Trigger-Discipline: parallelize result plotting

.gitignore

@@ -1,6 +1,5 @@
 __pycache__
 GW150914
-GW150914-origin
+GW150914*
-docs
+.codex
-*.tmp
+docs/
-

AMSS_NCKU_Input.py

@@ -16,7 +16,7 @@ import numpy
 File_directory   = "GW150914"                    ## output file directory
 Output_directory = "binary_output"               ## binary data file directory
                                                  ## The file directory name should not be too long
-MPI_processes    = 48                             ## number of mpi processes used in the simulation
+MPI_processes    = 64                             ## number of mpi processes used in the simulation
 
 GPU_Calculation  = "no"                          ## Use GPU or not 
                                                  ## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)

AMSS_NCKU_Program.py

@@ -9,6 +9,16 @@
 ##################################################################
 
 
+##################################################################
+
+## 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.
+if __name__ != '__main__':
+    import sys as _sys
+    _sys.exit(0)
+
+
 ##################################################################
 
 ## Print program introduction
@@ -424,26 +434,31 @@ print(
 
 import plot_xiaoqu
 import plot_GW_strain_amplitude_xiaoqu
+from parallel_plot_helper import run_plot_tasks_parallel
+
+plot_tasks = []
 
 ## Plot black hole trajectory
-plot_xiaoqu.generate_puncture_orbit_plot(   binary_results_directory, figure_directory )
+plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot,   (binary_results_directory, figure_directory) ) )
-plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
+plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot3D, (binary_results_directory, figure_directory) ) )
 
 ## Plot black hole separation vs. time
-plot_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
+plot_tasks.append( ( plot_xiaoqu.generate_puncture_distence_plot, (binary_results_directory, figure_directory) ) )
 
 ## Plot gravitational waveforms (psi4 and strain amplitude)
 for i in range(input_data.Detector_Number):
-    plot_xiaoqu.generate_gravitational_wave_psi4_plot( binary_results_directory, figure_directory, i )
+    plot_tasks.append( ( plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i) ) )
-    plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot( binary_results_directory, figure_directory, i )
+    plot_tasks.append( ( plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot, (binary_results_directory, figure_directory, i) ) )
 
 ## Plot ADM mass evolution
 for i in range(input_data.Detector_Number):
-    plot_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
+    plot_tasks.append( ( plot_xiaoqu.generate_ADMmass_plot, (binary_results_directory, figure_directory, i) ) )
 
 ## Plot Hamiltonian constraint violation over time
 for i in range(input_data.grid_level):
-    plot_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
+    plot_tasks.append( ( plot_xiaoqu.generate_constraint_check_plot, (binary_results_directory, figure_directory, i) ) )
+
+run_plot_tasks_parallel(plot_tasks)
 
 ## Plot stored binary data
 plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )

AMSS_NCKU_Verify_ASC26.py

@@ -1,279 +0,0 @@
-#!/usr/bin/env python3
-"""
-AMSS-NCKU GW150914 Simulation Regression Test Script
-
-Verification Requirements:
-1. XY-plane trajectory RMS error < 1% (Optimized vs. baseline, max of BH1 and BH2)
-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_rms_error(bh_data_ref, bh_data_target):
-    """
-    Calculate trajectory-based RMS error on the XY plane between baseline and optimized simulations.
-
-    This function computes the RMS error independently for BH1 and BH2 trajectories,
-    then returns the maximum of the two as the final RMS error metric.
-
-    For each black hole, the RMS is calculated as:
-        RMS = sqrt( (1/M) * sum( (Δr_i / r_i^max)^2 ) ) × 100%
-
-    where:
-        Δr_i = sqrt((x_ref,i - x_new,i)^2 + (y_ref,i - y_new,i)^2)
-        r_i^max = max(sqrt(x_ref,i^2 + y_ref,i^2), sqrt(x_new,i^2 + y_new,i^2))
-
-    Args:
-        bh_data_ref: Reference (baseline) trajectory data
-        bh_data_target: Target (optimized) trajectory data
-
-    Returns:
-        rms_value: Final RMS error as a percentage (max of BH1 and BH2)
-        error: Error message if any
-    """
-    # Align data: truncate to the length of the shorter dataset
-    M = min(len(bh_data_ref['time']), len(bh_data_target['time']))
-
-    if M < 10:
-        return None, "Insufficient data points for comparison"
-
-    # Extract XY coordinates for both black holes
-    x1_ref = bh_data_ref['x1'][:M]
-    y1_ref = bh_data_ref['y1'][:M]
-    x2_ref = bh_data_ref['x2'][:M]
-    y2_ref = bh_data_ref['y2'][:M]
-
-    x1_new = bh_data_target['x1'][:M]
-    y1_new = bh_data_target['y1'][:M]
-    x2_new = bh_data_target['x2'][:M]
-    y2_new = bh_data_target['y2'][:M]
-
-    # Calculate RMS for BH1
-    delta_r1 = np.sqrt((x1_ref - x1_new)**2 + (y1_ref - y1_new)**2)
-    r1_ref = np.sqrt(x1_ref**2 + y1_ref**2)
-    r1_new = np.sqrt(x1_new**2 + y1_new**2)
-    r1_max = np.maximum(r1_ref, r1_new)
-
-    # Calculate RMS for BH2
-    delta_r2 = np.sqrt((x2_ref - x2_new)**2 + (y2_ref - y2_new)**2)
-    r2_ref = np.sqrt(x2_ref**2 + y2_ref**2)
-    r2_new = np.sqrt(x2_new**2 + y2_new**2)
-    r2_max = np.maximum(r2_ref, r2_new)
-
-    # Avoid division by zero for BH1
-    valid_mask1 = r1_max > 1e-15
-    if np.sum(valid_mask1) < 10:
-        return None, "Insufficient valid data points for BH1"
-
-    terms1 = (delta_r1[valid_mask1] / r1_max[valid_mask1])**2
-    rms_bh1 = np.sqrt(np.mean(terms1)) * 100
-
-    # Avoid division by zero for BH2
-    valid_mask2 = r2_max > 1e-15
-    if np.sum(valid_mask2) < 10:
-        return None, "Insufficient valid data points for BH2"
-
-    terms2 = (delta_r2[valid_mask2] / r2_max[valid_mask2])**2
-    rms_bh2 = np.sqrt(np.mean(terms2)) * 100
-
-    # Final RMS is the maximum of BH1 and BH2
-    rms_final = max(rms_bh1, rms_bh2)
-
-    return rms_final, 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 report header"""
-    print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-    print(Color.BOLD + "   AMSS-NCKU GW150914 Simulation Regression Test Report" + Color.RESET)
-    print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-
-
-def print_rms_results(rms_rel, error, threshold=1.0):
-    """Print RMS error results"""
-    print(f"\n{Color.BOLD}1. RMS Error Analysis (Baseline vs Optimized){Color.RESET}")
-    print("-" * 45)
-
-    if error:
-        print(f"   {Color.RED}Error: {error}{Color.RESET}")
-        return False
-
-    passed = rms_rel < threshold
-
-    print(f"   RMS relative error: {rms_rel:.4f}%")
-    print(f"   Requirement:        < {threshold}%")
-    print(f"   Status:             {get_status_text(passed)}")
-
-    return passed
-
-
-def print_constraint_results(results, threshold=2.0):
-    """Print constraint violation results"""
-    print(f"\n{Color.BOLD}2. ADM Constraint Violation Analysis (Grid Level 0){Color.RESET}")
-    print("-" * 45)
-
-    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 summary"""
-    print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-    print(Color.BOLD + "Verification Summary" + Color.RESET)
-    print(Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
-
-    all_passed = rms_passed and constraint_passed
-    
-    res_rms = get_status_text(rms_passed)
-    res_con = get_status_text(constraint_passed)
-
-    print(f"   [1] RMS trajectory check:         {res_rms}")
-    print(f"   [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():
-    # Determine target (optimized) output directory
-    if len(sys.argv) > 1:
-        target_dir = sys.argv[1]
-    else:
-        script_dir = os.path.dirname(os.path.abspath(__file__))
-        target_dir = os.path.join(script_dir, "GW150914/AMSS_NCKU_output")
-
-    # Determine reference (baseline) directory
-    script_dir = os.path.dirname(os.path.abspath(__file__))
-    reference_dir = os.path.join(script_dir, "GW150914-origin/AMSS_NCKU_output")
-
-    # Data file paths
-    bh_file_ref = os.path.join(reference_dir, "bssn_BH.dat")
-    bh_file_target = os.path.join(target_dir, "bssn_BH.dat")
-    constraint_file = os.path.join(target_dir, "bssn_constraint.dat")
-
-    # Check if files exist
-    if not os.path.exists(bh_file_ref):
-        print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Baseline trajectory file not found: {bh_file_ref}")
-        sys.exit(1)
-
-    if not os.path.exists(bh_file_target):
-        print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Target trajectory file not found: {bh_file_target}")
-        sys.exit(1)
-
-    if not os.path.exists(constraint_file):
-        print(f"{Color.RED}{Color.BOLD}Error:{Color.RESET} Constraint data file not found: {constraint_file}")
-        sys.exit(1)
-
-    # Print header
-    print_header()
-    print(f"\n{Color.BOLD}Reference (Baseline):{Color.RESET} {Color.BLUE}{reference_dir}{Color.RESET}")
-    print(f"{Color.BOLD}Target (Optimized):  {Color.RESET} {Color.BLUE}{target_dir}{Color.RESET}")
-
-    # Load data
-    bh_data_ref = load_bh_trajectory(bh_file_ref)
-    bh_data_target = load_bh_trajectory(bh_file_target)
-    constraint_data = load_constraint_data(constraint_file)
-
-    # Calculate RMS error
-    rms_rel, error = calculate_rms_error(bh_data_ref, bh_data_target)
-    rms_passed = print_rms_results(rms_rel, error)
-
-    # Analyze constraint violation
-    constraint_results = analyze_constraint_violation(constraint_data)
-    constraint_passed = print_constraint_results(constraint_results)
-
-    # Print summary
-    all_passed = print_summary(rms_passed, constraint_passed)
-
-    # Return exit code
-    sys.exit(0 if all_passed else 1)
-
-
-if __name__ == "__main__":
-    main()

AMSS_NCKU_source/ABE.optrpt

@@ -1,710 +0,0 @@
-Begin optimization report for: __cxx_global_var_init
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, int, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::map()
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, int, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~map()
-=================================================================
-
-Begin optimization report for: __cxx_global_var_init.1
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, double, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::map()
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, double, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~map()
-=================================================================
-
-Begin optimization report for: __cxx_global_var_init.2
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::map()
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~map()
-=================================================================
-
-Begin optimization report for: main
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
-LOOP END
-
-LOOP BEGIN at ABE.C (125, 13)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::allocator<char>::allocator()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string<std::allocator<char>>(char const*, std::allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<char>::~__new_allocator()
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::insert(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair<char const (&) [9], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&, true>(char const (&) [9], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&)
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::~pair()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::~basic_string()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_iterator()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string()
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::find(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::operator!=(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&, std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&)
-=================================================================
-
-Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::end()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator->() const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::operator=(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::c_str() const
-=================================================================
-
-Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::operator<<<std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&, char const*)
-=================================================================
-
-Begin optimization report for: std::ostream::operator<<(std::ostream& (*)(std::ostream&))
-=================================================================
-
-Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::endl<char, std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&)
-=================================================================
-
-Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::basic_ifstream(char const*, std::_Ios_Openmode)
-=================================================================
-
-Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::good() const
-=================================================================
-
-Begin optimization report for: std::istream::getline(char*, long)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::operator=(char const*)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-=================================================================
-
-Begin optimization report for: bool std::operator==<char, std::char_traits<char>, std::allocator<char>>(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, char const*)
-=================================================================
-
-Begin optimization report for: atoi
-=================================================================
-
-Begin optimization report for: atof
-=================================================================
-
-Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::close()
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair<char const (&) [11], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&, true>(char const (&) [11], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&)
-=================================================================
-
-Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
-=================================================================
-
-Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::basic_ofstream()
-=================================================================
-
-Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::open(char const*, std::_Ios_Openmode)
-=================================================================
-
-Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::close()
-=================================================================
-
-Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
-=================================================================
-
-Begin optimization report for: std::ostream::operator<<(double)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
-=================================================================
-
-Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_key_compare<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_key_compare()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_header::_Rb_tree_header()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_header::_M_reset()
-=================================================================
-
-Begin optimization report for: __clang_call_terminate
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
-    remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
-    remark #25478: While loop unrolled by 2
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_begin()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_S_right(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_S_left(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
-=================================================================
-
-Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_get_Node_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_valptr()
-=================================================================
-
-Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>*)
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>::~pair()
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_ptr()
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_addr()
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_mbegin() const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
-=================================================================
-
-Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::allocator()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
-    remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
-    remark #25478: While loop unrolled by 2
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_begin()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_S_right(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_S_left(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
-=================================================================
-
-Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_get_Node_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_valptr()
-=================================================================
-
-Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>*)
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>::~pair()
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_ptr()
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_addr()
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_mbegin() const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
-=================================================================
-
-Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::allocator()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~_Rb_tree()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
-    remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_begin()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~__new_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_right(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_left(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
-=================================================================
-
-Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_Node_allocator()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_valptr()
-=================================================================
-
-Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*)
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_ptr()
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_addr()
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_mbegin() const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_data() const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_local_data()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::_Alloc_hider(char*, std::allocator<char>&&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_init_local_buf()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_set_length(unsigned long)
-=================================================================
-
-Begin optimization report for: std::__ptr_traits_ptr_to<char*, char, false>::pointer_to(char&)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<char>::__new_allocator(std::__new_allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_length(unsigned long)
-=================================================================
-
-Begin optimization report for: std::char_traits<char>::assign(char&, char const&)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<char>::__new_allocator()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_dispose()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::~_Alloc_hider()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_is_local() const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_destroy(unsigned long)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_local_data() const
-=================================================================
-
-Begin optimization report for: std::__ptr_traits_ptr_to<char const*, char const, false>::pointer_to(char const&)
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<char>>::deallocate(std::allocator<char>&, char*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_get_allocator()
-=================================================================
-
-Begin optimization report for: std::__new_allocator<char>::deallocate(char*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::_Alloc_hider(char*, std::allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::char_traits<char>::length(char const*)
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char const*>::difference_type std::distance<char const*>(char const*, char const*)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_data(char*)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_capacity(unsigned long)
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)::_Guard::_Guard(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>*)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy_chars(char*, char const*, char const*)
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)::_Guard::~_Guard()
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char const*>::difference_type std::__distance<char const*>(char const*, char const*, std::random_access_iterator_tag)
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char const*>::iterator_category std::__iterator_category<char const*>(char const* const&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy(char*, char const*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::char_traits<char>::copy(char*, char const*, unsigned long)
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__alloc_traits<std::allocator<char>, char>::_S_select_on_copy(std::allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_get_allocator() const
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::length() const
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<char>>::select_on_container_copy_construction(std::allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::allocator<char>::allocator(std::allocator<char> const&)
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char*>::difference_type std::distance<char*>(char*, char*)
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)::_Guard::_Guard(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>*)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy_chars(char*, char*, char*)
-=================================================================
-
-Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)::_Guard::~_Guard()
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char*>::difference_type std::__distance<char*>(char*, char*, std::random_access_iterator_tag)
-=================================================================
-
-Begin optimization report for: std::iterator_traits<char*>::iterator_category std::__iterator_category<char*>(char* const&)
-=================================================================
-
-Begin optimization report for: std::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool> std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_insert_unique<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (2113, 7)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_insert_unique_pos(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (2113, 7)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator()(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&) const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node::_Alloc_node(std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_insert_<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node>(std::_Rb_tree_node_base*, std::_Rb_tree_node_base*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&, std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node&)
-=================================================================
-
-Begin optimization report for: std::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool>::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool, true>(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>&&, bool&&)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_iterator(std::_Rb_tree_node_base*)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_end()
-=================================================================
-
-Begin optimization report for: std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::operator()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&) const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_key(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const*)
-=================================================================
-
-Begin optimization report for: std::operator==(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&, std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::begin()
-=================================================================
-
-Begin optimization report for: std::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*>::pair<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*&, std::_Rb_tree_node_base*&, true>(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*&, std::_Rb_tree_node_base*&)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator--()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_key(std::_Rb_tree_node_base const*)
-=================================================================
-
-Begin optimization report for: std::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*>::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*, true>(std::_Rb_tree_node_base* const&, std::_Rb_tree_node_base* const&)
-=================================================================
-
-Begin optimization report for: bool std::operator<<char, std::char_traits<char>, std::allocator<char>>(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::compare(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&) const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::size() const
-=================================================================
-
-Begin optimization report for: unsigned long const& std::min<unsigned long>(unsigned long const&, unsigned long const&)
-=================================================================
-
-Begin optimization report for: std::char_traits<char>::compare(char const*, char const*, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::data() const
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_compare(unsigned long, unsigned long)
-=================================================================
-
-Begin optimization report for: std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator()(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>> const&) const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_valptr() const
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_ptr() const
-=================================================================
-
-Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_addr() const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>* std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node::operator()<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&) const
-=================================================================
-
-Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>* std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_create_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_node()
-=================================================================
-
-Begin optimization report for: void std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_construct_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::allocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, unsigned long)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::allocate(unsigned long, void const*)
-=================================================================
-
-Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_max_size() const
-=================================================================
-
-Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::construct<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::construct<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&&)
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_use_local_data()
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::find(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_lower_bound(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, std::_Rb_tree_node_base*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-
-LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
-LOOP END
-=================================================================
-
-Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::end()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::assign(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
-=================================================================
-
-Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::setstate(std::_Ios_Iostate)
-=================================================================
-
-Begin optimization report for: std::operator|(std::_Ios_Iostate, std::_Ios_Iostate)
-=================================================================
-
-Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::rdstate() const
-=================================================================
-
-Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::flush<char, std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&)
-=================================================================
-
-Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::widen(char) const
-=================================================================
-
-Begin optimization report for: std::ctype<char> const& std::__check_facet<std::ctype<char>>(std::ctype<char> const*)
-=================================================================
-
-Begin optimization report for: std::ctype<char>::widen(char) const
-=================================================================
-
-Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::basic_ios()
-=================================================================
-
-Begin optimization report for: std::basic_istream<char, std::char_traits<char>>::basic_istream()
-=================================================================
-
-Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::open(char const*, std::_Ios_Openmode)
-=================================================================
-
-Begin optimization report for: std::basic_filebuf<char, std::char_traits<char>>::~basic_filebuf()
-=================================================================
-
-Begin optimization report for: std::basic_istream<char, std::char_traits<char>>::~basic_istream()
-=================================================================
-
-Begin optimization report for: std::operator|(std::_Ios_Openmode, std::_Ios_Openmode)
-=================================================================
-
-Begin optimization report for: std::basic_streambuf<char, std::char_traits<char>>::~basic_streambuf()
-=================================================================
-
-Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
-=================================================================
-
-Begin optimization report for: virtual thunk to std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
-=================================================================
-
-Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::assign(char const*)
-=================================================================
-
-Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>::basic_ostream()
-=================================================================
-
-Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>::~basic_ostream()
-=================================================================
-
-Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
-=================================================================
-
-Begin optimization report for: virtual thunk to std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
-=================================================================
-
-Begin optimization report for: _GLOBAL__sub_I_ABE.C
-=================================================================
-

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
+INTEGER::isign,nn
-DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
+double precision,dimension(2*nn)::dataa
-
+INTEGER::i,istep,j,m,mmax,n
-type(DFTI_DESCRIPTOR), pointer :: desc
+double precision::tempi,tempr
-integer :: status
+DOUBLE PRECISION::theta,wi,wpi,wpr,wr,wtemp
-
+n=2*nn
-! Create DFTI descriptor for 1D complex-to-complex transform
+j=1
-status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
+do i=1,n,2
-if (status /= 0) return
+  if(j.gt.i)then
-
+     tempr=dataa(j)
-! Set input/output storage as interleaved complex (default)
+     tempi=dataa(j+1)
-status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
+     dataa(j)=dataa(i)
-if (status /= 0) then
+     dataa(j+1)=dataa(i+1)
-   status = DftiFreeDescriptor(desc)
+     dataa(i)=tempr
-   return
+     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/TwoPunctures.h

@@ -1,7 +1,8 @@
-
 #ifndef TWO_PUNCTURES_H
 #define TWO_PUNCTURES_H
 
+#include <omp.h>
+
 #define StencilSize 19
 #define N_PlaneRelax 1
 #define NRELAX 200
@@ -42,6 +43,18 @@ 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;
@@ -58,6 +71,28 @@ 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);
@@ -116,23 +151,11 @@ 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)

AMSS_NCKU_source/bssn_rhs.f90

@@ -24,9 +24,6 @@
                         Gmx_Res, Gmy_Res, Gmz_Res,                             &
                Symmetry,Lev,eps,co)  result(gont)
 ! calculate constraint violation when co=0               
-#if (GAUGE == 6 || GAUGE == 7)
-  use mkl_vml
-#endif
   implicit none
 
 !~~~~~~> Input parameters:
@@ -100,13 +97,11 @@
 #endif
 
 #if (GAUGE == 6 || GAUGE == 7)
-  integer :: BHN,i,j,k, idx, total_points
+  integer :: BHN,i,j,k
   real*8, dimension(9) :: Porg
   real*8, dimension(3) :: Mass
-  real*8 :: r1,r2,M,A,w1,w2,C1,C2,denom_r
+  real*8 :: r1,r2,M,A,w1,w2,C1,C2
   real*8, dimension(ex(1),ex(2),ex(3)) :: reta
-  real*8, allocatable :: vml_r1(:), vml_r2(:)
-  real*8, allocatable :: vml_res1(:), vml_res2(:)
 
   call getpbh(BHN,Porg,Mass)
 #endif
@@ -867,41 +862,17 @@
    C1 = 1.d0/Mass(1) - A
    C2 = 1.d0/Mass(2) - A
 
-   denom_r = ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-   total_points = ex(1)*ex(2)*ex(3)
-   allocate(vml_r1(total_points), vml_r2(total_points))
-   allocate(vml_res1(total_points), vml_res2(total_points))
-
-   idx = 0
    do k=1,ex(3)
    do j=1,ex(2)
    do i=1,ex(1)
-     idx = idx + 1
+     r1 = ((Porg(1)-X(i))**2+(Porg(2)-Y(j))**2+(Porg(3)-Z(k))**2)/ &
-     r1 = ((Porg(1)-X(i))**2+(Porg(2)-Y(j))**2+(Porg(3)-Z(k))**2)/denom_r
+          ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-     r2 = ((Porg(4)-X(i))**2+(Porg(5)-Y(j))**2+(Porg(6)-Z(k))**2)/denom_r
+     r2 = ((Porg(4)-X(i))**2+(Porg(5)-Y(j))**2+(Porg(6)-Z(k))**2)/ &
-     
+          ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-     ! Prepare for 1/(1+w*r) -> vdInv
+     reta(i,j,k) = A + C1/(ONE+w1*r1) + C2/(ONE+w2*r2)
-     vml_r1(idx) = ONE + w1*r1
-     vml_r2(idx) = ONE + w2*r2
     enddo
     enddo
     enddo
-    
-    call vdInv(total_points, vml_r1, vml_res1)
-    call vdInv(total_points, vml_r2, vml_res2)
-
-    idx = 0
-    do k=1,ex(3)
-    do j=1,ex(2)
-    do i=1,ex(1)
-       idx = idx + 1
-       reta(i,j,k) = A + C1*vml_res1(idx) + C2*vml_res2(idx)
-    enddo
-    enddo
-    enddo
-
-    deallocate(vml_r1, vml_r2, vml_res1, vml_res2)
-
   else
     write(*,*) "not support BH_num in Jason's form 1",BHN
   endif
@@ -921,41 +892,17 @@
    C1 = 1.d0/Mass(1) - A
    C2 = 1.d0/Mass(2) - A
 
-   denom_r = ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-   total_points = ex(1)*ex(2)*ex(3)
-   allocate(vml_r1(total_points), vml_r2(total_points))
-   allocate(vml_res1(total_points), vml_res2(total_points))
-
-   idx = 0
    do k=1,ex(3)
    do j=1,ex(2)
    do i=1,ex(1)
-     idx = idx + 1
+     r1 = ((Porg(1)-X(i))**2+(Porg(2)-Y(j))**2+(Porg(3)-Z(k))**2)/ &
-     r1 = ((Porg(1)-X(i))**2+(Porg(2)-Y(j))**2+(Porg(3)-Z(k))**2)/denom_r
+          ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-     r2 = ((Porg(4)-X(i))**2+(Porg(5)-Y(j))**2+(Porg(6)-Z(k))**2)/denom_r
+     r2 = ((Porg(4)-X(i))**2+(Porg(5)-Y(j))**2+(Porg(6)-Z(k))**2)/ &
-     
+          ((Porg(1)-Porg(4))**2+(Porg(2)-Porg(5))**2+(Porg(3)-Porg(6))**2)
-     ! Prepare for dexp -> vdExp
+     reta(i,j,k) = A + C1*dexp(-w1*r1) + C2*dexp(-w2*r2)
-     vml_r1(idx) = -w1*r1
-     vml_r2(idx) = -w2*r2
     enddo
     enddo
     enddo
-
-    call vdExp(total_points, vml_r1, vml_res1)
-    call vdExp(total_points, vml_r2, vml_res2)
-
-    idx = 0
-    do k=1,ex(3)
-    do j=1,ex(2)
-    do i=1,ex(1)
-       idx = idx + 1
-       reta(i,j,k) = A + C1*vml_res1(idx) + C2*vml_res2(idx)
-    enddo
-    enddo
-    enddo
-
-    deallocate(vml_r1, vml_r2, vml_res1, vml_res2)
-
   else
     write(*,*) "not support BH_num in Jason's form 2",BHN
   endif

AMSS_NCKU_source/diff_new.f90

@@ -69,12 +69,8 @@
   fy = ZEO
   fz = ZEO
 
-! Intel compiler directives for aggressive vectorization
-!DIR$ SIMD
-!DIR$ IVDEP
   do k=1,ex(3)-1
   do j=1,ex(2)-1
-!DIR$ SIMD
   do i=1,ex(1)-1
 ! x direction   
         if(i+1 <= imax .and. i-1 >= imin)then
@@ -962,7 +958,6 @@
   real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3))   :: fh
   real*8, dimension(3) :: SoA
   integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
-  integer :: ib_s, ib_e, jb_s, jb_e, kb_s, kb_e
   real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
   integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
   real*8,  parameter :: ZEO=0.d0,ONE=1.d0, F60=6.d1
@@ -1002,66 +997,105 @@
   fy = ZEO
   fz = ZEO
 
-  ib_s = max(1, imin + 2)
-  ib_e = min(ex(1)-1, imax - 2)
-  jb_s = max(1, jmin + 2)
-  jb_e = min(ex(2)-1, jmax - 2)
-  kb_s = max(1, kmin + 2)
-  kb_e = min(ex(3)-1, kmax - 2)
-
-! Intel compiler directives for aggressive vectorization
-!DIR$ SIMD
-!DIR$ IVDEP
   do k=1,ex(3)-1
   do j=1,ex(2)-1
+  do i=1,ex(1)-1
+#if 0  
+! x direction   
+        if(i+2 <= imax .and. i-2 >= imin)then
+!
+!              f(i-2) - 8 f(i-1) + 8 f(i+1) - f(i+2)
+!  fx(i) = ---------------------------------------------
+!                             12 dx
+      fx(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))
 
-    ! Check if (j, k) are within the safe 4th-order range
+    elseif(i+1 <= imax .and. i-1 >= imin)then
-    if (k >= kb_s .and. k <= kb_e .and. j >= jb_s .and. j <= jb_e) then
+!
+!              - f(i-1) + f(i+1)
+!  fx(i) = --------------------------------
+!                     2 dx
+      fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
 
-        ! 1. Left Boundary Peel
+! set imax and imin 0
-        do i=1, min(ex(1)-1, ib_s-1)
-           if(i+1 <= imax .and. i-1 >= imin .and. &
-              j+1 <= jmax .and. j-1 >= jmin .and. &
-              k+1 <= kmax .and. k-1 >= kmin) then
-              fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
-              fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
-              fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
-           endif
-        enddo
-
-        ! 2. BULK CORE (No branches, full SIMD)
-        !DIR$ SIMD
-        do i=ib_s, ib_e
-            fx(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))
-            fy(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))
-            fz(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))
-        enddo
-
-        ! 3. Right Boundary Peel
-        do i=max(1, ib_e+1), ex(1)-1
-           if(i+1 <= imax .and. i-1 >= imin .and. &
-              j+1 <= jmax .and. j-1 >= jmin .and. &
-              k+1 <= kmax .and. k-1 >= kmin) then
-              fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
-              fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
-              fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
-           endif
-        enddo
-        
-    else
-        ! We are in a boundary slab (j or k is near edge)
-        ! Fallback to standard loop with checks (max 2nd order possible here)
-        do i=1,ex(1)-1
-           if(i+1 <= imax .and. i-1 >= imin .and. &
-              j+1 <= jmax .and. j-1 >= jmin .and. &
-              k+1 <= kmax .and. k-1 >= kmin) then
-              fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
-              fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
-              fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
-           endif
-        enddo
     endif
+! y direction   
+        if(j+2 <= jmax .and. j-2 >= jmin)then
 
+      fy(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 .and. j-1 >= jmin)then
+
+     fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
+
+! set jmax and jmin 0
+    endif
+! z direction   
+        if(k+2 <= kmax .and. k-2 >= kmin)then
+
+      fz(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 .and. k-1 >= kmin)then
+
+      fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
+
+! set kmax and kmin 0
+    endif
+#elif 0
+! x direction   
+        if(i+2 <= imax .and. i-2 >= imin)then
+!
+!              f(i-2) - 8 f(i-1) + 8 f(i+1) - f(i+2)
+!  fx(i) = ---------------------------------------------
+!                             12 dx
+      fx(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+3 <= imax .and. i-1 >= imin)then
+      fx(i,j,k)=d12dx*(-3.d0*fh(i-1,j,k)-1.d1*fh(i,j,k)+1.8d1*fh(i+1,j,k)-6.d0*fh(i+2,j,k)+fh(i+3,j,k))
+    elseif(i+1 <= imax .and. i-3 >= imin)then
+      fx(i,j,k)=d12dx*( 3.d0*fh(i+1,j,k)+1.d1*fh(i,j,k)-1.8d1*fh(i-1,j,k)+6.d0*fh(i-2,j,k)-fh(i-3,j,k))
+! set imax and imin 0
+    endif
+! y direction   
+        if(j+2 <= jmax .and. j-2 >= jmin)then
+
+      fy(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+3 <= jmax .and. j-1 >= jmin)then
+      fy(i,j,k)=d12dy*(-3.d0*fh(i,j-1,k)-1.d1*fh(i,j,k)+1.8d1*fh(i,j+1,k)-6.d0*fh(i,j+2,k)+fh(i,j+3,k))
+    elseif(j+1 <= jmax .and. j-3 >= jmin)then
+      fy(i,j,k)=d12dy*( 3.d0*fh(i,j+1,k)+1.d1*fh(i,j,k)-1.8d1*fh(i,j-1,k)+6.d0*fh(i,j-2,k)-fh(i,j-3,k))
+
+! set jmax and jmin 0
+    endif
+! z direction   
+        if(k+2 <= kmax .and. k-2 >= kmin)then
+
+      fz(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+3 <= kmax .and. k-1 >= kmin)then
+      fz(i,j,k)=d12dz*(-3.d0*fh(i,j,k-1)-1.d1*fh(i,j,k)+1.8d1*fh(i,j,k+1)-6.d0*fh(i,j,k+2)+fh(i,j,k+3))
+    elseif(k+1 <= kmax .and. k-3 >= kmin)then
+      fz(i,j,k)=d12dz*( 3.d0*fh(i,j,k+1)+1.d1*fh(i,j,k)-1.8d1*fh(i,j,k-1)+6.d0*fh(i,j,k-2)-fh(i,j,k-3))
+
+! set kmax and kmin 0
+    endif
+#else
+! for bam comparison
+   if(i+2 <= imax .and. i-2 >= imin .and. &
+      j+2 <= jmax .and. j-2 >= jmin .and. &
+      k+2 <= kmax .and. k-2 >= kmin) then
+      fx(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))
+      fy(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))
+      fz(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(i+1 <= imax .and. i-1 >= imin .and. &
+          j+1 <= jmax .and. j-1 >= jmin .and. &
+          k+1 <= kmax .and. k-1 >= kmin) then
+      fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
+      fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
+      fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
+   endif
+#endif
+  enddo
   enddo
   enddo
 
@@ -1977,12 +2011,8 @@
   fy = ZEO
   fz = ZEO
 
-! Intel compiler directives for aggressive vectorization
-!DIR$ SIMD
-!DIR$ IVDEP
   do k=1,ex(3)-1
   do j=1,ex(2)-1
-!DIR$ SIMD
   do i=1,ex(1)-1
 ! x direction   
         if(i+3 <= imax .and. i-3 >= imin)then
@@ -3050,12 +3080,8 @@
   fy = ZEO
   fz = ZEO
 
-! Intel compiler directives for aggressive vectorization
-!DIR$ SIMD
-!DIR$ IVDEP
   do k=1,ex(3)-1
   do j=1,ex(2)-1
-!DIR$ SIMD
   do i=1,ex(1)-1
 ! x direction
         if(i+4 <= imax .and. i-4 >= imin)then

AMSS_NCKU_source/enforce_algebra.f90

@@ -19,48 +19,60 @@
 
 !~~~~~~~> Local variable:
 
-  real*8, dimension(ex(1),ex(2),ex(3)) :: trA,detg
+  integer :: i,j,k
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz 
+  real*8 :: lgxx,lgyy,lgzz,ldetg
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
+  real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
+  real*8 :: ltrA,lscale
   real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
 
 !~~~~~~>
 
-  gxx = dxx + ONE
+  do k=1,ex(3)
-  gyy = dyy + ONE
+  do j=1,ex(2)
-  gzz = dzz + ONE
+  do i=1,ex(1)
 
-  detg =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
+    lgxx = dxx(i,j,k) + ONE
-          gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
+    lgyy = dyy(i,j,k) + ONE
-  gupxx =   ( gyy * gzz - gyz * gyz ) / detg
+    lgzz = dzz(i,j,k) + ONE
-  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
 
-  trA =         gupxx * Axx + gupyy * Ayy + gupzz * Azz &
+    ldetg =  lgxx * lgyy * lgzz &
-       + TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
+           + 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)
 
-  Axx = Axx - F1o3 * gxx * trA
+    lgupxx =   ( lgyy * lgzz - gyz(i,j,k) * gyz(i,j,k) ) / ldetg
-  Axy = Axy - F1o3 * gxy * trA
+    lgupxy = - ( gxy(i,j,k) * lgzz - gyz(i,j,k) * gxz(i,j,k) ) / ldetg
-  Axz = Axz - F1o3 * gxz * trA
+    lgupxz =   ( gxy(i,j,k) * gyz(i,j,k) - lgyy * gxz(i,j,k) ) / ldetg
-  Ayy = Ayy - F1o3 * gyy * trA
+    lgupyy =   ( lgxx * lgzz - gxz(i,j,k) * gxz(i,j,k) ) / ldetg
-  Ayz = Ayz - F1o3 * gyz * trA
+    lgupyz = - ( lgxx * gyz(i,j,k) - gxy(i,j,k) * gxz(i,j,k) ) / ldetg
-  Azz = Azz - F1o3 * gzz * trA
+    lgupzz =   ( lgxx * lgyy - gxy(i,j,k) * gxy(i,j,k) ) / ldetg
 
-  detg = ONE / ( detg ** F1o3 ) 
+    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))
 
-  gxx = gxx * detg
+    Axx(i,j,k) = Axx(i,j,k) - F1o3 * lgxx * ltrA
-  gxy = gxy * detg
+    Axy(i,j,k) = Axy(i,j,k) - F1o3 * gxy(i,j,k) * ltrA
-  gxz = gxz * detg
+    Axz(i,j,k) = Axz(i,j,k) - F1o3 * gxz(i,j,k) * ltrA
-  gyy = gyy * detg
+    Ayy(i,j,k) = Ayy(i,j,k) - F1o3 * lgyy * ltrA
-  gyz = gyz * detg
+    Ayz(i,j,k) = Ayz(i,j,k) - F1o3 * gyz(i,j,k) * ltrA
-  gzz = gzz * detg
+    Azz(i,j,k) = Azz(i,j,k) - F1o3 * lgzz * ltrA
 
-  dxx = gxx - ONE
+    lscale = ONE / ( ldetg ** F1o3 )
-  dyy = gyy - ONE
+
-  dzz = gzz - ONE
+    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
 
   return
 
@@ -83,50 +95,70 @@
 
 !~~~~~~~> Local variable:
 
-  real*8, dimension(ex(1),ex(2),ex(3)) :: trA
+  integer :: i,j,k
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz 
+  real*8 :: lgxx,lgyy,lgzz,lscale
-  real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
+  real*8 :: lgxy,lgxz,lgyz
+  real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
+  real*8 :: ltrA
   real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
 
 !~~~~~~>
 
-  gxx = dxx + ONE
+  do k=1,ex(3)
-  gyy = dyy + ONE
+  do j=1,ex(2)
-  gzz = dzz + ONE
+  do i=1,ex(1)
-! for g
-  gupzz =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
-           gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
 
-  gupzz = ONE / ( gupzz ** F1o3 ) 
+! 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)
 
-  gxx = gxx * gupzz
+    lscale =  lgxx * lgyy * lgzz + lgxy * lgyz * lgxz &
-  gxy = gxy * gupzz
+            + lgxz * lgxy * lgyz - lgxz * lgyy * lgxz &
-  gxz = gxz * gupzz
+            - lgxy * lgxy * lgzz - lgxx * lgyz * lgyz
-  gyy = gyy * gupzz
-  gyz = gyz * gupzz
-  gzz = gzz * gupzz
 
-  dxx = gxx - ONE
+    lscale = ONE / ( lscale ** F1o3 )
-  dyy = gyy - ONE
-  dzz = gzz - ONE
-! for A  
 
-  gupxx =   ( gyy * gzz - gyz * gyz )
+    lgxx = lgxx * lscale
-  gupxy = - ( gxy * gzz - gyz * gxz )
+    lgxy = lgxy * lscale
-  gupxz =   ( gxy * gyz - gyy * gxz )
+    lgxz = lgxz * lscale
-  gupyy =   ( gxx * gzz - gxz * gxz )
+    lgyy = lgyy * lscale
-  gupyz = - ( gxx * gyz - gxy * gxz )
+    lgyz = lgyz * lscale
-  gupzz =   ( gxx * gyy - gxy * gxy )
+    lgzz = lgzz * lscale
 
-  trA =         gupxx * Axx + gupyy * Ayy + gupzz * Azz &
+    dxx(i,j,k) = lgxx - ONE
-       + TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
+    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
 
-  Axx = Axx - F1o3 * gxx * trA
+! for A: trace-free using normalized metric (det=1, no division needed)
-  Axy = Axy - F1o3 * gxy * trA
+    lgupxx =   ( lgyy * lgzz - lgyz * lgyz )
-  Axz = Axz - F1o3 * gxz * trA
+    lgupxy = - ( lgxy * lgzz - lgyz * lgxz )
-  Ayy = Ayy - F1o3 * gyy * trA
+    lgupxz =   ( lgxy * lgyz - lgyy * lgxz )
-  Ayz = Ayz - F1o3 * gyz * trA
+    lgupyy =   ( lgxx * lgzz - lgxz * lgxz )
-  Azz = Azz - F1o3 * gzz * trA
+    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
 
   return
 

AMSS_NCKU_source/fmisc.f90

@@ -324,7 +324,6 @@ 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)
@@ -350,7 +349,6 @@ 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)
@@ -379,7 +377,6 @@ 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)
@@ -886,14 +883,17 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
 
   integer::i
 
-  funcc = 0.d0
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
   funcc(1:extc(1),1:extc(2),1:extc(3)) = func
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(-i,1:extc(2),1:extc(3)) = funcc(i+1,1:extc(2),1:extc(3))*SoA(1)
    enddo
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(:,-i,1:extc(3)) = funcc(:,i+1,1:extc(3))*SoA(2)
    enddo
+!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
    do i=0,ord-1
       funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
    enddo
@@ -912,7 +912,6 @@ 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)
@@ -941,7 +940,6 @@ 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)
@@ -1117,101 +1115,290 @@ end subroutine d2dump
 !------------------------------------------------------------------------------
 ! Lagrangian polynomial interpolation
 !------------------------------------------------------------------------------
+#ifndef POLINT6_USE_BARYCENTRIC
+#define POLINT6_USE_BARYCENTRIC 1
+#endif
 
-  subroutine polint(xa,ya,x,y,dy,ordn)
+!DIR$ ATTRIBUTES FORCEINLINE :: polint6_neville
-
+  subroutine polint6_neville(xa, ya, x, y, dy)
   implicit none
 
-!~~~~~~> Input Parameter:
+  real*8, dimension(6), intent(in) :: xa, ya
-  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
 
-!~~~~~~> Other parameter:
+  integer :: i, m, ns, n_m
+  real*8, dimension(6) :: c, d, ho
+  real*8 :: dif, dift, hp, h, den_val
 
-  integer :: m,n,ns
+  c = ya
-  real*8, dimension(ordn) :: c,d,den,ho
+  d = ya
-  real*8 :: dif,dift
+  ho = xa - x
 
-!~~~~~~>
+  ns = 1
+  dif = abs(x - xa(1))
 
-  n=ordn
+  do i = 2, 6
-  m=ordn
+    dift = abs(x - xa(i))
-
+    if (dift < dif) then
-  c=ya
+      ns = i
-  d=ya
+      dif = dift
-  ho=xa-x
+    end if
-
-  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)
+  y = ya(ns)
-  ns=ns-1
+  ns = ns - 1
-  do m=1,n-1
+
-    den(1:n-m)=ho(1:n-m)-ho(1+m:n)
+  do m = 1, 5
-    if (any(den(1:n-m) == 0.0))then
+    n_m = 6 - m
-      write(*,*) 'failure in polint for point',x
+    do i = 1, n_m
-      write(*,*) 'with input points: ',xa
+      hp = ho(i)
-      stop
+      h  = ho(i+m)
-    endif
+      den_val = hp - h
-    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)
+      if (den_val == 0.0d0) then
-    c(1:n-m)=ho(1:n-m)*den(1:n-m)
+        write(*,*) 'failure in polint for point',x
-    if (2*ns < n-m) then
+        write(*,*) 'with input points: ',xa
-      dy=c(ns+1)
+        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)
+      dy = d(ns)
-      ns=ns-1
+      ns = ns - 1
     end if
-    y=y+dy
+    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
+  real*8, intent(in) :: x
+  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
+
+  ns = 1
+  dif = abs(x - xa(1))
+
+  do i = 2, ordn
+    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, 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)
+    else
+      dy = d(ns)
+      ns = ns - 1
+    end if
+    y = y + dy
+  end do
+
+  return
   end subroutine polint
 !------------------------------------------------------------------------------
+! 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
 !
 !------------------------------------------------------------------------------
   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
 
-!~~~~~~> Other parameters:
+#ifdef POLINT_LEGACY_ORDER
-
   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
 
   return
-
   end subroutine polin2
 !------------------------------------------------------------------------------
 !
@@ -1219,18 +1406,15 @@ 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
 
-!~~~~~~> Other parameters:
+#ifdef POLINT_LEGACY_ORDER
-
   integer  :: i,j,m,n
   real*8, dimension(ordn,ordn) :: yatmp
   real*8, dimension(ordn) :: ymtmp
@@ -1239,24 +1423,40 @@ end subroutine d2dump
 
   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(x1a,ymtmp,x1,y,dy,ordn)
+  call polint(x3a, ymtmp, x3, y, dy, ordn)
+#endif
 
   return
-
   end subroutine polin3
 !--------------------------------------------------------------------------------------
 ! calculate L2norm  
@@ -1302,18 +1502,89 @@ 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)
-n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
+  allocate(f_flat(n_elements))
-allocate(f_flat(n_elements))
+  f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [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)
-f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
+  deallocate(f_flat)
-deallocate(f_flat)
 
 f_out = f_out*dX*dY*dZ
 
   return
 
   end subroutine l2normhelper
+!--------------------------------------------------------------------------------------
+  subroutine l2normhelper7(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&
+                           f1,f2,f3,f4,f5,f6,f7,f_out,gw)
+
+  implicit none
+!~~~~~~> Input parameters:
+  integer,intent(in ):: ex(1:3)
+  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3)),xmin,ymin,zmin,xmax,ymax,zmax
+  integer,intent(in)::gw
+  real*8, dimension(ex(1),ex(2),ex(3)),intent(in) :: f1,f2,f3,f4,f5,f6,f7
+  real*8, intent(out) :: f_out(7)
+!~~~~~~> Other variables:
+
+  real*8            :: dX, dY, dZ
+  integer::imin,jmin,kmin
+  integer::imax,jmax,kmax
+  integer::i,j,k
+  real*8 :: s1,s2,s3,s4,s5,s6,s7
+
+  dX = X(2) - X(1)
+  dY = Y(2) - Y(1)
+  dZ = Z(2) - Z(1)
+
+   imin = gw+1
+   jmin = gw+1
+   kmin = gw+1
+
+   imax = ex(1) - gw
+   jmax = ex(2) - gw
+   kmax = ex(3) - gw
+
+if(dabs(X(ex(1))-xmax) < dX) imax = ex(1)
+if(dabs(Y(ex(2))-ymax) < dY) jmax = ex(2)
+if(dabs(Z(ex(3))-zmax) < dZ) kmax = ex(3)
+if(dabs(X(1)-xmin) < dX) imin = 1
+if(dabs(Y(1)-ymin) < dY) jmin = 1
+if(dabs(Z(1)-zmin) < dZ) kmin = 1
+
+  s1 = 0.d0
+  s2 = 0.d0
+  s3 = 0.d0
+  s4 = 0.d0
+  s5 = 0.d0
+  s6 = 0.d0
+  s7 = 0.d0
+
+  do k=kmin,kmax
+    do j=jmin,jmax
+!DIR$ SIMD REDUCTION(+:s1,s2,s3,s4,s5,s6,s7)
+      do i=imin,imax
+        s1 = s1 + f1(i,j,k)*f1(i,j,k)
+        s2 = s2 + f2(i,j,k)*f2(i,j,k)
+        s3 = s3 + f3(i,j,k)*f3(i,j,k)
+        s4 = s4 + f4(i,j,k)*f4(i,j,k)
+        s5 = s5 + f5(i,j,k)*f5(i,j,k)
+        s6 = s6 + f6(i,j,k)*f6(i,j,k)
+        s7 = s7 + f7(i,j,k)*f7(i,j,k)
+      enddo
+    enddo
+  enddo
+
+  f_out(1) = s1*dX*dY*dZ
+  f_out(2) = s2*dX*dY*dZ
+  f_out(3) = s3*dX*dY*dZ
+  f_out(4) = s4*dX*dY*dZ
+  f_out(5) = s5*dX*dY*dZ
+  f_out(6) = s6*dX*dY*dZ
+  f_out(7) = s7*dX*dY*dZ
+
+  return
+
+  end subroutine l2normhelper7
 !--------------------------------------------------------------------------------------
 ! calculate L2norm especially for shell Blocks
   subroutine l2normhelper_sh(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&
@@ -1397,12 +1668,11 @@ 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
+  n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
-n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
+  allocate(f_flat(n_elements))
-allocate(f_flat(n_elements))
+  f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [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)
-f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
+  deallocate(f_flat)
-deallocate(f_flat)
 
 f_out = f_out*dX*dY*dZ
 
@@ -1494,12 +1764,11 @@ 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
 Nout = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
-allocate(f_flat(Nout))
+  allocate(f_flat(Nout))
-f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [Nout])
+  f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [Nout])
-f_out = DDOT(Nout, f_flat, 1, f_flat, 1)
+  f_out = DDOT(Nout, f_flat, 1, f_flat, 1)
-deallocate(f_flat)
+  deallocate(f_flat)
 
   return
 
@@ -1601,8 +1870,11 @@ deallocate(f_flat)
 ! f=3/8*f_1 + 3/4*f_2 - 1/8*f_3
 
   real*8,parameter::C1=3.d0/8.d0,C2=3.d0/4.d0,C3=-1.d0/8.d0
+  integer :: i,j,k
 
-  fout = C1*f1+C2*f2+C3*f3
+  do concurrent (k=1:ext(3), j=1:ext(2), i=1:ext(1))
+    fout(i,j,k) = C1*f1(i,j,k)+C2*f2(i,j,k)+C3*f3(i,j,k)
+  end do
 
   return
 
@@ -1733,20 +2005,16 @@ 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)
 
   return
@@ -1807,13 +2075,11 @@ 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)
 
   return
@@ -1906,7 +2172,6 @@ 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)
 
   return
@@ -2139,16 +2404,13 @@ 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)
+  integer :: i
   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, &
@@ -2163,12 +2425,9 @@ deallocate(f_flat)
      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
 

AMSS_NCKU_source/fmisc.h

@@ -13,6 +13,7 @@
 #define f_global_interpind2d global_interpind2d
 #define f_global_interpind1d global_interpind1d
 #define f_l2normhelper l2normhelper
+#define f_l2normhelper7 l2normhelper7
 #define f_l2normhelper_sh l2normhelper_sh
 #define f_l2normhelper_sh_rms l2normhelper_sh_rms
 #define f_average average
@@ -42,6 +43,7 @@
 #define f_global_interpind2d GLOBAL_INTERPIND2D
 #define f_global_interpind1d GLOBAL_INTERPIND1D
 #define f_l2normhelper L2NORMHELPER
+#define f_l2normhelper7 L2NORMHELPER7
 #define f_l2normhelper_sh L2NORMHELPER_SH
 #define f_l2normhelper_sh_rms L2NORMHELPER_SH_RMS
 #define f_average AVERAGE
@@ -71,6 +73,7 @@
 #define f_global_interpind2d global_interpind2d_
 #define f_global_interpind1d global_interpind1d_
 #define f_l2normhelper l2normhelper_
+#define f_l2normhelper7 l2normhelper7_
 #define f_l2normhelper_sh l2normhelper_sh_
 #define f_l2normhelper_sh_rms l2normhelper_sh_rms_
 #define f_average average_
@@ -164,6 +167,15 @@ extern "C"
 						double *, double &, int &);
 }
 
+extern "C"
+{
+	void f_l2normhelper7(int *, double *, double *, double *,
+						 double &, double &, double &,
+						 double &, double &, double &,
+						 double *, double *, double *, double *,
+						 double *, double *, double *, double *, int &);
+}
+
 extern "C"
 {
 	void f_l2normhelper_sh(int *, double *, double *, double *,

AMSS_NCKU_source/gaussj.C

@@ -16,66 +16,115 @@ using namespace std;
 #include <string.h>
 #include <math.h>
 #endif
-
+/* Linear equation solution by Gauss-Jordan elimination.
-// Intel oneMKL LAPACK interface
-#include <mkl_lapacke.h>
-/* Linear equation solution using Intel oneMKL LAPACK.
 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.
+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. */
 
 int gaussj(double *a, double *b, int n)
 {
-  // Allocate pivot array and workspace
+  double swap;
-  lapack_int *ipiv = new lapack_int[n];
-  lapack_int info;
 
-  // Make a copy of matrix a for solving (dgesv modifies it to LU form)
+  int *indxc, *indxr, *ipiv;
-  double *a_copy = new double[n * n];
+  indxc = new int[n];
-  for (int i = 0; i < n * n; i++) {
+  indxr = new int[n];
-    a_copy[i] = a[i];
+  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
+  for (l = n - 1; l >= 0; l--)
-  // 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 (indxr[l] != indxc[l])
-
+      for (k = 0; k < n; k++)
-  if (info != 0) {
+      {
-    cout << "gaussj: Singular Matrix (dgesv info=" << info << ")" << endl;
+        swap = a[k * n + indxr[l]];
-    delete[] ipiv;
+        a[k * n + indxr[l]] = a[k * n + indxc[l]];
-    delete[] a_copy;
+        a[k * n + indxc[l]] = swap;
-    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;
   }
 
+  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
+      SUM = 0.0D0
-      DGVV = DDOT(N, V, 1, W, 1)
+            DO 10 I = 1,N
+            SUM = SUM + V(I)*W(I)
+10          CONTINUE
+      DGVV = SUM
       RETURN
       END

AMSS_NCKU_source/makefile

@@ -2,6 +2,20 @@
 
 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)
+
+ARCH_OPT = -march=x86-64-v4
+CXXAPPFLAGS = -O3 $(ARCH_OPT) -fp-model fast=2 -fma -ipo \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
+f90appflags = -O3 $(ARCH_OPT) -fp-model fast=2 -fma -ipo \
+              -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
+TP_OPTFLAGS = -O3 $(ARCH_OPT) -fp-model fast=2 -fma -ipo \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
+
 .SUFFIXES: .o .f90 .C .for .cu
 
 .f90.o:
@@ -16,6 +30,12 @@ include makefile.inc
 .cu.o:
 	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
 
+TwoPunctures.o: TwoPunctures.C
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
+
+TwoPunctureABE.o: TwoPunctureABE.C
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
+
 # Input files
 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\
@@ -96,7 +116,7 @@ ABEGPU: $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
 	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
 
 TwoPunctureABE: $(TwoPunctureFILES)
-	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(TwoPunctureFILES) $(LDLIBS)
+	$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
 
 clean:
 	rm *.o ABE ABEGPU TwoPunctureABE make.log -f

AMSS_NCKU_source/makefile.inc

@@ -1,39 +1,27 @@
+
 ## 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)
+## Intel oneAPI version with oneMKL
 filein  = -I/usr/include/ -I${MKLROOT}/include
 
-## Using multi-threaded MKL for better scalability with MPI
+## Use sequential oneMKL to avoid introducing extra OpenMP behavior into ABE.
-## This allows MKL functions (FFT, BLAS, LAPACK) to use multiple threads internally
+LDLIBS  = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
-## while keeping the application code as pure MPI (no OpenMP pragmas in user code)
+
-LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -lifcore -limf -lmpi \
+## Optional Intel oneTBB allocator, kept aligned with main's build environment.
-          -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core \
+USE_TBBMALLOC ?= 1
-          -liomp5 -lpthread -lm -ldl
+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
 
-## Aggressive optimization flags for maximum performance:
-## -O3: Maximum optimization level
-## -xHost: Optimize for the host CPU architecture (Intel/AMD compatible)
-## -fp-model fast=2: Aggressive floating-point optimizations (allows reassociation)
-## -fma: Enable fused multiply-add instructions
-## -qopt-report=5: Generate detailed optimization reports
-## -qopt-report-phase=vec,loop: Report vectorization and loop optimizations
-## -march=native: Use all available CPU instructions
-## -mtune=native: Tune for the specific CPU
-## -funroll-loops: Aggressively unroll loops
-## -fno-alias: Assume no pointer aliasing (safe for Fortran arrays)
-## -qopt-prefetch: Enable aggressive prefetching
-## Note: OpenMP has been disabled (-qopenmp removed) due to performance issues
-CXXAPPFLAGS  = -O3 -xHost -march=native -mtune=native -fp-model fast=2 -fma \
-               -qopt-report=5 -qopt-report-phase=vec,loop \
-               -funroll-loops -fno-alias -qopt-prefetch \
-               -Dfortran3 -Dnewc -I${MKLROOT}/include
-f90appflags  = -O3 -xHost -march=native -mtune=native -fp-model fast=2 -fma \
-               -qopt-report=5 -qopt-report-phase=vec,loop \
-               -funroll-loops -fno-alias -qopt-prefetch \
-               -fpp -I${MKLROOT}/include
 f90          = ifx
 f77          = ifx
 CXX          = icpx

makefile_and_run.py

@@ -11,24 +11,6 @@
 import AMSS_NCKU_Input as input_data
 import subprocess
 
-## CPU core binding configuration using taskset
-## taskset ensures all child processes inherit the CPU affinity mask
-## This forces make and all compiler processes to use only nohz_full cores (4-55, 60-111)
-## Format: taskset -c 4-55,60-111 ensures processes only run on these cores
-NUMACTL_CPU_BIND = "taskset -c 4-55,60-111"
-
-## Build parallelism configuration
-## Use nohz_full cores (4-55, 60-111) for compilation: 52 + 52 = 104 cores
-## Set make -j to utilize available cores for faster builds
-BUILD_JOBS = 104
-
-## MKL threading configuration for hybrid MPI+threaded-MKL execution
-## Total cores available: 104 (cores 4-55, 60-111)
-## MPI processes: configured in AMSS_NCKU_Input.py (typically 48)
-## MKL threads per process: 104 / MPI_processes ≈ 2
-## This ensures full utilization of available cores
-MKL_NUM_THREADS = max(1, 104 // input_data.MPI_processes)
-
 
 ##################################################################
 
@@ -44,11 +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} ABE"
+        makefile_command  = "make -j96" + " 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(                                                    )
@@ -85,8 +67,8 @@ def makefile_TwoPunctureABE():
     print( " Compiling the AMSS-NCKU executable file TwoPunctureABE " )
     print(                                                            )
     
-    ## Build command with CPU binding to nohz_full cores
+    ## Build command
-    makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} TwoPunctureABE"
+    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) 
@@ -119,20 +101,14 @@ def run_ABE():
     print(                                                      )
     print( " Running the AMSS-NCKU executable file ABE/ABEGPU " ) 
     print(                                                      )
-    print( f" MPI processes: {input_data.MPI_processes}" )
-    print( f" MKL threads per process: {MKL_NUM_THREADS}" )
-    print( f" Total threads: {input_data.MPI_processes * MKL_NUM_THREADS}" )
-    print(                                                      )
 
     ## Define the command to run; cast other values to strings as needed
-    ## Set MKL threading environment variables for optimal performance
-    env_vars = f"export MKL_NUM_THREADS={MKL_NUM_THREADS} && export MKL_DYNAMIC=FALSE && "
     
     if (input_data.GPU_Calculation == "no"):
-        mpi_command         = env_vars + NUMACTL_CPU_BIND + " 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         = env_vars + 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
@@ -170,9 +146,8 @@ def run_TwoPunctureABE():
     print( " Running the AMSS-NCKU executable file TwoPunctureABE " ) 
     print(                                                          )
     
-    ## Define the command to run with MKL threading configuration
+    ## Define the command to run
-    env_vars = f"export MKL_NUM_THREADS={MKL_NUM_THREADS} && export MKL_DYNAMIC=FALSE && "
+    TwoPuncture_command         = "./TwoPunctureABE"
-    TwoPuncture_command         = env_vars + NUMACTL_CPU_BIND + " ./TwoPunctureABE"
     TwoPuncture_command_outfile = "TwoPunctureABE_out.log"
 
     ## Execute the command with subprocess.Popen and stream output

parallel_plot_helper.py

@@ -0,0 +1,12 @@
+import multiprocessing
+
+
+def run_plot_task(task):
+    func, args = task
+    return func(*args)
+
+
+def run_plot_tasks_parallel(plot_tasks):
+    ctx = multiprocessing.get_context('fork')
+    with ctx.Pool() as pool:
+        pool.map(run_plot_task, plot_tasks)

plot_GW_strain_amplitude_xiaoqu.py

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

plot_binary_data.py

@@ -8,16 +8,21 @@
 ##
 #################################################
 
+## Restrict OpenMP to one thread per process so that parallel
+## subprocess plotting does not multiply BLAS thread counts.
+import os
+os.environ.setdefault("OMP_NUM_THREADS", "1")
+
 import numpy
 import scipy
+import matplotlib
+matplotlib.use('Agg')                      ## use non-interactive backend for multiprocessing safety
 import matplotlib.pyplot    as     plt
 from   matplotlib.colors    import LogNorm
 from   mpl_toolkits.mplot3d import Axes3D
 ## import torch
 import AMSS_NCKU_Input      as input_data
 
-import os
-
 
 #########################################################################################
 
@@ -192,3 +197,11 @@ def get_data_xy( Rmin, Rmax, n, data0, time, figure_title, figure_outdir ):
 
 ####################################################################################
 
+## Allow standalone subprocess execution for parallel binary-data plotting.
+if __name__ == '__main__':
+    import sys
+    if len(sys.argv) != 4:
+        print(f"Usage: {sys.argv[0]} <filename> <binary_outdir> <figure_outdir>")
+        sys.exit(1)
+    plot_binary_data(sys.argv[1], sys.argv[2], sys.argv[3])
+

plot_xiaoqu.py

@@ -8,6 +8,8 @@
 #################################################
 
 import numpy                               ## numpy for array operations
+import matplotlib
+matplotlib.use('Agg')                      ## use non-interactive backend for multiprocessing safety
 import matplotlib.pyplot    as     plt     ## matplotlib for plotting
 from   mpl_toolkits.mplot3d import Axes3D  ## needed for 3D plots
 import glob
@@ -15,6 +17,9 @@ import os                                  ## operating system utilities
 
 import plot_binary_data
 import AMSS_NCKU_Input as input_data
+import subprocess
+import sys
+import multiprocessing
 
 # plt.rcParams['text.usetex'] = True  ## enable LaTeX fonts in plots
 
@@ -50,10 +55,34 @@ def generate_binary_data_plot( binary_outdir, figure_outdir ):
         file_list.append(x)
         print(x)
 
-    ## Plot each file in the list
+    ## Plot each file in parallel using subprocesses.
+    ## Each subprocess starts with BLAS thread limits in plot_binary_data.py.
+    script = os.path.join( os.path.dirname(__file__), "plot_binary_data.py" )
+    max_workers = min( multiprocessing.cpu_count(), len(file_list) ) if file_list else 0
+
+    running = []
+    failed  = []
     for filename in file_list:
         print(filename)
-        plot_binary_data.plot_binary_data(filename, binary_outdir, figure_outdir)
+        proc = subprocess.Popen(
+            [sys.executable, script, filename, binary_outdir, figure_outdir],
+        )
+        running.append( (proc, filename) )
+        if len(running) >= max_workers:
+            p, fn = running.pop(0)
+            p.wait()
+            if p.returncode != 0:
+                failed.append(fn)
+
+    for p, fn in running:
+        p.wait()
+        if p.returncode != 0:
+            failed.append(fn)
+
+    if failed:
+        print( " WARNING: the following binary data plots failed:" )
+        for fn in failed:
+            print( "   ", fn )
 
     print(                        )
     print( " Binary Data Plot Has been Finished " )