOTE: our dividing structure is (exclude ghost)
+// -1 0
+//       1  2
+// so (0,1) does not belong to any part for vertex structure
+// here we put (0,0.5) to left part and (0.5,1) to right part
+// BUT for cell structure the bbox is (-1.5,0.5) and (0.5,2.5), there is no missing region at all
+#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)
         {
-          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++;
+          flag = false;
+          break;
         }
       }
-    }
-  }
 
-  // Collect unique global owner ranks and translate to local ranks in Comm_here
-  // Then broadcast each owner's points via MPI_Bcast on Comm_here
-  {
-    int j = 0;
-    while (j < NN)
-    {
-      int cur_owner_global = owner_rank[j];
-      if (cur_owner_global < 0)
+      if (flag)
       {
-        // Point not found — skip (error check disabled for sub-communicator levels)
-        j++;
-        continue;
+        notfind = false;
+        if (myrank == BP->rank)
+        {
+          //---> interpolation
+          varl = VarList;
+          int k = 0;
+          while (varl) // run along variables
+          {
+            //              shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
+            //	  		                                    pox,ordn,varl->data->SoA,Symmetry);
+            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++;
+          }
+          weight[j] = 1;
+        }
       }
-      // Translate global rank to local rank in Comm_here
-      int cur_owner_local;
-      MPI_Group_translate_ranks(world_group, 1, &cur_owner_global, local_group, &cur_owner_local);
-
-      // Find contiguous run of points with the same owner
-      int jstart = j;
-      while (j < NN && owner_rank[j] == cur_owner_global)
-        j++;
-      int count = (j - jstart) * num_var;
-      MPI_Bcast(Shellf + jstart * num_var, count, MPI_DOUBLE, cur_owner_local, Comm_here);
+      if (Bp == ble)
+        break;
+      Bp = Bp->next;
     }
   }
 
-  MPI_Group_free(&world_group);
-  MPI_Group_free(&local_group);
-  delete[] owner_rank;
+  MPI_Allreduce(shellf, Shellf, NN * num_var, MPI_DOUBLE, MPI_SUM, Comm_here);
+  int *Weight;
+  Weight = new int[NN];
+  MPI_Allreduce(weight, Weight, NN, MPI_INT, MPI_SUM, Comm_here);
+
+  //  misc::tillherecheck("print me");
+  //  if(lmyrank == 0) cout<<"myrank = "<<myrank<<"print me"<<endl;
+
+  for (int i = 0; i < NN; i++)
+  {
+    if (Weight[i] > 1)
+    {
+      if (lmyrank == 0)
+        cout << "WARNING: Patch::Interp_Points meets multiple weight" << endl;
+      for (int j = 0; j < num_var; j++)
+        Shellf[j + i * num_var] = Shellf[j + i * num_var] / Weight[i];
+    }
+#if 0 // for not involved levels, this may fail     
+     else if(Weight[i] == 0 && lmyrank == 0)
+     {
+       cout<<"ERROR: Patch::Interp_Points fails to find point (";
+       for(int j=0;j<dim;j++)
+       {
+	  cout<<XX[j][i];
+	  if(j<dim-1) cout<<",";
+	  else        cout<<")";
+       }
+       cout<<" on Patch (";
+       for(int j=0;j<dim;j++)
+       {
+	  cout<<bbox[j]<<"+"<<lli[j]*getdX(j);
+	  if(j<dim-1) cout<<",";
+	  else        cout<<")--";
+       }
+       cout<<"(";
+       for(int j=0;j<dim;j++)
+       {
+	  cout<<bbox[dim+j]<<"-"<<uui[j]*getdX(j);
+	  if(j<dim-1) cout<<",";
+	  else        cout<<")"<<endl;
+       }
+#if 0
+       checkBlock();
+#else
+  cout<<"splited domains:"<<endl;
+  {
+     MyList<Block> *Bp=blb;
+     while(Bp)
+     {
+	Block *BP=Bp->data;
+
+	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 
+	}       
+       cout<<"(";
+       for(int j=0;j<dim;j++)
+       {
+	  cout<<llb[j]<<":"<<uub[j];
+	  if(j<dim-1) cout<<",";
+	  else        cout<<")"<<endl;
+       }
+	if(Bp == ble) break;
+	Bp=Bp->next;
+     }
+  }
+#endif       
+       MPI_Abort(MPI_COMM_WORLD,1);
+     }
+#endif
+  }
+
+  delete[] shellf;
+  delete[] weight;
+  delete[] Weight;
+  delete[] DH;
+  delete[] llb;
+  delete[] uub;
 }
 void Patch::checkBlock()
 {

AMSS_NCKU_source/MPatch.h

@@ -39,10 +39,6 @@ public:
 
    bool Find_Point(double *XX);
 
-   void Interp_Points(MyList<var> *VarList,
-                      int NN, double **XX,
-                      double *Shellf, int Symmetry,
-                      int Nmin_consumer, int Nmax_consumer);
    void Interp_Points(MyList<var> *VarList,
                       int NN, double **XX,
                       double *Shellf, int Symmetry, MPI_Comm Comm_here);

AMSS_NCKU_source/Parallel.h

@@ -32,16 +32,6 @@ 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));
@@ -91,43 +81,6 @@ namespace Parallel
                    int Symmetry);
   void Sync(Patch *Pat, MyList<var> *VarList, int Symmetry);
   void Sync(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
-  void Sync_merged(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
-
-  struct SyncCache {
-    bool valid;
-    int cpusize;
-    MyList<gridseg> **combined_src;
-    MyList<gridseg> **combined_dst;
-    int *send_lengths;
-    int *recv_lengths;
-    double **send_bufs;
-    double **recv_bufs;
-    int *send_buf_caps;
-    int *recv_buf_caps;
-    MPI_Request *reqs;
-    MPI_Status *stats;
-    int max_reqs;
-    bool lengths_valid;
-    SyncCache();
-    void invalidate();
-    void destroy();
-  };
-
-  void Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry, SyncCache &cache);
-  void transfer_cached(MyList<gridseg> **src, MyList<gridseg> **dst,
-                       MyList<var> *VarList1, MyList<var> *VarList2,
-                       int Symmetry, SyncCache &cache);
-
-  struct AsyncSyncState {
-    int req_no;
-    bool active;
-    AsyncSyncState() : req_no(0), active(false) {}
-  };
-
-  void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
-                  SyncCache &cache, AsyncSyncState &state);
-  void Sync_finish(SyncCache &cache, AsyncSyncState &state,
-                   MyList<var> *VarList, int Symmetry);
   void OutBdLow2Hi(Patch *Patc, Patch *Patf,
                    MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
                    int Symmetry);
@@ -140,15 +93,6 @@ 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/TwoPunctures.h

@@ -1,8 +1,7 @@
+
 #ifndef TWO_PUNCTURES_H
 #define TWO_PUNCTURES_H
 
-#include <omp.h>
-
 #define StencilSize 19
 #define N_PlaneRelax 1
 #define NRELAX 200
@@ -33,7 +32,7 @@ private:
        int npoints_A, npoints_B, npoints_phi;
 
        double target_M_plus, target_M_minus;
-
+       
        double admMass;
 
        double adm_tol;
@@ -43,18 +42,6 @@ private:
 
        int ntotal;
 
-       // ===== Precomputed spectral derivative matrices =====
-       double *D1_A, *D2_A;
-       double *D1_B, *D2_B;
-       double *DF1_phi, *DF2_phi;
-
-       // ===== Pre-allocated workspace for LineRelax (per-thread) =====
-       int max_threads;
-       double **ws_diag_be, **ws_e_be, **ws_f_be, **ws_b_be, **ws_x_be;
-       double **ws_l_be, **ws_u_be, **ws_d_be, **ws_y_be;
-       double **ws_diag_al, **ws_e_al, **ws_f_al, **ws_b_al, **ws_x_al;
-       double **ws_l_al, **ws_u_al, **ws_d_al, **ws_y_al;
-
        struct parameters
        {
               int nvar, n1, n2, n3;
@@ -71,28 +58,6 @@ public:
                     int Newtonmaxit);
        ~TwoPunctures();
 
-       // 02/07: New/modified methods
-       void allocate_workspace();
-       void free_workspace();
-       void precompute_derivative_matrices();
-       void build_cheb_deriv_matrices(int n, double *D1, double *D2);
-       void build_fourier_deriv_matrices(int N, double *DF1, double *DF2);
-       void Derivatives_AB3_MatMul(int nvar, int n1, int n2, int n3, derivs v);
-       void ThomasAlgorithm_ws(int N, double *b, double *a, double *c, double *x, double *q,
-                                double *l, double *u_ws, double *d, double *y);
-       void LineRelax_be_omp(double *dv,
-                         int const i, int const k, int const nvar,
-                         int const n1, int const n2, int const n3,
-                         double const *rhs, int const *ncols, int **cols,
-                         double **JFD, int tid);
-       void LineRelax_al_omp(double *dv,
-                         int const j, int const k, int const nvar,
-                         int const n1, int const n2, int const n3,
-                         double const *rhs, int const *ncols,
-                         int **cols, double **JFD, int tid);
-       void relax_omp(double *dv, int const nvar, int const n1, int const n2, int const n3,
-                  double const *rhs, int const *ncols, int **cols, double **JFD);
-
        void Solve();
        void set_initial_guess(derivs v);
        int index(int i, int j, int k, int l, int a, int b, int c, int d);
@@ -151,11 +116,23 @@ public:
        double BY_KKofxyz(double x, double y, double z);
        void SetMatrix_JFD(int nvar, int n1, int n2, int n3, derivs u, int *ncols, int **cols, double **Matrix);
        void J_times_dv(int nvar, int n1, int n2, int n3, derivs dv, double *Jdv, derivs u);
+       void relax(double *dv, int const nvar, int const n1, int const n2, int const n3,
+                  double const *rhs, int const *ncols, int **cols, double **JFD);
+       void LineRelax_be(double *dv,
+                         int const i, int const k, int const nvar,
+                         int const n1, int const n2, int const n3,
+                         double const *rhs, int const *ncols, int **cols,
+                         double **JFD);
        void JFD_times_dv(int i, int j, int k, int nvar, int n1, int n2,
                          int n3, derivs dv, derivs u, double *values);
        void LinEquations(double A, double B, double X, double R,
                          double x, double r, double phi,
                          double y, double z, derivs dU, derivs U, double *values);
+       void LineRelax_al(double *dv,
+                         int const j, int const k, int const nvar,
+                         int const n1, int const n2, int const n3,
+                         double const *rhs, int const *ncols,
+                         int **cols, double **JFD);
        void ThomasAlgorithm(int N, double *b, double *a, double *c, double *x, double *q);
        void Save(char *fname);
        // provided by Vasileios Paschalidis (vpaschal@illinois.edu)
@@ -164,4 +141,4 @@ public:
        void SpecCoef(parameters par, int ivar, double *v, double *cf);
 };
 
-#endif /* TWO_PUNCTURES_H */
+#endif /* TWO_PUNCTURES_H */

AMSS_NCKU_source/bssn_class.C

@@ -730,12 +730,6 @@ void bssn_class::Initialize()
     PhysTime = StartTime;
     Setup_Black_Hole_position();
   }
-
-  // Initialize sync caches (per-level, for predictor and corrector)
-  sync_cache_pre = new Parallel::SyncCache[GH->levels];
-  sync_cache_cor = new Parallel::SyncCache[GH->levels];
-  sync_cache_rp_coarse = new Parallel::SyncCache[GH->levels];
-  sync_cache_rp_fine = new Parallel::SyncCache[GH->levels];
 }
 
 //================================================================================================
@@ -987,32 +981,6 @@ bssn_class::~bssn_class()
   delete Azzz;
 #endif
 
-  // Destroy sync caches before GH
-  if (sync_cache_pre)
-  {
-    for (int i = 0; i < GH->levels; i++)
-      sync_cache_pre[i].destroy();
-    delete[] sync_cache_pre;
-  }
-  if (sync_cache_cor)
-  {
-    for (int i = 0; i < GH->levels; i++)
-      sync_cache_cor[i].destroy();
-    delete[] sync_cache_cor;
-  }
-  if (sync_cache_rp_coarse)
-  {
-    for (int i = 0; i < GH->levels; i++)
-      sync_cache_rp_coarse[i].destroy();
-    delete[] sync_cache_rp_coarse;
-  }
-  if (sync_cache_rp_fine)
-  {
-    for (int i = 0; i < GH->levels; i++)
-      sync_cache_rp_fine[i].destroy();
-    delete[] sync_cache_rp_fine;
-  }
-
   delete GH;
 #ifdef WithShell
   delete SH;
@@ -2213,7 +2181,6 @@ void bssn_class::Evolve(int Steps)
     GH->Regrid(Symmetry, BH_num, Porgbr, Porg0,
                SynchList_cor, OldStateList, StateList, SynchList_pre,
                fgt(PhysTime - dT_mon, StartTime, dT_mon / 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
 
 #if (REGLEV == 0 && (PSTR == 1 || PSTR == 2))
@@ -2426,10 +2393,9 @@ void bssn_class::RecursiveStep(int lev)
 #endif
 
 #if (REGLEV == 0)
-  if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
+  GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                       SynchList_cor, OldStateList, StateList, SynchList_pre,
-                      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(); }
+                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
 #endif
 }
 
@@ -2605,10 +2571,9 @@ void bssn_class::ParallelStep()
   delete[] tporg;
   delete[] tporgo;
 #if (REGLEV == 0)
-  if (GH->Regrid_Onelevel(GH->mylev, Symmetry, BH_num, Porgbr, Porg0,
+  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))
-  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(); }
+                      fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
 #endif
 }
 
@@ -2772,10 +2737,9 @@ void bssn_class::ParallelStep()
       if (lev + 1 >= GH->movls)
       {
         //	       GH->Regrid_Onelevel_aux(lev,Symmetry,BH_num,Porgbr,Porg0,
-        if (GH->Regrid_Onelevel(lev + 1, Symmetry, BH_num, Porgbr, Porg0,
+        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))
-        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(); }
+                            fgt(PhysTime - dT_levp1, StartTime, dT_levp1 / 2), ErrorMonitor);
 
         //               a_stream.clear();
         //               a_stream.str("");
@@ -2787,10 +2751,9 @@ void bssn_class::ParallelStep()
     // for this level
     if (YN == 1)
     {
-      if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
+      GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                           SynchList_cor, OldStateList, StateList, SynchList_pre,
-                          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(); }
+                          fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor);
 
       //               a_stream.clear();
       //               a_stream.str("");
@@ -2806,10 +2769,9 @@ void bssn_class::ParallelStep()
         if (YN == 1)
         {
           //	   GH->Regrid_Onelevel_aux(lev-2,Symmetry,BH_num,Porgbr,Porg0,
-          if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
+          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))
-          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(); }
+                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor);
 
           //               a_stream.clear();
           //               a_stream.str("");
@@ -2822,10 +2784,9 @@ void bssn_class::ParallelStep()
         if (i % 4 == 3)
         {
           //	   GH->Regrid_Onelevel_aux(lev-2,Symmetry,BH_num,Porgbr,Porg0,
-          if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
+          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))
-          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(); }
+                              fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor);
 
           //               a_stream.clear();
           //               a_stream.str("");
@@ -3197,7 +3158,21 @@ void bssn_class::Step(int lev, int YN)
     }
     Pp = Pp->next;
   }
-  // NOTE: error check deferred to after Shell Patch computation to reduce MPI_Allreduce calls
+  // check error information
+  {
+    int erh = ERROR;
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+  }
+  if (ERROR)
+  {
+    Parallel::Dump_Data(GH->PatL[lev], StateList, 0, PhysTime, dT_lev);
+    if (myrank == 0)
+    {
+      if (ErrorMonitor->outfile)
+        ErrorMonitor->outfile << "find NaN in state variables at t = " << PhysTime << ", lev = " << lev << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
+  }
 
 #ifdef WithShell
   // evolve Shell Patches
@@ -3215,9 +3190,9 @@ void bssn_class::Step(int lev, int YN)
         {
 #if (AGM == 0)
           f_enforce_ga(cg->shape,
-                       cg->fgfs[gxx0->sgfn], cg->fgfs[gxy0->sgfn], cg->fgfs[gxz0->sgfn],
+                       cg->fgfs[gxx0->sgfn], cg->fgfs[gxy0->sgfn], cg->fgfs[gxz0->sgfn], 
                        cg->fgfs[gyy0->sgfn], cg->fgfs[gyz0->sgfn], cg->fgfs[gzz0->sgfn],
-                       cg->fgfs[Axx0->sgfn], cg->fgfs[Axy0->sgfn], cg->fgfs[Axz0->sgfn],
+                       cg->fgfs[Axx0->sgfn], cg->fgfs[Axy0->sgfn], cg->fgfs[Axz0->sgfn], 
                        cg->fgfs[Ayy0->sgfn], cg->fgfs[Ayz0->sgfn], cg->fgfs[Azz0->sgfn]);
 #endif
 
@@ -3341,16 +3316,25 @@ void bssn_class::Step(int lev, int YN)
 #endif
   }
 
-  // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-  MPI_Request err_req;
+  // check error information
   {
     int erh = ERROR;
-    MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req);
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+  }
+
+  if (ERROR)
+  {
+    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
+    if (myrank == 0)
+    {
+      if (ErrorMonitor->outfile)
+        ErrorMonitor->outfile << "find NaN in state variables on Shell Patches at t = " << PhysTime << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
   }
 #endif
 
-  Parallel::AsyncSyncState async_pre;
-  Parallel::Sync_start(GH->PatL[lev], SynchList_pre, Symmetry, sync_cache_pre[lev], async_pre);
+  Parallel::Sync(GH->PatL[lev], SynchList_pre, Symmetry);
 
 #ifdef WithShell
   if (lev == 0)
@@ -3363,29 +3347,12 @@ void bssn_class::Step(int lev, int YN)
     {
       prev_clock = curr_clock;
       curr_clock = clock();
-      cout << " Shell stuff synchronization used "
-           << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
+      cout << " Shell stuff synchronization used " 
+           << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
            << " seconds! " << endl;
     }
   }
 #endif
-  Parallel::Sync_finish(sync_cache_pre[lev], async_pre, SynchList_pre, Symmetry);
-
-#ifdef WithShell
-  // Complete non-blocking error reduction and check
-  MPI_Wait(&err_req, MPI_STATUS_IGNORE);
-  if (ERROR)
-  {
-    Parallel::Dump_Data(GH->PatL[lev], StateList, 0, PhysTime, dT_lev);
-    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
-    if (myrank == 0)
-    {
-      if (ErrorMonitor->outfile)
-        ErrorMonitor->outfile << "find NaN in state variables at t = " << PhysTime << ", lev = " << lev << endl;
-      MPI_Abort(MPI_COMM_WORLD, 1);
-    }
-  }
-#endif
 
 #if (MAPBH == 0)
   // for black hole position
@@ -3561,7 +3528,24 @@ void bssn_class::Step(int lev, int YN)
       Pp = Pp->next;
     }
 
-    // NOTE: error check deferred to after Shell Patch computation to reduce MPI_Allreduce calls
+    // check error information
+    {
+      int erh = ERROR;
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+    }
+
+    if (ERROR)
+    {
+      Parallel::Dump_Data(GH->PatL[lev], SynchList_pre, 0, PhysTime, dT_lev);
+      if (myrank == 0)
+      {
+        if (ErrorMonitor->outfile)
+          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count 
+                                << " variables at t = " << PhysTime 
+                                << ", lev = " << lev << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
+    }
 
 #ifdef WithShell
     // evolve Shell Patches
@@ -3579,9 +3563,9 @@ void bssn_class::Step(int lev, int YN)
           {
 #if (AGM == 0)
             f_enforce_ga(cg->shape,
-                         cg->fgfs[gxx->sgfn], cg->fgfs[gxy->sgfn], cg->fgfs[gxz->sgfn],
+                         cg->fgfs[gxx->sgfn], cg->fgfs[gxy->sgfn], cg->fgfs[gxz->sgfn], 
                          cg->fgfs[gyy->sgfn], cg->fgfs[gyz->sgfn], cg->fgfs[gzz->sgfn],
-                         cg->fgfs[Axx->sgfn], cg->fgfs[Axy->sgfn], cg->fgfs[Axz->sgfn],
+                         cg->fgfs[Axx->sgfn], cg->fgfs[Axy->sgfn], cg->fgfs[Axz->sgfn], 
                          cg->fgfs[Ayy->sgfn], cg->fgfs[Ayz->sgfn], cg->fgfs[Azz->sgfn]);
 #elif (AGM == 1)
             if (iter_count == 3)
@@ -3701,16 +3685,26 @@ void bssn_class::Step(int lev, int YN)
         sPp = sPp->next;
       }
     }
-    // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-    MPI_Request err_req_cor;
+    // check error information
     {
       int erh = ERROR;
-      MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req_cor);
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+    }
+    if (ERROR)
+    {
+      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
+      if (myrank == 0)
+      {
+        if (ErrorMonitor->outfile)
+          ErrorMonitor->outfile << "find NaN on Shell Patches in RK4 substep#" 
+                                << iter_count << " variables at t = " 
+                                << PhysTime << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
     }
 #endif
 
-    Parallel::AsyncSyncState async_cor;
-    Parallel::Sync_start(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_cor[lev], async_cor);
+    Parallel::Sync(GH->PatL[lev], SynchList_cor, Symmetry);
 
 #ifdef WithShell
     if (lev == 0)
@@ -3723,31 +3717,12 @@ void bssn_class::Step(int lev, int YN)
       {
         prev_clock = curr_clock;
         curr_clock = clock();
-        cout << " Shell stuff synchronization used "
-             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
+        cout << " Shell stuff synchronization used " 
+             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
              << " seconds! " << endl;
       }
     }
 #endif
-    Parallel::Sync_finish(sync_cache_cor[lev], async_cor, SynchList_cor, Symmetry);
-
-#ifdef WithShell
-    // Complete non-blocking error reduction and check
-    MPI_Wait(&err_req_cor, MPI_STATUS_IGNORE);
-    if (ERROR)
-    {
-      Parallel::Dump_Data(GH->PatL[lev], SynchList_pre, 0, PhysTime, dT_lev);
-      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
-      if (myrank == 0)
-      {
-        if (ErrorMonitor->outfile)
-          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count
-                                << " variables at t = " << PhysTime
-                                << ", lev = " << lev << endl;
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-    }
-#endif
 
 #if (MAPBH == 0)
     // for black hole position
@@ -4059,7 +4034,22 @@ void bssn_class::Step(int lev, int YN)
     }
     Pp = Pp->next;
   }
-  // NOTE: error check deferred to after Shell Patch computation to reduce MPI_Allreduce calls
+  // check error information
+  {
+    int erh = ERROR;
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+  }
+  if (ERROR)
+  {
+    Parallel::Dump_Data(GH->PatL[lev], StateList, 0, PhysTime, dT_lev);
+    if (myrank == 0)
+    {
+      if (ErrorMonitor->outfile)
+        ErrorMonitor->outfile << "find NaN in state variables at t = " << PhysTime 
+                              << ", lev = " << lev << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
+  }
 
 #ifdef WithShell
   // evolve Shell Patches
@@ -4077,15 +4067,15 @@ void bssn_class::Step(int lev, int YN)
         {
 #if (AGM == 0)
           f_enforce_ga(cg->shape,
-                       cg->fgfs[gxx0->sgfn], cg->fgfs[gxy0->sgfn], cg->fgfs[gxz0->sgfn],
+                       cg->fgfs[gxx0->sgfn], cg->fgfs[gxy0->sgfn], cg->fgfs[gxz0->sgfn], 
                        cg->fgfs[gyy0->sgfn], cg->fgfs[gyz0->sgfn], cg->fgfs[gzz0->sgfn],
-                       cg->fgfs[Axx0->sgfn], cg->fgfs[Axy0->sgfn], cg->fgfs[Axz0->sgfn],
+                       cg->fgfs[Axx0->sgfn], cg->fgfs[Axy0->sgfn], cg->fgfs[Axz0->sgfn], 
                        cg->fgfs[Ayy0->sgfn], cg->fgfs[Ayz0->sgfn], cg->fgfs[Azz0->sgfn]);
 #endif
 
           if (f_compute_rhs_bssn_ss(cg->shape, TRK4, cg->X[0], cg->X[1], cg->X[2],
-                                    cg->fgfs[fngfs + ShellPatch::gx],
-                                    cg->fgfs[fngfs + ShellPatch::gy],
+                                    cg->fgfs[fngfs + ShellPatch::gx], 
+                                    cg->fgfs[fngfs + ShellPatch::gy], 
                                     cg->fgfs[fngfs + ShellPatch::gz],
                                     cg->fgfs[fngfs + ShellPatch::drhodx], 
                                     cg->fgfs[fngfs + ShellPatch::drhody], 
@@ -4200,16 +4190,25 @@ void bssn_class::Step(int lev, int YN)
   }
 #endif
   }
-  // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-  MPI_Request err_req;
+  // check error information
   {
     int erh = ERROR;
-    MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req);
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+  }
+  if (ERROR)
+  {
+    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
+    if (myrank == 0)
+    {
+      if (ErrorMonitor->outfile)
+        ErrorMonitor->outfile << "find NaN in state variables on Shell Patches at t = " 
+                              << PhysTime << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
   }
 #endif
 
-  Parallel::AsyncSyncState async_pre;
-  Parallel::Sync_start(GH->PatL[lev], SynchList_pre, Symmetry, sync_cache_pre[lev], async_pre);
+  Parallel::Sync(GH->PatL[lev], SynchList_pre, Symmetry);
 
 #ifdef WithShell
   if (lev == 0)
@@ -4222,27 +4221,9 @@ void bssn_class::Step(int lev, int YN)
     {
       prev_clock = curr_clock;
       curr_clock = clock();
-      cout << " Shell stuff synchronization used "
-           << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
-           << " seconds! " << endl;
-    }
-  }
-#endif
-  Parallel::Sync_finish(sync_cache_pre[lev], async_pre, SynchList_pre, Symmetry);
-
-#ifdef WithShell
-  // Complete non-blocking error reduction and check
-  MPI_Wait(&err_req, MPI_STATUS_IGNORE);
-  if (ERROR)
-  {
-    Parallel::Dump_Data(GH->PatL[lev], StateList, 0, PhysTime, dT_lev);
-    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
-    if (myrank == 0)
-    {
-      if (ErrorMonitor->outfile)
-        ErrorMonitor->outfile << "find NaN in state variables at t = " << PhysTime
-                              << ", lev = " << lev << endl;
-      MPI_Abort(MPI_COMM_WORLD, 1);
+      cout << " Shell stuff synchronization used " 
+      << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
+      << " seconds! " << endl;
     }
   }
 #endif
@@ -4405,7 +4386,23 @@ void bssn_class::Step(int lev, int YN)
       Pp = Pp->next;
     }
 
-    // NOTE: error check deferred to after Shell Patch computation to reduce MPI_Allreduce calls
+    // check error information
+    {
+      int erh = ERROR;
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+    }
+    if (ERROR)
+    {
+      Parallel::Dump_Data(GH->PatL[lev], SynchList_pre, 0, PhysTime, dT_lev);
+      if (myrank == 0)
+      {
+        if (ErrorMonitor->outfile)
+          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count 
+                                << " variables at t = " << PhysTime 
+                                << ", lev = " << lev << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
+    }
 
 #ifdef WithShell
     // evolve Shell Patches
@@ -4423,9 +4420,9 @@ void bssn_class::Step(int lev, int YN)
           {
 #if (AGM == 0)
             f_enforce_ga(cg->shape,
-                         cg->fgfs[gxx->sgfn], cg->fgfs[gxy->sgfn], cg->fgfs[gxz->sgfn],
+                         cg->fgfs[gxx->sgfn], cg->fgfs[gxy->sgfn], cg->fgfs[gxz->sgfn], 
                          cg->fgfs[gyy->sgfn], cg->fgfs[gyz->sgfn], cg->fgfs[gzz->sgfn],
-                         cg->fgfs[Axx->sgfn], cg->fgfs[Axy->sgfn], cg->fgfs[Axz->sgfn],
+                         cg->fgfs[Axx->sgfn], cg->fgfs[Axy->sgfn], cg->fgfs[Axz->sgfn], 
                          cg->fgfs[Ayy->sgfn], cg->fgfs[Ayz->sgfn], cg->fgfs[Azz->sgfn]);
 #elif (AGM == 1)
             if (iter_count == 3)
@@ -4545,16 +4542,25 @@ void bssn_class::Step(int lev, int YN)
         sPp = sPp->next;
       }
     }
-    // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-    MPI_Request err_req_cor;
+    // check error information
     {
       int erh = ERROR;
-      MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req_cor);
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+    }
+    if (ERROR)
+    {
+      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
+      if (myrank == 0)
+      {
+        if (ErrorMonitor->outfile)
+          ErrorMonitor->outfile << "find NaN on Shell Patches in RK4 substep#" << iter_count 
+                                << " variables at t = " << PhysTime << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
     }
 #endif
 
-    Parallel::AsyncSyncState async_cor;
-    Parallel::Sync_start(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_cor[lev], async_cor);
+    Parallel::Sync(GH->PatL[lev], SynchList_cor, Symmetry);
 
 #ifdef WithShell
     if (lev == 0)
@@ -4567,30 +4573,11 @@ void bssn_class::Step(int lev, int YN)
       {
         prev_clock = curr_clock;
         curr_clock = clock();
-        cout << " Shell stuff synchronization used "
-             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
+        cout << " Shell stuff synchronization used " 
+             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
              << " seconds! " << endl;
       }
     }
-#endif
-    Parallel::Sync_finish(sync_cache_cor[lev], async_cor, SynchList_cor, Symmetry);
-
-#ifdef WithShell
-    // Complete non-blocking error reduction and check
-    MPI_Wait(&err_req_cor, MPI_STATUS_IGNORE);
-    if (ERROR)
-    {
-      Parallel::Dump_Data(GH->PatL[lev], SynchList_pre, 0, PhysTime, dT_lev);
-      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
-      if (myrank == 0)
-      {
-        if (ErrorMonitor->outfile)
-          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count
-                                << " variables at t = " << PhysTime
-                                << ", lev = " << lev << endl;
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-    }
 #endif
     // for black hole position
     if (BH_num > 0 && lev == GH->levels - 1)
@@ -4956,19 +4943,11 @@ void bssn_class::Step(int lev, int YN)
 
   //   misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"after Predictor rhs calculation");
 
-  // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-  MPI_Request err_req;
+  // check error information
   {
     int erh = ERROR;
-    MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, GH->Commlev[lev], &err_req);
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, GH->Commlev[lev]);
   }
-
-  //   misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Predictor sync");
-
-  Parallel::Sync_cached(GH->PatL[lev], SynchList_pre, Symmetry, sync_cache_pre[lev]);
-
-  // Complete non-blocking error reduction and check
-  MPI_Wait(&err_req, MPI_STATUS_IGNORE);
   if (ERROR)
   {
     Parallel::Dump_Data(GH->PatL[lev], StateList, 0, PhysTime, dT_lev);
@@ -4980,6 +4959,10 @@ void bssn_class::Step(int lev, int YN)
     }
   }
 
+  //   misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Predictor sync");
+
+  Parallel::Sync(GH->PatL[lev], SynchList_pre, Symmetry);
+
 #if (MAPBH == 0)
   // for black hole position
   if (BH_num > 0 && lev == GH->levels - 1)
@@ -5157,34 +5140,30 @@ void bssn_class::Step(int lev, int YN)
 
     //   misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Corrector error check");
 
-    // Non-blocking error reduction overlapped with Sync to hide Allreduce latency
-    MPI_Request err_req_cor;
+    // check error information
     {
       int erh = ERROR;
-      MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, GH->Commlev[lev], &err_req_cor);
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, GH->Commlev[lev]);
     }
-
-    //    misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Corrector sync");
-
-    Parallel::Sync_cached(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_cor[lev]);
-
-    //    misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"after Corrector sync");
-
-    // Complete non-blocking error reduction and check
-    MPI_Wait(&err_req_cor, MPI_STATUS_IGNORE);
     if (ERROR)
     {
       Parallel::Dump_Data(GH->PatL[lev], SynchList_pre, 0, PhysTime, dT_lev);
       if (myrank == 0)
       {
         if (ErrorMonitor->outfile)
-          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count
-                                << " variables at t = " << PhysTime
+          ErrorMonitor->outfile << "find NaN in RK4 substep#" << iter_count 
+                                << " variables at t = " << PhysTime 
                                 << ", lev = " << lev << endl;
         MPI_Abort(MPI_COMM_WORLD, 1);
       }
     }
 
+    //    misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Corrector sync");
+
+    Parallel::Sync(GH->PatL[lev], SynchList_cor, Symmetry);
+
+    //    misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"after Corrector sync");
+
 #if (MAPBH == 0)
     // for black hole position
     if (BH_num > 0 && lev == GH->levels - 1)
@@ -5468,11 +5447,21 @@ void bssn_class::SHStep()
 #if (PSTR == 1 || PSTR == 2)
 //   misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before Predictor's error check");
 #endif
-  // Non-blocking error reduction overlapped with Synch to hide Allreduce latency
-  MPI_Request err_req;
+  // check error information
   {
     int erh = ERROR;
-    MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req);
+    MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+  }
+
+  if (ERROR)
+  {
+    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
+    if (myrank == 0)
+    {
+      if (ErrorMonitor->outfile)
+        ErrorMonitor->outfile << "find NaN in state variables on Shell Patches at t = " << PhysTime << endl;
+      MPI_Abort(MPI_COMM_WORLD, 1);
+    }
   }
 
   {
@@ -5484,25 +5473,12 @@ void bssn_class::SHStep()
     {
       prev_clock = curr_clock;
       curr_clock = clock();
-      cout << " Shell stuff synchronization used "
-           << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
+      cout << " Shell stuff synchronization used " 
+           << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
            << " seconds! " << endl;
     }
   }
 
-  // Complete non-blocking error reduction and check
-  MPI_Wait(&err_req, MPI_STATUS_IGNORE);
-  if (ERROR)
-  {
-    SH->Dump_Data(StateList, 0, PhysTime, dT_lev);
-    if (myrank == 0)
-    {
-      if (ErrorMonitor->outfile)
-        ErrorMonitor->outfile << "find NaN in state variables on Shell Patches at t = " << PhysTime << endl;
-      MPI_Abort(MPI_COMM_WORLD, 1);
-    }
-  }
-
   // corrector
   for (iter_count = 1; iter_count < 4; iter_count++)
   {
@@ -5645,11 +5621,21 @@ void bssn_class::SHStep()
         sPp = sPp->next;
       }
     }
-    // Non-blocking error reduction overlapped with Synch to hide Allreduce latency
-    MPI_Request err_req_cor;
+    // check error information
     {
       int erh = ERROR;
-      MPI_Iallreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD, &err_req_cor);
+      MPI_Allreduce(&erh, &ERROR, 1, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
+    }
+    if (ERROR)
+    {
+      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
+      if (myrank == 0)
+      {
+        if (ErrorMonitor->outfile)
+          ErrorMonitor->outfile << "find NaN on Shell Patches in RK4 substep#" << iter_count 
+                                << " variables at t = " << PhysTime << endl;
+        MPI_Abort(MPI_COMM_WORLD, 1);
+      }
     }
 
     {
@@ -5661,26 +5647,12 @@ void bssn_class::SHStep()
       {
         prev_clock = curr_clock;
         curr_clock = clock();
-        cout << " Shell stuff synchronization used "
-             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC)
+        cout << " Shell stuff synchronization used " 
+             << (double)(curr_clock - prev_clock) / ((double)CLOCKS_PER_SEC) 
              << " seconds! " << endl;
       }
     }
 
-    // Complete non-blocking error reduction and check
-    MPI_Wait(&err_req_cor, MPI_STATUS_IGNORE);
-    if (ERROR)
-    {
-      SH->Dump_Data(SynchList_pre, 0, PhysTime, dT_lev);
-      if (myrank == 0)
-      {
-        if (ErrorMonitor->outfile)
-          ErrorMonitor->outfile << "find NaN on Shell Patches in RK4 substep#" << iter_count
-                                << " variables at t = " << PhysTime << endl;
-        MPI_Abort(MPI_COMM_WORLD, 1);
-      }
-    }
-
     sPp = SH->PatL;
     while (sPp)
     {
@@ -5809,7 +5781,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 //       misc::tillherecheck(GH->Commlev[GH->mylev],GH->start_rank[GH->mylev],a_stream.str());
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], SynchList_pre, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], SynchList_pre, Symmetry);
 
 #if (PSTR == 1 || PSTR == 2)
 //       a_stream.clear();
@@ -5819,11 +5791,21 @@ 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(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -5860,7 +5842,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 //       misc::tillherecheck(GH->Commlev[GH->mylev],GH->start_rank[GH->mylev],a_stream.str());
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], SL, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], SL, Symmetry);
 
 #if (PSTR == 1 || PSTR == 2)
 //       a_stream.clear();
@@ -5870,11 +5852,21 @@ 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(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -5888,7 +5880,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 #endif
     }
 
-    Parallel::Sync_cached(GH->PatL[lev], SL, Symmetry, sync_cache_rp_fine[lev]);
+    Parallel::Sync(GH->PatL[lev], SL, Symmetry);
 
 #if (PSTR == 1 || PSTR == 2)
 //    a_stream.clear();
@@ -5946,14 +5938,24 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, GH->rsul[lev], Symmetry);
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], SynchList_pre, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], SynchList_pre, Symmetry);
 
 #if (RPB == 0)
+      Ppc = GH->PatL[lev - 1];
+      while (Ppc)
+      {
+        Pp = GH->PatL[lev];
+        while (Pp)
+        {
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -5968,21 +5970,31 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, GH->rsul[lev], Symmetry);
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], SL, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], SL, Symmetry);
 
 #if (RPB == 0)
+      Ppc = GH->PatL[lev - 1];
+      while (Ppc)
+      {
+        Pp = GH->PatL[lev];
+        while (Pp)
+        {
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
 #endif
     }
 
-    Parallel::Sync_cached(GH->PatL[lev], SL, Symmetry, sync_cache_rp_fine[lev]);
+    Parallel::Sync(GH->PatL[lev], SL, Symmetry);
   }
 }
 
@@ -6033,14 +6045,24 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, SynchList_pre, GH->rsul[lev], Symmetry);
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], SynchList_pre, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], SynchList_pre, Symmetry);
 
 #if (RPB == 0)
+      Ppc = GH->PatL[lev - 1];
+      while (Ppc)
+      {
+        Pp = GH->PatL[lev];
+        while (Pp)
+        {
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -6057,21 +6079,31 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, StateList, GH->rsul[lev], Symmetry);
 #endif
 
-      Parallel::Sync_cached(GH->PatL[lev - 1], StateList, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], StateList, Symmetry);
 
 #if (RPB == 0)
+      Ppc = GH->PatL[lev - 1];
+      while (Ppc)
+      {
+        Pp = GH->PatL[lev];
+        while (Pp)
+        {
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
 #endif
     }
 
-    Parallel::Sync_cached(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_rp_fine[lev]);
+    Parallel::Sync(GH->PatL[lev], SynchList_cor, Symmetry);
   }
 }
 
@@ -6101,11 +6133,21 @@ 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(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -6114,11 +6156,21 @@ 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(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Hi(Ppc->data, Pp->data, StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
-      Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
+          Parallel::OutBdLow2Himix(Ppc->data, Pp->data, 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);
@@ -6134,10 +6186,10 @@ void bssn_class::ProlongRestrict(int lev, int YN, bool BB)
 #else
       Parallel::Restrict_after(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, StateList, Symmetry);
 #endif
-      Parallel::Sync_cached(GH->PatL[lev - 1], StateList, Symmetry, sync_cache_rp_coarse[lev]);
+      Parallel::Sync(GH->PatL[lev - 1], StateList, Symmetry);
     }
 
-    Parallel::Sync_cached(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_rp_fine[lev]);
+    Parallel::Sync(GH->PatL[lev], SynchList_cor, Symmetry);
   }
 }
 #undef MIXOUTB

AMSS_NCKU_source/bssn_class.h

@@ -126,11 +126,6 @@ public:
        MyList<var> *OldStateList, *DumpList;
        MyList<var> *ConstraintList;
 
-       Parallel::SyncCache *sync_cache_pre;  // per-level cache for predictor sync
-       Parallel::SyncCache *sync_cache_cor;  // per-level cache for corrector sync
-       Parallel::SyncCache *sync_cache_rp_coarse;  // RestrictProlong sync on PatL[lev-1]
-       Parallel::SyncCache *sync_cache_rp_fine;    // RestrictProlong sync on PatL[lev]
-
        monitor *ErrorMonitor, *Psi4Monitor, *BHMonitor, *MAPMonitor;
        monitor *ConVMonitor;
        surface_integral *Waveshell;

AMSS_NCKU_source/bssn_gpu.cu

@@ -18,7 +18,7 @@ using namespace std;
 #include <fstream>
 #endif
 
-void compare_result_gpu(int ftag1,double * datac,int data_num){
+static void compare_result_gpu(int ftag1,double * datac,int data_num){
 	double * data = (double*)malloc(sizeof(double)*data_num);
 	cudaMemcpy(data, datac, data_num * sizeof(double), cudaMemcpyDeviceToHost);
 	compare_result(ftag1,data,data_num);
@@ -83,7 +83,7 @@ inline void sub_enforce_ga(int matrix_size){
 	double * trA = M_ chin1;
 	enforce_ga<<<GRID_DIM,BLOCK_DIM>>>(trA);
 	cudaMemset(trA,0,matrix_size * sizeof(double));
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 	
 	//cudaMemset(Mh_ gupxx,0,matrix_size * sizeof(double));
 	//trA gxx,gyy,gzz gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
@@ -273,13 +273,13 @@ __global__ void sub_symmetry_bd_partK(int ord,double * func, double * funcc,doub
 #endif //ifdef Vertex
 inline void sub_symmetry_bd(int ord,double * func, double * funcc,double * SoA){
 	sub_symmetry_bd_partF<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_symmetry_bd_partI<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc,SoA[0]);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_symmetry_bd_partJ<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc,SoA[1]);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_symmetry_bd_partK<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc,SoA[2]);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 }
 
 
@@ -378,9 +378,9 @@ inline void sub_fdderivs(double * f,double *fh,double *fxx,double *fxy,double *f
 	cudaMemset(fyy,0,_3D_SIZE[0] * sizeof(double));
 	cudaMemset(fyz,0,_3D_SIZE[0] * sizeof(double));
 	cudaMemset(fzz,0,_3D_SIZE[0] * sizeof(double));
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 	sub_fdderivs_part1<<<GRID_DIM,BLOCK_DIM>>>(f,fh,fxx,fxy,fxz,fyy,fyz,fzz);
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 }
 
 __global__ void sub_fderivs_part1(double * f,double * fh,double *fx,double *fy,double *fz  )
@@ -445,9 +445,9 @@ inline void sub_fderivs(double * f,double * fh,double *fx,double *fy,double *fz,
 	cudaMemset(fy,0,_3D_SIZE[0] * sizeof(double));
 	cudaMemset(fz,0,_3D_SIZE[0] * sizeof(double));
 	
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 	sub_fderivs_part1<<<GRID_DIM,BLOCK_DIM>>>(f,fh,fx,fy,fz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 }
 
 __global__ void computeRicci_part1(double * dst)
@@ -465,9 +465,9 @@ __global__ void computeRicci_part1(double * dst)
  inline void computeRicci(double * src,double* dst,double * SoA, Meta* meta)
 {
 	sub_fdderivs(src,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,SoA);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	computeRicci_part1<<<GRID_DIM,BLOCK_DIM>>>(dst);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 }/*Exception*/
 
@@ -524,9 +524,9 @@ __global__ void sub_kodis_part1(double *f,double *fh,double *f_rhs)
 inline void sub_kodis(double *f,double *fh,double *f_rhs,double *SoA)
 {
 	sub_symmetry_bd(3,f,fh,SoA);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_kodis_part1<<<GRID_DIM,BLOCK_DIM>>>(f,fh,f_rhs);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 }
  
 __global__ void  sub_lopsided_part1(double *f,double* fh,double *f_rhs,double *Sfx,double *Sfy,double *Sfz)
@@ -617,9 +617,9 @@ __global__ void  sub_lopsided_part1(double *f,double* fh,double *f_rhs,double *S
 
 inline void  sub_lopsided(double *f,double*fh,double *f_rhs,double *Sfx,double *Sfy,double *Sfz,double *SoA){
 	sub_symmetry_bd(3,f,fh,SoA);
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 	sub_lopsided_part1<<<GRID_DIM,BLOCK_DIM>>>(f,fh,f_rhs,Sfx,Sfy,Sfz);
-	cudaThreadSynchronize(); 
+	cudaDeviceSynchronize(); 
 }
 
 __global__ void compute_rhs_bssn_part1() 
@@ -2656,13 +2656,13 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 
 
 #ifdef TIMING1
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	gettimeofday(&tv2, NULL);
    	cout<<"TIME USED"<<TimeBetween(tv1, tv2)<<endl; 
 #endif	
 	//cout<<"GPU meta data ready.\n";
 	
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 
 //--------------test constant memory address & value--------------
 /*	double rank = mpi_rank;
@@ -2685,7 +2685,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 	//sub_enforce_ga(matrix_size);
 	//4.1-----compute rhs---------
 	compute_rhs_bssn_part1<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 
 	sub_fderivs(Mh_ betax,Mh_ fh,Mh_ betaxx,Mh_ betaxy,Mh_ betaxz,ass);
 	sub_fderivs(Mh_ betay,Mh_ fh,Mh_ betayx,Mh_ betayy,Mh_ betayz,sas);
@@ -2701,7 +2701,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 	sub_fderivs(Mh_ gyz,Mh_ fh,Mh_ gyzx,Mh_ gyzy,Mh_ gyzz, saa);
   	
   	compute_rhs_bssn_part2<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs(Mh_ betax,Mh_ fh,Mh_ gxxx,Mh_ gxyx,Mh_ gxzx,Mh_ gyyx,Mh_ gyzx,Mh_ gzzx,ass);
 	sub_fdderivs(Mh_ betay,Mh_ fh,Mh_ gxxy,Mh_ gxyy,Mh_ gxzy,Mh_ gyyy,Mh_ gyzy,Mh_ gzzy,sas);
@@ -2711,7 +2711,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 	sub_fderivs( Mh_ Gamz, Mh_ fh,Mh_ Gamzx, Mh_ Gamzy, Mh_ Gamzz,ssa);
 	
 	compute_rhs_bssn_part3<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	computeRicci(Mh_ dxx,Mh_ Rxx,sss, meta);
 	computeRicci(Mh_ dyy,Mh_ Ryy,sss, meta);
@@ -2720,20 +2720,20 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 	computeRicci(Mh_ gxz,Mh_ Rxz,asa, meta);
 	computeRicci(Mh_ gyz,Mh_ Ryz,saa, meta);
 	
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	compute_rhs_bssn_part4<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs(Mh_ chi,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,sss);
 	
 	compute_rhs_bssn_part5<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs(Mh_ Lap,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,sss);
 	
 	compute_rhs_bssn_part6<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 #if (GAUGE == 2 || GAUGE == 3 || GAUGE == 4 || GAUGE == 5)
 	sub_fderivs(Mh_ chi,Mh_ fh, Mh_ dtSfx_rhs, Mh_ dtSfy_rhs, Mh_ dtSfz_rhs,sss);
@@ -2805,7 +2805,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 	
 	if(co == 0){
 		compute_rhs_bssn_part7<<<GRID_DIM,BLOCK_DIM>>>();
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 
 		sub_fderivs(Mh_ Axx,Mh_ fh,Mh_ gxxx,Mh_ gxxy,Mh_ gxxz,sss);
 		sub_fderivs(Mh_ Axy,Mh_ fh,Mh_ gxyx,Mh_ gxyy,Mh_ gxyz,aas);
@@ -2814,7 +2814,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 		sub_fderivs(Mh_ Ayz,Mh_ fh,Mh_ gyzx,Mh_ gyzy,Mh_ gyzz,saa);
 		sub_fderivs(Mh_ Azz,Mh_ fh,Mh_ gzzx,Mh_ gzzy,Mh_ gzzz,sss);
 		compute_rhs_bssn_part8<<<GRID_DIM,BLOCK_DIM>>>();
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 	}
 
 #if (ABV == 1)
@@ -2895,7 +2895,7 @@ int gpu_rhs(int calledby, int mpi_rank, int *ex, double &T,double *X, double *Y,
 //-------------------FOR GPU TEST----------------------
 //-----------------------------------------------------
 #ifdef TIMING
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	gettimeofday(&tv2, NULL);
    	cout<<"MPI rank is: "<<mpi_rank<<" GPU TIME is"<<TimeBetween(tv1, tv2)<<" (s)."<<endl; 
 #endif

AMSS_NCKU_source/bssn_gpu.h

@@ -4,6 +4,17 @@
 #include "bssn_macro.h"
 #include "macrodef.fh"
 
+// CUDA error checking macro for CUDA 13 compatibility
+#define CUDA_SAFE_CALL(call) \
+    do { \
+        cudaError_t err = call; \
+        if (err != cudaSuccess) { \
+            fprintf(stderr, "CUDA error in %s:%d: %s\n", __FILE__, __LINE__, \
+                    cudaGetErrorString(err)); \
+            exit(EXIT_FAILURE); \
+        } \
+    } while(0)
+
 #define DEVICE_ID 0
 // #define DEVICE_ID_BY_MPI_RANK
 #define GRID_DIM 256

AMSS_NCKU_source/bssn_gpu_rhs_ss.cu

@@ -20,7 +20,7 @@ using namespace std;
 
 __device__ volatile unsigned int global_count = 0;
 
-void compare_result_gpu(int ftag1,double * datac,int data_num){
+static void compare_result_gpu(int ftag1,double * datac,int data_num){
 	double * data = (double*)malloc(sizeof(double)*data_num);
 	cudaMemcpy(data, datac, data_num * sizeof(double), cudaMemcpyDeviceToHost);
 	compare_result(ftag1,data,data_num);
@@ -153,11 +153,11 @@ __global__ void sub_symmetry_bd_ss_partJ(int ord,double * func, double * funcc,d
 
 inline void sub_symmetry_bd_ss(int ord,double * func, double * funcc,double * SoA){
 	sub_symmetry_bd_ss_partF<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_symmetry_bd_ss_partI<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc,SoA[0]);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	sub_symmetry_bd_ss_partJ<<<GRID_DIM,BLOCK_DIM>>>(ord,func,funcc,SoA[1]);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 }
 
 __global__ void sub_fderivs_shc_part1(double *fx,double *fy,double *fz){
@@ -247,13 +247,13 @@ inline void sub_fderivs_shc(int& sst,double * f,double * fh,double *fx,double *f
 	//cudaMemset(Msh_ gy,0,h_3D_SIZE[0] * sizeof(double));
 	//cudaMemset(Msh_ gz,0,h_3D_SIZE[0] * sizeof(double));
 	sub_symmetry_bd_ss(2,f,fh,SoA1);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(0,fh,h_3D_SIZE[2]);	
 	sub_fderivs_sh<<<GRID_DIM,BLOCK_DIM>>>(fh,Msh_ gx,Msh_ gy,Msh_ gz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fderivs_shc_part1<<<GRID_DIM,BLOCK_DIM>>>(fx,fy,fz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(1,fx,h_3D_SIZE[0]);
 			//compare_result_gpu(2,fy,h_3D_SIZE[0]);
 			//compare_result_gpu(3,fz,h_3D_SIZE[0]);
@@ -451,17 +451,17 @@ inline void sub_fdderivs_shc(int& sst,double * f,double * fh,
 	
 	//fderivs_sh
 	sub_symmetry_bd_ss(2,f,fh,SoA1);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(1,fh,h_3D_SIZE[2]);	
 	sub_fderivs_sh<<<GRID_DIM,BLOCK_DIM>>>(fh,Msh_ gx,Msh_ gy,Msh_ gz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	//fdderivs_sh
 	sub_symmetry_bd_ss(2,f,fh,SoA1);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(21,fh,h_3D_SIZE[2]);
 	sub_fdderivs_sh<<<GRID_DIM,BLOCK_DIM>>>(fh,Msh_ gxx,Msh_ gxy,Msh_ gxz,Msh_ gyy,Msh_ gyz,Msh_ gzz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			/*compare_result_gpu(11,Msh_ gx,h_3D_SIZE[0]);
 			compare_result_gpu(12,Msh_ gy,h_3D_SIZE[0]);
 			compare_result_gpu(13,Msh_ gz,h_3D_SIZE[0]);
@@ -472,7 +472,7 @@ inline void sub_fdderivs_shc(int& sst,double * f,double * fh,
 			compare_result_gpu(5,Msh_ gyz,h_3D_SIZE[0]);
 			compare_result_gpu(6,Msh_ gzz,h_3D_SIZE[0]);*/
 	sub_fdderivs_shc_part1<<<GRID_DIM,BLOCK_DIM>>>(fxx,fxy,fxz,fyy,fyz,fzz);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			/*compare_result_gpu(1,fxx,h_3D_SIZE[0]);
 			compare_result_gpu(2,fxy,h_3D_SIZE[0]);
 			compare_result_gpu(3,fxz,h_3D_SIZE[0]);
@@ -496,9 +496,9 @@ __global__ void computeRicci_ss_part1(double * dst)
  inline void computeRicci_ss(int &sst,double * src,double* dst,double * SoA, Meta* meta)
 {
 	sub_fdderivs_shc(sst,src,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,SoA);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	computeRicci_ss_part1<<<GRID_DIM,BLOCK_DIM>>>(dst);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 }
 __global__ void sub_lopsided_ss_part1(double * dst)
@@ -516,9 +516,9 @@ __global__ void sub_lopsided_ss_part1(double * dst)
 inline void sub_lopsided_ss(int& sst,double *src,double* dst,double *SoA)
 {
 		sub_fderivs_shc(sst,src,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,SoA);
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 		sub_lopsided_ss_part1<<<GRID_DIM,BLOCK_DIM>>>(dst);
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 }
 
 __global__ void sub_kodis_sh_part1(double *f,double *fh,double *f_rhs)
@@ -590,11 +590,11 @@ inline void sub_kodis_ss(int &sst,double *f,double *fh,double *f_rhs,double *SoA
 	}
 			//compare_result_gpu(10,f,h_3D_SIZE[0]);
 	sub_symmetry_bd_ss(3,f,fh,SoA1);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(0,fh,h_3D_SIZE[3]);
 			
 	sub_kodis_sh_part1<<<GRID_DIM,BLOCK_DIM>>>(f,fh,f_rhs);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 			//compare_result_gpu(1,f_rhs,h_3D_SIZE[0]);
 }
 
@@ -2287,13 +2287,13 @@ int gpu_rhs_ss(RHS_SS_PARA)
 
 
 #ifdef TIMING1
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	gettimeofday(&tv2, NULL);
    	cout<<"TIME USED"<<TimeBetween(tv1, tv2)<<endl; 
 #endif	
 	//cout<<"GPU meta data ready.\n";
 	
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 
 
 //-------------get device info-------------------------------------
@@ -2306,7 +2306,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	//sub_enforce_ga(matrix_size);
 	//4.1-----compute rhs---------
 	compute_rhs_ss_part1<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 
 	sub_fderivs_shc(sst,Mh_ betax,Mh_ fh,Mh_ betaxx,Mh_ betaxy,Mh_ betaxz,ass);
 	sub_fderivs_shc(sst,Mh_ betay,Mh_ fh,Mh_ betayx,Mh_ betayy,Mh_ betayz,sas);
@@ -2322,7 +2322,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	sub_fderivs_shc(sst,Mh_ gyz,Mh_ fh,Mh_ gyzx,Mh_ gyzy,Mh_ gyzz, saa);
 	
 	compute_rhs_ss_part2<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs_shc(sst,Mh_ betax,Mh_ fh,Mh_ gxxx,Mh_ gxyx,Mh_ gxzx,Mh_ gyyx,Mh_ gyzx,Mh_ gzzx,ass);
 	sub_fdderivs_shc(sst,Mh_ betay,Mh_ fh,Mh_ gxxy,Mh_ gxyy,Mh_ gxzy,Mh_ gyyy,Mh_ gyzy,Mh_ gzzy,sas);
@@ -2332,7 +2332,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	sub_fderivs_shc( sst,Mh_ Gamz, Mh_ fh,Mh_ Gamzx, Mh_ Gamzy, Mh_ Gamzz,ssa);
 	
 	compute_rhs_ss_part3<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	computeRicci_ss(sst,Mh_ dxx,Mh_ Rxx,sss, meta);
 	computeRicci_ss(sst,Mh_ dyy,Mh_ Ryy,sss, meta);
@@ -2340,25 +2340,25 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	computeRicci_ss(sst,Mh_ gxy,Mh_ Rxy,aas, meta);
 	computeRicci_ss(sst,Mh_ gxz,Mh_ Rxz,asa, meta);
 	computeRicci_ss(sst,Mh_ gyz,Mh_ Ryz,saa, meta);
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	compute_rhs_ss_part4<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs_shc(sst,Mh_ chi,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,sss);
 	
-	//cudaThreadSynchronize();
+	//cudaDeviceSynchronize();
 	//compare_result_gpu(0,Mh_ chi,h_3D_SIZE[0]);
 	//compare_result_gpu(1,Mh_ chi,h_3D_SIZE[0]);
 	//compare_result_gpu(2,Mh_ fyz,h_3D_SIZE[0]);
 	
 	compute_rhs_ss_part5<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 	sub_fdderivs_shc(sst,Mh_ Lap,Mh_ fh,Mh_ fxx,Mh_ fxy,Mh_ fxz,Mh_ fyy,Mh_ fyz,Mh_ fzz,sss);
 	
 	compute_rhs_ss_part6<<<GRID_DIM,BLOCK_DIM>>>();
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	
 #if (GAUGE == 2 || GAUGE == 3 || GAUGE == 4 || GAUGE == 5)
 	sub_fderivs_shc(sst,Mh_ chi,Mh_ fh, Mh_ dtSfx_rhs, Mh_ dtSfy_rhs, Mh_ dtSfz_rhs,sss);
@@ -2423,7 +2423,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	}
 	if(co == 0){
 		compute_rhs_ss_part7<<<GRID_DIM,BLOCK_DIM>>>();
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 
 		sub_fderivs_shc(sst,Mh_ Axx,Mh_ fh,Mh_ gxxx,Mh_ gxxy,Mh_ gxxz,sss);
 		sub_fderivs_shc(sst,Mh_ Axy,Mh_ fh,Mh_ gxyx,Mh_ gxyy,Mh_ gxyz,aas);
@@ -2432,7 +2432,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 		sub_fderivs_shc(sst,Mh_ Ayz,Mh_ fh,Mh_ gyzx,Mh_ gyzy,Mh_ gyzz,saa);
 		sub_fderivs_shc(sst,Mh_ Azz,Mh_ fh,Mh_ gzzx,Mh_ gzzy,Mh_ gzzz,sss);
 		compute_rhs_ss_part8<<<GRID_DIM,BLOCK_DIM>>>();
-		cudaThreadSynchronize();
+		cudaDeviceSynchronize();
 	}
 	
 #if (ABV == 1)
@@ -2512,7 +2512,7 @@ int gpu_rhs_ss(RHS_SS_PARA)
 	//test kodis
 	//sub_kodis_sh(sst,Msh_ drhodx,Mh_ fh2,Msh_ drhody,sss);
 #ifdef TIMING
-	cudaThreadSynchronize();
+	cudaDeviceSynchronize();
 	gettimeofday(&tv2, NULL);
    	cout<<"MPI rank is: "<<mpi_rank<<" GPU TIME is"<<TimeBetween(tv1, tv2)<<" (s)."<<endl; 
 #endif

AMSS_NCKU_source/bssn_rhs.f90

@@ -106,8 +106,7 @@
   call getpbh(BHN,Porg,Mass)
 #endif
 
-!!! sanity check (disabled in production builds for performance)
-#ifdef DEBUG
+!!! sanity check
   dX = sum(chi)+sum(trK)+sum(dxx)+sum(gxy)+sum(gxz)+sum(dyy)+sum(gyz)+sum(dzz) &
       +sum(Axx)+sum(Axy)+sum(Axz)+sum(Ayy)+sum(Ayz)+sum(Azz)                   &
       +sum(Gamx)+sum(Gamy)+sum(Gamz)                                           &
@@ -137,7 +136,6 @@
      gont = 1
      return
   endif
-#endif
 
   PI = dacos(-ONE)
 
@@ -945,60 +943,103 @@
   SSA(2)=SYM
   SSA(3)=ANTI
 
-!!!!!!!!!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.
+!!!!!!!!!advection term part
 
-  call lopsided_kodis(ex,X,Y,Z,gxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided_kodis(ex,X,Y,Z,gxy,gxy_rhs,betax,betay,betaz,Symmetry,AAS,eps)
-  call lopsided_kodis(ex,X,Y,Z,gxz,gxz_rhs,betax,betay,betaz,Symmetry,ASA,eps)
-  call lopsided_kodis(ex,X,Y,Z,gyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided_kodis(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA,eps)
-  call lopsided_kodis(ex,X,Y,Z,gzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided(ex,X,Y,Z,gxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided(ex,X,Y,Z,gxy,gxy_rhs,betax,betay,betaz,Symmetry,AAS)
+  call lopsided(ex,X,Y,Z,gxz,gxz_rhs,betax,betay,betaz,Symmetry,ASA)
+  call lopsided(ex,X,Y,Z,gyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA)
+  call lopsided(ex,X,Y,Z,gzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS)
 
-  call lopsided_kodis(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided_kodis(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS,eps)
-  call lopsided_kodis(ex,X,Y,Z,Axz,Axz_rhs,betax,betay,betaz,Symmetry,ASA,eps)
-  call lopsided_kodis(ex,X,Y,Z,Ayy,Ayy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided_kodis(ex,X,Y,Z,Ayz,Ayz_rhs,betax,betay,betaz,Symmetry,SAA,eps)
-  call lopsided_kodis(ex,X,Y,Z,Azz,Azz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS)
+  call lopsided(ex,X,Y,Z,Axz,Axz_rhs,betax,betay,betaz,Symmetry,ASA)
+  call lopsided(ex,X,Y,Z,Ayy,Ayy_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided(ex,X,Y,Z,Ayz,Ayz_rhs,betax,betay,betaz,Symmetry,SAA)
+  call lopsided(ex,X,Y,Z,Azz,Azz_rhs,betax,betay,betaz,Symmetry,SSS)
 
-  call lopsided_kodis(ex,X,Y,Z,chi,chi_rhs,betax,betay,betaz,Symmetry,SSS,eps)
-  call lopsided_kodis(ex,X,Y,Z,trK,trK_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided(ex,X,Y,Z,chi,chi_rhs,betax,betay,betaz,Symmetry,SSS)
+  call lopsided(ex,X,Y,Z,trK,trK_rhs,betax,betay,betaz,Symmetry,SSS)
 
-  call lopsided_kodis(ex,X,Y,Z,Gamx,Gamx_rhs,betax,betay,betaz,Symmetry,ASS,eps)
-  call lopsided_kodis(ex,X,Y,Z,Gamy,Gamy_rhs,betax,betay,betaz,Symmetry,SAS,eps)
-  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,Gamx,Gamx_rhs,betax,betay,betaz,Symmetry,ASS)
+  call lopsided(ex,X,Y,Z,Gamy,Gamy_rhs,betax,betay,betaz,Symmetry,SAS)
+  call lopsided(ex,X,Y,Z,Gamz,Gamz_rhs,betax,betay,betaz,Symmetry,SSA)
+!!
   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

@@ -1,36 +0,0 @@
-#ifndef BSSN_RHS_CUDA_H
-#define BSSN_RHS_CUDA_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-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);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

AMSS_NCKU_source/bssn_step_gpu.C

@@ -1676,8 +1676,11 @@ void bssn_class::Step_GPU(int lev, int YN)
 #endif // PSTR == ?
 
 //--------------------------With Shell--------------------------
+// Note: SHStep() implementation is in bssn_gpu_class.C
 
 #ifdef WithShell
+#if 0
+// This SHStep() implementation has been moved to bssn_gpu_class.C to avoid duplicate definition
 void bssn_class::SHStep()
 {
   int lev = 0;
@@ -1938,5 +1941,5 @@ void bssn_class::SHStep()
     sPp = sPp->next;
   }
 }
-d
+#endif // #if 0
 #endif // withshell

AMSS_NCKU_source/cgh.C

@@ -130,11 +130,7 @@ 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)
@@ -1305,13 +1301,13 @@ bool cgh::Interp_One_Point(MyList<var> *VarList,
 }
 
 
-bool cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+void 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 false;
+    return;
 
 #if (0)
   // #if (PSTR == 1 || PSTR == 2)
@@ -1400,7 +1396,7 @@ bool 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 false;
+      return;
     }
     // x direction
     rr = (Porg0[bhi][0] - handle[lev][grd][0]) / dX;
@@ -1504,7 +1500,6 @@ bool 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);
-   bool Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
+   void 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

@@ -69,12 +69,10 @@
   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
-! x direction
+! x direction   
         if(i+1 <= imax .and. i-1 >= imin)then
 !
 !              - f(i-1) + f(i+1)
@@ -373,8 +371,6 @@
   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/enforce_algebra.f90

@@ -18,61 +18,49 @@
   real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Ayy,Ayz,Azz
 
 !~~~~~~~> Local variable:
-
-  integer :: i,j,k
-  real*8 :: lgxx,lgyy,lgzz,ldetg
-  real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
-  real*8 :: ltrA,lscale
+  
+  real*8, dimension(ex(1),ex(2),ex(3)) :: trA,detg
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz 
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
   real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
 
 !~~~~~~>
 
-  do k=1,ex(3)
-  do j=1,ex(2)
-  do i=1,ex(1)
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
 
-    lgxx = dxx(i,j,k) + ONE
-    lgyy = dyy(i,j,k) + ONE
-    lgzz = dzz(i,j,k) + ONE
+  detg =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
+          gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
+  gupxx =   ( gyy * gzz - gyz * gyz ) / detg
+  gupxy = - ( gxy * gzz - gyz * gxz ) / detg
+  gupxz =   ( gxy * gyz - gyy * gxz ) / detg
+  gupyy =   ( gxx * gzz - gxz * gxz ) / detg
+  gupyz = - ( gxx * gyz - gxy * gxz ) / detg
+  gupzz =   ( gxx * gyy - gxy * gxy ) / detg
 
-    ldetg =  lgxx * lgyy * lgzz &
-           + gxy(i,j,k) * gyz(i,j,k) * gxz(i,j,k) &
-           + gxz(i,j,k) * gxy(i,j,k) * gyz(i,j,k) &
-           - gxz(i,j,k) * lgyy * gxz(i,j,k) &
-           - gxy(i,j,k) * gxy(i,j,k) * lgzz &
-           - lgxx * gyz(i,j,k) * gyz(i,j,k)
+  trA =         gupxx * Axx + gupyy * Ayy + gupzz * Azz &
+       + TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
 
-    lgupxx =   ( lgyy * lgzz - gyz(i,j,k) * gyz(i,j,k) ) / ldetg
-    lgupxy = - ( gxy(i,j,k) * lgzz - gyz(i,j,k) * gxz(i,j,k) ) / ldetg
-    lgupxz =   ( gxy(i,j,k) * gyz(i,j,k) - lgyy * gxz(i,j,k) ) / ldetg
-    lgupyy =   ( lgxx * lgzz - gxz(i,j,k) * gxz(i,j,k) ) / ldetg
-    lgupyz = - ( lgxx * gyz(i,j,k) - gxy(i,j,k) * gxz(i,j,k) ) / ldetg
-    lgupzz =   ( lgxx * lgyy - gxy(i,j,k) * gxy(i,j,k) ) / ldetg
+  Axx = Axx - F1o3 * gxx * trA
+  Axy = Axy - F1o3 * gxy * trA
+  Axz = Axz - F1o3 * gxz * trA
+  Ayy = Ayy - F1o3 * gyy * trA
+  Ayz = Ayz - F1o3 * gyz * trA
+  Azz = Azz - F1o3 * gzz * trA
 
-    ltrA =         lgupxx * Axx(i,j,k) + lgupyy * Ayy(i,j,k) &
-                 + lgupzz * Azz(i,j,k) &
-         + TWO * (lgupxy * Axy(i,j,k) + lgupxz * Axz(i,j,k) &
-                 + lgupyz * Ayz(i,j,k))
+  detg = ONE / ( detg ** F1o3 ) 
+  
+  gxx = gxx * detg
+  gxy = gxy * detg
+  gxz = gxz * detg
+  gyy = gyy * detg
+  gyz = gyz * detg
+  gzz = gzz * detg
 
-    Axx(i,j,k) = Axx(i,j,k) - F1o3 * lgxx * ltrA
-    Axy(i,j,k) = Axy(i,j,k) - F1o3 * gxy(i,j,k) * ltrA
-    Axz(i,j,k) = Axz(i,j,k) - F1o3 * gxz(i,j,k) * ltrA
-    Ayy(i,j,k) = Ayy(i,j,k) - F1o3 * lgyy * ltrA
-    Ayz(i,j,k) = Ayz(i,j,k) - F1o3 * gyz(i,j,k) * ltrA
-    Azz(i,j,k) = Azz(i,j,k) - F1o3 * lgzz * ltrA
-
-    lscale = ONE / ( ldetg ** F1o3 )
-
-    dxx(i,j,k) = lgxx * lscale - ONE
-    gxy(i,j,k) = gxy(i,j,k) * lscale
-    gxz(i,j,k) = gxz(i,j,k) * lscale
-    dyy(i,j,k) = lgyy * lscale - ONE
-    gyz(i,j,k) = gyz(i,j,k) * lscale
-    dzz(i,j,k) = lgzz * lscale - ONE
-
-  enddo
-  enddo
-  enddo
+  dxx = gxx - ONE
+  dyy = gyy - ONE
+  dzz = gzz - ONE
 
   return
 
@@ -94,71 +82,51 @@
   real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Ayy,Ayz,Azz
 
 !~~~~~~~> Local variable:
-
-  integer :: i,j,k
-  real*8 :: lgxx,lgyy,lgzz,lscale
-  real*8 :: lgxy,lgxz,lgyz
-  real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
-  real*8 :: ltrA
+  
+  real*8, dimension(ex(1),ex(2),ex(3)) :: trA
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz 
+  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
   real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
 
 !~~~~~~>
 
-  do k=1,ex(3)
-  do j=1,ex(2)
-  do i=1,ex(1)
+  gxx = dxx + ONE
+  gyy = dyy + ONE
+  gzz = dzz + ONE
+! for g
+  gupzz =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
+           gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
 
-! for g: normalize determinant first
-    lgxx = dxx(i,j,k) + ONE
-    lgyy = dyy(i,j,k) + ONE
-    lgzz = dzz(i,j,k) + ONE
-    lgxy = gxy(i,j,k)
-    lgxz = gxz(i,j,k)
-    lgyz = gyz(i,j,k)
+  gupzz = ONE / ( gupzz ** F1o3 ) 
+  
+  gxx = gxx * gupzz
+  gxy = gxy * gupzz
+  gxz = gxz * gupzz
+  gyy = gyy * gupzz
+  gyz = gyz * gupzz
+  gzz = gzz * gupzz
 
-    lscale =  lgxx * lgyy * lgzz + lgxy * lgyz * lgxz &
-            + lgxz * lgxy * lgyz - lgxz * lgyy * lgxz &
-            - lgxy * lgxy * lgzz - lgxx * lgyz * lgyz
+  dxx = gxx - ONE
+  dyy = gyy - ONE
+  dzz = gzz - ONE
+! for A  
 
-    lscale = ONE / ( lscale ** F1o3 )
+  gupxx =   ( gyy * gzz - gyz * gyz )
+  gupxy = - ( gxy * gzz - gyz * gxz )
+  gupxz =   ( gxy * gyz - gyy * gxz )
+  gupyy =   ( gxx * gzz - gxz * gxz )
+  gupyz = - ( gxx * gyz - gxy * gxz )
+  gupzz =   ( gxx * gyy - gxy * gxy )
 
-    lgxx = lgxx * lscale
-    lgxy = lgxy * lscale
-    lgxz = lgxz * lscale
-    lgyy = lgyy * lscale
-    lgyz = lgyz * lscale
-    lgzz = lgzz * lscale
+  trA =         gupxx * Axx + gupyy * Ayy + gupzz * Azz &
+       + TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
 
-    dxx(i,j,k) = lgxx - ONE
-    gxy(i,j,k) = lgxy
-    gxz(i,j,k) = lgxz
-    dyy(i,j,k) = lgyy - ONE
-    gyz(i,j,k) = lgyz
-    dzz(i,j,k) = lgzz - ONE
-
-! for A: trace-free using normalized metric (det=1, no division needed)
-    lgupxx =   ( lgyy * lgzz - lgyz * lgyz )
-    lgupxy = - ( lgxy * lgzz - lgyz * lgxz )
-    lgupxz =   ( lgxy * lgyz - lgyy * lgxz )
-    lgupyy =   ( lgxx * lgzz - lgxz * lgxz )
-    lgupyz = - ( lgxx * lgyz - lgxy * lgxz )
-    lgupzz =   ( lgxx * lgyy - lgxy * lgxy )
-
-    ltrA =         lgupxx * Axx(i,j,k) + lgupyy * Ayy(i,j,k) &
-                 + lgupzz * Azz(i,j,k) &
-         + TWO * (lgupxy * Axy(i,j,k) + lgupxz * Axz(i,j,k) &
-                 + lgupyz * Ayz(i,j,k))
-
-    Axx(i,j,k) = Axx(i,j,k) - F1o3 * lgxx * ltrA
-    Axy(i,j,k) = Axy(i,j,k) - F1o3 * lgxy * ltrA
-    Axz(i,j,k) = Axz(i,j,k) - F1o3 * lgxz * ltrA
-    Ayy(i,j,k) = Ayy(i,j,k) - F1o3 * lgyy * ltrA
-    Ayz(i,j,k) = Ayz(i,j,k) - F1o3 * lgyz * ltrA
-    Azz(i,j,k) = Azz(i,j,k) - F1o3 * lgzz * ltrA
-
-  enddo
-  enddo
-  enddo
+  Axx = Axx - F1o3 * gxx * trA
+  Axy = Axy - F1o3 * gxy * trA
+  Axz = Axz - F1o3 * gxz * trA
+  Ayy = Ayy - F1o3 * gyy * trA
+  Ayz = Ayz - F1o3 * gyz * trA
+  Azz = Azz - F1o3 * gzz * trA
 
   return
 

AMSS_NCKU_source/fdderivs_c.C

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

AMSS_NCKU_source/fderivs_c.C

@@ -1,150 +0,0 @@
-#include "tool.h"
-
-/*
- * C 版 fderivs
- *
- * Fortran:
- * subroutine fderivs(ex,f,fx,fy,fz,X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
- *
- * 约定：
- *   f, fx, fy, fz: ex1*ex2*ex3，按 idx_ex 布局
- *   X: ex1, Y: ex2, Z: ex3
- */
-void fderivs(const int ex[3],
-             const double *f,
-             double *fx, double *fy, double *fz,
-             const double *X, const double *Y, const double *Z,
-             double SYM1, double SYM2, double SYM3,
-             int Symmetry, int onoff)
-{
-    (void)onoff; // Fortran 里没用到
-
-    const double ZEO = 0.0, ONE = 1.0;
-    const double TWO = 2.0, EIT = 8.0;
-    const double F12 = 12.0;
-
-    const int NO_SYMM = 0, EQ_SYMM = 1; // OCTANT=2 在本子程序里不直接用
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    // dX = X(2)-X(1) -> C: X[1]-X[0]
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    // Fortran 1-based bounds
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -1;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -1;
-
-    // SoA(1:3) = SYM1,SYM2,SYM3
-    const double SoA[3] = { SYM1, SYM2, SYM3 };
-
-    // fh: (ex1+2)*(ex2+2)*(ex3+2) because ord=2
-    const size_t nx = (size_t)ex1 + 2;
-    const size_t ny = (size_t)ex2 + 2;
-    const size_t nz = (size_t)ex3 + 2;
-    const size_t fh_size = nx * ny * nz;
-    static double *fh = NULL;
-    static size_t cap = 0;
-
-    if (fh_size > cap) {
-        free(fh);
-        fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
-        cap = fh_size;
-    }
-    // double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    // call symmetry_bd(2,ex,f,fh,SoA)
-    symmetry_bd(2, ex, f, fh, SoA);
-
-    const double d12dx = ONE / F12 / dX;
-    const double d12dy = ONE / F12 / dY;
-    const double d12dz = ONE / F12 / dZ;
-
-    const double d2dx  = ONE / TWO / dX;
-    const double d2dy  = ONE / TWO / dY;
-    const double d2dz  = ONE / TWO / dZ;
-
-    // fx = fy = fz = 0
-    const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
-    for (size_t p = 0; p < all; ++p) {
-        fx[p] = ZEO;
-        fy[p] = ZEO;
-        fz[p] = ZEO;
-    }
-
-    /*
-     * 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) <= imaxF && (iF - 2) >= iminF &&
-                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
-                    (kF + 2) <= kmaxF && (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) <= imaxF && (iF - 1) >= iminF &&
-                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
-                         (kF + 1) <= kmaxF && (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/fmisc.f90

@@ -324,6 +324,7 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+  funcc = 0.d0
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -349,6 +350,7 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+  funcc = 0.d0
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -377,6 +379,7 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+  funcc = 0.d0
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+2,1:extc(2),1:extc(3))*SoA(1)
@@ -883,17 +886,14 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
 
   integer::i
 
-!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
+  funcc = 0.d0
   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
@@ -912,6 +912,7 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+  funcc = 0.d0
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
@@ -940,6 +941,7 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
 
   integer::i
 
+  funcc = 0.d0
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
@@ -1111,323 +1113,105 @@ end subroutine d2dump
 !~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 !~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 !~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-! common code for cell and vertex
-!------------------------------------------------------------------------------
-! 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
-
-  integer, intent(in) :: ordn
-  real*8, dimension(ordn), intent(in) :: xa, ya
+! common code for cell and vertex
+!------------------------------------------------------------------------------
+! Lagrangian polynomial interpolation
+!------------------------------------------------------------------------------
+
+  subroutine polint(xa,ya,x,y,dy,ordn)
+
+  implicit none
+
+!~~~~~~> Input Parameter:
+  integer,intent(in) :: ordn
+  real*8, dimension(ordn), intent(in) :: xa,ya
   real*8, intent(in) :: x
-  real*8, intent(out) :: y, dy
+  real*8, intent(out) :: y,dy
 
-  integer :: i, m, ns, n_m
-  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
+!~~~~~~> Other parameter:
 
-  ns = 1
-  dif = abs(x - xa(1))
+  integer :: m,n,ns
+  real*8, dimension(ordn) :: c,d,den,ho
+  real*8 :: dif,dift
 
-  do i = 2, ordn
-    dift = abs(x - xa(i))
-    if (dift < dif) then
-      ns = i
-      dif = dift
-    end if
+!~~~~~~>
+
+  n=ordn
+  m=ordn
+
+  c=ya
+  d=ya
+  ho=xa-x
+
+  ns=1
+  dif=abs(x-xa(1))
+  do m=1,n
+   dift=abs(x-xa(m))
+   if(dift < dif) then
+    ns=m
+    dif=dift
+   end if
   end do
 
-  y = ya(ns)
-  ns = ns - 1
-
-  do m = 1, ordn - 1
-    n_m = ordn - 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)
+  y=ya(ns)
+  ns=ns-1
+  do m=1,n-1
+    den(1:n-m)=ho(1:n-m)-ho(1+m:n)
+    if (any(den(1:n-m) == 0.0))then
+      write(*,*) 'failure in polint for point',x
+      write(*,*) 'with input points: ',xa
+      stop
+    endif
+    den(1:n-m)=(c(2:n-m+1)-d(1:n-m))/den(1:n-m)
+    d(1:n-m)=ho(1+m:n)*den(1:n-m)
+    c(1:n-m)=ho(1:n-m)*den(1:n-m)
+    if (2*ns < n-m) then
+      dy=c(ns+1)
     else
-      dy = d(ns)
-      ns = ns - 1
+      dy=d(ns)
+      ns=ns-1
     end if
-    y = y + dy
+    y=y+dy
   end do
 
-  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
+  return
 
-  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
-!
-!------------------------------------------------------------------------------
+  end subroutine polint
+!------------------------------------------------------------------------------
+!
+! interpolation in 2 dimensions, follow yx order
+!
+!------------------------------------------------------------------------------
   subroutine polin2(x1a,x2a,ya,x1,x2,y,dy,ordn)
+
   implicit none
 
+!~~~~~~> Input parameters:
   integer,intent(in) :: ordn
   real*8, dimension(1:ordn), intent(in) :: x1a,x2a
   real*8, dimension(1:ordn,1:ordn), intent(in) :: ya
   real*8, intent(in) :: x1,x2
   real*8, intent(out) :: y,dy
 
-#ifdef POLINT_LEGACY_ORDER
+!~~~~~~> Other parameters:
+
   integer  :: i,m
   real*8, dimension(ordn) :: ymtmp
   real*8, dimension(ordn) :: yntmp
 
   m=size(x1a)
+  
   do i=1,m
+
     yntmp=ya(i,:)
     call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
-  end do
-  call polint(x1a,ymtmp,x1,y,dy,ordn)
-#else
-  integer  :: j
-  real*8, dimension(ordn) :: ymtmp
-  real*8 :: dy_temp
 
-  do j=1,ordn
-    call polint(x1a, ya(:,j), x1, ymtmp(j), dy_temp, ordn)
   end do
-  call polint(x2a, ymtmp, x2, y, dy, ordn)
-#endif
+
+  call polint(x1a,ymtmp,x1,y,dy,ordn)
 
   return
+
   end subroutine polin2
 !------------------------------------------------------------------------------
 !
@@ -1435,60 +1219,47 @@ end subroutine d2dump
 !
 !------------------------------------------------------------------------------
   subroutine polin3(x1a,x2a,x3a,ya,x1,x2,x3,y,dy,ordn)
+
   implicit none
 
+!~~~~~~> Input parameters:
   integer,intent(in) :: ordn
   real*8, dimension(1:ordn), intent(in) :: x1a,x2a,x3a
   real*8, dimension(1:ordn,1:ordn,1:ordn), intent(in) :: ya
   real*8, intent(in) :: x1,x2,x3
   real*8, intent(out) :: y,dy
 
-#ifdef POLINT_LEGACY_ORDER
-  integer  :: i,j,m,n
-  real*8, dimension(ordn,ordn) :: yatmp
-  real*8, dimension(ordn) :: ymtmp
-  real*8, dimension(ordn) :: yntmp
+!~~~~~~> Other parameters:
+
+  integer  :: i,j,m,n
+  real*8, dimension(ordn,ordn) :: yatmp
+  real*8, dimension(ordn) :: ymtmp
+  real*8, dimension(ordn) :: yntmp
   real*8, dimension(ordn) :: yqtmp
 
   m=size(x1a)
   n=size(x2a)
+  
   do i=1,m
    do j=1,n
+
     yqtmp=ya(i,j,:)
     call polint(x3a,yqtmp,x3,yatmp(i,j),dy,ordn)
+
    end do
-    yntmp=yatmp(i,:)
-    call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
-  end do
-  call polint(x1a,ymtmp,x1,y,dy,ordn)
-#else
-  integer  :: i, j, k
-  real*8, dimension(ordn) :: w1, w2
-  real*8, dimension(ordn) :: ymtmp
-  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
-      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
-    ymtmp(k) = yx_sum
-  end do
-
-  call polint(x3a, ymtmp, x3, y, dy, ordn)
-#endif
-
-  return
-  end subroutine polin3
+
+    yntmp=yatmp(i,:)
+    call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
+
+  end do
+
+  call polint(x1a,ymtmp,x1,y,dy,ordn)
+
+  return
+
+  end subroutine polin3
 !--------------------------------------------------------------------------------------
-! calculate L2norm
+! calculate L2norm  
   subroutine l2normhelper(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&
                           f,f_out,gw)
 
@@ -1505,9 +1276,7 @@ end subroutine d2dump
   real*8            :: dX, dY, dZ
   integer::imin,jmin,kmin
   integer::imax,jmax,kmax
-  integer::i,j,k,n_elements
-  real*8, dimension(:), allocatable :: f_flat
-  real*8, external :: DDOT
+  integer::i,j,k
 
   dX = X(2) - X(1)
   dY = Y(2) - Y(1)
@@ -1531,12 +1300,7 @@ if(dabs(X(1)-xmin) < dX) imin = 1
 if(dabs(Y(1)-ymin) < dY) jmin = 1
 if(dabs(Z(1)-zmin) < dZ) kmin = 1
 
-! Optimized with oneMKL BLAS DDOT for dot product
-n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
-allocate(f_flat(n_elements))
-f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
-f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
-deallocate(f_flat)
+f_out = sum(f(imin:imax,jmin:jmax,kmin:kmax)*f(imin:imax,jmin:jmax,kmin:kmax))
 
 f_out = f_out*dX*dY*dZ
 
@@ -1561,9 +1325,7 @@ f_out = f_out*dX*dY*dZ
   real*8            :: dX, dY, dZ
   integer::imin,jmin,kmin
   integer::imax,jmax,kmax
-  integer::i,j,k,n_elements
-  real*8, dimension(:), allocatable :: f_flat
-  real*8, external :: DDOT
+  integer::i,j,k
 
   real*8 :: PIo4
 
@@ -1626,12 +1388,7 @@ if(Symmetry==2)then
   if(dabs(ymin+gw*dY)<dY.and.Y(1)<0.d0) jmin = gw+1
 endif
 
-! Optimized with oneMKL BLAS DDOT for dot product
-n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
-allocate(f_flat(n_elements))
-f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
-f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
-deallocate(f_flat)
+f_out = sum(f(imin:imax,jmin:jmax,kmin:kmax)*f(imin:imax,jmin:jmax,kmin:kmax))
 
 f_out = f_out*dX*dY*dZ
 
@@ -1659,8 +1416,6 @@ f_out = f_out*dX*dY*dZ
   integer::imin,jmin,kmin
   integer::imax,jmax,kmax
   integer::i,j,k
-  real*8, dimension(:), allocatable :: f_flat
-  real*8, external :: DDOT
 
   real*8 :: PIo4
 
@@ -1723,12 +1478,11 @@ if(Symmetry==2)then
   if(dabs(ymin+gw*dY)<dY.and.Y(1)<0.d0) jmin = gw+1
 endif
 
-! Optimized with oneMKL BLAS DDOT for dot product
+f_out = sum(f(imin:imax,jmin:jmax,kmin:kmax)*f(imin:imax,jmin:jmax,kmin:kmax))
+
+f_out = f_out
+
 Nout = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
-allocate(f_flat(Nout))
-f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [Nout])
-f_out = DDOT(Nout, f_flat, 1, f_flat, 1)
-deallocate(f_flat)
 
   return
 
@@ -1829,14 +1583,11 @@ 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
-
-  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
+  real*8,parameter::C1=3.d0/8.d0,C2=3.d0/4.d0,C3=-1.d0/8.d0
+
+  fout = C1*f1+C2*f2+C3*f3
+
+  return
 
   end subroutine average2
 !-----------------------------------------------------------------------------  
@@ -1929,7 +1680,6 @@ deallocate(f_flat)
   real*8, dimension(ORDN,ORDN) :: tmp2
   real*8, dimension(ORDN) :: tmp1
   real*8, dimension(3) :: SoAh
-  real*8, external :: DDOT
 
 ! +1 because c++ gives 0 for first point
   cxB = inds+1  
@@ -1965,21 +1715,20 @@ deallocate(f_flat)
      ya=fh(cxB(1):cxT(1),cxB(2):cxT(2),cxB(3):cxT(3))
   endif 
 
-  ! Optimized with BLAS operations for better performance
-  ! First dimension: z-direction weighted sum
   tmp2=0
   do m=1,ORDN
     tmp2 = tmp2 + coef(2*ORDN+m)*ya(:,:,m)
   enddo
 
-  ! Second dimension: y-direction weighted sum
   tmp1=0
   do m=1,ORDN
     tmp1 = tmp1 + coef(ORDN+m)*tmp2(:,m)
   enddo
 
-  ! Third dimension: x-direction weighted sum using BLAS DDOT
-  f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
+  f_int=0
+  do m=1,ORDN
+    f_int = f_int + coef(m)*tmp1(m)
+  enddo
 
   return
 
@@ -2009,7 +1758,6 @@ deallocate(f_flat)
   real*8, dimension(ORDN,ORDN) :: ya
   real*8, dimension(ORDN) :: tmp1
   real*8, dimension(2) :: SoAh
-  real*8, external :: DDOT
 
 ! +1 because c++ gives 0 for first point
   cxB = inds(1:2)+1  
@@ -2039,14 +1787,15 @@ deallocate(f_flat)
      ya=fh(cxB(1):cxT(1),cxB(2):cxT(2),inds(3))
   endif 
 
-  ! Optimized with BLAS operations
   tmp1=0
   do m=1,ORDN
     tmp1 = tmp1 + coef(ORDN+m)*ya(:,m)
   enddo
 
-  ! Use BLAS DDOT for final weighted sum
-  f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
+  f_int=0
+  do m=1,ORDN
+    f_int = f_int + coef(m)*tmp1(m)
+  enddo
 
   return
 
@@ -2077,7 +1826,6 @@ deallocate(f_flat)
   real*8, dimension(ORDN) :: ya
   real*8 :: SoAh
   integer,dimension(3) :: inds
-  real*8, external :: DDOT
 
 ! +1 because c++ gives 0 for first point
   inds = indsi + 1
@@ -2138,8 +1886,10 @@ deallocate(f_flat)
           write(*,*)"error in global_interpind1d, not recognized dumyd = ",dumyd
   endif
 
-  ! Optimized with BLAS DDOT for weighted sum
-  f_int = DDOT(ORDN, coef, 1, ya, 1)
+  f_int=0
+  do m=1,ORDN
+    f_int = f_int + coef(m)*ya(m)
+  enddo
 
   return
 
@@ -2371,38 +2121,24 @@ deallocate(f_flat)
 
   end function fWigner_d_function
 !----------------------------------
-! Optimized factorial function using lookup table for small N
-! and log-gamma for large N to avoid overflow
   function ffact(N) result(gont)
   implicit none
   integer,intent(in) :: N
 
   real*8 :: gont
-  integer :: i
 
-  ! Lookup table for factorials 0! to 20! (precomputed)
-  real*8, parameter, dimension(0:20) :: fact_table = [ &
-    1.d0, 1.d0, 2.d0, 6.d0, 24.d0, 120.d0, 720.d0, 5040.d0, 40320.d0, &
-    362880.d0, 3628800.d0, 39916800.d0, 479001600.d0, 6227020800.d0, &
-    87178291200.d0, 1307674368000.d0, 20922789888000.d0, &
-    355687428096000.d0, 6402373705728000.d0, 121645100408832000.d0, &
-    2432902008176640000.d0 ]
+  integer :: i
 
 ! sanity check
   if(N < 0)then
      write(*,*) "ffact: error input for factorial"
-     gont = 1.d0
      return
   endif
 
-  ! Use lookup table for small N (fast path)
-  if(N <= 20)then
-     gont = fact_table(N)
-  else
-     ! Use log-gamma function for large N: N! = exp(log_gamma(N+1))
-     ! This avoids overflow and is computed efficiently
-     gont = exp(log_gamma(dble(N+1)))
-  endif
+  gont = 1.d0
+  do i=1,N
+     gont = gont*i
+  enddo
 
   return
 

AMSS_NCKU_source/gaussj.C

@@ -16,66 +16,115 @@ using namespace std;
 #include <string.h>
 #include <math.h>
 #endif
-
-// Intel oneMKL LAPACK interface
-#include <mkl_lapacke.h>
-/* Linear equation solution using Intel oneMKL LAPACK.
+/* Linear equation solution by Gauss-Jordan elimination.
 a[0..n-1][0..n-1] is the input matrix. b[0..n-1] is input
 containing the right-hand side vectors. On output a is
 replaced by its matrix inverse, and b is replaced by the
-corresponding set of solution vectors.
-
-Mathematical equivalence:
-  Solves: A * x = b  =>  x = A^(-1) * b
-  Original Gauss-Jordan and LAPACK dgesv/dgetri produce identical results
-  within numerical precision. */
+corresponding set of solution vectors */
 
 int gaussj(double *a, double *b, int n)
 {
-  // Allocate pivot array and workspace
-  lapack_int *ipiv = new lapack_int[n];
-  lapack_int info;
+  double swap;
 
-  // Make a copy of matrix a for solving (dgesv modifies it to LU form)
-  double *a_copy = new double[n * n];
-  for (int i = 0; i < n * n; i++) {
-    a_copy[i] = a[i];
+  int *indxc, *indxr, *ipiv;
+  indxc = new int[n];
+  indxr = new int[n];
+  ipiv = new int[n];
+
+  int i, icol, irow, j, k, l, ll;
+  double big, dum, pivinv, temp;
+
+  for (j = 0; j < n; j++)
+    ipiv[j] = 0;
+  for (i = 0; i < n; i++)
+  {
+    big = 0.0;
+    for (j = 0; j < n; j++)
+      if (ipiv[j] != 1)
+        for (k = 0; k < n; k++)
+        {
+          if (ipiv[k] == 0)
+          {
+            if (fabs(a[j * n + k]) >= big)
+            {
+              big = fabs(a[j * n + k]);
+              irow = j;
+              icol = k;
+            }
+          }
+          else if (ipiv[k] > 1)
+          {
+            cout << "gaussj: Singular Matrix-1" << endl;
+            for (int ii = 0; ii < n; ii++)
+            {
+              for (int jj = 0; jj < n; jj++)
+                cout << a[ii * n + jj] << " ";
+              cout << endl;
+            }
+            return 1; // error return
+          }
+        }
+
+    ipiv[icol] = ipiv[icol] + 1;
+    if (irow != icol)
+    {
+      for (l = 0; l < n; l++)
+      {
+        swap = a[irow * n + l];
+        a[irow * n + l] = a[icol * n + l];
+        a[icol * n + l] = swap;
+      }
+
+      swap = b[irow];
+      b[irow] = b[icol];
+      b[icol] = swap;
+    }
+
+    indxr[i] = irow;
+    indxc[i] = icol;
+
+    if (a[icol * n + icol] == 0.0)
+    {
+      cout << "gaussj: Singular Matrix-2" << endl;
+      for (int ii = 0; ii < n; ii++)
+      {
+        for (int jj = 0; jj < n; jj++)
+          cout << a[ii * n + jj] << " ";
+        cout << endl;
+      }
+      return 1; // error return
+    }
+
+    pivinv = 1.0 / a[icol * n + icol];
+    a[icol * n + icol] = 1.0;
+    for (l = 0; l < n; l++)
+      a[icol * n + l] *= pivinv;
+    b[icol] *= pivinv;
+    for (ll = 0; ll < n; ll++)
+      if (ll != icol)
+      {
+        dum = a[ll * n + icol];
+        a[ll * n + icol] = 0.0;
+        for (l = 0; l < n; l++)
+          a[ll * n + l] -= a[icol * n + l] * dum;
+        b[ll] -= b[icol] * dum;
+      }
   }
 
-  // Step 1: Solve linear system A*x = b using LU decomposition
-  // LAPACKE_dgesv uses column-major by default, but we use row-major
-  info = LAPACKE_dgesv(LAPACK_ROW_MAJOR, n, 1, a_copy, n, ipiv, b, 1);
-
-  if (info != 0) {
-    cout << "gaussj: Singular Matrix (dgesv info=" << info << ")" << endl;
-    delete[] ipiv;
-    delete[] a_copy;
-    return 1;
-  }
-
-  // Step 2: Compute matrix inverse A^(-1) using LU factorization
-  // First do LU factorization of original matrix a
-  info = LAPACKE_dgetrf(LAPACK_ROW_MAJOR, n, n, a, n, ipiv);
-
-  if (info != 0) {
-    cout << "gaussj: Singular Matrix (dgetrf info=" << info << ")" << endl;
-    delete[] ipiv;
-    delete[] a_copy;
-    return 1;
-  }
-
-  // Then compute inverse from LU factorization
-  info = LAPACKE_dgetri(LAPACK_ROW_MAJOR, n, a, n, ipiv);
-
-  if (info != 0) {
-    cout << "gaussj: Singular Matrix (dgetri info=" << info << ")" << endl;
-    delete[] ipiv;
-    delete[] a_copy;
-    return 1;
+  for (l = n - 1; l >= 0; l--)
+  {
+    if (indxr[l] != indxc[l])
+      for (k = 0; k < n; k++)
+      {
+        swap = a[k * n + indxr[l]];
+        a[k * n + indxr[l]] = a[k * n + indxc[l]];
+        a[k * n + indxc[l]] = swap;
+      }
   }
 
+  delete[] indxc;
+  delete[] indxr;
   delete[] ipiv;
-  delete[] a_copy;
 
   return 0;
 }

AMSS_NCKU_source/ilucg.f90

@@ -512,10 +512,11 @@
       IMPLICIT DOUBLE PRECISION (A-H,O-Z)
       DIMENSION V(N),W(N)
 !     SUBROUTINE TO COMPUTE DOUBLE PRECISION VECTOR DOT PRODUCT.
-!     Optimized using Intel oneMKL BLAS ddot
-!     Mathematical equivalence: DGVV = sum_{i=1}^{N} V(i)*W(i)
 
-      DOUBLE PRECISION, EXTERNAL :: DDOT
-      DGVV = DDOT(N, V, 1, W, 1)
+      SUM = 0.0D0
+            DO 10 I = 1,N
+            SUM = SUM + V(I)*W(I)
+10          CONTINUE
+      DGVV = SUM
       RETURN
       END

AMSS_NCKU_source/interp_lb_profile.C

@@ -1,107 +0,0 @@
-#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

@@ -1,38 +0,0 @@
-#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

@@ -1,27 +0,0 @@
-/* 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

@@ -65,8 +65,6 @@ 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

@@ -1,109 +0,0 @@
-#include "tool.h"
-
-/*
- * C 版 kodis
- *
- * Fortran signature:
- * subroutine kodis(ex,X,Y,Z,f,f_rhs,SoA,Symmetry,eps)
- *
- * 约定：
- *   X: ex1, Y: ex2, Z: ex3
- *   f, f_rhs: ex1*ex2*ex3 按 idx_ex 布局
- *   SoA[3]
- *   eps: double
- */
-void kodis(const int ex[3],
-           const double *X, const double *Y, const double *Z,
-           const double *f, double *f_rhs,
-           const double SoA[3],
-           int Symmetry, double eps)
-{
-    const double ONE = 1.0, SIX = 6.0, FIT = 15.0, TWT = 20.0;
-    const double cof = 64.0;             // 2^6
-    const int NO_SYMM = 0, OCTANT = 2;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    // Fortran: dX = X(2)-X(1) -> C: X[1]-X[0]
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-    (void)ONE; // ONE 在原 Fortran 里只是参数，这里不一定用得上
-
-    // Fortran: imax=ex(1) 等是 1-based 上界
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    // Fortran: imin=jmin=kmin=1，某些对称情况变 -2
-    int iminF = 1, jminF = 1, kminF = 1;
-
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
-    if (Symmetry == OCTANT && fabs(X[0]) < dX) iminF = -2;
-    if (Symmetry == OCTANT && fabs(Y[0]) < dY) jminF = -2;
-
-    // 分配 fh：大小 (ex1+3)*(ex2+3)*(ex3+3)，对应 ord=3
-    const size_t nx = (size_t)ex1 + 3;
-    const size_t ny = (size_t)ex2 + 3;
-    const size_t nz = (size_t)ex3 + 3;
-    const size_t fh_size = nx * ny * nz;
-
-    double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    // Fortran: call symmetry_bd(3,ex,f,fh,SoA)
-    symmetry_bd(3, ex, f, fh, SoA);
-
-    /*
-     * Fortran loops:
-     * do k=1,ex3
-     * do j=1,ex2
-     * do i=1,ex1
-     *
-     * C: k0=0..ex3-1, j0=0..ex2-1, i0=0..ex1-1
-     * 并定义 Fortran index: iF=i0+1, ...
-     */
-    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/lopsided_c.C

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

AMSS_NCKU_source/lopsidediff.f90

@@ -487,201 +487,6 @@ 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

@@ -1,77 +1,83 @@
-
-#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
-
-define tetradtype
-    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 Cell or Vertex
-    Cell center or Vertex center
-
-define ghost_width
-    2nd order: 2
-    4th order: 3
-    6th order: 4
-    8th order: 5
-
-define WithShell
-    use shell or not
-
-define CPBC
-    use constraint preserving boundary condition or not
-    only affect Z4c
-    CPBC only supports WithShell
-
-define GAUGE
-    0: B^i 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
-
-define CPBC_ghost_width  (ghost_width)
-    buffer points for CPBC boundary
-
-define ABV
-    0: using BSSN variable for constraint violation and psi4 calculation
-    1: using ADM variable for constraint violation and psi4 calculation
-
-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   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) )
-    5: shell with   phi(r) = phi0 * Exp(-(r-r0)**2/sigma), V = 0
-
-#endif
-
+
+
+#if 0
+note here
+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)
+#endif
+#define tetradtype 2
+
+#if 0
+note here
+Cell center or Vertex center
+#endif
+#define Cell
+
+#if 0
+note here
+2nd order: 2
+4th order: 3
+6th order: 4
+8th order: 5
+#endif
+#define ghost_width 3
+
+#if 0
+note here
+use shell or not
+#endif
+#define WithShell
+
+#if 0
+note here
+use constraint preserving boundary condition or not
+only affect Z4c
+#endif
+#define CPBC
+
+#if 0
+note here
+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
+#endif
+#define GAUGE 2
+
+#if 0
+buffer points for CPBC boundary
+#endif
+#define CPBC_ghost_width  (ghost_width)
+
+#if 0
+using BSSN variable for constraint violation and psi4 calculation: 0
+using ADM variable for constraint violation and psi4 calculation: 1
+#endif
+#define ABV 0
+
+#if 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 = 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

@@ -1,145 +1,112 @@
-
-#ifndef MICRODEF_H
-#define MICRODEF_H
-
-#include "macrodef.fh"  
-
-// application parameters
-
-#define SommerType 0
-
-#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 With_AHF
-//     using Apparent Horizon Finder
-//
-// define Psi4type
-//     Psi4 calculation method
-//     0: EB method
-//     1: 4-D method
-//
-// define Point_Psi4
-//     for Using point psi4 or not
-//
-// define RPS
-//     RestrictProlong in Step (0) or after Step (1)
-//
-// define AGM
-//     Enforce algebra constraint
-//     for every RK4 sub step: 0
-//     only when iter_count == 3: 1
-//     after routine Step: 2
-//
-// define RPB
-//     Restrict Prolong using BAM style 1 or old style 0
-//
-// define MAPBH
-//     1: move Analysis out ot 4 sub steps and treat PBH with Euler method
-//
-// define PSTR
-//     parallel structure
-//     0: level by level
-//     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
-//
-// define USE_GPU
-//     use gpu or not
-//
-// define CHECKDETAIL
-//     use checkpoint for every process
-//
-// define FAKECHECK
-//     use FakeCheckPrepare to write CheckPoint
-//
-
-////================================================================
-//  some basic parameters for numerical calculation
-////================================================================
-
-#define dim 3
-
-//#define Cell or Vertex in "macrodef.fh" 
-
-#define buffer_width 6
-
-#define SC_width buffer_width
-
-#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
-
-#define PACK 1
-#define UNPACK 2
-
-#define Mymax(a,b) (((a) > (b)) ? (a) : (b))
-#define Mymin(a,b) (((a) < (b)) ? (a) : (b))
-
-#define feq(a,b,d) (fabs(a-b)<d)
-#define flt(a,b,d) ((a-b)<d)
-#define fgt(a,b,d) ((a-b)>d)
-
-#define TINY 1e-10
-
-#endif   /* MICRODEF_H */
-
+
+#ifndef MICRODEF_H
+#define MICRODEF_H
+
+#include "microdef.fh"
+
+// application parameters
+
+/// ****
+// sommerfeld boundary type
+// 0: bam, 1: shibata
+#define SommerType 0
+
+/// ****
+// for Using Gauss-Legendre quadrature in theta direction
+#define GaussInt
+
+/// ****
+// 0: BSSN vacuum
+// 1: coupled to scalar field
+// 2: Z4c vacuum
+// 3: coupled to Maxwell field
+//
+#define ABEtype 2
+
+/// ****
+// using Apparent Horizon Finder
+//#define With_AHF
+
+/// ****
+// Psi4 calculation method
+// 0: EB method
+// 1: 4-D method
+//
+#define Psi4type 0
+
+/// ****
+// for Using point psi4 or not
+//#define Point_Psi4
+
+/// ****
+// RestrictProlong in Step (0) or after Step (1)
+#define RPS 1
+
+/// ****
+// Enforce algebra constraint
+// for every RK4 sub step: 0
+// only when iter_count == 3: 1
+// after routine Step: 2
+#define AGM 0
+
+/// ****
+// Restrict Prolong using BAM style 1 or old style 0
+#define RPB 0
+
+/// ****
+// 1: move Analysis out ot 4 sub steps and treat PBH with Euler method
+#define MAPBH 1
+
+/// ****
+// parallel structure, 0: level by level, 1: considering all levels, 2: as 1 but reverse the CPU order, 3: Frank's scheme
+#define PSTR 0
+
+/// ****
+// regrid for every level or for all levels at a time
+// 0: for every level; 1: for all
+#define REGLEV 0
+
+/// ****
+// use gpu or not
+//#define USE_GPU
+
+/// ****
+// use checkpoint for every process
+//#define CHECKDETAIL
+
+/// ****
+// use FakeCheckPrepare to write CheckPoint
+//#define FAKECHECK
+////================================================================
+//  some basic parameters for numerical calculation
+#define dim 3
+
+//#define Cell or Vertex in "microdef.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)
+
+#if(buffer_width < ghost_width)
+#error we always assume buffer_width>ghost_width
+#endif
+
+#define PACK 1
+#define UNPACK 2
+
+#define Mymax(a,b) (((a) > (b)) ? (a) : (b))
+#define Mymin(a,b) (((a) < (b)) ? (a) : (b))
+
+#define feq(a,b,d) (fabs(a-b)<d)
+#define flt(a,b,d) ((a-b)<d)
+#define fgt(a,b,d) ((a-b)>d)
+
+#define TINY 1e-10
+
+#endif   /* MICRODEF_H */

AMSS_NCKU_source/makefile

@@ -2,33 +2,6 @@
 
 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:
@@ -43,70 +16,13 @@ endif
 .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} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
-
-TwoPunctureABE.o: TwoPunctureABE.C
-	${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 interp_lb_profile.o
+	   NullShellPatch2_Evo.o writefile_f.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\
@@ -116,9 +32,9 @@ 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_BASE = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
+F90FILES = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
 	   prolongrestrict_cell.o prolongrestrict_vertex.o\
-	   $(RK4_F90_OBJ) diff_new.o kodiss.o kodiss_sh.o\
+	   rungekutta4_rout.o bssn_rhs.o 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\
@@ -129,14 +45,6 @@ F90FILES_BASE = 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 \
@@ -149,7 +57,7 @@ TwoPunctureFILES = TwoPunctureABE.o TwoPunctures.o
 CUDAFILES = bssn_gpu.o bssn_gpu_rhs_ss.o
 
 # file dependences
-$(C++FILES) $(C++FILES_GPU) $(F90FILES) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
+$(C++FILES) $(C++FILESGPU) $(F90FILES) $(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\
@@ -172,7 +80,7 @@ $(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) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.h
+$(C++FILES) $(C++FILES_GPU) $(AHFDOBJS) $(CUDAFILES): macrodef.h
 
 TwoPunctureFILES: TwoPunctures.h
 
@@ -181,17 +89,14 @@ $(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
 misc.o : zbesh.o
 
 # projects
-ABE: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
-	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS) -lcudart $(CUDA_LIB_PATH)
-
-ABE_CUDA: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
-	$(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)
+ABE: $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) 
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
+	
+ABEGPU: $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
 
 TwoPunctureABE: $(TwoPunctureFILES)
-	$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(TwoPunctureFILES) $(LDLIBS)
 
 clean:
-	rm *.o ABE ABE_CUDA ABEGPU TwoPunctureABE make.log -f
+	rm *.o ABE ABEGPU TwoPunctureABE make.log -f

AMSS_NCKU_source/makefile.inc

@@ -1,65 +1,22 @@
-## GCC version (commented out)
-## filein  = -I/usr/include -I/usr/lib/x86_64-linux-gnu/mpich/include -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
-## filein  = -I/usr/include/ -I/usr/include/openmpi-x86_64/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
-## LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
 
-## Intel oneAPI version with oneMKL (Optimized for performance)
-filein  = -I/usr/include/ -I${MKLROOT}/include
+filein  = -I/usr/include -I/usr/include/openmpi-x86_64 -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
 
-## 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 -liomp5
+##filein  = -I/usr/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/ -I/usr/lib/cuda/include
 
-## 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
+LDLIBS  = -L/usr/lib64/openmpi/lib -Wl,-rpath,/usr/lib64/openmpi/lib -lmpi -lgfortran -L/usr/local/cuda-13.1/lib64 -Wl,-rpath,/usr/local/cuda-13.1/lib64 -lcudart -lcuda 
+##LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -L/usr/lib/cuda/lib64 -lcudart -lmpi -lgfortran
 
-## 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
+CXXAPPFLAGS  = -O3 -Wno-deprecated -Dfortran3 -Dnewc
+#f90appflags = -O3 -fpp
+f90appflags  = -O3 -x f95-cpp-input
+f90          = gfortran 
+f77          = gfortran 
+CXX          = g++
+CC           = gcc
+CLINKER      = mpic++ 
 
-## 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
-
-f90          = ifx
-f77          = ifx
-CXX          = icpx
-CC           = icx
-CLINKER      = mpiicpx
-
-Cu = nvcc
-CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
+Cu = /usr/local/cuda-13.1/bin/nvcc
+CUDA_LIB_PATH = -L/usr/local/cuda-13.1/lib64 -I/usr/include -I/usr/local/cuda-13.1/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 -arch=sm_80
+# RTX 4050 uses Ada Lovelace architecture (compute capability 8.9)
+CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch=sm_89 -Dfortran3 -Dnewc

AMSS_NCKU_source/prolongrestrict_cell.f90

@@ -217,6 +217,7 @@
   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)
@@ -579,7 +580,7 @@
             tmp1(ghost_width-cxI(1)+cxB(1)  :ghost_width-cxI(1)+cxT(1)  ) = funf(cxB(1):cxT(1),j,k)
          endif
 
-         call polint0(X,tmp1,funf(i,j,k),2*ghost_width)
+         call polint(X,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
 
 ! for y direction
        elseif(sum(fg).eq.2.and.fg(2) .eq. 0.and. &
@@ -689,7 +690,7 @@
             tmp1(ghost_width-cxI(2)+cxB(2)  :ghost_width-cxI(2)+cxT(2)  ) = funf(i,cxB(2):cxT(2),k)
          endif
 
-         call polint0(Y,tmp1,funf(i,j,k),2*ghost_width)
+         call polint(Y,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
 
 ! for z direction
        elseif(sum(fg).eq.2.and.fg(3) .eq. 0.and. &
@@ -801,7 +802,7 @@
             tmp1(ghost_width-cxI(3)+cxB(3)  :ghost_width-cxI(3)+cxT(3)  ) = funf(i,j,cxB(3):cxT(3))
          endif
 
-         call polint0(Z,tmp1,funf(i,j,k),2*ghost_width)
+         call polint(Z,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
 
 #else
 
@@ -1933,35 +1934,18 @@
 ! 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,px,py,pz
+  integer :: i,j,k,ii,jj,kk
   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
@@ -2036,140 +2020,145 @@
           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
-
+  call symmetry_bd(3,extc,func,funcc,SoA)
+     
 !~~~~~~> 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
- do k = kmino, kmaxo
-     pz = piz(k)
-     kc = ciz(k)
+       if(ii/2*2==ii)then
+         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)= 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
 
-     do j = jmino, jmaxo
-        py = piy(j)
-        jc = ciy(j)
+       if(jj/2*2==jj)then
+             tmp1= C1*tmp2(:,1)+C2*tmp2(:,2)+C3*tmp2(:,3)+C4*tmp2(:,4)+C5*tmp2(:,5)+C6*tmp2(:,6)
+       else
+             tmp1= C6*tmp2(:,1)+C5*tmp2(:,2)+C4*tmp2(:,3)+C3*tmp2(:,4)+C2*tmp2(:,5)+C1*tmp2(:,6)
+       endif
 
-! --- 步骤 1 & 2 融合：分段处理 X 轴，提升 Cache 命中率 ---
-        ! 我们将 ii 循环逻辑重组，减少对 funcc 的跨行重复访问
-        do ii = 1, extc(1)
-           ! 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）
-           ! 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
+       if(ii/2*2==ii)then
+             funf(i,j,k)= C1*tmp1(1)+C2*tmp1(2)+C3*tmp1(3)+C4*tmp1(4)+C5*tmp1(5)+C6*tmp1(6)
+       else
+             funf(i,j,k)= C6*tmp1(1)+C5*tmp1(2)+C4*tmp1(3)+C3*tmp1(4)+C2*tmp1(5)+C1*tmp1(6)
+       endif
 #endif
+    enddo
+   enddo
+  enddo
+
   return
 
   end subroutine prolong3
@@ -2368,14 +2357,7 @@ end do
   integer::imino,imaxo,jmino,jmaxo,kmino,kmaxo
 
   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
@@ -2454,86 +2436,9 @@ end do
           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
+  call symmetry_bd(2,extf,funf,funff,SoA)
 
 !~~~~~~> 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
@@ -2557,7 +2462,7 @@ end do
     enddo
    enddo
   enddo
-#endif
+  
   return
 
   end subroutine restrict3

AMSS_NCKU_source/prolongrestrict_vertex.f90

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

AMSS_NCKU_source/rungekutta4_rout_c.C

@@ -1,155 +0,0 @@
-#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

@@ -1,246 +0,0 @@
-#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

@@ -220,9 +220,16 @@ void surface_integral::surf_Wave(double rex, int lev, cgh *GH, var *Rpsi4, var *
     pox[2][n] = rex * nz_g[n];
   }
 
+  double *shellf;
+  shellf = new double[n_tot * InList];
+
+  GH->PatL[lev]->data->Interp_Points(DG_List, n_tot, pox, shellf, Symmetry);
+
   int mp, Lp, Nmin, Nmax;
+
   mp = n_tot / cpusize;
   Lp = n_tot - cpusize * mp;
+
   if (Lp > myrank)
   {
     Nmin = myrank * mp + myrank;
@@ -234,11 +241,6 @@ void surface_integral::surf_Wave(double rex, int lev, cgh *GH, var *Rpsi4, var *
     Nmax = Nmin + mp - 1;
   }
 
-  double *shellf;
-  shellf = new double[n_tot * InList];
-
-  GH->PatL[lev]->data->Interp_Points(DG_List, n_tot, pox, shellf, Symmetry, Nmin, Nmax);
-
   //|~~~~~> Integrate the dot product of Dphi with the surface normal.
 
   double *RP_out, *IP_out;
@@ -361,17 +363,8 @@ void surface_integral::surf_Wave(double rex, int lev, cgh *GH, var *Rpsi4, var *
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -563,17 +556,8 @@ void surface_integral::surf_Wave(double rex, int lev, cgh *GH, var *Rpsi4, var *
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, Comm_here);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, Comm_here);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, Comm_here);
 
   //|------= Free memory.
 
@@ -751,17 +735,8 @@ void surface_integral::surf_Wave(double rex, int lev, ShellPatch *GH, var *Rpsi4
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -1009,17 +984,8 @@ void surface_integral::surf_Wave(double rex, int lev, ShellPatch *GH,
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -1453,17 +1419,8 @@ void surface_integral::surf_Wave(double rex, int lev, ShellPatch *GH,
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -1897,17 +1854,8 @@ void surface_integral::surf_Wave(double rex, int lev, cgh *GH,
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -2092,17 +2040,8 @@ void surface_integral::surf_Wave(double rex, int lev, NullShellPatch2 *GH, var *
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -2287,17 +2226,8 @@ void surface_integral::surf_Wave(double rex, int lev, NullShellPatch *GH, var *R
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 
@@ -2384,9 +2314,25 @@ void surface_integral::surf_MassPAng(double rex, int lev, cgh *GH, var *chi, var
     pox[2][n] = rex * nz_g[n];
   }
 
+  double *shellf;
+  shellf = new double[n_tot * InList];
+
+  // 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);
+
+  double Mass_out = 0;
+  double ang_outx, ang_outy, ang_outz;
+  double p_outx, p_outy, p_outz;
+  ang_outx = ang_outy = ang_outz = 0.0;
+  p_outx = p_outy = p_outz = 0.0;
+  const double f1o8 = 0.125;
+
   int mp, Lp, Nmin, Nmax;
+
   mp = n_tot / cpusize;
   Lp = n_tot - cpusize * mp;
+
   if (Lp > myrank)
   {
     Nmin = myrank * mp + myrank;
@@ -2398,20 +2344,6 @@ void surface_integral::surf_MassPAng(double rex, int lev, cgh *GH, var *chi, var
     Nmax = Nmin + mp - 1;
   }
 
-  double *shellf;
-  shellf = new double[n_tot * InList];
-
-  // 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, Nmin, Nmax);
-
-  double Mass_out = 0;
-  double ang_outx, ang_outy, ang_outz;
-  double p_outx, p_outy, p_outz;
-  ang_outx = ang_outy = ang_outz = 0.0;
-  p_outx = p_outy = p_outz = 0.0;
-  const double f1o8 = 0.125;
-
   double Chi, Psi;
   double Gxx, Gxy, Gxz, Gyy, Gyz, Gzz;
   double gupxx, gupxy, gupxz, gupyy, gupyz, gupzz;
@@ -2532,13 +2464,15 @@ void surface_integral::surf_MassPAng(double rex, int lev, cgh *GH, var *chi, var
     }
   }
 
-  {
-    double scalar_out[7] = {Mass_out, ang_outx, ang_outy, ang_outz, p_outx, p_outy, p_outz};
-    double scalar_in[7];
-    MPI_Allreduce(scalar_out, scalar_in, 7, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    mass = scalar_in[0]; sx = scalar_in[1]; sy = scalar_in[2]; sz = scalar_in[3];
-    px = scalar_in[4]; py = scalar_in[5]; pz = scalar_in[6];
-  }
+  MPI_Allreduce(&Mass_out, &mass, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+
+  MPI_Allreduce(&ang_outx, &sx, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&ang_outy, &sy, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&ang_outz, &sz, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+
+  MPI_Allreduce(&p_outx, &px, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&p_outy, &py, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&p_outz, &pz, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
 #ifdef GaussInt
   mass = mass * rex * rex * dphi * factor;
@@ -2801,13 +2735,15 @@ void surface_integral::surf_MassPAng(double rex, int lev, cgh *GH, var *chi, var
     }
   }
 
-  {
-    double scalar_out[7] = {Mass_out, ang_outx, ang_outy, ang_outz, p_outx, p_outy, p_outz};
-    double scalar_in[7];
-    MPI_Allreduce(scalar_out, scalar_in, 7, MPI_DOUBLE, MPI_SUM, Comm_here);
-    mass = scalar_in[0]; sx = scalar_in[1]; sy = scalar_in[2]; sz = scalar_in[3];
-    px = scalar_in[4]; py = scalar_in[5]; pz = scalar_in[6];
-  }
+  MPI_Allreduce(&Mass_out, &mass, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+
+  MPI_Allreduce(&ang_outx, &sx, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+  MPI_Allreduce(&ang_outy, &sy, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+  MPI_Allreduce(&ang_outz, &sz, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+
+  MPI_Allreduce(&p_outx, &px, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+  MPI_Allreduce(&p_outy, &py, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
+  MPI_Allreduce(&p_outz, &pz, 1, MPI_DOUBLE, MPI_SUM, Comm_here);
 
 #ifdef GaussInt
   mass = mass * rex * rex * dphi * factor;
@@ -3084,13 +3020,15 @@ void surface_integral::surf_MassPAng(double rex, int lev, ShellPatch *GH, var *c
     }
   }
 
-  {
-    double scalar_out[7] = {Mass_out, ang_outx, ang_outy, ang_outz, p_outx, p_outy, p_outz};
-    double scalar_in[7];
-    MPI_Allreduce(scalar_out, scalar_in, 7, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    mass = scalar_in[0]; sx = scalar_in[1]; sy = scalar_in[2]; sz = scalar_in[3];
-    px = scalar_in[4]; py = scalar_in[5]; pz = scalar_in[6];
-  }
+  MPI_Allreduce(&Mass_out, &mass, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+
+  MPI_Allreduce(&ang_outx, &sx, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&ang_outy, &sy, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&ang_outz, &sz, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+
+  MPI_Allreduce(&p_outx, &px, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&p_outy, &py, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(&p_outz, &pz, 1, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
 #ifdef GaussInt
   mass = mass * rex * rex * dphi * factor;
@@ -3669,17 +3607,8 @@ void surface_integral::surf_Wave(double rex, cgh *GH, ShellPatch *SH,
   }
   //|------+  Communicate and sum the results from each processor.
 
-  {
-    double *RPIP_out = new double[2 * NN];
-    double *RPIP = new double[2 * NN];
-    memcpy(RPIP_out, RP_out, NN * sizeof(double));
-    memcpy(RPIP_out + NN, IP_out, NN * sizeof(double));
-    MPI_Allreduce(RPIP_out, RPIP, 2 * NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-    memcpy(RP, RPIP, NN * sizeof(double));
-    memcpy(IP, RPIP + NN, NN * sizeof(double));
-    delete[] RPIP_out;
-    delete[] RPIP;
-  }
+  MPI_Allreduce(RP_out, RP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
+  MPI_Allreduce(IP_out, IP, NN, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
 
   //|------= Free memory.
 

AMSS_NCKU_source/tool.h

@@ -1,27 +0,0 @@
-#include "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

@@ -1,72 +0,0 @@
-#!/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

@@ -10,48 +10,6 @@
 
 import AMSS_NCKU_Input as input_data
 import subprocess
-import time
-
-
-def get_last_n_cores_per_socket(n=32):
-    """
-    Read CPU topology via lscpu and return a taskset -c string
-    selecting the last `n` cores of each NUMA node (socket).
-
-    Example: 2 sockets x 56 cores each, n=32 -> node0: 24-55, node1: 80-111
-    -> "taskset -c 24-55,80-111"
-    """
-    result = subprocess.run(["lscpu", "--parse=NODE,CPU"], capture_output=True, text=True)
-
-    # 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
 
 
 ##################################################################
@@ -68,11 +26,11 @@ def makefile_ABE():
     print( " Compiling the AMSS-NCKU executable file ABE/ABEGPU " ) 
     print(                                                        )
 
-    ## Build command with CPU binding to nohz_full cores
+    ## Build command
     if (input_data.GPU_Calculation == "no"):
-        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} INTERP_LB_MODE=optimize ABE"
+        makefile_command  = "make -j4" + " ABE"
     elif (input_data.GPU_Calculation == "yes"):
-        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABEGPU"
+        makefile_command  = "make -j4" + " ABEGPU"
     else:
         print( " CPU/GPU numerical calculation setting is wrong " )
         print(                                                    )
@@ -109,8 +67,8 @@ def makefile_TwoPunctureABE():
     print( " Compiling the AMSS-NCKU executable file TwoPunctureABE " )
     print(                                                            )
     
-    ## Build command with CPU binding to nohz_full cores
-    makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} TwoPunctureABE"
+    ## Build command
+    makefile_command = "make" + " TwoPunctureABE"
 
     ## Execute the command with subprocess.Popen and stream output
     makefile_process = subprocess.Popen(makefile_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True) 
@@ -147,11 +105,10 @@ 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_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
-        #mpi_command         = " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
+        mpi_command         = "mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
         mpi_command_outfile = "ABE_out.log"
     elif (input_data.GPU_Calculation == "yes"):
-        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
+        mpi_command         = "mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
         mpi_command_outfile = "ABEGPU_out.log"
  
     ## Execute the MPI command and stream output
@@ -184,14 +141,13 @@ def run_ABE():
 ## Run the AMSS-NCKU TwoPuncture program TwoPunctureABE
 
 def run_TwoPunctureABE():
-    tp_time1=time.time()
+
     print(                                                          )
     print( " Running the AMSS-NCKU executable file TwoPunctureABE " ) 
     print(                                                          )
     
     ## Define the command to run
-    #TwoPuncture_command         = NUMACTL_CPU_BIND + " ./TwoPunctureABE"
-    TwoPuncture_command         = " ./TwoPunctureABE"
+    TwoPuncture_command         = "./TwoPunctureABE"
     TwoPuncture_command_outfile = "TwoPunctureABE_out.log"
 
     ## Execute the command with subprocess.Popen and stream output
@@ -212,9 +168,7 @@ def run_TwoPunctureABE():
     print(                                               )
     print( " The TwoPunctureABE simulation is finished " ) 
     print(                                               )
-    tp_time2=time.time()
-    et=tp_time2-tp_time1
-    print(f"Used time: {et}")
+    
     return
 
 ##################################################################

parallel_plot_helper.py

@@ -1,29 +0,0 @@
-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)

pgo_profile/PGO_Profile_Analysis.md

@@ -1,97 +0,0 @@
-# AMSS-NCKU PGO Profile Analysis Report
-
-## 1. Profiling Environment
-
-| Item | Value |
-|------|-------|
-| Compiler | Intel oneAPI DPC++/C++ 2025.3.0 (icpx/ifx) |
-| Instrumentation Flag | `-fprofile-instr-generate` |
-| Optimization Level (instrumented) | `-O2 -xHost -fma` |
-| MPI Processes | 1 (single process to avoid MPI+instrumentation deadlock) |
-| Profile File | `default_9725750769337483397_0.profraw` (327 KB) |
-| Merged Profile | `default.profdata` (394 KB) |
-| llvm-profdata | `/home/intel/oneapi/compiler/2025.3/bin/compiler/llvm-profdata` |
-
-## 2. Reduced Simulation Parameters (for profiling run)
-
-| Parameter | Production Value | Profiling Value |
-|-----------|-----------------|-----------------|
-| MPI_processes | 64 | 1 |
-| grid_level | 9 | 4 |
-| static_grid_level | 5 | 3 |
-| static_grid_number | 96 | 24 |
-| moving_grid_number | 48 | 16 |
-| largest_box_xyz_max | 320^3 | 160^3 |
-| Final_Evolution_Time | 1000.0 | 10.0 |
-| Evolution_Step_Number | 10,000,000 | 1,000 |
-| Detector_Number | 12 | 2 |
-
-## 3. Profile Summary
-
-| Metric | Value |
-|--------|-------|
-| Total instrumented functions | 1,392 |
-| Functions with non-zero counts | 117 (8.4%) |
-| Functions with zero counts | 1,275 (91.6%) |
-| Maximum function entry count | 386,459,248 |
-| Maximum internal block count | 370,477,680 |
-| Total block count | 4,198,023,118 |
-
-## 4. Top 20 Hotspot Functions
-
-| Rank | Total Count | Max Block Count | Function | Category |
-|------|------------|-----------------|----------|----------|
-| 1 | 1,241,601,732 | 370,477,680 | `polint_` | Interpolation |
-| 2 | 755,994,435 | 230,156,640 | `prolong3_` | Grid prolongation |
-| 3 | 667,964,095 | 3,697,792 | `compute_rhs_bssn_` | BSSN RHS evolution |
-| 4 | 539,736,051 | 386,459,248 | `symmetry_bd_` | Symmetry boundary |
-| 5 | 277,310,808 | 53,170,728 | `lopsided_` | Lopsided FD stencil |
-| 6 | 155,534,488 | 94,535,040 | `decide3d_` | 3D grid decision |
-| 7 | 119,267,712 | 19,266,048 | `rungekutta4_rout_` | RK4 time integrator |
-| 8 | 91,574,616 | 48,824,160 | `kodis_` | Kreiss-Oliger dissipation |
-| 9 | 67,555,389 | 43,243,680 | `fderivs_` | Finite differences |
-| 10 | 55,296,000 | 42,246,144 | `misc::fact(int)` | Factorial utility |
-| 11 | 43,191,071 | 27,663,328 | `fdderivs_` | 2nd-order FD derivatives |
-| 12 | 36,233,965 | 22,429,440 | `restrict3_` | Grid restriction |
-| 13 | 24,698,512 | 17,231,520 | `polin3_` | Polynomial interpolation |
-| 14 | 22,962,942 | 20,968,768 | `copy_` | Data copy |
-| 15 | 20,135,696 | 17,259,168 | `Ansorg::barycentric(...)` | Spectral interpolation |
-| 16 | 14,650,224 | 7,224,768 | `Ansorg::barycentric_omega(...)` | Spectral weights |
-| 17 | 13,242,296 | 2,871,920 | `global_interp_` | Global interpolation |
-| 18 | 12,672,000 | 7,734,528 | `sommerfeld_rout_` | Sommerfeld boundary |
-| 19 | 6,872,832 | 1,880,064 | `sommerfeld_routbam_` | Sommerfeld boundary (BAM) |
-| 20 | 5,709,900 | 2,809,632 | `l2normhelper_` | L2 norm computation |
-
-## 5. Hotspot Category Breakdown
-
-Top 20 functions account for ~98% of total execution counts:
-
-| Category | Functions | Combined Count | Share |
-|----------|-----------|---------------|-------|
-| Interpolation / Prolongation / Restriction | polint_, prolong3_, restrict3_, polin3_, global_interp_, Ansorg::* | ~2,093M | ~50% |
-| BSSN RHS + FD stencils | compute_rhs_bssn_, lopsided_, fderivs_, fdderivs_ | ~1,056M | ~25% |
-| Boundary conditions | symmetry_bd_, sommerfeld_rout_, sommerfeld_routbam_ | ~559M | ~13% |
-| Time integration | rungekutta4_rout_ | ~119M | ~3% |
-| Dissipation | kodis_ | ~92M | ~2% |
-| Utilities | misc::fact, decide3d_, copy_, l2normhelper_ | ~256M | ~6% |
-
-## 6. Conclusions
-
-1. **Profile data is valid**: 1,392 functions instrumented, 117 exercised with ~4.2 billion total counts.
-2. **Hotspot concentration is high**: Top 5 functions alone account for ~76% of all counts, which is ideal for PGO — the compiler has strong branch/layout optimization targets.
-3. **Fortran numerical kernels dominate**: `polint_`, `prolong3_`, `compute_rhs_bssn_`, `symmetry_bd_`, `lopsided_` are all Fortran routines in the inner evolution loop. PGO will optimize their branch prediction and basic block layout.
-4. **91.6% of functions have zero counts**: These are code paths for unused features (GPU, BSSN-EScalar, BSSN-EM, Z4C, etc.). PGO will deprioritize them, improving instruction cache utilization.
-5. **Profile is representative**: Despite the reduced grid size, the code path coverage matches production — the same kernels (RHS, prolongation, restriction, boundary) are exercised. PGO branch probabilities from this profile will transfer well to full-scale runs.
-
-## 7. PGO Phase 2 Usage
-
-To apply the profile, use the following flags in `makefile.inc`:
-
-```makefile
-CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-              -fprofile-instr-use=/home/amss/AMSS-NCKU/pgo_profile/default.profdata \
-              -Dfortran3 -Dnewc -I${MKLROOT}/include
-f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-              -fprofile-instr-use=/home/amss/AMSS-NCKU/pgo_profile/default.profdata \
-              -align array64byte -fpp -I${MKLROOT}/include
-```

plot_GW_strain_amplitude_xiaoqu.py

@@ -11,8 +11,6 @@
 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

@@ -8,23 +8,16 @@
 ##
 #################################################
 
-## 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
+
 
 #########################################################################################
 
@@ -199,19 +192,3 @@ 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

@@ -8,8 +8,6 @@
 #################################################
 
 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
@@ -17,9 +15,6 @@ 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
 
@@ -55,40 +50,10 @@ def generate_binary_data_plot( binary_outdir, figure_outdir ):
         file_list.append(x)
         print(x)
 
-    ## 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  = []
+    ## Plot each file in the list
     for filename in file_list:
         print(filename)
-        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 )
+        plot_binary_data.plot_binary_data(filename, binary_outdir, figure_outdir)
 
     print(                        )
     print( " Binary Data Plot Has been Finished " )